hello
hello

📌S Retain class distribution for seed 1:
Class 0: 4500
Class 1: 4500
Class 2: 4500
Class 3: 4500
Class 4: 4500
Class 5: 4500
Class 6: 4500
Class 7: 4500
Class 8: 4500
Class 9: 4500

📌S Forget class distribution for seed 1:
Class 0: 500
Class 1: 500
Class 2: 500
Class 3: 500
Class 4: 500
Class 5: 500
Class 6: 500
Class 7: 500
Class 8: 500
Class 9: 500

📊 Updated class distribution:
Retain set:
  Class 0: 4625
  Class 1: 4625
  Class 2: 4625
  Class 3: 4625
  Class 4: 4625
  Class 5: 4625
  Class 6: 4625
  Class 7: 4625
  Class 8: 4625
  Class 9: 4625
Forget set:
  Class 0: 375
  Class 1: 375
  Class 2: 375
  Class 3: 375
  Class 4: 375
  Class 5: 375
  Class 6: 375
  Class 7: 375
  Class 8: 375
  Class 9: 375
hello
hello
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/46250]	Loss: 2.5776	LR: 0.000000
Training Epoch: 1 [512/46250]	Loss: 2.5302	LR: 0.000552
Training Epoch: 1 [768/46250]	Loss: 2.4547	LR: 0.001105
Training Epoch: 1 [1024/46250]	Loss: 2.5292	LR: 0.001657
Training Epoch: 1 [1280/46250]	Loss: 2.4245	LR: 0.002210
Training Epoch: 1 [1536/46250]	Loss: 2.3356	LR: 0.002762
Training Epoch: 1 [1792/46250]	Loss: 2.1971	LR: 0.003315
Training Epoch: 1 [2048/46250]	Loss: 2.0339	LR: 0.003867
Training Epoch: 1 [2304/46250]	Loss: 1.8279	LR: 0.004420
Training Epoch: 1 [2560/46250]	Loss: 1.6226	LR: 0.004972
Training Epoch: 1 [2816/46250]	Loss: 1.3808	LR: 0.005525
Training Epoch: 1 [3072/46250]	Loss: 1.1799	LR: 0.006077
Training Epoch: 1 [3328/46250]	Loss: 0.9743	LR: 0.006630
Training Epoch: 1 [3584/46250]	Loss: 0.7398	LR: 0.007182
Training Epoch: 1 [3840/46250]	Loss: 0.6160	LR: 0.007735
Training Epoch: 1 [4096/46250]	Loss: 0.4853	LR: 0.008287
Training Epoch: 1 [4352/46250]	Loss: 0.3251	LR: 0.008840
Training Epoch: 1 [4608/46250]	Loss: 0.4447	LR: 0.009392
Training Epoch: 1 [4864/46250]	Loss: 0.3234	LR: 0.009945
Training Epoch: 1 [5120/46250]	Loss: 0.2488	LR: 0.010497
Training Epoch: 1 [5376/46250]	Loss: 0.2605	LR: 0.011050
Training Epoch: 1 [5632/46250]	Loss: 0.2369	LR: 0.011602
Training Epoch: 1 [5888/46250]	Loss: 0.2623	LR: 0.012155
Training Epoch: 1 [6144/46250]	Loss: 0.2257	LR: 0.012707
Training Epoch: 1 [6400/46250]	Loss: 0.2199	LR: 0.013260
Training Epoch: 1 [6656/46250]	Loss: 0.2012	LR: 0.013812
Training Epoch: 1 [6912/46250]	Loss: 0.2692	LR: 0.014365
Training Epoch: 1 [7168/46250]	Loss: 0.1802	LR: 0.014917
Training Epoch: 1 [7424/46250]	Loss: 0.2528	LR: 0.015470
Training Epoch: 1 [7680/46250]	Loss: 0.3228	LR: 0.016022
Training Epoch: 1 [7936/46250]	Loss: 0.1817	LR: 0.016575
Training Epoch: 1 [8192/46250]	Loss: 0.2590	LR: 0.017127
Training Epoch: 1 [8448/46250]	Loss: 0.1376	LR: 0.017680
Training Epoch: 1 [8704/46250]	Loss: 0.3436	LR: 0.018232
Training Epoch: 1 [8960/46250]	Loss: 0.2523	LR: 0.018785
Training Epoch: 1 [9216/46250]	Loss: 0.2409	LR: 0.019337
Training Epoch: 1 [9472/46250]	Loss: 0.2205	LR: 0.019890
Training Epoch: 1 [9728/46250]	Loss: 0.2855	LR: 0.020442
Training Epoch: 1 [9984/46250]	Loss: 0.1488	LR: 0.020994
Training Epoch: 1 [10240/46250]	Loss: 0.1633	LR: 0.021547
Training Epoch: 1 [10496/46250]	Loss: 0.2500	LR: 0.022099
Training Epoch: 1 [10752/46250]	Loss: 0.2284	LR: 0.022652
Training Epoch: 1 [11008/46250]	Loss: 0.1920	LR: 0.023204
Training Epoch: 1 [11264/46250]	Loss: 0.2224	LR: 0.023757
Training Epoch: 1 [11520/46250]	Loss: 0.2427	LR: 0.024309
Training Epoch: 1 [11776/46250]	Loss: 0.1804	LR: 0.024862
Training Epoch: 1 [12032/46250]	Loss: 0.3064	LR: 0.025414
Training Epoch: 1 [12288/46250]	Loss: 0.2228	LR: 0.025967
Training Epoch: 1 [12544/46250]	Loss: 0.1625	LR: 0.026519
Training Epoch: 1 [12800/46250]	Loss: 0.3126	LR: 0.027072
Training Epoch: 1 [13056/46250]	Loss: 0.1755	LR: 0.027624
Training Epoch: 1 [13312/46250]	Loss: 0.2269	LR: 0.028177
Training Epoch: 1 [13568/46250]	Loss: 0.2352	LR: 0.028729
Training Epoch: 1 [13824/46250]	Loss: 0.2329	LR: 0.029282
Training Epoch: 1 [14080/46250]	Loss: 0.2030	LR: 0.029834
Training Epoch: 1 [14336/46250]	Loss: 0.2302	LR: 0.030387
Training Epoch: 1 [14592/46250]	Loss: 0.3431	LR: 0.030939
Training Epoch: 1 [14848/46250]	Loss: 0.2495	LR: 0.031492
Training Epoch: 1 [15104/46250]	Loss: 0.3606	LR: 0.032044
Training Epoch: 1 [15360/46250]	Loss: 0.4063	LR: 0.032597
Training Epoch: 1 [15616/46250]	Loss: 0.4398	LR: 0.033149
Training Epoch: 1 [15872/46250]	Loss: 0.5384	LR: 0.033702
Training Epoch: 1 [16128/46250]	Loss: 0.3033	LR: 0.034254
Training Epoch: 1 [16384/46250]	Loss: 0.1704	LR: 0.034807
Training Epoch: 1 [16640/46250]	Loss: 0.2718	LR: 0.035359
Training Epoch: 1 [16896/46250]	Loss: 0.3178	LR: 0.035912
Training Epoch: 1 [17152/46250]	Loss: 0.2934	LR: 0.036464
Training Epoch: 1 [17408/46250]	Loss: 0.2429	LR: 0.037017
Training Epoch: 1 [17664/46250]	Loss: 0.2902	LR: 0.037569
Training Epoch: 1 [17920/46250]	Loss: 0.2923	LR: 0.038122
Training Epoch: 1 [18176/46250]	Loss: 0.2019	LR: 0.038674
Training Epoch: 1 [18432/46250]	Loss: 0.2660	LR: 0.039227
Training Epoch: 1 [18688/46250]	Loss: 0.3111	LR: 0.039779
Training Epoch: 1 [18944/46250]	Loss: 0.2585	LR: 0.040331
Training Epoch: 1 [19200/46250]	Loss: 0.3184	LR: 0.040884
Training Epoch: 1 [19456/46250]	Loss: 0.3758	LR: 0.041436
Training Epoch: 1 [19712/46250]	Loss: 0.2183	LR: 0.041989
Training Epoch: 1 [19968/46250]	Loss: 0.3200	LR: 0.042541
Training Epoch: 1 [20224/46250]	Loss: 0.1874	LR: 0.043094
Training Epoch: 1 [20480/46250]	Loss: 0.2163	LR: 0.043646
Training Epoch: 1 [20736/46250]	Loss: 0.2467	LR: 0.044199
Training Epoch: 1 [20992/46250]	Loss: 0.1948	LR: 0.044751
Training Epoch: 1 [21248/46250]	Loss: 0.2876	LR: 0.045304
Training Epoch: 1 [21504/46250]	Loss: 0.2058	LR: 0.045856
Training Epoch: 1 [21760/46250]	Loss: 0.2649	LR: 0.046409
Training Epoch: 1 [22016/46250]	Loss: 0.2857	LR: 0.046961
Training Epoch: 1 [22272/46250]	Loss: 0.1708	LR: 0.047514
Training Epoch: 1 [22528/46250]	Loss: 0.2654	LR: 0.048066
Training Epoch: 1 [22784/46250]	Loss: 0.2075	LR: 0.048619
Training Epoch: 1 [23040/46250]	Loss: 0.2974	LR: 0.049171
Training Epoch: 1 [23296/46250]	Loss: 0.2776	LR: 0.049724
Training Epoch: 1 [23552/46250]	Loss: 0.1407	LR: 0.050276
Training Epoch: 1 [23808/46250]	Loss: 0.2655	LR: 0.050829
Training Epoch: 1 [24064/46250]	Loss: 0.2850	LR: 0.051381
Training Epoch: 1 [24320/46250]	Loss: 0.2053	LR: 0.051934
Training Epoch: 1 [24576/46250]	Loss: 0.1206	LR: 0.052486
Training Epoch: 1 [24832/46250]	Loss: 0.2411	LR: 0.053039
Training Epoch: 1 [25088/46250]	Loss: 0.2254	LR: 0.053591
Training Epoch: 1 [25344/46250]	Loss: 0.3182	LR: 0.054144
Training Epoch: 1 [25600/46250]	Loss: 0.2153	LR: 0.054696
Training Epoch: 1 [25856/46250]	Loss: 0.2885	LR: 0.055249
Training Epoch: 1 [26112/46250]	Loss: 0.3653	LR: 0.055801
Training Epoch: 1 [26368/46250]	Loss: 0.2470	LR: 0.056354
Training Epoch: 1 [26624/46250]	Loss: 0.2658	LR: 0.056906
Training Epoch: 1 [26880/46250]	Loss: 0.1930	LR: 0.057459
Training Epoch: 1 [27136/46250]	Loss: 0.2544	LR: 0.058011
Training Epoch: 1 [27392/46250]	Loss: 0.2364	LR: 0.058564
Training Epoch: 1 [27648/46250]	Loss: 0.1905	LR: 0.059116
Training Epoch: 1 [27904/46250]	Loss: 0.2054	LR: 0.059669
Training Epoch: 1 [28160/46250]	Loss: 0.1794	LR: 0.060221
Training Epoch: 1 [28416/46250]	Loss: 0.2304	LR: 0.060773
Training Epoch: 1 [28672/46250]	Loss: 0.1807	LR: 0.061326
Training Epoch: 1 [28928/46250]	Loss: 0.1069	LR: 0.061878
Training Epoch: 1 [29184/46250]	Loss: 0.2324	LR: 0.062431
Training Epoch: 1 [29440/46250]	Loss: 0.1513	LR: 0.062983
Training Epoch: 1 [29696/46250]	Loss: 0.1144	LR: 0.063536
Training Epoch: 1 [29952/46250]	Loss: 0.1002	LR: 0.064088
Training Epoch: 1 [30208/46250]	Loss: 0.1306	LR: 0.064641
Training Epoch: 1 [30464/46250]	Loss: 0.1862	LR: 0.065193
Training Epoch: 1 [30720/46250]	Loss: 0.2067	LR: 0.065746
Training Epoch: 1 [30976/46250]	Loss: 0.1151	LR: 0.066298
Training Epoch: 1 [31232/46250]	Loss: 0.2576	LR: 0.066851
Training Epoch: 1 [31488/46250]	Loss: 0.3849	LR: 0.067403
Training Epoch: 1 [31744/46250]	Loss: 0.2202	LR: 0.067956
Training Epoch: 1 [32000/46250]	Loss: 0.3117	LR: 0.068508
Training Epoch: 1 [32256/46250]	Loss: 0.2222	LR: 0.069061
Training Epoch: 1 [32512/46250]	Loss: 0.4900	LR: 0.069613
Training Epoch: 1 [32768/46250]	Loss: 0.1158	LR: 0.070166
Training Epoch: 1 [33024/46250]	Loss: 0.1884	LR: 0.070718
Training Epoch: 1 [33280/46250]	Loss: 0.3447	LR: 0.071271
Training Epoch: 1 [33536/46250]	Loss: 0.2620	LR: 0.071823
Training Epoch: 1 [33792/46250]	Loss: 0.1698	LR: 0.072376
Training Epoch: 1 [34048/46250]	Loss: 0.1321	LR: 0.072928
Training Epoch: 1 [34304/46250]	Loss: 0.2687	LR: 0.073481
Training Epoch: 1 [34560/46250]	Loss: 0.2809	LR: 0.074033
Training Epoch: 1 [34816/46250]	Loss: 0.2004	LR: 0.074586
Training Epoch: 1 [35072/46250]	Loss: 0.1997	LR: 0.075138
Training Epoch: 1 [35328/46250]	Loss: 0.4485	LR: 0.075691
Training Epoch: 1 [35584/46250]	Loss: 0.2168	LR: 0.076243
Training Epoch: 1 [35840/46250]	Loss: 0.2750	LR: 0.076796
Training Epoch: 1 [36096/46250]	Loss: 0.2712	LR: 0.077348
Training Epoch: 1 [36352/46250]	Loss: 0.1994	LR: 0.077901
Training Epoch: 1 [36608/46250]	Loss: 0.2755	LR: 0.078453
Training Epoch: 1 [36864/46250]	Loss: 0.1743	LR: 0.079006
Training Epoch: 1 [37120/46250]	Loss: 0.2336	LR: 0.079558
Training Epoch: 1 [37376/46250]	Loss: 0.2143	LR: 0.080110
Training Epoch: 1 [37632/46250]	Loss: 0.1685	LR: 0.080663
Training Epoch: 1 [37888/46250]	Loss: 0.2990	LR: 0.081215
Training Epoch: 1 [38144/46250]	Loss: 0.2352	LR: 0.081768
Training Epoch: 1 [38400/46250]	Loss: 0.4095	LR: 0.082320
Training Epoch: 1 [38656/46250]	Loss: 0.1586	LR: 0.082873
Training Epoch: 1 [38912/46250]	Loss: 0.1730	LR: 0.083425
Training Epoch: 1 [39168/46250]	Loss: 0.2744	LR: 0.083978
Training Epoch: 1 [39424/46250]	Loss: 0.2266	LR: 0.084530
Training Epoch: 1 [39680/46250]	Loss: 0.2759	LR: 0.085083
Training Epoch: 1 [39936/46250]	Loss: 0.3227	LR: 0.085635
Training Epoch: 1 [40192/46250]	Loss: 0.2556	LR: 0.086188
Training Epoch: 1 [40448/46250]	Loss: 0.3181	LR: 0.086740
Training Epoch: 1 [40704/46250]	Loss: 0.2930	LR: 0.087293
Training Epoch: 1 [40960/46250]	Loss: 0.3417	LR: 0.087845
Training Epoch: 1 [41216/46250]	Loss: 0.2099	LR: 0.088398
Training Epoch: 1 [41472/46250]	Loss: 0.2974	LR: 0.088950
Training Epoch: 1 [41728/46250]	Loss: 0.1707	LR: 0.089503
Training Epoch: 1 [41984/46250]	Loss: 0.2966	LR: 0.090055
Training Epoch: 1 [42240/46250]	Loss: 0.2319	LR: 0.090608
Training Epoch: 1 [42496/46250]	Loss: 0.1597	LR: 0.091160
Training Epoch: 1 [42752/46250]	Loss: 0.2791	LR: 0.091713
Training Epoch: 1 [43008/46250]	Loss: 0.1654	LR: 0.092265
Training Epoch: 1 [43264/46250]	Loss: 0.2246	LR: 0.092818
Training Epoch: 1 [43520/46250]	Loss: 0.2352	LR: 0.093370
Training Epoch: 1 [43776/46250]	Loss: 0.2240	LR: 0.093923
Training Epoch: 1 [44032/46250]	Loss: 0.2887	LR: 0.094475
Training Epoch: 1 [44288/46250]	Loss: 0.2698	LR: 0.095028
Training Epoch: 1 [44544/46250]	Loss: 0.2188	LR: 0.095580
Training Epoch: 1 [44800/46250]	Loss: 0.3682	LR: 0.096133
Training Epoch: 1 [45056/46250]	Loss: 0.2089	LR: 0.096685
Training Epoch: 1 [45312/46250]	Loss: 0.1762	LR: 0.097238
Training Epoch: 1 [45568/46250]	Loss: 0.2933	LR: 0.097790
Training Epoch: 1 [45824/46250]	Loss: 0.2675	LR: 0.098343
Training Epoch: 1 [46080/46250]	Loss: 0.3213	LR: 0.098895
Training Epoch: 1 [46250/46250]	Loss: 0.2467	LR: 0.099448
Epoch 1 - Average Train Loss: 0.3809, Train Accuracy: 0.8777
Epoch 1 training time consumed: 335.53s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0006, Accuracy: 0.9491, Time consumed:23.53s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_18h_15m_14s/ViT-Cifar10-seed1-ret25-1-best.pth
Training Epoch: 2 [256/46250]	Loss: 0.2288	LR: 0.100000
Training Epoch: 2 [512/46250]	Loss: 0.1174	LR: 0.100000
Training Epoch: 2 [768/46250]	Loss: 0.2571	LR: 0.100000
Training Epoch: 2 [1024/46250]	Loss: 0.2533	LR: 0.100000
Training Epoch: 2 [1280/46250]	Loss: 0.1691	LR: 0.100000
Training Epoch: 2 [1536/46250]	Loss: 0.2207	LR: 0.100000
Training Epoch: 2 [1792/46250]	Loss: 0.1289	LR: 0.100000
Training Epoch: 2 [2048/46250]	Loss: 0.2090	LR: 0.100000
Training Epoch: 2 [2304/46250]	Loss: 0.1688	LR: 0.100000
Training Epoch: 2 [2560/46250]	Loss: 0.1631	LR: 0.100000
Training Epoch: 2 [2816/46250]	Loss: 0.1681	LR: 0.100000
Training Epoch: 2 [3072/46250]	Loss: 0.1305	LR: 0.100000
Training Epoch: 2 [3328/46250]	Loss: 0.1950	LR: 0.100000
Training Epoch: 2 [3584/46250]	Loss: 0.3531	LR: 0.100000
Training Epoch: 2 [3840/46250]	Loss: 0.2938	LR: 0.100000
Training Epoch: 2 [4096/46250]	Loss: 0.3937	LR: 0.100000
Training Epoch: 2 [4352/46250]	Loss: 0.3307	LR: 0.100000
Training Epoch: 2 [4608/46250]	Loss: 0.4721	LR: 0.100000
Training Epoch: 2 [4864/46250]	Loss: 0.3275	LR: 0.100000
Training Epoch: 2 [5120/46250]	Loss: 0.2641	LR: 0.100000
Training Epoch: 2 [5376/46250]	Loss: 1.3667	LR: 0.100000
Training Epoch: 2 [5632/46250]	Loss: 1.1824	LR: 0.100000
Training Epoch: 2 [5888/46250]	Loss: 0.9833	LR: 0.100000
Training Epoch: 2 [6144/46250]	Loss: 2.2022	LR: 0.100000
Training Epoch: 2 [6400/46250]	Loss: 2.4996	LR: 0.100000
Training Epoch: 2 [6656/46250]	Loss: 2.4273	LR: 0.100000
Training Epoch: 2 [6912/46250]	Loss: 2.3188	LR: 0.100000
Training Epoch: 2 [7168/46250]	Loss: 2.2726	LR: 0.100000
Training Epoch: 2 [7424/46250]	Loss: 2.3278	LR: 0.100000
Training Epoch: 2 [7680/46250]	Loss: 2.3868	LR: 0.100000
Training Epoch: 2 [7936/46250]	Loss: 2.2682	LR: 0.100000
Training Epoch: 2 [8192/46250]	Loss: 2.3144	LR: 0.100000
Training Epoch: 2 [8448/46250]	Loss: 2.2627	LR: 0.100000
Training Epoch: 2 [8704/46250]	Loss: 2.3836	LR: 0.100000
Training Epoch: 2 [8960/46250]	Loss: 2.2483	LR: 0.100000
Training Epoch: 2 [9216/46250]	Loss: 2.2725	LR: 0.100000
Training Epoch: 2 [9472/46250]	Loss: 2.2146	LR: 0.100000
Training Epoch: 2 [9728/46250]	Loss: 2.2143	LR: 0.100000
Training Epoch: 2 [9984/46250]	Loss: 2.2424	LR: 0.100000
Training Epoch: 2 [10240/46250]	Loss: 2.2916	LR: 0.100000
Training Epoch: 2 [10496/46250]	Loss: 2.2480	LR: 0.100000
Training Epoch: 2 [10752/46250]	Loss: 2.2250	LR: 0.100000
Training Epoch: 2 [11008/46250]	Loss: 2.3133	LR: 0.100000
Training Epoch: 2 [11264/46250]	Loss: 2.1582	LR: 0.100000
Training Epoch: 2 [11520/46250]	Loss: 2.1478	LR: 0.100000
Training Epoch: 2 [11776/46250]	Loss: 2.2341	LR: 0.100000
Training Epoch: 2 [12032/46250]	Loss: 2.1935	LR: 0.100000
Training Epoch: 2 [12288/46250]	Loss: 2.1324	LR: 0.100000
Training Epoch: 2 [12544/46250]	Loss: 2.1655	LR: 0.100000
Training Epoch: 2 [12800/46250]	Loss: 2.1072	LR: 0.100000
Training Epoch: 2 [13056/46250]	Loss: 2.1590	LR: 0.100000
Training Epoch: 2 [13312/46250]	Loss: 2.1807	LR: 0.100000
Training Epoch: 2 [13568/46250]	Loss: 2.0781	LR: 0.100000
Training Epoch: 2 [13824/46250]	Loss: 2.1525	LR: 0.100000
Training Epoch: 2 [14080/46250]	Loss: 2.1183	LR: 0.100000
Training Epoch: 2 [14336/46250]	Loss: 2.0555	LR: 0.100000
Training Epoch: 2 [14592/46250]	Loss: 2.0537	LR: 0.100000
Training Epoch: 2 [14848/46250]	Loss: 2.0680	LR: 0.100000
Training Epoch: 2 [15104/46250]	Loss: 2.0294	LR: 0.100000
Training Epoch: 2 [15360/46250]	Loss: 2.0587	LR: 0.100000
Training Epoch: 2 [15616/46250]	Loss: 2.0347	LR: 0.100000
Training Epoch: 2 [15872/46250]	Loss: 2.0713	LR: 0.100000
Training Epoch: 2 [16128/46250]	Loss: 2.0132	LR: 0.100000
Training Epoch: 2 [16384/46250]	Loss: 1.9719	LR: 0.100000
Training Epoch: 2 [16640/46250]	Loss: 1.9611	LR: 0.100000
Training Epoch: 2 [16896/46250]	Loss: 2.0315	LR: 0.100000
Training Epoch: 2 [17152/46250]	Loss: 2.0525	LR: 0.100000
Training Epoch: 2 [17408/46250]	Loss: 1.9398	LR: 0.100000
Training Epoch: 2 [17664/46250]	Loss: 1.9963	LR: 0.100000
Training Epoch: 2 [17920/46250]	Loss: 1.9845	LR: 0.100000
Training Epoch: 2 [18176/46250]	Loss: 2.0580	LR: 0.100000
Training Epoch: 2 [18432/46250]	Loss: 1.9879	LR: 0.100000
Training Epoch: 2 [18688/46250]	Loss: 1.9905	LR: 0.100000
Training Epoch: 2 [18944/46250]	Loss: 1.8568	LR: 0.100000
Training Epoch: 2 [19200/46250]	Loss: 1.8913	LR: 0.100000
Training Epoch: 2 [19456/46250]	Loss: 1.9409	LR: 0.100000
Training Epoch: 2 [19712/46250]	Loss: 1.9937	LR: 0.100000
Training Epoch: 2 [19968/46250]	Loss: 2.0281	LR: 0.100000
Training Epoch: 2 [20224/46250]	Loss: 1.9063	LR: 0.100000
Training Epoch: 2 [20480/46250]	Loss: 1.9421	LR: 0.100000
Training Epoch: 2 [20736/46250]	Loss: 1.9433	LR: 0.100000
Training Epoch: 2 [20992/46250]	Loss: 2.0419	LR: 0.100000
Training Epoch: 2 [21248/46250]	Loss: 1.9063	LR: 0.100000
Training Epoch: 2 [21504/46250]	Loss: 1.9704	LR: 0.100000
Training Epoch: 2 [21760/46250]	Loss: 1.8205	LR: 0.100000
Training Epoch: 2 [22016/46250]	Loss: 1.8390	LR: 0.100000
Training Epoch: 2 [22272/46250]	Loss: 1.9697	LR: 0.100000
Training Epoch: 2 [22528/46250]	Loss: 1.9180	LR: 0.100000
Training Epoch: 2 [22784/46250]	Loss: 1.8511	LR: 0.100000
Training Epoch: 2 [23040/46250]	Loss: 1.8921	LR: 0.100000
Training Epoch: 2 [23296/46250]	Loss: 1.8394	LR: 0.100000
Training Epoch: 2 [23552/46250]	Loss: 1.8878	LR: 0.100000
Training Epoch: 2 [23808/46250]	Loss: 1.9370	LR: 0.100000
Training Epoch: 2 [24064/46250]	Loss: 1.8831	LR: 0.100000
Training Epoch: 2 [24320/46250]	Loss: 1.9287	LR: 0.100000
Training Epoch: 2 [24576/46250]	Loss: 1.8251	LR: 0.100000
Training Epoch: 2 [24832/46250]	Loss: 1.8226	LR: 0.100000
Training Epoch: 2 [25088/46250]	Loss: 1.9313	LR: 0.100000
Training Epoch: 2 [25344/46250]	Loss: 1.8204	LR: 0.100000
Training Epoch: 2 [25600/46250]	Loss: 1.8359	LR: 0.100000
Training Epoch: 2 [25856/46250]	Loss: 1.7858	LR: 0.100000
Training Epoch: 2 [26112/46250]	Loss: 1.8251	LR: 0.100000
Training Epoch: 2 [26368/46250]	Loss: 1.8951	LR: 0.100000
Training Epoch: 2 [26624/46250]	Loss: 1.7864	LR: 0.100000
Training Epoch: 2 [26880/46250]	Loss: 1.8965	LR: 0.100000
Training Epoch: 2 [27136/46250]	Loss: 1.8084	LR: 0.100000
Training Epoch: 2 [27392/46250]	Loss: 1.7735	LR: 0.100000
Training Epoch: 2 [27648/46250]	Loss: 1.8244	LR: 0.100000
Training Epoch: 2 [27904/46250]	Loss: 1.7184	LR: 0.100000
Training Epoch: 2 [28160/46250]	Loss: 1.8065	LR: 0.100000
Training Epoch: 2 [28416/46250]	Loss: 1.7271	LR: 0.100000
Training Epoch: 2 [28672/46250]	Loss: 1.7432	LR: 0.100000
Training Epoch: 2 [28928/46250]	Loss: 1.7396	LR: 0.100000
Training Epoch: 2 [29184/46250]	Loss: 1.6890	LR: 0.100000
Training Epoch: 2 [29440/46250]	Loss: 1.8176	LR: 0.100000
Training Epoch: 2 [29696/46250]	Loss: 1.6903	LR: 0.100000
Training Epoch: 2 [29952/46250]	Loss: 1.7689	LR: 0.100000
Training Epoch: 2 [30208/46250]	Loss: 1.7730	LR: 0.100000
Training Epoch: 2 [30464/46250]	Loss: 1.6525	LR: 0.100000
Training Epoch: 2 [30720/46250]	Loss: 1.7357	LR: 0.100000
Training Epoch: 2 [30976/46250]	Loss: 1.6708	LR: 0.100000
Training Epoch: 2 [31232/46250]	Loss: 1.6877	LR: 0.100000
Training Epoch: 2 [31488/46250]	Loss: 1.6893	LR: 0.100000
Training Epoch: 2 [31744/46250]	Loss: 1.6759	LR: 0.100000
Training Epoch: 2 [32000/46250]	Loss: 1.7243	LR: 0.100000
Training Epoch: 2 [32256/46250]	Loss: 1.6779	LR: 0.100000
Training Epoch: 2 [32512/46250]	Loss: 1.6626	LR: 0.100000
Training Epoch: 2 [32768/46250]	Loss: 1.5809	LR: 0.100000
Training Epoch: 2 [33024/46250]	Loss: 1.6019	LR: 0.100000
Training Epoch: 2 [33280/46250]	Loss: 1.5774	LR: 0.100000
Training Epoch: 2 [33536/46250]	Loss: 1.6760	LR: 0.100000
Training Epoch: 2 [33792/46250]	Loss: 1.6364	LR: 0.100000
Training Epoch: 2 [34048/46250]	Loss: 1.6935	LR: 0.100000
Training Epoch: 2 [34304/46250]	Loss: 1.5920	LR: 0.100000
Training Epoch: 2 [34560/46250]	Loss: 1.6896	LR: 0.100000
Training Epoch: 2 [34816/46250]	Loss: 1.7269	LR: 0.100000
Training Epoch: 2 [35072/46250]	Loss: 1.6172	LR: 0.100000
Training Epoch: 2 [35328/46250]	Loss: 1.5904	LR: 0.100000
Training Epoch: 2 [35584/46250]	Loss: 1.6923	LR: 0.100000
Training Epoch: 2 [35840/46250]	Loss: 1.6027	LR: 0.100000
Training Epoch: 2 [36096/46250]	Loss: 1.5897	LR: 0.100000
Training Epoch: 2 [36352/46250]	Loss: 1.5245	LR: 0.100000
Training Epoch: 2 [36608/46250]	Loss: 1.6006	LR: 0.100000
Training Epoch: 2 [36864/46250]	Loss: 1.6242	LR: 0.100000
Training Epoch: 2 [37120/46250]	Loss: 1.5593	LR: 0.100000
Training Epoch: 2 [37376/46250]	Loss: 1.4986	LR: 0.100000
Training Epoch: 2 [37632/46250]	Loss: 1.5512	LR: 0.100000
Training Epoch: 2 [37888/46250]	Loss: 1.4945	LR: 0.100000
Training Epoch: 2 [38144/46250]	Loss: 1.5277	LR: 0.100000
Training Epoch: 2 [38400/46250]	Loss: 1.4654	LR: 0.100000
Training Epoch: 2 [38656/46250]	Loss: 1.4918	LR: 0.100000
Training Epoch: 2 [38912/46250]	Loss: 1.6987	LR: 0.100000
Training Epoch: 2 [39168/46250]	Loss: 1.6061	LR: 0.100000
Training Epoch: 2 [39424/46250]	Loss: 1.4507	LR: 0.100000
Training Epoch: 2 [39680/46250]	Loss: 1.6337	LR: 0.100000
Training Epoch: 2 [39936/46250]	Loss: 1.4419	LR: 0.100000
Training Epoch: 2 [40192/46250]	Loss: 1.5675	LR: 0.100000
Training Epoch: 2 [40448/46250]	Loss: 1.7554	LR: 0.100000
Training Epoch: 2 [40704/46250]	Loss: 1.6365	LR: 0.100000
Training Epoch: 2 [40960/46250]	Loss: 1.5350	LR: 0.100000
Training Epoch: 2 [41216/46250]	Loss: 1.6350	LR: 0.100000
Training Epoch: 2 [41472/46250]	Loss: 1.4827	LR: 0.100000
Training Epoch: 2 [41728/46250]	Loss: 1.5126	LR: 0.100000
Training Epoch: 2 [41984/46250]	Loss: 1.5316	LR: 0.100000
Training Epoch: 2 [42240/46250]	Loss: 1.5088	LR: 0.100000
Training Epoch: 2 [42496/46250]	Loss: 1.5174	LR: 0.100000
Training Epoch: 2 [42752/46250]	Loss: 1.4082	LR: 0.100000
Training Epoch: 2 [43008/46250]	Loss: 1.5263	LR: 0.100000
Training Epoch: 2 [43264/46250]	Loss: 1.4200	LR: 0.100000
Training Epoch: 2 [43520/46250]	Loss: 1.3923	LR: 0.100000
Training Epoch: 2 [43776/46250]	Loss: 1.4574	LR: 0.100000
Training Epoch: 2 [44032/46250]	Loss: 1.4958	LR: 0.100000
Training Epoch: 2 [44288/46250]	Loss: 1.4440	LR: 0.100000
Training Epoch: 2 [44544/46250]	Loss: 1.5324	LR: 0.100000
Training Epoch: 2 [44800/46250]	Loss: 1.5029	LR: 0.100000
Training Epoch: 2 [45056/46250]	Loss: 1.5027	LR: 0.100000
Training Epoch: 2 [45312/46250]	Loss: 1.4216	LR: 0.100000
Training Epoch: 2 [45568/46250]	Loss: 1.4977	LR: 0.100000
Training Epoch: 2 [45824/46250]	Loss: 1.4667	LR: 0.100000
Training Epoch: 2 [46080/46250]	Loss: 1.4756	LR: 0.100000
Training Epoch: 2 [46250/46250]	Loss: 1.4054	LR: 0.100000
Epoch 2 - Average Train Loss: 1.6515, Train Accuracy: 0.3878
Epoch 2 training time consumed: 334.74s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0056, Accuracy: 0.4964, Time consumed:23.56s
Training Epoch: 3 [256/46250]	Loss: 1.2898	LR: 0.100000
Training Epoch: 3 [512/46250]	Loss: 1.4357	LR: 0.100000
Training Epoch: 3 [768/46250]	Loss: 1.3904	LR: 0.100000
Training Epoch: 3 [1024/46250]	Loss: 1.5714	LR: 0.100000
Training Epoch: 3 [1280/46250]	Loss: 1.5250	LR: 0.100000
Training Epoch: 3 [1536/46250]	Loss: 1.5198	LR: 0.100000
Training Epoch: 3 [1792/46250]	Loss: 1.4659	LR: 0.100000
Training Epoch: 3 [2048/46250]	Loss: 1.3723	LR: 0.100000
Training Epoch: 3 [2304/46250]	Loss: 1.4373	LR: 0.100000
Training Epoch: 3 [2560/46250]	Loss: 1.3144	LR: 0.100000
Training Epoch: 3 [2816/46250]	Loss: 1.3606	LR: 0.100000
Training Epoch: 3 [3072/46250]	Loss: 1.3307	LR: 0.100000
Training Epoch: 3 [3328/46250]	Loss: 1.3603	LR: 0.100000
Training Epoch: 3 [3584/46250]	Loss: 1.3158	LR: 0.100000
Training Epoch: 3 [3840/46250]	Loss: 1.3306	LR: 0.100000
Training Epoch: 3 [4096/46250]	Loss: 1.4465	LR: 0.100000
Training Epoch: 3 [4352/46250]	Loss: 1.2357	LR: 0.100000
Training Epoch: 3 [4608/46250]	Loss: 1.3615	LR: 0.100000
Training Epoch: 3 [4864/46250]	Loss: 1.2378	LR: 0.100000
Training Epoch: 3 [5120/46250]	Loss: 1.2283	LR: 0.100000
Training Epoch: 3 [5376/46250]	Loss: 1.2801	LR: 0.100000
Training Epoch: 3 [5632/46250]	Loss: 1.2365	LR: 0.100000
Training Epoch: 3 [5888/46250]	Loss: 1.3678	LR: 0.100000
Training Epoch: 3 [6144/46250]	Loss: 1.2721	LR: 0.100000
Training Epoch: 3 [6400/46250]	Loss: 1.1206	LR: 0.100000
Training Epoch: 3 [6656/46250]	Loss: 1.2006	LR: 0.100000
Training Epoch: 3 [6912/46250]	Loss: 1.2351	LR: 0.100000
Training Epoch: 3 [7168/46250]	Loss: 1.1841	LR: 0.100000
Training Epoch: 3 [7424/46250]	Loss: 1.3583	LR: 0.100000
Training Epoch: 3 [7680/46250]	Loss: 1.0950	LR: 0.100000
Training Epoch: 3 [7936/46250]	Loss: 1.3194	LR: 0.100000
Training Epoch: 3 [8192/46250]	Loss: 1.4069	LR: 0.100000
Training Epoch: 3 [8448/46250]	Loss: 1.0285	LR: 0.100000
Training Epoch: 3 [8704/46250]	Loss: 1.2409	LR: 0.100000
Training Epoch: 3 [8960/46250]	Loss: 1.1499	LR: 0.100000
Training Epoch: 3 [9216/46250]	Loss: 1.1245	LR: 0.100000
Training Epoch: 3 [9472/46250]	Loss: 1.1349	LR: 0.100000
Training Epoch: 3 [9728/46250]	Loss: 1.0764	LR: 0.100000
Training Epoch: 3 [9984/46250]	Loss: 1.1321	LR: 0.100000
Training Epoch: 3 [10240/46250]	Loss: 1.0978	LR: 0.100000
Training Epoch: 3 [10496/46250]	Loss: 1.1123	LR: 0.100000
Training Epoch: 3 [10752/46250]	Loss: 1.1276	LR: 0.100000
Training Epoch: 3 [11008/46250]	Loss: 1.0922	LR: 0.100000
Training Epoch: 3 [11264/46250]	Loss: 0.9138	LR: 0.100000
Training Epoch: 3 [11520/46250]	Loss: 1.0948	LR: 0.100000
Training Epoch: 3 [11776/46250]	Loss: 1.0702	LR: 0.100000
Training Epoch: 3 [12032/46250]	Loss: 1.1892	LR: 0.100000
Training Epoch: 3 [12288/46250]	Loss: 1.0766	LR: 0.100000
Training Epoch: 3 [12544/46250]	Loss: 0.8191	LR: 0.100000
Training Epoch: 3 [12800/46250]	Loss: 1.0578	LR: 0.100000
Training Epoch: 3 [13056/46250]	Loss: 1.0742	LR: 0.100000
Training Epoch: 3 [13312/46250]	Loss: 1.0441	LR: 0.100000
Training Epoch: 3 [13568/46250]	Loss: 1.1750	LR: 0.100000
Training Epoch: 3 [13824/46250]	Loss: 0.9702	LR: 0.100000
Training Epoch: 3 [14080/46250]	Loss: 1.0549	LR: 0.100000
Training Epoch: 3 [14336/46250]	Loss: 0.8937	LR: 0.100000
Training Epoch: 3 [14592/46250]	Loss: 1.0191	LR: 0.100000
Training Epoch: 3 [14848/46250]	Loss: 0.9234	LR: 0.100000
Training Epoch: 3 [15104/46250]	Loss: 0.9334	LR: 0.100000
Training Epoch: 3 [15360/46250]	Loss: 0.8602	LR: 0.100000
Training Epoch: 3 [15616/46250]	Loss: 0.9496	LR: 0.100000
Training Epoch: 3 [15872/46250]	Loss: 0.8663	LR: 0.100000
Training Epoch: 3 [16128/46250]	Loss: 0.9486	LR: 0.100000
Training Epoch: 3 [16384/46250]	Loss: 0.9333	LR: 0.100000
Training Epoch: 3 [16640/46250]	Loss: 0.8363	LR: 0.100000
Training Epoch: 3 [16896/46250]	Loss: 1.0959	LR: 0.100000
Training Epoch: 3 [17152/46250]	Loss: 0.8953	LR: 0.100000
Training Epoch: 3 [17408/46250]	Loss: 0.8196	LR: 0.100000
Training Epoch: 3 [17664/46250]	Loss: 0.7484	LR: 0.100000
Training Epoch: 3 [17920/46250]	Loss: 0.8738	LR: 0.100000
Training Epoch: 3 [18176/46250]	Loss: 0.7495	LR: 0.100000
Training Epoch: 3 [18432/46250]	Loss: 0.7437	LR: 0.100000
Training Epoch: 3 [18688/46250]	Loss: 0.9500	LR: 0.100000
Training Epoch: 3 [18944/46250]	Loss: 0.7979	LR: 0.100000
Training Epoch: 3 [19200/46250]	Loss: 0.8421	LR: 0.100000
Training Epoch: 3 [19456/46250]	Loss: 0.7852	LR: 0.100000
Training Epoch: 3 [19712/46250]	Loss: 0.8715	LR: 0.100000
Training Epoch: 3 [19968/46250]	Loss: 0.7368	LR: 0.100000
Training Epoch: 3 [20224/46250]	Loss: 0.6879	LR: 0.100000
Training Epoch: 3 [20480/46250]	Loss: 0.8278	LR: 0.100000
Training Epoch: 3 [20736/46250]	Loss: 0.7565	LR: 0.100000
Training Epoch: 3 [20992/46250]	Loss: 0.5840	LR: 0.100000
Training Epoch: 3 [21248/46250]	Loss: 0.7976	LR: 0.100000
Training Epoch: 3 [21504/46250]	Loss: 0.5203	LR: 0.100000
Training Epoch: 3 [21760/46250]	Loss: 0.6747	LR: 0.100000
Training Epoch: 3 [22016/46250]	Loss: 0.6294	LR: 0.100000
Training Epoch: 3 [22272/46250]	Loss: 0.5122	LR: 0.100000
Training Epoch: 3 [22528/46250]	Loss: 0.8750	LR: 0.100000
Training Epoch: 3 [22784/46250]	Loss: 0.5049	LR: 0.100000
Training Epoch: 3 [23040/46250]	Loss: 0.5397	LR: 0.100000
Training Epoch: 3 [23296/46250]	Loss: 0.5915	LR: 0.100000
Training Epoch: 3 [23552/46250]	Loss: 0.5814	LR: 0.100000
Training Epoch: 3 [23808/46250]	Loss: 0.4689	LR: 0.100000
Training Epoch: 3 [24064/46250]	Loss: 0.4501	LR: 0.100000
Training Epoch: 3 [24320/46250]	Loss: 0.5458	LR: 0.100000
Training Epoch: 3 [24576/46250]	Loss: 0.4764	LR: 0.100000
Training Epoch: 3 [24832/46250]	Loss: 0.4583	LR: 0.100000
Training Epoch: 3 [25088/46250]	Loss: 0.4876	LR: 0.100000
Training Epoch: 3 [25344/46250]	Loss: 0.3753	LR: 0.100000
Training Epoch: 3 [25600/46250]	Loss: 0.3744	LR: 0.100000
Training Epoch: 3 [25856/46250]	Loss: 0.4430	LR: 0.100000
Training Epoch: 3 [26112/46250]	Loss: 0.3104	LR: 0.100000
Training Epoch: 3 [26368/46250]	Loss: 0.3960	LR: 0.100000
Training Epoch: 3 [26624/46250]	Loss: 0.3814	LR: 0.100000
Training Epoch: 3 [26880/46250]	Loss: 0.3892	LR: 0.100000
Training Epoch: 3 [27136/46250]	Loss: 0.4220	LR: 0.100000
Training Epoch: 3 [27392/46250]	Loss: 0.2496	LR: 0.100000
Training Epoch: 3 [27648/46250]	Loss: 0.4286	LR: 0.100000
Training Epoch: 3 [27904/46250]	Loss: 0.3641	LR: 0.100000
Training Epoch: 3 [28160/46250]	Loss: 0.4109	LR: 0.100000
Training Epoch: 3 [28416/46250]	Loss: 0.3838	LR: 0.100000
Training Epoch: 3 [28672/46250]	Loss: 0.4220	LR: 0.100000
Training Epoch: 3 [28928/46250]	Loss: 0.3252	LR: 0.100000
Training Epoch: 3 [29184/46250]	Loss: 0.3649	LR: 0.100000
Training Epoch: 3 [29440/46250]	Loss: 0.3631	LR: 0.100000
Training Epoch: 3 [29696/46250]	Loss: 0.3709	LR: 0.100000
Training Epoch: 3 [29952/46250]	Loss: 0.4888	LR: 0.100000
Training Epoch: 3 [30208/46250]	Loss: 0.7039	LR: 0.100000
Training Epoch: 3 [30464/46250]	Loss: 0.5181	LR: 0.100000
Training Epoch: 3 [30720/46250]	Loss: 0.6661	LR: 0.100000
Training Epoch: 3 [30976/46250]	Loss: 0.6024	LR: 0.100000
Training Epoch: 3 [31232/46250]	Loss: 0.5767	LR: 0.100000
Training Epoch: 3 [31488/46250]	Loss: 0.4338	LR: 0.100000
Training Epoch: 3 [31744/46250]	Loss: 0.4148	LR: 0.100000
Training Epoch: 3 [32000/46250]	Loss: 0.2848	LR: 0.100000
Training Epoch: 3 [32256/46250]	Loss: 0.4693	LR: 0.100000
Training Epoch: 3 [32512/46250]	Loss: 0.3582	LR: 0.100000
Training Epoch: 3 [32768/46250]	Loss: 0.4428	LR: 0.100000
Training Epoch: 3 [33024/46250]	Loss: 0.4440	LR: 0.100000
Training Epoch: 3 [33280/46250]	Loss: 0.3194	LR: 0.100000
Training Epoch: 3 [33536/46250]	Loss: 0.4403	LR: 0.100000
Training Epoch: 3 [33792/46250]	Loss: 0.5329	LR: 0.100000
Training Epoch: 3 [34048/46250]	Loss: 0.4529	LR: 0.100000
Training Epoch: 3 [34304/46250]	Loss: 0.4471	LR: 0.100000
Training Epoch: 3 [34560/46250]	Loss: 0.3599	LR: 0.100000
Training Epoch: 3 [34816/46250]	Loss: 0.2948	LR: 0.100000
Training Epoch: 3 [35072/46250]	Loss: 0.3777	LR: 0.100000
Training Epoch: 3 [35328/46250]	Loss: 0.3460	LR: 0.100000
Training Epoch: 3 [35584/46250]	Loss: 0.4770	LR: 0.100000
Training Epoch: 3 [35840/46250]	Loss: 0.3209	LR: 0.100000
Training Epoch: 3 [36096/46250]	Loss: 0.3195	LR: 0.100000
Training Epoch: 3 [36352/46250]	Loss: 0.2177	LR: 0.100000
Training Epoch: 3 [36608/46250]	Loss: 0.3949	LR: 0.100000
Training Epoch: 3 [36864/46250]	Loss: 0.2959	LR: 0.100000
Training Epoch: 3 [37120/46250]	Loss: 0.2856	LR: 0.100000
Training Epoch: 3 [37376/46250]	Loss: 0.3275	LR: 0.100000
Training Epoch: 3 [37632/46250]	Loss: 0.2900	LR: 0.100000
Training Epoch: 3 [37888/46250]	Loss: 0.2451	LR: 0.100000
Training Epoch: 3 [38144/46250]	Loss: 0.3867	LR: 0.100000
Training Epoch: 3 [38400/46250]	Loss: 0.3282	LR: 0.100000
Training Epoch: 3 [38656/46250]	Loss: 0.1917	LR: 0.100000
Training Epoch: 3 [38912/46250]	Loss: 0.2946	LR: 0.100000
Training Epoch: 3 [39168/46250]	Loss: 0.2795	LR: 0.100000
Training Epoch: 3 [39424/46250]	Loss: 0.1910	LR: 0.100000
Training Epoch: 3 [39680/46250]	Loss: 0.2264	LR: 0.100000
Training Epoch: 3 [39936/46250]	Loss: 0.2874	LR: 0.100000
Training Epoch: 3 [40192/46250]	Loss: 0.2101	LR: 0.100000
Training Epoch: 3 [40448/46250]	Loss: 0.3425	LR: 0.100000
Training Epoch: 3 [40704/46250]	Loss: 0.3898	LR: 0.100000
Training Epoch: 3 [40960/46250]	Loss: 0.3165	LR: 0.100000
Training Epoch: 3 [41216/46250]	Loss: 0.1701	LR: 0.100000
Training Epoch: 3 [41472/46250]	Loss: 0.3683	LR: 0.100000
Training Epoch: 3 [41728/46250]	Loss: 0.3363	LR: 0.100000
Training Epoch: 3 [41984/46250]	Loss: 0.2487	LR: 0.100000
Training Epoch: 3 [42240/46250]	Loss: 0.4050	LR: 0.100000
Training Epoch: 3 [42496/46250]	Loss: 0.2978	LR: 0.100000
Training Epoch: 3 [42752/46250]	Loss: 0.2936	LR: 0.100000
Training Epoch: 3 [43008/46250]	Loss: 0.4124	LR: 0.100000
Training Epoch: 3 [43264/46250]	Loss: 0.3182	LR: 0.100000
Training Epoch: 3 [43520/46250]	Loss: 0.2798	LR: 0.100000
Training Epoch: 3 [43776/46250]	Loss: 0.2632	LR: 0.100000
Training Epoch: 3 [44032/46250]	Loss: 0.2054	LR: 0.100000
Training Epoch: 3 [44288/46250]	Loss: 0.2954	LR: 0.100000
Training Epoch: 3 [44544/46250]	Loss: 0.2749	LR: 0.100000
Training Epoch: 3 [44800/46250]	Loss: 0.1570	LR: 0.100000
Training Epoch: 3 [45056/46250]	Loss: 0.4036	LR: 0.100000
Training Epoch: 3 [45312/46250]	Loss: 0.3488	LR: 0.100000
Training Epoch: 3 [45568/46250]	Loss: 0.2430	LR: 0.100000
Training Epoch: 3 [45824/46250]	Loss: 0.2669	LR: 0.100000
Training Epoch: 3 [46080/46250]	Loss: 0.3938	LR: 0.100000
Training Epoch: 3 [46250/46250]	Loss: 0.3124	LR: 0.100000
Epoch 3 - Average Train Loss: 0.7144, Train Accuracy: 0.7480
Epoch 3 training time consumed: 334.88s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0010, Accuracy: 0.9108, Time consumed:23.61s
Training Epoch: 4 [256/46250]	Loss: 0.3247	LR: 0.100000
Training Epoch: 4 [512/46250]	Loss: 0.3196	LR: 0.100000
Training Epoch: 4 [768/46250]	Loss: 0.2477	LR: 0.100000
Training Epoch: 4 [1024/46250]	Loss: 0.3532	LR: 0.100000
Training Epoch: 4 [1280/46250]	Loss: 0.2597	LR: 0.100000
Training Epoch: 4 [1536/46250]	Loss: 0.2110	LR: 0.100000
Training Epoch: 4 [1792/46250]	Loss: 0.2478	LR: 0.100000
Training Epoch: 4 [2048/46250]	Loss: 0.3667	LR: 0.100000
Training Epoch: 4 [2304/46250]	Loss: 0.2267	LR: 0.100000
Training Epoch: 4 [2560/46250]	Loss: 0.2680	LR: 0.100000
Training Epoch: 4 [2816/46250]	Loss: 0.2480	LR: 0.100000
Training Epoch: 4 [3072/46250]	Loss: 0.2768	LR: 0.100000
Training Epoch: 4 [3328/46250]	Loss: 0.1963	LR: 0.100000
Training Epoch: 4 [3584/46250]	Loss: 0.2019	LR: 0.100000
Training Epoch: 4 [3840/46250]	Loss: 0.2308	LR: 0.100000
Training Epoch: 4 [4096/46250]	Loss: 0.2355	LR: 0.100000
Training Epoch: 4 [4352/46250]	Loss: 0.2448	LR: 0.100000
Training Epoch: 4 [4608/46250]	Loss: 0.3113	LR: 0.100000
Training Epoch: 4 [4864/46250]	Loss: 0.2843	LR: 0.100000
Training Epoch: 4 [5120/46250]	Loss: 0.2749	LR: 0.100000
Training Epoch: 4 [5376/46250]	Loss: 0.2141	LR: 0.100000
Training Epoch: 4 [5632/46250]	Loss: 0.2396	LR: 0.100000
Training Epoch: 4 [5888/46250]	Loss: 0.1761	LR: 0.100000
Training Epoch: 4 [6144/46250]	Loss: 0.1905	LR: 0.100000
Training Epoch: 4 [6400/46250]	Loss: 0.1945	LR: 0.100000
Training Epoch: 4 [6656/46250]	Loss: 0.2112	LR: 0.100000
Training Epoch: 4 [6912/46250]	Loss: 0.2880	LR: 0.100000
Training Epoch: 4 [7168/46250]	Loss: 0.2334	LR: 0.100000
Training Epoch: 4 [7424/46250]	Loss: 0.1872	LR: 0.100000
Training Epoch: 4 [7680/46250]	Loss: 0.2344	LR: 0.100000
Training Epoch: 4 [7936/46250]	Loss: 0.2651	LR: 0.100000
Training Epoch: 4 [8192/46250]	Loss: 0.1719	LR: 0.100000
Training Epoch: 4 [8448/46250]	Loss: 0.2079	LR: 0.100000
Training Epoch: 4 [8704/46250]	Loss: 0.2062	LR: 0.100000
Training Epoch: 4 [8960/46250]	Loss: 0.1610	LR: 0.100000
Training Epoch: 4 [9216/46250]	Loss: 0.2019	LR: 0.100000
Training Epoch: 4 [9472/46250]	Loss: 0.1590	LR: 0.100000
Training Epoch: 4 [9728/46250]	Loss: 0.1373	LR: 0.100000
Training Epoch: 4 [9984/46250]	Loss: 0.2650	LR: 0.100000
Training Epoch: 4 [10240/46250]	Loss: 0.2076	LR: 0.100000
Training Epoch: 4 [10496/46250]	Loss: 0.2463	LR: 0.100000
Training Epoch: 4 [10752/46250]	Loss: 0.2454	LR: 0.100000
Training Epoch: 4 [11008/46250]	Loss: 0.2214	LR: 0.100000
Training Epoch: 4 [11264/46250]	Loss: 0.2624	LR: 0.100000
Training Epoch: 4 [11520/46250]	Loss: 0.1993	LR: 0.100000
Training Epoch: 4 [11776/46250]	Loss: 0.2516	LR: 0.100000
Training Epoch: 4 [12032/46250]	Loss: 0.2262	LR: 0.100000
Training Epoch: 4 [12288/46250]	Loss: 0.2567	LR: 0.100000
Training Epoch: 4 [12544/46250]	Loss: 0.3901	LR: 0.100000
Training Epoch: 4 [12800/46250]	Loss: 0.3702	LR: 0.100000
Training Epoch: 4 [13056/46250]	Loss: 0.1746	LR: 0.100000
Training Epoch: 4 [13312/46250]	Loss: 0.2633	LR: 0.100000
Training Epoch: 4 [13568/46250]	Loss: 0.3204	LR: 0.100000
Training Epoch: 4 [13824/46250]	Loss: 0.1661	LR: 0.100000
Training Epoch: 4 [14080/46250]	Loss: 0.2173	LR: 0.100000
Training Epoch: 4 [14336/46250]	Loss: 0.2007	LR: 0.100000
Training Epoch: 4 [14592/46250]	Loss: 0.2485	LR: 0.100000
Training Epoch: 4 [14848/46250]	Loss: 0.1896	LR: 0.100000
Training Epoch: 4 [15104/46250]	Loss: 0.2476	LR: 0.100000
Training Epoch: 4 [15360/46250]	Loss: 0.1336	LR: 0.100000
Training Epoch: 4 [15616/46250]	Loss: 0.3075	LR: 0.100000
Training Epoch: 4 [15872/46250]	Loss: 0.2052	LR: 0.100000
Training Epoch: 4 [16128/46250]	Loss: 0.1746	LR: 0.100000
Training Epoch: 4 [16384/46250]	Loss: 0.2052	LR: 0.100000
Training Epoch: 4 [16640/46250]	Loss: 0.2173	LR: 0.100000
Training Epoch: 4 [16896/46250]	Loss: 0.2047	LR: 0.100000
Training Epoch: 4 [17152/46250]	Loss: 0.2059	LR: 0.100000
Training Epoch: 4 [17408/46250]	Loss: 0.2373	LR: 0.100000
Training Epoch: 4 [17664/46250]	Loss: 0.2295	LR: 0.100000
Training Epoch: 4 [17920/46250]	Loss: 0.2600	LR: 0.100000
Training Epoch: 4 [18176/46250]	Loss: 0.2371	LR: 0.100000
Training Epoch: 4 [18432/46250]	Loss: 0.1487	LR: 0.100000
Training Epoch: 4 [18688/46250]	Loss: 0.2052	LR: 0.100000
Training Epoch: 4 [18944/46250]	Loss: 0.1638	LR: 0.100000
Training Epoch: 4 [19200/46250]	Loss: 0.1594	LR: 0.100000
Training Epoch: 4 [19456/46250]	Loss: 0.1837	LR: 0.100000
Training Epoch: 4 [19712/46250]	Loss: 0.1606	LR: 0.100000
Training Epoch: 4 [19968/46250]	Loss: 0.2012	LR: 0.100000
Training Epoch: 4 [20224/46250]	Loss: 0.2391	LR: 0.100000
Training Epoch: 4 [20480/46250]	Loss: 0.2016	LR: 0.100000
Training Epoch: 4 [20736/46250]	Loss: 0.2034	LR: 0.100000
Training Epoch: 4 [20992/46250]	Loss: 0.1660	LR: 0.100000
Training Epoch: 4 [21248/46250]	Loss: 0.1912	LR: 0.100000
Training Epoch: 4 [21504/46250]	Loss: 0.2060	LR: 0.100000
Training Epoch: 4 [21760/46250]	Loss: 0.2533	LR: 0.100000
Training Epoch: 4 [22016/46250]	Loss: 0.1486	LR: 0.100000
Training Epoch: 4 [22272/46250]	Loss: 0.1649	LR: 0.100000
Training Epoch: 4 [22528/46250]	Loss: 0.3010	LR: 0.100000
Training Epoch: 4 [22784/46250]	Loss: 0.1950	LR: 0.100000
Training Epoch: 4 [23040/46250]	Loss: 0.1991	LR: 0.100000
Training Epoch: 4 [23296/46250]	Loss: 0.1800	LR: 0.100000
Training Epoch: 4 [23552/46250]	Loss: 0.1152	LR: 0.100000
Training Epoch: 4 [23808/46250]	Loss: 0.1501	LR: 0.100000
Training Epoch: 4 [24064/46250]	Loss: 0.1903	LR: 0.100000
Training Epoch: 4 [24320/46250]	Loss: 0.1254	LR: 0.100000
Training Epoch: 4 [24576/46250]	Loss: 0.2265	LR: 0.100000
Training Epoch: 4 [24832/46250]	Loss: 0.1791	LR: 0.100000
Training Epoch: 4 [25088/46250]	Loss: 0.1757	LR: 0.100000
Training Epoch: 4 [25344/46250]	Loss: 0.1403	LR: 0.100000
Training Epoch: 4 [25600/46250]	Loss: 0.2765	LR: 0.100000
Training Epoch: 4 [25856/46250]	Loss: 0.2812	LR: 0.100000
Training Epoch: 4 [26112/46250]	Loss: 0.1693	LR: 0.100000
Training Epoch: 4 [26368/46250]	Loss: 0.1783	LR: 0.100000
Training Epoch: 4 [26624/46250]	Loss: 0.2006	LR: 0.100000
Training Epoch: 4 [26880/46250]	Loss: 0.1218	LR: 0.100000
Training Epoch: 4 [27136/46250]	Loss: 0.2046	LR: 0.100000
Training Epoch: 4 [27392/46250]	Loss: 0.1704	LR: 0.100000
Training Epoch: 4 [27648/46250]	Loss: 0.1717	LR: 0.100000
Training Epoch: 4 [27904/46250]	Loss: 0.2522	LR: 0.100000
Training Epoch: 4 [28160/46250]	Loss: 0.1764	LR: 0.100000
Training Epoch: 4 [28416/46250]	Loss: 0.1906	LR: 0.100000
Training Epoch: 4 [28672/46250]	Loss: 0.2180	LR: 0.100000
Training Epoch: 4 [28928/46250]	Loss: 0.1517	LR: 0.100000
Training Epoch: 4 [29184/46250]	Loss: 0.2777	LR: 0.100000
Training Epoch: 4 [29440/46250]	Loss: 0.2435	LR: 0.100000
Training Epoch: 4 [29696/46250]	Loss: 0.1502	LR: 0.100000
Training Epoch: 4 [29952/46250]	Loss: 0.1536	LR: 0.100000
Training Epoch: 4 [30208/46250]	Loss: 0.2306	LR: 0.100000
Training Epoch: 4 [30464/46250]	Loss: 0.2954	LR: 0.100000
Training Epoch: 4 [30720/46250]	Loss: 0.1605	LR: 0.100000
Training Epoch: 4 [30976/46250]	Loss: 0.1292	LR: 0.100000
Training Epoch: 4 [31232/46250]	Loss: 0.1460	LR: 0.100000
Training Epoch: 4 [31488/46250]	Loss: 0.2298	LR: 0.100000
Training Epoch: 4 [31744/46250]	Loss: 0.1155	LR: 0.100000
Training Epoch: 4 [32000/46250]	Loss: 0.1217	LR: 0.100000
Training Epoch: 4 [32256/46250]	Loss: 0.3061	LR: 0.100000
Training Epoch: 4 [32512/46250]	Loss: 0.2743	LR: 0.100000
Training Epoch: 4 [32768/46250]	Loss: 0.2274	LR: 0.100000
Training Epoch: 4 [33024/46250]	Loss: 0.1911	LR: 0.100000
Training Epoch: 4 [33280/46250]	Loss: 0.1067	LR: 0.100000
Training Epoch: 4 [33536/46250]	Loss: 0.2305	LR: 0.100000
Training Epoch: 4 [33792/46250]	Loss: 0.2254	LR: 0.100000
Training Epoch: 4 [34048/46250]	Loss: 0.2228	LR: 0.100000
Training Epoch: 4 [34304/46250]	Loss: 0.1340	LR: 0.100000
Training Epoch: 4 [34560/46250]	Loss: 0.1526	LR: 0.100000
Training Epoch: 4 [34816/46250]	Loss: 0.1368	LR: 0.100000
Training Epoch: 4 [35072/46250]	Loss: 0.1331	LR: 0.100000
Training Epoch: 4 [35328/46250]	Loss: 0.2329	LR: 0.100000
Training Epoch: 4 [35584/46250]	Loss: 0.1984	LR: 0.100000
Training Epoch: 4 [35840/46250]	Loss: 0.1807	LR: 0.100000
Training Epoch: 4 [36096/46250]	Loss: 0.2434	LR: 0.100000
Training Epoch: 4 [36352/46250]	Loss: 0.1836	LR: 0.100000
Training Epoch: 4 [36608/46250]	Loss: 0.1894	LR: 0.100000
Training Epoch: 4 [36864/46250]	Loss: 0.2122	LR: 0.100000
Training Epoch: 4 [37120/46250]	Loss: 0.1912	LR: 0.100000
Training Epoch: 4 [37376/46250]	Loss: 0.2361	LR: 0.100000
Training Epoch: 4 [37632/46250]	Loss: 0.2219	LR: 0.100000
Training Epoch: 4 [37888/46250]	Loss: 0.2071	LR: 0.100000
Training Epoch: 4 [38144/46250]	Loss: 0.1184	LR: 0.100000
Training Epoch: 4 [38400/46250]	Loss: 0.1682	LR: 0.100000
Training Epoch: 4 [38656/46250]	Loss: 0.1719	LR: 0.100000
Training Epoch: 4 [38912/46250]	Loss: 0.1746	LR: 0.100000
Training Epoch: 4 [39168/46250]	Loss: 0.2319	LR: 0.100000
Training Epoch: 4 [39424/46250]	Loss: 0.1470	LR: 0.100000
Training Epoch: 4 [39680/46250]	Loss: 0.2736	LR: 0.100000
Training Epoch: 4 [39936/46250]	Loss: 0.2422	LR: 0.100000
Training Epoch: 4 [40192/46250]	Loss: 0.3095	LR: 0.100000
Training Epoch: 4 [40448/46250]	Loss: 0.1738	LR: 0.100000
Training Epoch: 4 [40704/46250]	Loss: 0.2208	LR: 0.100000
Training Epoch: 4 [40960/46250]	Loss: 0.2117	LR: 0.100000
Training Epoch: 4 [41216/46250]	Loss: 0.1758	LR: 0.100000
Training Epoch: 4 [41472/46250]	Loss: 0.2301	LR: 0.100000
Training Epoch: 4 [41728/46250]	Loss: 0.2014	LR: 0.100000
Training Epoch: 4 [41984/46250]	Loss: 0.1840	LR: 0.100000
Training Epoch: 4 [42240/46250]	Loss: 0.1360	LR: 0.100000
Training Epoch: 4 [42496/46250]	Loss: 0.1598	LR: 0.100000
Training Epoch: 4 [42752/46250]	Loss: 0.1662	LR: 0.100000
Training Epoch: 4 [43008/46250]	Loss: 0.2333	LR: 0.100000
Training Epoch: 4 [43264/46250]	Loss: 0.1964	LR: 0.100000
Training Epoch: 4 [43520/46250]	Loss: 0.1258	LR: 0.100000
Training Epoch: 4 [43776/46250]	Loss: 0.1441	LR: 0.100000
Training Epoch: 4 [44032/46250]	Loss: 0.1561	LR: 0.100000
Training Epoch: 4 [44288/46250]	Loss: 0.2305	LR: 0.100000
Training Epoch: 4 [44544/46250]	Loss: 0.1810	LR: 0.100000
Training Epoch: 4 [44800/46250]	Loss: 0.1917	LR: 0.100000
Training Epoch: 4 [45056/46250]	Loss: 0.1741	LR: 0.100000
Training Epoch: 4 [45312/46250]	Loss: 0.1798	LR: 0.100000
Training Epoch: 4 [45568/46250]	Loss: 0.2432	LR: 0.100000
Training Epoch: 4 [45824/46250]	Loss: 0.3027	LR: 0.100000
Training Epoch: 4 [46080/46250]	Loss: 0.2456	LR: 0.100000
Training Epoch: 4 [46250/46250]	Loss: 0.2302	LR: 0.100000
Epoch 4 - Average Train Loss: 0.2108, Train Accuracy: 0.9288
Epoch 4 training time consumed: 335.64s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0007, Accuracy: 0.9430, Time consumed:23.68s
Training Epoch: 5 [256/46250]	Loss: 0.1443	LR: 0.100000
Training Epoch: 5 [512/46250]	Loss: 0.3027	LR: 0.100000
Training Epoch: 5 [768/46250]	Loss: 0.2573	LR: 0.100000
Training Epoch: 5 [1024/46250]	Loss: 0.2108	LR: 0.100000
Training Epoch: 5 [1280/46250]	Loss: 0.2627	LR: 0.100000
Training Epoch: 5 [1536/46250]	Loss: 0.1851	LR: 0.100000
Training Epoch: 5 [1792/46250]	Loss: 0.1742	LR: 0.100000
Training Epoch: 5 [2048/46250]	Loss: 0.2043	LR: 0.100000
Training Epoch: 5 [2304/46250]	Loss: 0.1551	LR: 0.100000
Training Epoch: 5 [2560/46250]	Loss: 0.1895	LR: 0.100000
Training Epoch: 5 [2816/46250]	Loss: 0.1672	LR: 0.100000
Training Epoch: 5 [3072/46250]	Loss: 0.1827	LR: 0.100000
Training Epoch: 5 [3328/46250]	Loss: 0.1403	LR: 0.100000
Training Epoch: 5 [3584/46250]	Loss: 0.2189	LR: 0.100000
Training Epoch: 5 [3840/46250]	Loss: 0.1473	LR: 0.100000
Training Epoch: 5 [4096/46250]	Loss: 0.1631	LR: 0.100000
Training Epoch: 5 [4352/46250]	Loss: 0.2014	LR: 0.100000
Training Epoch: 5 [4608/46250]	Loss: 0.1611	LR: 0.100000
Training Epoch: 5 [4864/46250]	Loss: 0.1530	LR: 0.100000
Training Epoch: 5 [5120/46250]	Loss: 0.2301	LR: 0.100000
Training Epoch: 5 [5376/46250]	Loss: 0.1281	LR: 0.100000
Training Epoch: 5 [5632/46250]	Loss: 0.1603	LR: 0.100000
Training Epoch: 5 [5888/46250]	Loss: 0.1260	LR: 0.100000
Training Epoch: 5 [6144/46250]	Loss: 0.2102	LR: 0.100000
Training Epoch: 5 [6400/46250]	Loss: 0.1448	LR: 0.100000
Training Epoch: 5 [6656/46250]	Loss: 0.1805	LR: 0.100000
Training Epoch: 5 [6912/46250]	Loss: 0.1475	LR: 0.100000
Training Epoch: 5 [7168/46250]	Loss: 0.3148	LR: 0.100000
Training Epoch: 5 [7424/46250]	Loss: 0.2082	LR: 0.100000
Training Epoch: 5 [7680/46250]	Loss: 0.1457	LR: 0.100000
Training Epoch: 5 [7936/46250]	Loss: 0.3092	LR: 0.100000
Training Epoch: 5 [8192/46250]	Loss: 0.1396	LR: 0.100000
Training Epoch: 5 [8448/46250]	Loss: 0.3646	LR: 0.100000
Training Epoch: 5 [8704/46250]	Loss: 0.1932	LR: 0.100000
Training Epoch: 5 [8960/46250]	Loss: 0.3474	LR: 0.100000
Training Epoch: 5 [9216/46250]	Loss: 0.2014	LR: 0.100000
Training Epoch: 5 [9472/46250]	Loss: 0.2201	LR: 0.100000
Training Epoch: 5 [9728/46250]	Loss: 0.1737	LR: 0.100000
Training Epoch: 5 [9984/46250]	Loss: 0.2433	LR: 0.100000
Training Epoch: 5 [10240/46250]	Loss: 0.1633	LR: 0.100000
Training Epoch: 5 [10496/46250]	Loss: 0.1504	LR: 0.100000
Training Epoch: 5 [10752/46250]	Loss: 0.2124	LR: 0.100000
Training Epoch: 5 [11008/46250]	Loss: 0.1811	LR: 0.100000
Training Epoch: 5 [11264/46250]	Loss: 0.2116	LR: 0.100000
Training Epoch: 5 [11520/46250]	Loss: 0.0749	LR: 0.100000
Training Epoch: 5 [11776/46250]	Loss: 0.2087	LR: 0.100000
Training Epoch: 5 [12032/46250]	Loss: 0.1756	LR: 0.100000
Training Epoch: 5 [12288/46250]	Loss: 0.1551	LR: 0.100000
Training Epoch: 5 [12544/46250]	Loss: 0.1966	LR: 0.100000
Training Epoch: 5 [12800/46250]	Loss: 0.2450	LR: 0.100000
Training Epoch: 5 [13056/46250]	Loss: 0.1905	LR: 0.100000
Training Epoch: 5 [13312/46250]	Loss: 0.2962	LR: 0.100000
Training Epoch: 5 [13568/46250]	Loss: 0.1344	LR: 0.100000
Training Epoch: 5 [13824/46250]	Loss: 0.3103	LR: 0.100000
Training Epoch: 5 [14080/46250]	Loss: 0.1661	LR: 0.100000
Training Epoch: 5 [14336/46250]	Loss: 0.1550	LR: 0.100000
Training Epoch: 5 [14592/46250]	Loss: 0.2136	LR: 0.100000
Training Epoch: 5 [14848/46250]	Loss: 0.2694	LR: 0.100000
Training Epoch: 5 [15104/46250]	Loss: 0.1769	LR: 0.100000
Training Epoch: 5 [15360/46250]	Loss: 0.1850	LR: 0.100000
Training Epoch: 5 [15616/46250]	Loss: 0.2972	LR: 0.100000
Training Epoch: 5 [15872/46250]	Loss: 0.1417	LR: 0.100000
Training Epoch: 5 [16128/46250]	Loss: 0.1400	LR: 0.100000
Training Epoch: 5 [16384/46250]	Loss: 0.1554	LR: 0.100000
Training Epoch: 5 [16640/46250]	Loss: 0.0975	LR: 0.100000
Training Epoch: 5 [16896/46250]	Loss: 0.1203	LR: 0.100000
Training Epoch: 5 [17152/46250]	Loss: 0.1980	LR: 0.100000
Training Epoch: 5 [17408/46250]	Loss: 0.1786	LR: 0.100000
Training Epoch: 5 [17664/46250]	Loss: 0.2405	LR: 0.100000
Training Epoch: 5 [17920/46250]	Loss: 0.2407	LR: 0.100000
Training Epoch: 5 [18176/46250]	Loss: 0.1501	LR: 0.100000
Training Epoch: 5 [18432/46250]	Loss: 0.1181	LR: 0.100000
Training Epoch: 5 [18688/46250]	Loss: 0.2406	LR: 0.100000
Training Epoch: 5 [18944/46250]	Loss: 0.1266	LR: 0.100000
Training Epoch: 5 [19200/46250]	Loss: 0.1242	LR: 0.100000
Training Epoch: 5 [19456/46250]	Loss: 0.0926	LR: 0.100000
Training Epoch: 5 [19712/46250]	Loss: 0.1719	LR: 0.100000
Training Epoch: 5 [19968/46250]	Loss: 0.2033	LR: 0.100000
Training Epoch: 5 [20224/46250]	Loss: 0.2899	LR: 0.100000
Training Epoch: 5 [20480/46250]	Loss: 0.2007	LR: 0.100000
Training Epoch: 5 [20736/46250]	Loss: 0.2098	LR: 0.100000
Training Epoch: 5 [20992/46250]	Loss: 0.1531	LR: 0.100000
Training Epoch: 5 [21248/46250]	Loss: 0.1333	LR: 0.100000
Training Epoch: 5 [21504/46250]	Loss: 0.2330	LR: 0.100000
Training Epoch: 5 [21760/46250]	Loss: 0.1564	LR: 0.100000
Training Epoch: 5 [22016/46250]	Loss: 0.2139	LR: 0.100000
Training Epoch: 5 [22272/46250]	Loss: 0.1899	LR: 0.100000
Training Epoch: 5 [22528/46250]	Loss: 0.2218	LR: 0.100000
Training Epoch: 5 [22784/46250]	Loss: 0.2259	LR: 0.100000
Training Epoch: 5 [23040/46250]	Loss: 0.2150	LR: 0.100000
Training Epoch: 5 [23296/46250]	Loss: 0.1608	LR: 0.100000
Training Epoch: 5 [23552/46250]	Loss: 0.1708	LR: 0.100000
Training Epoch: 5 [23808/46250]	Loss: 0.2365	LR: 0.100000
Training Epoch: 5 [24064/46250]	Loss: 0.1920	LR: 0.100000
Training Epoch: 5 [24320/46250]	Loss: 0.1395	LR: 0.100000
Training Epoch: 5 [24576/46250]	Loss: 0.1893	LR: 0.100000
Training Epoch: 5 [24832/46250]	Loss: 0.2043	LR: 0.100000
Training Epoch: 5 [25088/46250]	Loss: 0.2160	LR: 0.100000
Training Epoch: 5 [25344/46250]	Loss: 0.3037	LR: 0.100000
Training Epoch: 5 [25600/46250]	Loss: 0.1130	LR: 0.100000
Training Epoch: 5 [25856/46250]	Loss: 0.1387	LR: 0.100000
Training Epoch: 5 [26112/46250]	Loss: 0.1911	LR: 0.100000
Training Epoch: 5 [26368/46250]	Loss: 0.1795	LR: 0.100000
Training Epoch: 5 [26624/46250]	Loss: 0.1847	LR: 0.100000
Training Epoch: 5 [26880/46250]	Loss: 0.2660	LR: 0.100000
Training Epoch: 5 [27136/46250]	Loss: 0.1621	LR: 0.100000
Training Epoch: 5 [27392/46250]	Loss: 0.1851	LR: 0.100000
Training Epoch: 5 [27648/46250]	Loss: 0.1996	LR: 0.100000
Training Epoch: 5 [27904/46250]	Loss: 0.2099	LR: 0.100000
Training Epoch: 5 [28160/46250]	Loss: 0.1604	LR: 0.100000
Training Epoch: 5 [28416/46250]	Loss: 0.1672	LR: 0.100000
Training Epoch: 5 [28672/46250]	Loss: 0.1586	LR: 0.100000
Training Epoch: 5 [28928/46250]	Loss: 0.1335	LR: 0.100000
Training Epoch: 5 [29184/46250]	Loss: 0.2619	LR: 0.100000
Training Epoch: 5 [29440/46250]	Loss: 0.1637	LR: 0.100000
Training Epoch: 5 [29696/46250]	Loss: 0.1233	LR: 0.100000
Training Epoch: 5 [29952/46250]	Loss: 0.1406	LR: 0.100000
Training Epoch: 5 [30208/46250]	Loss: 0.1902	LR: 0.100000
Training Epoch: 5 [30464/46250]	Loss: 0.1553	LR: 0.100000
Training Epoch: 5 [30720/46250]	Loss: 0.1398	LR: 0.100000
Training Epoch: 5 [30976/46250]	Loss: 0.1675	LR: 0.100000
Training Epoch: 5 [31232/46250]	Loss: 0.2172	LR: 0.100000
Training Epoch: 5 [31488/46250]	Loss: 0.1396	LR: 0.100000
Training Epoch: 5 [31744/46250]	Loss: 0.1997	LR: 0.100000
Training Epoch: 5 [32000/46250]	Loss: 0.2051	LR: 0.100000
Training Epoch: 5 [32256/46250]	Loss: 0.1676	LR: 0.100000
Training Epoch: 5 [32512/46250]	Loss: 0.1597	LR: 0.100000
Training Epoch: 5 [32768/46250]	Loss: 0.1472	LR: 0.100000
Training Epoch: 5 [33024/46250]	Loss: 0.1641	LR: 0.100000
Training Epoch: 5 [33280/46250]	Loss: 0.2292	LR: 0.100000
Training Epoch: 5 [33536/46250]	Loss: 0.1280	LR: 0.100000
Training Epoch: 5 [33792/46250]	Loss: 0.1833	LR: 0.100000
Training Epoch: 5 [34048/46250]	Loss: 0.1267	LR: 0.100000
Training Epoch: 5 [34304/46250]	Loss: 0.1340	LR: 0.100000
Training Epoch: 5 [34560/46250]	Loss: 0.1624	LR: 0.100000
Training Epoch: 5 [34816/46250]	Loss: 0.2071	LR: 0.100000
Training Epoch: 5 [35072/46250]	Loss: 0.2050	LR: 0.100000
Training Epoch: 5 [35328/46250]	Loss: 0.2284	LR: 0.100000
Training Epoch: 5 [35584/46250]	Loss: 0.1317	LR: 0.100000
Training Epoch: 5 [35840/46250]	Loss: 0.1758	LR: 0.100000
Training Epoch: 5 [36096/46250]	Loss: 0.1696	LR: 0.100000
Training Epoch: 5 [36352/46250]	Loss: 0.1602	LR: 0.100000
Training Epoch: 5 [36608/46250]	Loss: 0.2380	LR: 0.100000
Training Epoch: 5 [36864/46250]	Loss: 0.1838	LR: 0.100000
Training Epoch: 5 [37120/46250]	Loss: 0.1442	LR: 0.100000
Training Epoch: 5 [37376/46250]	Loss: 0.2373	LR: 0.100000
Training Epoch: 5 [37632/46250]	Loss: 0.1994	LR: 0.100000
Training Epoch: 5 [37888/46250]	Loss: 0.2108	LR: 0.100000
Training Epoch: 5 [38144/46250]	Loss: 0.2084	LR: 0.100000
Training Epoch: 5 [38400/46250]	Loss: 0.2051	LR: 0.100000
Training Epoch: 5 [38656/46250]	Loss: 0.2669	LR: 0.100000
Training Epoch: 5 [38912/46250]	Loss: 0.1371	LR: 0.100000
Training Epoch: 5 [39168/46250]	Loss: 0.2177	LR: 0.100000
Training Epoch: 5 [39424/46250]	Loss: 0.3010	LR: 0.100000
Training Epoch: 5 [39680/46250]	Loss: 0.2824	LR: 0.100000
Training Epoch: 5 [39936/46250]	Loss: 0.2222	LR: 0.100000
Training Epoch: 5 [40192/46250]	Loss: 0.1805	LR: 0.100000
Training Epoch: 5 [40448/46250]	Loss: 0.2581	LR: 0.100000
Training Epoch: 5 [40704/46250]	Loss: 0.2119	LR: 0.100000
Training Epoch: 5 [40960/46250]	Loss: 0.2668	LR: 0.100000
Training Epoch: 5 [41216/46250]	Loss: 0.2926	LR: 0.100000
Training Epoch: 5 [41472/46250]	Loss: 0.2448	LR: 0.100000
Training Epoch: 5 [41728/46250]	Loss: 0.1767	LR: 0.100000
Training Epoch: 5 [41984/46250]	Loss: 0.2463	LR: 0.100000
Training Epoch: 5 [42240/46250]	Loss: 0.1979	LR: 0.100000
Training Epoch: 5 [42496/46250]	Loss: 0.1276	LR: 0.100000
Training Epoch: 5 [42752/46250]	Loss: 0.1994	LR: 0.100000
Training Epoch: 5 [43008/46250]	Loss: 0.1909	LR: 0.100000
Training Epoch: 5 [43264/46250]	Loss: 0.1747	LR: 0.100000
Training Epoch: 5 [43520/46250]	Loss: 0.2043	LR: 0.100000
Training Epoch: 5 [43776/46250]	Loss: 0.1998	LR: 0.100000
Training Epoch: 5 [44032/46250]	Loss: 0.2079	LR: 0.100000
Training Epoch: 5 [44288/46250]	Loss: 0.2343	LR: 0.100000
Training Epoch: 5 [44544/46250]	Loss: 0.2948	LR: 0.100000
Training Epoch: 5 [44800/46250]	Loss: 0.1773	LR: 0.100000
Training Epoch: 5 [45056/46250]	Loss: 0.2389	LR: 0.100000
Training Epoch: 5 [45312/46250]	Loss: 0.1920	LR: 0.100000
Training Epoch: 5 [45568/46250]	Loss: 0.1540	LR: 0.100000
Training Epoch: 5 [45824/46250]	Loss: 0.2220	LR: 0.100000
Training Epoch: 5 [46080/46250]	Loss: 0.3701	LR: 0.100000
Training Epoch: 5 [46250/46250]	Loss: 0.0845	LR: 0.100000
Epoch 5 - Average Train Loss: 0.1936, Train Accuracy: 0.9337
Epoch 5 training time consumed: 335.77s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0008, Accuracy: 0.9319, Time consumed:23.64s
Training Epoch: 6 [256/46250]	Loss: 0.1053	LR: 0.100000
Training Epoch: 6 [512/46250]	Loss: 0.2211	LR: 0.100000
Training Epoch: 6 [768/46250]	Loss: 0.1980	LR: 0.100000
Training Epoch: 6 [1024/46250]	Loss: 0.1776	LR: 0.100000
Training Epoch: 6 [1280/46250]	Loss: 0.2825	LR: 0.100000
Training Epoch: 6 [1536/46250]	Loss: 0.1454	LR: 0.100000
Training Epoch: 6 [1792/46250]	Loss: 0.0914	LR: 0.100000
Training Epoch: 6 [2048/46250]	Loss: 0.1693	LR: 0.100000
Training Epoch: 6 [2304/46250]	Loss: 0.2879	LR: 0.100000
Training Epoch: 6 [2560/46250]	Loss: 0.2041	LR: 0.100000
Training Epoch: 6 [2816/46250]	Loss: 0.1460	LR: 0.100000
Training Epoch: 6 [3072/46250]	Loss: 0.2516	LR: 0.100000
Training Epoch: 6 [3328/46250]	Loss: 0.1318	LR: 0.100000
Training Epoch: 6 [3584/46250]	Loss: 0.1756	LR: 0.100000
Training Epoch: 6 [3840/46250]	Loss: 0.2669	LR: 0.100000
Training Epoch: 6 [4096/46250]	Loss: 0.1145	LR: 0.100000
Training Epoch: 6 [4352/46250]	Loss: 0.2549	LR: 0.100000
Training Epoch: 6 [4608/46250]	Loss: 0.1473	LR: 0.100000
Training Epoch: 6 [4864/46250]	Loss: 0.1048	LR: 0.100000
Training Epoch: 6 [5120/46250]	Loss: 0.2144	LR: 0.100000
Training Epoch: 6 [5376/46250]	Loss: 0.2096	LR: 0.100000
Training Epoch: 6 [5632/46250]	Loss: 0.2617	LR: 0.100000
Training Epoch: 6 [5888/46250]	Loss: 0.1417	LR: 0.100000
Training Epoch: 6 [6144/46250]	Loss: 0.2930	LR: 0.100000
Training Epoch: 6 [6400/46250]	Loss: 0.2698	LR: 0.100000
Training Epoch: 6 [6656/46250]	Loss: 0.1734	LR: 0.100000
Training Epoch: 6 [6912/46250]	Loss: 0.2094	LR: 0.100000
Training Epoch: 6 [7168/46250]	Loss: 0.2071	LR: 0.100000
Training Epoch: 6 [7424/46250]	Loss: 0.1619	LR: 0.100000
Training Epoch: 6 [7680/46250]	Loss: 0.1797	LR: 0.100000
Training Epoch: 6 [7936/46250]	Loss: 0.2159	LR: 0.100000
Training Epoch: 6 [8192/46250]	Loss: 0.1721	LR: 0.100000
Training Epoch: 6 [8448/46250]	Loss: 0.1278	LR: 0.100000
Training Epoch: 6 [8704/46250]	Loss: 0.1933	LR: 0.100000
Training Epoch: 6 [8960/46250]	Loss: 0.2951	LR: 0.100000
Training Epoch: 6 [9216/46250]	Loss: 0.2572	LR: 0.100000
Training Epoch: 6 [9472/46250]	Loss: 0.1544	LR: 0.100000
Training Epoch: 6 [9728/46250]	Loss: 0.2305	LR: 0.100000
Training Epoch: 6 [9984/46250]	Loss: 0.1479	LR: 0.100000
Training Epoch: 6 [10240/46250]	Loss: 0.2646	LR: 0.100000
Training Epoch: 6 [10496/46250]	Loss: 0.2443	LR: 0.100000
Training Epoch: 6 [10752/46250]	Loss: 0.1734	LR: 0.100000
Training Epoch: 6 [11008/46250]	Loss: 0.2215	LR: 0.100000
Training Epoch: 6 [11264/46250]	Loss: 0.2340	LR: 0.100000
Training Epoch: 6 [11520/46250]	Loss: 0.3061	LR: 0.100000
Training Epoch: 6 [11776/46250]	Loss: 0.1126	LR: 0.100000
Training Epoch: 6 [12032/46250]	Loss: 0.1017	LR: 0.100000
Training Epoch: 6 [12288/46250]	Loss: 0.1550	LR: 0.100000
Training Epoch: 6 [12544/46250]	Loss: 0.2452	LR: 0.100000
Training Epoch: 6 [12800/46250]	Loss: 0.2526	LR: 0.100000
Training Epoch: 6 [13056/46250]	Loss: 0.2163	LR: 0.100000
Training Epoch: 6 [13312/46250]	Loss: 0.2743	LR: 0.100000
Training Epoch: 6 [13568/46250]	Loss: 0.2117	LR: 0.100000
Training Epoch: 6 [13824/46250]	Loss: 0.3076	LR: 0.100000
Training Epoch: 6 [14080/46250]	Loss: 0.2880	LR: 0.100000
Training Epoch: 6 [14336/46250]	Loss: 0.2275	LR: 0.100000
Training Epoch: 6 [14592/46250]	Loss: 0.2261	LR: 0.100000
Training Epoch: 6 [14848/46250]	Loss: 0.1887	LR: 0.100000
Training Epoch: 6 [15104/46250]	Loss: 0.2453	LR: 0.100000
Training Epoch: 6 [15360/46250]	Loss: 0.1907	LR: 0.100000
Training Epoch: 6 [15616/46250]	Loss: 0.1441	LR: 0.100000
Training Epoch: 6 [15872/46250]	Loss: 0.1441	LR: 0.100000
Training Epoch: 6 [16128/46250]	Loss: 0.2756	LR: 0.100000
Training Epoch: 6 [16384/46250]	Loss: 0.1474	LR: 0.100000
Training Epoch: 6 [16640/46250]	Loss: 0.1618	LR: 0.100000
Training Epoch: 6 [16896/46250]	Loss: 0.2611	LR: 0.100000
Training Epoch: 6 [17152/46250]	Loss: 0.1299	LR: 0.100000
Training Epoch: 6 [17408/46250]	Loss: 0.1878	LR: 0.100000
Training Epoch: 6 [17664/46250]	Loss: 0.3140	LR: 0.100000
Training Epoch: 6 [17920/46250]	Loss: 0.1543	LR: 0.100000
Training Epoch: 6 [18176/46250]	Loss: 0.1151	LR: 0.100000
Training Epoch: 6 [18432/46250]	Loss: 0.2084	LR: 0.100000
Training Epoch: 6 [18688/46250]	Loss: 0.1805	LR: 0.100000
Training Epoch: 6 [18944/46250]	Loss: 0.1915	LR: 0.100000
Training Epoch: 6 [19200/46250]	Loss: 0.2157	LR: 0.100000
Training Epoch: 6 [19456/46250]	Loss: 0.2301	LR: 0.100000
Training Epoch: 6 [19712/46250]	Loss: 0.1949	LR: 0.100000
Training Epoch: 6 [19968/46250]	Loss: 0.2374	LR: 0.100000
Training Epoch: 6 [20224/46250]	Loss: 0.2443	LR: 0.100000
Training Epoch: 6 [20480/46250]	Loss: 0.3078	LR: 0.100000
Training Epoch: 6 [20736/46250]	Loss: 0.2175	LR: 0.100000
Training Epoch: 6 [20992/46250]	Loss: 0.3659	LR: 0.100000
Training Epoch: 6 [21248/46250]	Loss: 0.2641	LR: 0.100000
Training Epoch: 6 [21504/46250]	Loss: 0.2998	LR: 0.100000
Training Epoch: 6 [21760/46250]	Loss: 0.1938	LR: 0.100000
Training Epoch: 6 [22016/46250]	Loss: 0.1917	LR: 0.100000
Training Epoch: 6 [22272/46250]	Loss: 0.2129	LR: 0.100000
Training Epoch: 6 [22528/46250]	Loss: 0.2035	LR: 0.100000
Training Epoch: 6 [22784/46250]	Loss: 0.2445	LR: 0.100000
Training Epoch: 6 [23040/46250]	Loss: 0.2148	LR: 0.100000
Training Epoch: 6 [23296/46250]	Loss: 0.1638	LR: 0.100000
Training Epoch: 6 [23552/46250]	Loss: 0.1601	LR: 0.100000
Training Epoch: 6 [23808/46250]	Loss: 0.1644	LR: 0.100000
Training Epoch: 6 [24064/46250]	Loss: 0.2000	LR: 0.100000
Training Epoch: 6 [24320/46250]	Loss: 0.1625	LR: 0.100000
Training Epoch: 6 [24576/46250]	Loss: 0.2977	LR: 0.100000
Training Epoch: 6 [24832/46250]	Loss: 0.1388	LR: 0.100000
Training Epoch: 6 [25088/46250]	Loss: 0.1509	LR: 0.100000
Training Epoch: 6 [25344/46250]	Loss: 0.1734	LR: 0.100000
Training Epoch: 6 [25600/46250]	Loss: 0.1992	LR: 0.100000
Training Epoch: 6 [25856/46250]	Loss: 0.1658	LR: 0.100000
Training Epoch: 6 [26112/46250]	Loss: 0.2639	LR: 0.100000
Training Epoch: 6 [26368/46250]	Loss: 0.2410	LR: 0.100000
Training Epoch: 6 [26624/46250]	Loss: 0.1838	LR: 0.100000
Training Epoch: 6 [26880/46250]	Loss: 0.2280	LR: 0.100000
Training Epoch: 6 [27136/46250]	Loss: 0.2047	LR: 0.100000
Training Epoch: 6 [27392/46250]	Loss: 0.2009	LR: 0.100000
Training Epoch: 6 [27648/46250]	Loss: 0.2243	LR: 0.100000
Training Epoch: 6 [27904/46250]	Loss: 0.2110	LR: 0.100000
Training Epoch: 6 [28160/46250]	Loss: 0.1645	LR: 0.100000
Training Epoch: 6 [28416/46250]	Loss: 0.1371	LR: 0.100000
Training Epoch: 6 [28672/46250]	Loss: 0.1223	LR: 0.100000
Training Epoch: 6 [28928/46250]	Loss: 0.1363	LR: 0.100000
Training Epoch: 6 [29184/46250]	Loss: 0.1384	LR: 0.100000
Training Epoch: 6 [29440/46250]	Loss: 0.2351	LR: 0.100000
Training Epoch: 6 [29696/46250]	Loss: 0.1883	LR: 0.100000
Training Epoch: 6 [29952/46250]	Loss: 0.2661	LR: 0.100000
Training Epoch: 6 [30208/46250]	Loss: 0.1886	LR: 0.100000
Training Epoch: 6 [30464/46250]	Loss: 0.1825	LR: 0.100000
Training Epoch: 6 [30720/46250]	Loss: 0.2156	LR: 0.100000
Training Epoch: 6 [30976/46250]	Loss: 0.2344	LR: 0.100000
Training Epoch: 6 [31232/46250]	Loss: 0.2317	LR: 0.100000
Training Epoch: 6 [31488/46250]	Loss: 0.2017	LR: 0.100000
Training Epoch: 6 [31744/46250]	Loss: 0.2044	LR: 0.100000
Training Epoch: 6 [32000/46250]	Loss: 0.1255	LR: 0.100000
Training Epoch: 6 [32256/46250]	Loss: 0.1925	LR: 0.100000
Training Epoch: 6 [32512/46250]	Loss: 0.2713	LR: 0.100000
Training Epoch: 6 [32768/46250]	Loss: 0.1757	LR: 0.100000
Training Epoch: 6 [33024/46250]	Loss: 0.1913	LR: 0.100000
Training Epoch: 6 [33280/46250]	Loss: 0.2618	LR: 0.100000
Training Epoch: 6 [33536/46250]	Loss: 0.1985	LR: 0.100000
Training Epoch: 6 [33792/46250]	Loss: 0.1323	LR: 0.100000
Training Epoch: 6 [34048/46250]	Loss: 0.2121	LR: 0.100000
Training Epoch: 6 [34304/46250]	Loss: 0.2437	LR: 0.100000
Training Epoch: 6 [34560/46250]	Loss: 0.2135	LR: 0.100000
Training Epoch: 6 [34816/46250]	Loss: 0.1817	LR: 0.100000
Training Epoch: 6 [35072/46250]	Loss: 0.1966	LR: 0.100000
Training Epoch: 6 [35328/46250]	Loss: 0.2000	LR: 0.100000
Training Epoch: 6 [35584/46250]	Loss: 0.1486	LR: 0.100000
Training Epoch: 6 [35840/46250]	Loss: 0.2785	LR: 0.100000
Training Epoch: 6 [36096/46250]	Loss: 0.0900	LR: 0.100000
Training Epoch: 6 [36352/46250]	Loss: 0.2361	LR: 0.100000
Training Epoch: 6 [36608/46250]	Loss: 0.3099	LR: 0.100000
Training Epoch: 6 [36864/46250]	Loss: 0.1532	LR: 0.100000
Training Epoch: 6 [37120/46250]	Loss: 0.3459	LR: 0.100000
Training Epoch: 6 [37376/46250]	Loss: 0.1417	LR: 0.100000
Training Epoch: 6 [37632/46250]	Loss: 0.1667	LR: 0.100000
Training Epoch: 6 [37888/46250]	Loss: 0.2140	LR: 0.100000
Training Epoch: 6 [38144/46250]	Loss: 0.2800	LR: 0.100000
Training Epoch: 6 [38400/46250]	Loss: 0.2150	LR: 0.100000
Training Epoch: 6 [38656/46250]	Loss: 0.2831	LR: 0.100000
Training Epoch: 6 [38912/46250]	Loss: 0.2182	LR: 0.100000
Training Epoch: 6 [39168/46250]	Loss: 0.1745	LR: 0.100000
Training Epoch: 6 [39424/46250]	Loss: 0.4190	LR: 0.100000
Training Epoch: 6 [39680/46250]	Loss: 0.2138	LR: 0.100000
Training Epoch: 6 [39936/46250]	Loss: 0.2329	LR: 0.100000
Training Epoch: 6 [40192/46250]	Loss: 0.2607	LR: 0.100000
Training Epoch: 6 [40448/46250]	Loss: 0.2220	LR: 0.100000
Training Epoch: 6 [40704/46250]	Loss: 0.1942	LR: 0.100000
Training Epoch: 6 [40960/46250]	Loss: 0.1734	LR: 0.100000
Training Epoch: 6 [41216/46250]	Loss: 0.1541	LR: 0.100000
Training Epoch: 6 [41472/46250]	Loss: 0.2351	LR: 0.100000
Training Epoch: 6 [41728/46250]	Loss: 0.1620	LR: 0.100000
Training Epoch: 6 [41984/46250]	Loss: 0.2999	LR: 0.100000
Training Epoch: 6 [42240/46250]	Loss: 0.2164	LR: 0.100000
Training Epoch: 6 [42496/46250]	Loss: 0.1575	LR: 0.100000
Training Epoch: 6 [42752/46250]	Loss: 0.1692	LR: 0.100000
Training Epoch: 6 [43008/46250]	Loss: 0.2275	LR: 0.100000
Training Epoch: 6 [43264/46250]	Loss: 0.1880	LR: 0.100000
Training Epoch: 6 [43520/46250]	Loss: 0.1801	LR: 0.100000
Training Epoch: 6 [43776/46250]	Loss: 0.1764	LR: 0.100000
Training Epoch: 6 [44032/46250]	Loss: 0.1961	LR: 0.100000
Training Epoch: 6 [44288/46250]	Loss: 0.2472	LR: 0.100000
Training Epoch: 6 [44544/46250]	Loss: 0.1992	LR: 0.100000
Training Epoch: 6 [44800/46250]	Loss: 0.1574	LR: 0.100000
Training Epoch: 6 [45056/46250]	Loss: 0.2140	LR: 0.100000
Training Epoch: 6 [45312/46250]	Loss: 0.1993	LR: 0.100000
Training Epoch: 6 [45568/46250]	Loss: 0.2656	LR: 0.100000
Training Epoch: 6 [45824/46250]	Loss: 0.1763	LR: 0.100000
Training Epoch: 6 [46080/46250]	Loss: 0.1721	LR: 0.100000
Training Epoch: 6 [46250/46250]	Loss: 0.2245	LR: 0.100000
Epoch 6 - Average Train Loss: 0.2060, Train Accuracy: 0.9284
Epoch 6 training time consumed: 335.78s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0007, Accuracy: 0.9417, Time consumed:23.66s
Training Epoch: 7 [256/46250]	Loss: 0.1422	LR: 0.020000
Training Epoch: 7 [512/46250]	Loss: 0.1495	LR: 0.020000
Training Epoch: 7 [768/46250]	Loss: 0.1360	LR: 0.020000
Training Epoch: 7 [1024/46250]	Loss: 0.1367	LR: 0.020000
Training Epoch: 7 [1280/46250]	Loss: 0.1201	LR: 0.020000
Training Epoch: 7 [1536/46250]	Loss: 0.1476	LR: 0.020000
Training Epoch: 7 [1792/46250]	Loss: 0.1321	LR: 0.020000
Training Epoch: 7 [2048/46250]	Loss: 0.0770	LR: 0.020000
Training Epoch: 7 [2304/46250]	Loss: 0.0569	LR: 0.020000
Training Epoch: 7 [2560/46250]	Loss: 0.0703	LR: 0.020000
Training Epoch: 7 [2816/46250]	Loss: 0.1006	LR: 0.020000
Training Epoch: 7 [3072/46250]	Loss: 0.1301	LR: 0.020000
Training Epoch: 7 [3328/46250]	Loss: 0.1036	LR: 0.020000
Training Epoch: 7 [3584/46250]	Loss: 0.0956	LR: 0.020000
Training Epoch: 7 [3840/46250]	Loss: 0.0782	LR: 0.020000
Training Epoch: 7 [4096/46250]	Loss: 0.1397	LR: 0.020000
Training Epoch: 7 [4352/46250]	Loss: 0.0716	LR: 0.020000
Training Epoch: 7 [4608/46250]	Loss: 0.0763	LR: 0.020000
Training Epoch: 7 [4864/46250]	Loss: 0.0924	LR: 0.020000
Training Epoch: 7 [5120/46250]	Loss: 0.0676	LR: 0.020000
Training Epoch: 7 [5376/46250]	Loss: 0.0761	LR: 0.020000
Training Epoch: 7 [5632/46250]	Loss: 0.0622	LR: 0.020000
Training Epoch: 7 [5888/46250]	Loss: 0.0685	LR: 0.020000
Training Epoch: 7 [6144/46250]	Loss: 0.0611	LR: 0.020000
Training Epoch: 7 [6400/46250]	Loss: 0.0770	LR: 0.020000
Training Epoch: 7 [6656/46250]	Loss: 0.0746	LR: 0.020000
Training Epoch: 7 [6912/46250]	Loss: 0.0527	LR: 0.020000
Training Epoch: 7 [7168/46250]	Loss: 0.0646	LR: 0.020000
Training Epoch: 7 [7424/46250]	Loss: 0.0609	LR: 0.020000
Training Epoch: 7 [7680/46250]	Loss: 0.0565	LR: 0.020000
Training Epoch: 7 [7936/46250]	Loss: 0.0498	LR: 0.020000
Training Epoch: 7 [8192/46250]	Loss: 0.0987	LR: 0.020000
Training Epoch: 7 [8448/46250]	Loss: 0.0561	LR: 0.020000
Training Epoch: 7 [8704/46250]	Loss: 0.0480	LR: 0.020000
Training Epoch: 7 [8960/46250]	Loss: 0.0885	LR: 0.020000
Training Epoch: 7 [9216/46250]	Loss: 0.0632	LR: 0.020000
Training Epoch: 7 [9472/46250]	Loss: 0.0639	LR: 0.020000
Training Epoch: 7 [9728/46250]	Loss: 0.1174	LR: 0.020000
Training Epoch: 7 [9984/46250]	Loss: 0.0517	LR: 0.020000
Training Epoch: 7 [10240/46250]	Loss: 0.0713	LR: 0.020000
Training Epoch: 7 [10496/46250]	Loss: 0.1217	LR: 0.020000
Training Epoch: 7 [10752/46250]	Loss: 0.0571	LR: 0.020000
Training Epoch: 7 [11008/46250]	Loss: 0.0319	LR: 0.020000
Training Epoch: 7 [11264/46250]	Loss: 0.0658	LR: 0.020000
Training Epoch: 7 [11520/46250]	Loss: 0.0552	LR: 0.020000
Training Epoch: 7 [11776/46250]	Loss: 0.0837	LR: 0.020000
Training Epoch: 7 [12032/46250]	Loss: 0.0456	LR: 0.020000
Training Epoch: 7 [12288/46250]	Loss: 0.0692	LR: 0.020000
Training Epoch: 7 [12544/46250]	Loss: 0.0507	LR: 0.020000
Training Epoch: 7 [12800/46250]	Loss: 0.0508	LR: 0.020000
Training Epoch: 7 [13056/46250]	Loss: 0.0693	LR: 0.020000
Training Epoch: 7 [13312/46250]	Loss: 0.0593	LR: 0.020000
Training Epoch: 7 [13568/46250]	Loss: 0.0674	LR: 0.020000
Training Epoch: 7 [13824/46250]	Loss: 0.0239	LR: 0.020000
Training Epoch: 7 [14080/46250]	Loss: 0.0578	LR: 0.020000
Training Epoch: 7 [14336/46250]	Loss: 0.0570	LR: 0.020000
Training Epoch: 7 [14592/46250]	Loss: 0.0660	LR: 0.020000
Training Epoch: 7 [14848/46250]	Loss: 0.0939	LR: 0.020000
Training Epoch: 7 [15104/46250]	Loss: 0.0885	LR: 0.020000
Training Epoch: 7 [15360/46250]	Loss: 0.0873	LR: 0.020000
Training Epoch: 7 [15616/46250]	Loss: 0.0177	LR: 0.020000
Training Epoch: 7 [15872/46250]	Loss: 0.0553	LR: 0.020000
Training Epoch: 7 [16128/46250]	Loss: 0.0442	LR: 0.020000
Training Epoch: 7 [16384/46250]	Loss: 0.0732	LR: 0.020000
Training Epoch: 7 [16640/46250]	Loss: 0.0768	LR: 0.020000
Training Epoch: 7 [16896/46250]	Loss: 0.1325	LR: 0.020000
Training Epoch: 7 [17152/46250]	Loss: 0.1496	LR: 0.020000
Training Epoch: 7 [17408/46250]	Loss: 0.1023	LR: 0.020000
Training Epoch: 7 [17664/46250]	Loss: 0.0711	LR: 0.020000
Training Epoch: 7 [17920/46250]	Loss: 0.0395	LR: 0.020000
Training Epoch: 7 [18176/46250]	Loss: 0.1060	LR: 0.020000
Training Epoch: 7 [18432/46250]	Loss: 0.1121	LR: 0.020000
Training Epoch: 7 [18688/46250]	Loss: 0.0753	LR: 0.020000
Training Epoch: 7 [18944/46250]	Loss: 0.1055	LR: 0.020000
Training Epoch: 7 [19200/46250]	Loss: 0.0481	LR: 0.020000
Training Epoch: 7 [19456/46250]	Loss: 0.0728	LR: 0.020000
Training Epoch: 7 [19712/46250]	Loss: 0.0633	LR: 0.020000
Training Epoch: 7 [19968/46250]	Loss: 0.0980	LR: 0.020000
Training Epoch: 7 [20224/46250]	Loss: 0.0508	LR: 0.020000
Training Epoch: 7 [20480/46250]	Loss: 0.0534	LR: 0.020000
Training Epoch: 7 [20736/46250]	Loss: 0.0304	LR: 0.020000
Training Epoch: 7 [20992/46250]	Loss: 0.0565	LR: 0.020000
Training Epoch: 7 [21248/46250]	Loss: 0.0722	LR: 0.020000
Training Epoch: 7 [21504/46250]	Loss: 0.0916	LR: 0.020000
Training Epoch: 7 [21760/46250]	Loss: 0.0509	LR: 0.020000
Training Epoch: 7 [22016/46250]	Loss: 0.0841	LR: 0.020000
Training Epoch: 7 [22272/46250]	Loss: 0.0544	LR: 0.020000
Training Epoch: 7 [22528/46250]	Loss: 0.0694	LR: 0.020000
Training Epoch: 7 [22784/46250]	Loss: 0.0458	LR: 0.020000
Training Epoch: 7 [23040/46250]	Loss: 0.0469	LR: 0.020000
Training Epoch: 7 [23296/46250]	Loss: 0.0649	LR: 0.020000
Training Epoch: 7 [23552/46250]	Loss: 0.0335	LR: 0.020000
Training Epoch: 7 [23808/46250]	Loss: 0.0679	LR: 0.020000
Training Epoch: 7 [24064/46250]	Loss: 0.0353	LR: 0.020000
Training Epoch: 7 [24320/46250]	Loss: 0.0605	LR: 0.020000
Training Epoch: 7 [24576/46250]	Loss: 0.0613	LR: 0.020000
Training Epoch: 7 [24832/46250]	Loss: 0.0780	LR: 0.020000
Training Epoch: 7 [25088/46250]	Loss: 0.0513	LR: 0.020000
Training Epoch: 7 [25344/46250]	Loss: 0.0572	LR: 0.020000
Training Epoch: 7 [25600/46250]	Loss: 0.0603	LR: 0.020000
Training Epoch: 7 [25856/46250]	Loss: 0.0719	LR: 0.020000
Training Epoch: 7 [26112/46250]	Loss: 0.0451	LR: 0.020000
Training Epoch: 7 [26368/46250]	Loss: 0.0929	LR: 0.020000
Training Epoch: 7 [26624/46250]	Loss: 0.0386	LR: 0.020000
Training Epoch: 7 [26880/46250]	Loss: 0.0549	LR: 0.020000
Training Epoch: 7 [27136/46250]	Loss: 0.0440	LR: 0.020000
Training Epoch: 7 [27392/46250]	Loss: 0.0914	LR: 0.020000
Training Epoch: 7 [27648/46250]	Loss: 0.0901	LR: 0.020000
Training Epoch: 7 [27904/46250]	Loss: 0.0610	LR: 0.020000
Training Epoch: 7 [28160/46250]	Loss: 0.0592	LR: 0.020000
Training Epoch: 7 [28416/46250]	Loss: 0.1470	LR: 0.020000
Training Epoch: 7 [28672/46250]	Loss: 0.1100	LR: 0.020000
Training Epoch: 7 [28928/46250]	Loss: 0.0799	LR: 0.020000
Training Epoch: 7 [29184/46250]	Loss: 0.0372	LR: 0.020000
Training Epoch: 7 [29440/46250]	Loss: 0.0691	LR: 0.020000
Training Epoch: 7 [29696/46250]	Loss: 0.0504	LR: 0.020000
Training Epoch: 7 [29952/46250]	Loss: 0.0635	LR: 0.020000
Training Epoch: 7 [30208/46250]	Loss: 0.1018	LR: 0.020000
Training Epoch: 7 [30464/46250]	Loss: 0.0621	LR: 0.020000
Training Epoch: 7 [30720/46250]	Loss: 0.0399	LR: 0.020000
Training Epoch: 7 [30976/46250]	Loss: 0.0372	LR: 0.020000
Training Epoch: 7 [31232/46250]	Loss: 0.0500	LR: 0.020000
Training Epoch: 7 [31488/46250]	Loss: 0.0395	LR: 0.020000
Training Epoch: 7 [31744/46250]	Loss: 0.1301	LR: 0.020000
Training Epoch: 7 [32000/46250]	Loss: 0.0724	LR: 0.020000
Training Epoch: 7 [32256/46250]	Loss: 0.0525	LR: 0.020000
Training Epoch: 7 [32512/46250]	Loss: 0.0694	LR: 0.020000
Training Epoch: 7 [32768/46250]	Loss: 0.0692	LR: 0.020000
Training Epoch: 7 [33024/46250]	Loss: 0.0624	LR: 0.020000
Training Epoch: 7 [33280/46250]	Loss: 0.0181	LR: 0.020000
Training Epoch: 7 [33536/46250]	Loss: 0.0914	LR: 0.020000
Training Epoch: 7 [33792/46250]	Loss: 0.0350	LR: 0.020000
Training Epoch: 7 [34048/46250]	Loss: 0.0256	LR: 0.020000
Training Epoch: 7 [34304/46250]	Loss: 0.0466	LR: 0.020000
Training Epoch: 7 [34560/46250]	Loss: 0.0790	LR: 0.020000
Training Epoch: 7 [34816/46250]	Loss: 0.0743	LR: 0.020000
Training Epoch: 7 [35072/46250]	Loss: 0.0966	LR: 0.020000
Training Epoch: 7 [35328/46250]	Loss: 0.0346	LR: 0.020000
Training Epoch: 7 [35584/46250]	Loss: 0.0489	LR: 0.020000
Training Epoch: 7 [35840/46250]	Loss: 0.0632	LR: 0.020000
Training Epoch: 7 [36096/46250]	Loss: 0.0684	LR: 0.020000
Training Epoch: 7 [36352/46250]	Loss: 0.0584	LR: 0.020000
Training Epoch: 7 [36608/46250]	Loss: 0.0765	LR: 0.020000
Training Epoch: 7 [36864/46250]	Loss: 0.0649	LR: 0.020000
Training Epoch: 7 [37120/46250]	Loss: 0.0692	LR: 0.020000
Training Epoch: 7 [37376/46250]	Loss: 0.0965	LR: 0.020000
Training Epoch: 7 [37632/46250]	Loss: 0.0501	LR: 0.020000
Training Epoch: 7 [37888/46250]	Loss: 0.0623	LR: 0.020000
Training Epoch: 7 [38144/46250]	Loss: 0.0923	LR: 0.020000
Training Epoch: 7 [38400/46250]	Loss: 0.0811	LR: 0.020000
Training Epoch: 7 [38656/46250]	Loss: 0.0755	LR: 0.020000
Training Epoch: 7 [38912/46250]	Loss: 0.0589	LR: 0.020000
Training Epoch: 7 [39168/46250]	Loss: 0.0784	LR: 0.020000
Training Epoch: 7 [39424/46250]	Loss: 0.0660	LR: 0.020000
Training Epoch: 7 [39680/46250]	Loss: 0.0785	LR: 0.020000
Training Epoch: 7 [39936/46250]	Loss: 0.0657	LR: 0.020000
Training Epoch: 7 [40192/46250]	Loss: 0.1247	LR: 0.020000
Training Epoch: 7 [40448/46250]	Loss: 0.0923	LR: 0.020000
Training Epoch: 7 [40704/46250]	Loss: 0.0483	LR: 0.020000
Training Epoch: 7 [40960/46250]	Loss: 0.0321	LR: 0.020000
Training Epoch: 7 [41216/46250]	Loss: 0.0572	LR: 0.020000
Training Epoch: 7 [41472/46250]	Loss: 0.0678	LR: 0.020000
Training Epoch: 7 [41728/46250]	Loss: 0.0236	LR: 0.020000
Training Epoch: 7 [41984/46250]	Loss: 0.1055	LR: 0.020000
Training Epoch: 7 [42240/46250]	Loss: 0.0645	LR: 0.020000
Training Epoch: 7 [42496/46250]	Loss: 0.0548	LR: 0.020000
Training Epoch: 7 [42752/46250]	Loss: 0.0358	LR: 0.020000
Training Epoch: 7 [43008/46250]	Loss: 0.0547	LR: 0.020000
Training Epoch: 7 [43264/46250]	Loss: 0.0533	LR: 0.020000
Training Epoch: 7 [43520/46250]	Loss: 0.0292	LR: 0.020000
Training Epoch: 7 [43776/46250]	Loss: 0.0391	LR: 0.020000
Training Epoch: 7 [44032/46250]	Loss: 0.0680	LR: 0.020000
Training Epoch: 7 [44288/46250]	Loss: 0.0913	LR: 0.020000
Training Epoch: 7 [44544/46250]	Loss: 0.0711	LR: 0.020000
Training Epoch: 7 [44800/46250]	Loss: 0.0996	LR: 0.020000
Training Epoch: 7 [45056/46250]	Loss: 0.0647	LR: 0.020000
Training Epoch: 7 [45312/46250]	Loss: 0.0497	LR: 0.020000
Training Epoch: 7 [45568/46250]	Loss: 0.0955	LR: 0.020000
Training Epoch: 7 [45824/46250]	Loss: 0.0647	LR: 0.020000
Training Epoch: 7 [46080/46250]	Loss: 0.0802	LR: 0.020000
Training Epoch: 7 [46250/46250]	Loss: 0.0628	LR: 0.020000
Epoch 7 - Average Train Loss: 0.0712, Train Accuracy: 0.9756
Epoch 7 training time consumed: 336.18s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0004, Accuracy: 0.9693, Time consumed:23.61s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_18h_15m_14s/ViT-Cifar10-seed1-ret25-7-best.pth
Training Epoch: 8 [256/46250]	Loss: 0.0600	LR: 0.020000
Training Epoch: 8 [512/46250]	Loss: 0.1019	LR: 0.020000
Training Epoch: 8 [768/46250]	Loss: 0.0283	LR: 0.020000
Training Epoch: 8 [1024/46250]	Loss: 0.0522	LR: 0.020000
Training Epoch: 8 [1280/46250]	Loss: 0.0413	LR: 0.020000
Training Epoch: 8 [1536/46250]	Loss: 0.0531	LR: 0.020000
Training Epoch: 8 [1792/46250]	Loss: 0.0590	LR: 0.020000
Training Epoch: 8 [2048/46250]	Loss: 0.0722	LR: 0.020000
Training Epoch: 8 [2304/46250]	Loss: 0.0693	LR: 0.020000
Training Epoch: 8 [2560/46250]	Loss: 0.0231	LR: 0.020000
Training Epoch: 8 [2816/46250]	Loss: 0.0566	LR: 0.020000
Training Epoch: 8 [3072/46250]	Loss: 0.0504	LR: 0.020000
Training Epoch: 8 [3328/46250]	Loss: 0.0542	LR: 0.020000
Training Epoch: 8 [3584/46250]	Loss: 0.0398	LR: 0.020000
Training Epoch: 8 [3840/46250]	Loss: 0.0764	LR: 0.020000
Training Epoch: 8 [4096/46250]	Loss: 0.0713	LR: 0.020000
Training Epoch: 8 [4352/46250]	Loss: 0.0191	LR: 0.020000
Training Epoch: 8 [4608/46250]	Loss: 0.0733	LR: 0.020000
Training Epoch: 8 [4864/46250]	Loss: 0.0522	LR: 0.020000
Training Epoch: 8 [5120/46250]	Loss: 0.0470	LR: 0.020000
Training Epoch: 8 [5376/46250]	Loss: 0.0548	LR: 0.020000
Training Epoch: 8 [5632/46250]	Loss: 0.0619	LR: 0.020000
Training Epoch: 8 [5888/46250]	Loss: 0.0270	LR: 0.020000
Training Epoch: 8 [6144/46250]	Loss: 0.0463	LR: 0.020000
Training Epoch: 8 [6400/46250]	Loss: 0.0514	LR: 0.020000
Training Epoch: 8 [6656/46250]	Loss: 0.0410	LR: 0.020000
Training Epoch: 8 [6912/46250]	Loss: 0.0636	LR: 0.020000
Training Epoch: 8 [7168/46250]	Loss: 0.0890	LR: 0.020000
Training Epoch: 8 [7424/46250]	Loss: 0.0308	LR: 0.020000
Training Epoch: 8 [7680/46250]	Loss: 0.0392	LR: 0.020000
Training Epoch: 8 [7936/46250]	Loss: 0.0353	LR: 0.020000
Training Epoch: 8 [8192/46250]	Loss: 0.0713	LR: 0.020000
Training Epoch: 8 [8448/46250]	Loss: 0.0455	LR: 0.020000
Training Epoch: 8 [8704/46250]	Loss: 0.0257	LR: 0.020000
Training Epoch: 8 [8960/46250]	Loss: 0.0581	LR: 0.020000
Training Epoch: 8 [9216/46250]	Loss: 0.0244	LR: 0.020000
Training Epoch: 8 [9472/46250]	Loss: 0.0411	LR: 0.020000
Training Epoch: 8 [9728/46250]	Loss: 0.0401	LR: 0.020000
Training Epoch: 8 [9984/46250]	Loss: 0.0772	LR: 0.020000
Training Epoch: 8 [10240/46250]	Loss: 0.0932	LR: 0.020000
Training Epoch: 8 [10496/46250]	Loss: 0.0155	LR: 0.020000
Training Epoch: 8 [10752/46250]	Loss: 0.0415	LR: 0.020000
Training Epoch: 8 [11008/46250]	Loss: 0.0445	LR: 0.020000
Training Epoch: 8 [11264/46250]	Loss: 0.0561	LR: 0.020000
Training Epoch: 8 [11520/46250]	Loss: 0.0321	LR: 0.020000
Training Epoch: 8 [11776/46250]	Loss: 0.0872	LR: 0.020000
Training Epoch: 8 [12032/46250]	Loss: 0.0536	LR: 0.020000
Training Epoch: 8 [12288/46250]	Loss: 0.0405	LR: 0.020000
Training Epoch: 8 [12544/46250]	Loss: 0.0535	LR: 0.020000
Training Epoch: 8 [12800/46250]	Loss: 0.0254	LR: 0.020000
Training Epoch: 8 [13056/46250]	Loss: 0.0622	LR: 0.020000
Training Epoch: 8 [13312/46250]	Loss: 0.0258	LR: 0.020000
Training Epoch: 8 [13568/46250]	Loss: 0.0626	LR: 0.020000
Training Epoch: 8 [13824/46250]	Loss: 0.0434	LR: 0.020000
Training Epoch: 8 [14080/46250]	Loss: 0.0384	LR: 0.020000
Training Epoch: 8 [14336/46250]	Loss: 0.0482	LR: 0.020000
Training Epoch: 8 [14592/46250]	Loss: 0.0483	LR: 0.020000
Training Epoch: 8 [14848/46250]	Loss: 0.0297	LR: 0.020000
Training Epoch: 8 [15104/46250]	Loss: 0.0602	LR: 0.020000
Training Epoch: 8 [15360/46250]	Loss: 0.0544	LR: 0.020000
Training Epoch: 8 [15616/46250]	Loss: 0.0255	LR: 0.020000
Training Epoch: 8 [15872/46250]	Loss: 0.0397	LR: 0.020000
Training Epoch: 8 [16128/46250]	Loss: 0.0480	LR: 0.020000
Training Epoch: 8 [16384/46250]	Loss: 0.0193	LR: 0.020000
Training Epoch: 8 [16640/46250]	Loss: 0.0453	LR: 0.020000
Training Epoch: 8 [16896/46250]	Loss: 0.0412	LR: 0.020000
Training Epoch: 8 [17152/46250]	Loss: 0.0305	LR: 0.020000
Training Epoch: 8 [17408/46250]	Loss: 0.0766	LR: 0.020000
Training Epoch: 8 [17664/46250]	Loss: 0.0363	LR: 0.020000
Training Epoch: 8 [17920/46250]	Loss: 0.0266	LR: 0.020000
Training Epoch: 8 [18176/46250]	Loss: 0.0573	LR: 0.020000
Training Epoch: 8 [18432/46250]	Loss: 0.0283	LR: 0.020000
Training Epoch: 8 [18688/46250]	Loss: 0.0186	LR: 0.020000
Training Epoch: 8 [18944/46250]	Loss: 0.0542	LR: 0.020000
Training Epoch: 8 [19200/46250]	Loss: 0.0708	LR: 0.020000
Training Epoch: 8 [19456/46250]	Loss: 0.0343	LR: 0.020000
Training Epoch: 8 [19712/46250]	Loss: 0.0503	LR: 0.020000
Training Epoch: 8 [19968/46250]	Loss: 0.0389	LR: 0.020000
Training Epoch: 8 [20224/46250]	Loss: 0.0434	LR: 0.020000
Training Epoch: 8 [20480/46250]	Loss: 0.0567	LR: 0.020000
Training Epoch: 8 [20736/46250]	Loss: 0.0411	LR: 0.020000
Training Epoch: 8 [20992/46250]	Loss: 0.0840	LR: 0.020000
Training Epoch: 8 [21248/46250]	Loss: 0.0306	LR: 0.020000
Training Epoch: 8 [21504/46250]	Loss: 0.0319	LR: 0.020000
Training Epoch: 8 [21760/46250]	Loss: 0.0333	LR: 0.020000
Training Epoch: 8 [22016/46250]	Loss: 0.0283	LR: 0.020000
Training Epoch: 8 [22272/46250]	Loss: 0.0492	LR: 0.020000
Training Epoch: 8 [22528/46250]	Loss: 0.0885	LR: 0.020000
Training Epoch: 8 [22784/46250]	Loss: 0.0482	LR: 0.020000
Training Epoch: 8 [23040/46250]	Loss: 0.0586	LR: 0.020000
Training Epoch: 8 [23296/46250]	Loss: 0.0442	LR: 0.020000
Training Epoch: 8 [23552/46250]	Loss: 0.0631	LR: 0.020000
Training Epoch: 8 [23808/46250]	Loss: 0.0230	LR: 0.020000
Training Epoch: 8 [24064/46250]	Loss: 0.0737	LR: 0.020000
Training Epoch: 8 [24320/46250]	Loss: 0.0334	LR: 0.020000
Training Epoch: 8 [24576/46250]	Loss: 0.0781	LR: 0.020000
Training Epoch: 8 [24832/46250]	Loss: 0.0323	LR: 0.020000
Training Epoch: 8 [25088/46250]	Loss: 0.0307	LR: 0.020000
Training Epoch: 8 [25344/46250]	Loss: 0.0272	LR: 0.020000
Training Epoch: 8 [25600/46250]	Loss: 0.0529	LR: 0.020000
Training Epoch: 8 [25856/46250]	Loss: 0.0309	LR: 0.020000
Training Epoch: 8 [26112/46250]	Loss: 0.0662	LR: 0.020000
Training Epoch: 8 [26368/46250]	Loss: 0.0846	LR: 0.020000
Training Epoch: 8 [26624/46250]	Loss: 0.0646	LR: 0.020000
Training Epoch: 8 [26880/46250]	Loss: 0.0892	LR: 0.020000
Training Epoch: 8 [27136/46250]	Loss: 0.0318	LR: 0.020000
Training Epoch: 8 [27392/46250]	Loss: 0.0360	LR: 0.020000
Training Epoch: 8 [27648/46250]	Loss: 0.0286	LR: 0.020000
Training Epoch: 8 [27904/46250]	Loss: 0.0684	LR: 0.020000
Training Epoch: 8 [28160/46250]	Loss: 0.0388	LR: 0.020000
Training Epoch: 8 [28416/46250]	Loss: 0.0579	LR: 0.020000
Training Epoch: 8 [28672/46250]	Loss: 0.0359	LR: 0.020000
Training Epoch: 8 [28928/46250]	Loss: 0.0443	LR: 0.020000
Training Epoch: 8 [29184/46250]	Loss: 0.0651	LR: 0.020000
Training Epoch: 8 [29440/46250]	Loss: 0.0642	LR: 0.020000
Training Epoch: 8 [29696/46250]	Loss: 0.0966	LR: 0.020000
Training Epoch: 8 [29952/46250]	Loss: 0.0471	LR: 0.020000
Training Epoch: 8 [30208/46250]	Loss: 0.0567	LR: 0.020000
Training Epoch: 8 [30464/46250]	Loss: 0.0386	LR: 0.020000
Training Epoch: 8 [30720/46250]	Loss: 0.0528	LR: 0.020000
Training Epoch: 8 [30976/46250]	Loss: 0.0261	LR: 0.020000
Training Epoch: 8 [31232/46250]	Loss: 0.0249	LR: 0.020000
Training Epoch: 8 [31488/46250]	Loss: 0.0309	LR: 0.020000
Training Epoch: 8 [31744/46250]	Loss: 0.0325	LR: 0.020000
Training Epoch: 8 [32000/46250]	Loss: 0.0193	LR: 0.020000
Training Epoch: 8 [32256/46250]	Loss: 0.0620	LR: 0.020000
Training Epoch: 8 [32512/46250]	Loss: 0.0638	LR: 0.020000
Training Epoch: 8 [32768/46250]	Loss: 0.0426	LR: 0.020000
Training Epoch: 8 [33024/46250]	Loss: 0.0775	LR: 0.020000
Training Epoch: 8 [33280/46250]	Loss: 0.0570	LR: 0.020000
Training Epoch: 8 [33536/46250]	Loss: 0.0309	LR: 0.020000
Training Epoch: 8 [33792/46250]	Loss: 0.0558	LR: 0.020000
Training Epoch: 8 [34048/46250]	Loss: 0.0467	LR: 0.020000
Training Epoch: 8 [34304/46250]	Loss: 0.0816	LR: 0.020000
Training Epoch: 8 [34560/46250]	Loss: 0.0357	LR: 0.020000
Training Epoch: 8 [34816/46250]	Loss: 0.0629	LR: 0.020000
Training Epoch: 8 [35072/46250]	Loss: 0.0328	LR: 0.020000
Training Epoch: 8 [35328/46250]	Loss: 0.0628	LR: 0.020000
Training Epoch: 8 [35584/46250]	Loss: 0.0471	LR: 0.020000
Training Epoch: 8 [35840/46250]	Loss: 0.0342	LR: 0.020000
Training Epoch: 8 [36096/46250]	Loss: 0.0711	LR: 0.020000
Training Epoch: 8 [36352/46250]	Loss: 0.0466	LR: 0.020000
Training Epoch: 8 [36608/46250]	Loss: 0.0496	LR: 0.020000
Training Epoch: 8 [36864/46250]	Loss: 0.0342	LR: 0.020000
Training Epoch: 8 [37120/46250]	Loss: 0.0469	LR: 0.020000
Training Epoch: 8 [37376/46250]	Loss: 0.0565	LR: 0.020000
Training Epoch: 8 [37632/46250]	Loss: 0.0529	LR: 0.020000
Training Epoch: 8 [37888/46250]	Loss: 0.0435	LR: 0.020000
Training Epoch: 8 [38144/46250]	Loss: 0.0359	LR: 0.020000
Training Epoch: 8 [38400/46250]	Loss: 0.0545	LR: 0.020000
Training Epoch: 8 [38656/46250]	Loss: 0.0677	LR: 0.020000
Training Epoch: 8 [38912/46250]	Loss: 0.0518	LR: 0.020000
Training Epoch: 8 [39168/46250]	Loss: 0.0505	LR: 0.020000
Training Epoch: 8 [39424/46250]	Loss: 0.0318	LR: 0.020000
Training Epoch: 8 [39680/46250]	Loss: 0.0409	LR: 0.020000
Training Epoch: 8 [39936/46250]	Loss: 0.0393	LR: 0.020000
Training Epoch: 8 [40192/46250]	Loss: 0.0513	LR: 0.020000
Training Epoch: 8 [40448/46250]	Loss: 0.0464	LR: 0.020000
Training Epoch: 8 [40704/46250]	Loss: 0.0496	LR: 0.020000
Training Epoch: 8 [40960/46250]	Loss: 0.0404	LR: 0.020000
Training Epoch: 8 [41216/46250]	Loss: 0.0529	LR: 0.020000
Training Epoch: 8 [41472/46250]	Loss: 0.0376	LR: 0.020000
Training Epoch: 8 [41728/46250]	Loss: 0.0638	LR: 0.020000
Training Epoch: 8 [41984/46250]	Loss: 0.0553	LR: 0.020000
Training Epoch: 8 [42240/46250]	Loss: 0.0740	LR: 0.020000
Training Epoch: 8 [42496/46250]	Loss: 0.0583	LR: 0.020000
Training Epoch: 8 [42752/46250]	Loss: 0.0536	LR: 0.020000
Training Epoch: 8 [43008/46250]	Loss: 0.0554	LR: 0.020000
Training Epoch: 8 [43264/46250]	Loss: 0.0531	LR: 0.020000
Training Epoch: 8 [43520/46250]	Loss: 0.0440	LR: 0.020000
Training Epoch: 8 [43776/46250]	Loss: 0.0469	LR: 0.020000
Training Epoch: 8 [44032/46250]	Loss: 0.0542	LR: 0.020000
Training Epoch: 8 [44288/46250]	Loss: 0.0411	LR: 0.020000
Training Epoch: 8 [44544/46250]	Loss: 0.0474	LR: 0.020000
Training Epoch: 8 [44800/46250]	Loss: 0.0218	LR: 0.020000
Training Epoch: 8 [45056/46250]	Loss: 0.0224	LR: 0.020000
Training Epoch: 8 [45312/46250]	Loss: 0.0362	LR: 0.020000
Training Epoch: 8 [45568/46250]	Loss: 0.0426	LR: 0.020000
Training Epoch: 8 [45824/46250]	Loss: 0.0312	LR: 0.020000
Training Epoch: 8 [46080/46250]	Loss: 0.0637	LR: 0.020000
Training Epoch: 8 [46250/46250]	Loss: 0.0741	LR: 0.020000
Epoch 8 - Average Train Loss: 0.0489, Train Accuracy: 0.9822
Epoch 8 training time consumed: 335.18s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0004, Accuracy: 0.9718, Time consumed:23.62s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_18h_15m_14s/ViT-Cifar10-seed1-ret25-8-best.pth
Valid (Test) Dl:  10000
Train Dl:  50000
Retain Train Dl:  46250
Forget Train Dl:  3750
Retain Valid Dl:  46250
Forget Valid Dl:  3750
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 3750 samples
Set1 Distribution: 3750 samples
Set2 Distribution: 3750 samples
Set1 Distribution: 3750 samples
Set2 Distribution: 3750 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 97.24609375
Retain Accuracy: 98.73423767089844
Zero-Retain Forget (ZRF): 0.7555802464485168
Membership Inference Attack (MIA): 0.8098666666666666
Forget vs Retain Membership Inference Attack (MIA): 0.538
Forget vs Test Membership Inference Attack (MIA): 0.522
Test vs Retain Membership Inference Attack (MIA): 0.522
Train vs Test Membership Inference Attack (MIA): 0.518
Forget Set Accuracy (Df): 95.89075469970703
Method Execution Time: 5315.03 seconds
