hello
hello

📌S Retain class distribution for seed 8:
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 8:
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
72

📊 Updated class distribution:
Retain set:
  Class 0: 4875
  Class 1: 4875
  Class 2: 4875
  Class 3: 4875
  Class 4: 4875
  Class 5: 4875
  Class 6: 4875
  Class 7: 4875
  Class 8: 4875
  Class 9: 4875
Forget set:
  Class 0: 125
  Class 1: 125
  Class 2: 125
  Class 3: 125
  Class 4: 125
  Class 5: 125
  Class 6: 125
  Class 7: 125
  Class 8: 125
  Class 9: 125
hello
hello
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/48750]	Loss: 2.4656	LR: 0.000000
Training Epoch: 1 [512/48750]	Loss: 2.4135	LR: 0.000524
Training Epoch: 1 [768/48750]	Loss: 2.4444	LR: 0.001047
Training Epoch: 1 [1024/48750]	Loss: 2.4006	LR: 0.001571
Training Epoch: 1 [1280/48750]	Loss: 2.3011	LR: 0.002094
Training Epoch: 1 [1536/48750]	Loss: 2.2450	LR: 0.002618
Training Epoch: 1 [1792/48750]	Loss: 2.0259	LR: 0.003141
Training Epoch: 1 [2048/48750]	Loss: 1.8399	LR: 0.003665
Training Epoch: 1 [2304/48750]	Loss: 1.6194	LR: 0.004188
Training Epoch: 1 [2560/48750]	Loss: 1.4646	LR: 0.004712
Training Epoch: 1 [2816/48750]	Loss: 1.2898	LR: 0.005236
Training Epoch: 1 [3072/48750]	Loss: 1.0365	LR: 0.005759
Training Epoch: 1 [3328/48750]	Loss: 0.9358	LR: 0.006283
Training Epoch: 1 [3584/48750]	Loss: 0.6646	LR: 0.006806
Training Epoch: 1 [3840/48750]	Loss: 0.5307	LR: 0.007330
Training Epoch: 1 [4096/48750]	Loss: 0.4389	LR: 0.007853
Training Epoch: 1 [4352/48750]	Loss: 0.3644	LR: 0.008377
Training Epoch: 1 [4608/48750]	Loss: 0.3134	LR: 0.008901
Training Epoch: 1 [4864/48750]	Loss: 0.2420	LR: 0.009424
Training Epoch: 1 [5120/48750]	Loss: 0.2051	LR: 0.009948
Training Epoch: 1 [5376/48750]	Loss: 0.1510	LR: 0.010471
Training Epoch: 1 [5632/48750]	Loss: 0.2422	LR: 0.010995
Training Epoch: 1 [5888/48750]	Loss: 0.2026	LR: 0.011518
Training Epoch: 1 [6144/48750]	Loss: 0.2069	LR: 0.012042
Training Epoch: 1 [6400/48750]	Loss: 0.2270	LR: 0.012565
Training Epoch: 1 [6656/48750]	Loss: 0.1832	LR: 0.013089
Training Epoch: 1 [6912/48750]	Loss: 0.1172	LR: 0.013613
Training Epoch: 1 [7168/48750]	Loss: 0.3670	LR: 0.014136
Training Epoch: 1 [7424/48750]	Loss: 0.1518	LR: 0.014660
Training Epoch: 1 [7680/48750]	Loss: 0.2362	LR: 0.015183
Training Epoch: 1 [7936/48750]	Loss: 0.2511	LR: 0.015707
Training Epoch: 1 [8192/48750]	Loss: 0.1952	LR: 0.016230
Training Epoch: 1 [8448/48750]	Loss: 0.1611	LR: 0.016754
Training Epoch: 1 [8704/48750]	Loss: 0.2568	LR: 0.017277
Training Epoch: 1 [8960/48750]	Loss: 0.2328	LR: 0.017801
Training Epoch: 1 [9216/48750]	Loss: 0.2252	LR: 0.018325
Training Epoch: 1 [9472/48750]	Loss: 0.2018	LR: 0.018848
Training Epoch: 1 [9728/48750]	Loss: 0.3569	LR: 0.019372
Training Epoch: 1 [9984/48750]	Loss: 0.3137	LR: 0.019895
Training Epoch: 1 [10240/48750]	Loss: 0.3593	LR: 0.020419
Training Epoch: 1 [10496/48750]	Loss: 0.4439	LR: 0.020942
Training Epoch: 1 [10752/48750]	Loss: 0.2794	LR: 0.021466
Training Epoch: 1 [11008/48750]	Loss: 0.5026	LR: 0.021990
Training Epoch: 1 [11264/48750]	Loss: 0.5749	LR: 0.022513
Training Epoch: 1 [11520/48750]	Loss: 0.3132	LR: 0.023037
Training Epoch: 1 [11776/48750]	Loss: 0.7655	LR: 0.023560
Training Epoch: 1 [12032/48750]	Loss: 0.6615	LR: 0.024084
Training Epoch: 1 [12288/48750]	Loss: 0.7620	LR: 0.024607
Training Epoch: 1 [12544/48750]	Loss: 0.5462	LR: 0.025131
Training Epoch: 1 [12800/48750]	Loss: 0.4822	LR: 0.025654
Training Epoch: 1 [13056/48750]	Loss: 0.3738	LR: 0.026178
Training Epoch: 1 [13312/48750]	Loss: 0.4773	LR: 0.026702
Training Epoch: 1 [13568/48750]	Loss: 0.3334	LR: 0.027225
Training Epoch: 1 [13824/48750]	Loss: 0.3508	LR: 0.027749
Training Epoch: 1 [14080/48750]	Loss: 0.2624	LR: 0.028272
Training Epoch: 1 [14336/48750]	Loss: 0.3258	LR: 0.028796
Training Epoch: 1 [14592/48750]	Loss: 0.3323	LR: 0.029319
Training Epoch: 1 [14848/48750]	Loss: 0.4487	LR: 0.029843
Training Epoch: 1 [15104/48750]	Loss: 0.3039	LR: 0.030366
Training Epoch: 1 [15360/48750]	Loss: 0.2515	LR: 0.030890
Training Epoch: 1 [15616/48750]	Loss: 0.2096	LR: 0.031414
Training Epoch: 1 [15872/48750]	Loss: 0.3429	LR: 0.031937
Training Epoch: 1 [16128/48750]	Loss: 0.2373	LR: 0.032461
Training Epoch: 1 [16384/48750]	Loss: 0.2041	LR: 0.032984
Training Epoch: 1 [16640/48750]	Loss: 0.2205	LR: 0.033508
Training Epoch: 1 [16896/48750]	Loss: 0.2083	LR: 0.034031
Training Epoch: 1 [17152/48750]	Loss: 0.3996	LR: 0.034555
Training Epoch: 1 [17408/48750]	Loss: 0.1750	LR: 0.035079
Training Epoch: 1 [17664/48750]	Loss: 0.3258	LR: 0.035602
Training Epoch: 1 [17920/48750]	Loss: 0.2495	LR: 0.036126
Training Epoch: 1 [18176/48750]	Loss: 0.2765	LR: 0.036649
Training Epoch: 1 [18432/48750]	Loss: 0.1800	LR: 0.037173
Training Epoch: 1 [18688/48750]	Loss: 0.2788	LR: 0.037696
Training Epoch: 1 [18944/48750]	Loss: 0.2218	LR: 0.038220
Training Epoch: 1 [19200/48750]	Loss: 0.3215	LR: 0.038743
Training Epoch: 1 [19456/48750]	Loss: 0.2022	LR: 0.039267
Training Epoch: 1 [19712/48750]	Loss: 0.1142	LR: 0.039791
Training Epoch: 1 [19968/48750]	Loss: 0.2789	LR: 0.040314
Training Epoch: 1 [20224/48750]	Loss: 0.2706	LR: 0.040838
Training Epoch: 1 [20480/48750]	Loss: 0.2305	LR: 0.041361
Training Epoch: 1 [20736/48750]	Loss: 0.1318	LR: 0.041885
Training Epoch: 1 [20992/48750]	Loss: 0.2129	LR: 0.042408
Training Epoch: 1 [21248/48750]	Loss: 0.1384	LR: 0.042932
Training Epoch: 1 [21504/48750]	Loss: 0.1573	LR: 0.043455
Training Epoch: 1 [21760/48750]	Loss: 0.1772	LR: 0.043979
Training Epoch: 1 [22016/48750]	Loss: 0.1406	LR: 0.044503
Training Epoch: 1 [22272/48750]	Loss: 0.1414	LR: 0.045026
Training Epoch: 1 [22528/48750]	Loss: 0.1999	LR: 0.045550
Training Epoch: 1 [22784/48750]	Loss: 0.1778	LR: 0.046073
Training Epoch: 1 [23040/48750]	Loss: 0.1578	LR: 0.046597
Training Epoch: 1 [23296/48750]	Loss: 0.1986	LR: 0.047120
Training Epoch: 1 [23552/48750]	Loss: 0.1908	LR: 0.047644
Training Epoch: 1 [23808/48750]	Loss: 0.2313	LR: 0.048168
Training Epoch: 1 [24064/48750]	Loss: 0.2875	LR: 0.048691
Training Epoch: 1 [24320/48750]	Loss: 0.1900	LR: 0.049215
Training Epoch: 1 [24576/48750]	Loss: 0.1639	LR: 0.049738
Training Epoch: 1 [24832/48750]	Loss: 0.1682	LR: 0.050262
Training Epoch: 1 [25088/48750]	Loss: 0.1616	LR: 0.050785
Training Epoch: 1 [25344/48750]	Loss: 0.2358	LR: 0.051309
Training Epoch: 1 [25600/48750]	Loss: 0.2137	LR: 0.051832
Training Epoch: 1 [25856/48750]	Loss: 0.1316	LR: 0.052356
Training Epoch: 1 [26112/48750]	Loss: 0.1543	LR: 0.052880
Training Epoch: 1 [26368/48750]	Loss: 0.2344	LR: 0.053403
Training Epoch: 1 [26624/48750]	Loss: 0.2381	LR: 0.053927
Training Epoch: 1 [26880/48750]	Loss: 0.2082	LR: 0.054450
Training Epoch: 1 [27136/48750]	Loss: 0.2099	LR: 0.054974
Training Epoch: 1 [27392/48750]	Loss: 0.3098	LR: 0.055497
Training Epoch: 1 [27648/48750]	Loss: 0.1523	LR: 0.056021
Training Epoch: 1 [27904/48750]	Loss: 0.1801	LR: 0.056545
Training Epoch: 1 [28160/48750]	Loss: 0.2345	LR: 0.057068
Training Epoch: 1 [28416/48750]	Loss: 0.1747	LR: 0.057592
Training Epoch: 1 [28672/48750]	Loss: 0.1524	LR: 0.058115
Training Epoch: 1 [28928/48750]	Loss: 0.1911	LR: 0.058639
Training Epoch: 1 [29184/48750]	Loss: 0.1128	LR: 0.059162
Training Epoch: 1 [29440/48750]	Loss: 0.1815	LR: 0.059686
Training Epoch: 1 [29696/48750]	Loss: 0.1809	LR: 0.060209
Training Epoch: 1 [29952/48750]	Loss: 0.2055	LR: 0.060733
Training Epoch: 1 [30208/48750]	Loss: 0.1943	LR: 0.061257
Training Epoch: 1 [30464/48750]	Loss: 0.1856	LR: 0.061780
Training Epoch: 1 [30720/48750]	Loss: 0.1339	LR: 0.062304
Training Epoch: 1 [30976/48750]	Loss: 0.2475	LR: 0.062827
Training Epoch: 1 [31232/48750]	Loss: 0.1937	LR: 0.063351
Training Epoch: 1 [31488/48750]	Loss: 0.2367	LR: 0.063874
Training Epoch: 1 [31744/48750]	Loss: 0.1600	LR: 0.064398
Training Epoch: 1 [32000/48750]	Loss: 0.2409	LR: 0.064921
Training Epoch: 1 [32256/48750]	Loss: 0.1729	LR: 0.065445
Training Epoch: 1 [32512/48750]	Loss: 0.2396	LR: 0.065969
Training Epoch: 1 [32768/48750]	Loss: 0.1708	LR: 0.066492
Training Epoch: 1 [33024/48750]	Loss: 0.2243	LR: 0.067016
Training Epoch: 1 [33280/48750]	Loss: 0.1751	LR: 0.067539
Training Epoch: 1 [33536/48750]	Loss: 0.1949	LR: 0.068063
Training Epoch: 1 [33792/48750]	Loss: 0.2098	LR: 0.068586
Training Epoch: 1 [34048/48750]	Loss: 0.2261	LR: 0.069110
Training Epoch: 1 [34304/48750]	Loss: 0.2800	LR: 0.069634
Training Epoch: 1 [34560/48750]	Loss: 0.2665	LR: 0.070157
Training Epoch: 1 [34816/48750]	Loss: 0.2644	LR: 0.070681
Training Epoch: 1 [35072/48750]	Loss: 0.2813	LR: 0.071204
Training Epoch: 1 [35328/48750]	Loss: 0.1856	LR: 0.071728
Training Epoch: 1 [35584/48750]	Loss: 0.2360	LR: 0.072251
Training Epoch: 1 [35840/48750]	Loss: 0.1702	LR: 0.072775
Training Epoch: 1 [36096/48750]	Loss: 0.1604	LR: 0.073298
Training Epoch: 1 [36352/48750]	Loss: 0.2289	LR: 0.073822
Training Epoch: 1 [36608/48750]	Loss: 0.1847	LR: 0.074346
Training Epoch: 1 [36864/48750]	Loss: 0.1835	LR: 0.074869
Training Epoch: 1 [37120/48750]	Loss: 0.2392	LR: 0.075393
Training Epoch: 1 [37376/48750]	Loss: 0.2121	LR: 0.075916
Training Epoch: 1 [37632/48750]	Loss: 0.2273	LR: 0.076440
Training Epoch: 1 [37888/48750]	Loss: 0.1388	LR: 0.076963
Training Epoch: 1 [38144/48750]	Loss: 0.1942	LR: 0.077487
Training Epoch: 1 [38400/48750]	Loss: 0.2571	LR: 0.078010
Training Epoch: 1 [38656/48750]	Loss: 0.1497	LR: 0.078534
Training Epoch: 1 [38912/48750]	Loss: 0.2412	LR: 0.079058
Training Epoch: 1 [39168/48750]	Loss: 0.3015	LR: 0.079581
Training Epoch: 1 [39424/48750]	Loss: 0.4312	LR: 0.080105
Training Epoch: 1 [39680/48750]	Loss: 0.1531	LR: 0.080628
Training Epoch: 1 [39936/48750]	Loss: 0.2204	LR: 0.081152
Training Epoch: 1 [40192/48750]	Loss: 0.2763	LR: 0.081675
Training Epoch: 1 [40448/48750]	Loss: 0.3178	LR: 0.082199
Training Epoch: 1 [40704/48750]	Loss: 0.2273	LR: 0.082723
Training Epoch: 1 [40960/48750]	Loss: 0.2784	LR: 0.083246
Training Epoch: 1 [41216/48750]	Loss: 0.3452	LR: 0.083770
Training Epoch: 1 [41472/48750]	Loss: 0.3161	LR: 0.084293
Training Epoch: 1 [41728/48750]	Loss: 0.2204	LR: 0.084817
Training Epoch: 1 [41984/48750]	Loss: 0.2820	LR: 0.085340
Training Epoch: 1 [42240/48750]	Loss: 0.1979	LR: 0.085864
Training Epoch: 1 [42496/48750]	Loss: 0.3593	LR: 0.086387
Training Epoch: 1 [42752/48750]	Loss: 0.2427	LR: 0.086911
Training Epoch: 1 [43008/48750]	Loss: 0.2865	LR: 0.087435
Training Epoch: 1 [43264/48750]	Loss: 0.2586	LR: 0.087958
Training Epoch: 1 [43520/48750]	Loss: 0.2650	LR: 0.088482
Training Epoch: 1 [43776/48750]	Loss: 0.3891	LR: 0.089005
Training Epoch: 1 [44032/48750]	Loss: 0.2147	LR: 0.089529
Training Epoch: 1 [44288/48750]	Loss: 0.3883	LR: 0.090052
Training Epoch: 1 [44544/48750]	Loss: 0.2968	LR: 0.090576
Training Epoch: 1 [44800/48750]	Loss: 0.2885	LR: 0.091099
Training Epoch: 1 [45056/48750]	Loss: 0.3545	LR: 0.091623
Training Epoch: 1 [45312/48750]	Loss: 0.2384	LR: 0.092147
Training Epoch: 1 [45568/48750]	Loss: 0.3076	LR: 0.092670
Training Epoch: 1 [45824/48750]	Loss: 0.2180	LR: 0.093194
Training Epoch: 1 [46080/48750]	Loss: 0.4684	LR: 0.093717
Training Epoch: 1 [46336/48750]	Loss: 0.2575	LR: 0.094241
Training Epoch: 1 [46592/48750]	Loss: 0.2531	LR: 0.094764
Training Epoch: 1 [46848/48750]	Loss: 0.3611	LR: 0.095288
Training Epoch: 1 [47104/48750]	Loss: 0.3249	LR: 0.095812
Training Epoch: 1 [47360/48750]	Loss: 0.3003	LR: 0.096335
Training Epoch: 1 [47616/48750]	Loss: 0.2301	LR: 0.096859
Training Epoch: 1 [47872/48750]	Loss: 0.2876	LR: 0.097382
Training Epoch: 1 [48128/48750]	Loss: 0.2907	LR: 0.097906
Training Epoch: 1 [48384/48750]	Loss: 0.2029	LR: 0.098429
Training Epoch: 1 [48640/48750]	Loss: 0.2238	LR: 0.098953
Training Epoch: 1 [48750/48750]	Loss: 0.2207	LR: 0.099476
Epoch 1 - Average Train Loss: 0.3719, Train Accuracy: 0.8802
Epoch 1 training time consumed: 352.28s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0009, Accuracy: 0.9299, Time consumed:23.50s
Saving weights file to checkpoint/retrain/ViT/Sunday_20_July_2025_00h_27m_43s/ViT-Cifar10-seed8-ret75-1-best.pth
Training Epoch: 2 [256/48750]	Loss: 0.3504	LR: 0.100000
Training Epoch: 2 [512/48750]	Loss: 0.2988	LR: 0.100000
Training Epoch: 2 [768/48750]	Loss: 0.3660	LR: 0.100000
Training Epoch: 2 [1024/48750]	Loss: 0.2877	LR: 0.100000
Training Epoch: 2 [1280/48750]	Loss: 0.1971	LR: 0.100000
Training Epoch: 2 [1536/48750]	Loss: 0.3175	LR: 0.100000
Training Epoch: 2 [1792/48750]	Loss: 0.3473	LR: 0.100000
Training Epoch: 2 [2048/48750]	Loss: 0.2164	LR: 0.100000
Training Epoch: 2 [2304/48750]	Loss: 0.3771	LR: 0.100000
Training Epoch: 2 [2560/48750]	Loss: 0.2161	LR: 0.100000
Training Epoch: 2 [2816/48750]	Loss: 0.3892	LR: 0.100000
Training Epoch: 2 [3072/48750]	Loss: 0.3373	LR: 0.100000
Training Epoch: 2 [3328/48750]	Loss: 0.3511	LR: 0.100000
Training Epoch: 2 [3584/48750]	Loss: 0.1543	LR: 0.100000
Training Epoch: 2 [3840/48750]	Loss: 0.3681	LR: 0.100000
Training Epoch: 2 [4096/48750]	Loss: 0.2635	LR: 0.100000
Training Epoch: 2 [4352/48750]	Loss: 0.2527	LR: 0.100000
Training Epoch: 2 [4608/48750]	Loss: 0.2128	LR: 0.100000
Training Epoch: 2 [4864/48750]	Loss: 0.1801	LR: 0.100000
Training Epoch: 2 [5120/48750]	Loss: 0.2501	LR: 0.100000
Training Epoch: 2 [5376/48750]	Loss: 0.1773	LR: 0.100000
Training Epoch: 2 [5632/48750]	Loss: 0.3592	LR: 0.100000
Training Epoch: 2 [5888/48750]	Loss: 0.3150	LR: 0.100000
Training Epoch: 2 [6144/48750]	Loss: 0.2164	LR: 0.100000
Training Epoch: 2 [6400/48750]	Loss: 0.1458	LR: 0.100000
Training Epoch: 2 [6656/48750]	Loss: 0.2141	LR: 0.100000
Training Epoch: 2 [6912/48750]	Loss: 0.2725	LR: 0.100000
Training Epoch: 2 [7168/48750]	Loss: 0.2475	LR: 0.100000
Training Epoch: 2 [7424/48750]	Loss: 0.1828	LR: 0.100000
Training Epoch: 2 [7680/48750]	Loss: 0.3942	LR: 0.100000
Training Epoch: 2 [7936/48750]	Loss: 0.2154	LR: 0.100000
Training Epoch: 2 [8192/48750]	Loss: 0.3524	LR: 0.100000
Training Epoch: 2 [8448/48750]	Loss: 0.2803	LR: 0.100000
Training Epoch: 2 [8704/48750]	Loss: 0.3717	LR: 0.100000
Training Epoch: 2 [8960/48750]	Loss: 0.3394	LR: 0.100000
Training Epoch: 2 [9216/48750]	Loss: 0.2181	LR: 0.100000
Training Epoch: 2 [9472/48750]	Loss: 0.2235	LR: 0.100000
Training Epoch: 2 [9728/48750]	Loss: 0.3131	LR: 0.100000
Training Epoch: 2 [9984/48750]	Loss: 0.2161	LR: 0.100000
Training Epoch: 2 [10240/48750]	Loss: 0.2892	LR: 0.100000
Training Epoch: 2 [10496/48750]	Loss: 0.2028	LR: 0.100000
Training Epoch: 2 [10752/48750]	Loss: 0.2222	LR: 0.100000
Training Epoch: 2 [11008/48750]	Loss: 0.2837	LR: 0.100000
Training Epoch: 2 [11264/48750]	Loss: 0.1681	LR: 0.100000
Training Epoch: 2 [11520/48750]	Loss: 0.3214	LR: 0.100000
Training Epoch: 2 [11776/48750]	Loss: 0.2823	LR: 0.100000
Training Epoch: 2 [12032/48750]	Loss: 0.1809	LR: 0.100000
Training Epoch: 2 [12288/48750]	Loss: 0.1927	LR: 0.100000
Training Epoch: 2 [12544/48750]	Loss: 0.2623	LR: 0.100000
Training Epoch: 2 [12800/48750]	Loss: 0.1644	LR: 0.100000
Training Epoch: 2 [13056/48750]	Loss: 0.1739	LR: 0.100000
Training Epoch: 2 [13312/48750]	Loss: 0.2000	LR: 0.100000
Training Epoch: 2 [13568/48750]	Loss: 0.1887	LR: 0.100000
Training Epoch: 2 [13824/48750]	Loss: 0.2048	LR: 0.100000
Training Epoch: 2 [14080/48750]	Loss: 0.2179	LR: 0.100000
Training Epoch: 2 [14336/48750]	Loss: 0.2428	LR: 0.100000
Training Epoch: 2 [14592/48750]	Loss: 0.2933	LR: 0.100000
Training Epoch: 2 [14848/48750]	Loss: 0.3280	LR: 0.100000
Training Epoch: 2 [15104/48750]	Loss: 0.2249	LR: 0.100000
Training Epoch: 2 [15360/48750]	Loss: 0.2939	LR: 0.100000
Training Epoch: 2 [15616/48750]	Loss: 0.1679	LR: 0.100000
Training Epoch: 2 [15872/48750]	Loss: 0.2897	LR: 0.100000
Training Epoch: 2 [16128/48750]	Loss: 0.3187	LR: 0.100000
Training Epoch: 2 [16384/48750]	Loss: 0.3086	LR: 0.100000
Training Epoch: 2 [16640/48750]	Loss: 0.1518	LR: 0.100000
Training Epoch: 2 [16896/48750]	Loss: 0.2343	LR: 0.100000
Training Epoch: 2 [17152/48750]	Loss: 0.2225	LR: 0.100000
Training Epoch: 2 [17408/48750]	Loss: 0.2342	LR: 0.100000
Training Epoch: 2 [17664/48750]	Loss: 0.2504	LR: 0.100000
Training Epoch: 2 [17920/48750]	Loss: 0.3322	LR: 0.100000
Training Epoch: 2 [18176/48750]	Loss: 0.2312	LR: 0.100000
Training Epoch: 2 [18432/48750]	Loss: 0.3380	LR: 0.100000
Training Epoch: 2 [18688/48750]	Loss: 0.2899	LR: 0.100000
Training Epoch: 2 [18944/48750]	Loss: 0.4317	LR: 0.100000
Training Epoch: 2 [19200/48750]	Loss: 0.1891	LR: 0.100000
Training Epoch: 2 [19456/48750]	Loss: 0.3320	LR: 0.100000
Training Epoch: 2 [19712/48750]	Loss: 0.2410	LR: 0.100000
Training Epoch: 2 [19968/48750]	Loss: 0.2816	LR: 0.100000
Training Epoch: 2 [20224/48750]	Loss: 0.2982	LR: 0.100000
Training Epoch: 2 [20480/48750]	Loss: 0.1718	LR: 0.100000
Training Epoch: 2 [20736/48750]	Loss: 0.1586	LR: 0.100000
Training Epoch: 2 [20992/48750]	Loss: 0.3014	LR: 0.100000
Training Epoch: 2 [21248/48750]	Loss: 0.1654	LR: 0.100000
Training Epoch: 2 [21504/48750]	Loss: 0.1425	LR: 0.100000
Training Epoch: 2 [21760/48750]	Loss: 0.2821	LR: 0.100000
Training Epoch: 2 [22016/48750]	Loss: 1.0415	LR: 0.100000
Training Epoch: 2 [22272/48750]	Loss: 2.4205	LR: 0.100000
Training Epoch: 2 [22528/48750]	Loss: 2.3196	LR: 0.100000
Training Epoch: 2 [22784/48750]	Loss: 2.3541	LR: 0.100000
Training Epoch: 2 [23040/48750]	Loss: 2.3513	LR: 0.100000
Training Epoch: 2 [23296/48750]	Loss: 2.3270	LR: 0.100000
Training Epoch: 2 [23552/48750]	Loss: 2.4028	LR: 0.100000
Training Epoch: 2 [23808/48750]	Loss: 2.4177	LR: 0.100000
Training Epoch: 2 [24064/48750]	Loss: 2.2819	LR: 0.100000
Training Epoch: 2 [24320/48750]	Loss: 2.2932	LR: 0.100000
Training Epoch: 2 [24576/48750]	Loss: 2.2890	LR: 0.100000
Training Epoch: 2 [24832/48750]	Loss: 2.3672	LR: 0.100000
Training Epoch: 2 [25088/48750]	Loss: 2.3296	LR: 0.100000
Training Epoch: 2 [25344/48750]	Loss: 2.2587	LR: 0.100000
Training Epoch: 2 [25600/48750]	Loss: 2.3045	LR: 0.100000
Training Epoch: 2 [25856/48750]	Loss: 2.3331	LR: 0.100000
Training Epoch: 2 [26112/48750]	Loss: 2.2853	LR: 0.100000
Training Epoch: 2 [26368/48750]	Loss: 2.2438	LR: 0.100000
Training Epoch: 2 [26624/48750]	Loss: 2.3403	LR: 0.100000
Training Epoch: 2 [26880/48750]	Loss: 2.2933	LR: 0.100000
Training Epoch: 2 [27136/48750]	Loss: 2.2569	LR: 0.100000
Training Epoch: 2 [27392/48750]	Loss: 2.1886	LR: 0.100000
Training Epoch: 2 [27648/48750]	Loss: 2.2152	LR: 0.100000
Training Epoch: 2 [27904/48750]	Loss: 2.2227	LR: 0.100000
Training Epoch: 2 [28160/48750]	Loss: 2.1882	LR: 0.100000
Training Epoch: 2 [28416/48750]	Loss: 2.1495	LR: 0.100000
Training Epoch: 2 [28672/48750]	Loss: 2.1997	LR: 0.100000
Training Epoch: 2 [28928/48750]	Loss: 2.1446	LR: 0.100000
Training Epoch: 2 [29184/48750]	Loss: 2.1382	LR: 0.100000
Training Epoch: 2 [29440/48750]	Loss: 2.0938	LR: 0.100000
Training Epoch: 2 [29696/48750]	Loss: 2.0921	LR: 0.100000
Training Epoch: 2 [29952/48750]	Loss: 2.1574	LR: 0.100000
Training Epoch: 2 [30208/48750]	Loss: 2.1225	LR: 0.100000
Training Epoch: 2 [30464/48750]	Loss: 2.1361	LR: 0.100000
Training Epoch: 2 [30720/48750]	Loss: 2.1147	LR: 0.100000
Training Epoch: 2 [30976/48750]	Loss: 2.0208	LR: 0.100000
Training Epoch: 2 [31232/48750]	Loss: 2.1716	LR: 0.100000
Training Epoch: 2 [31488/48750]	Loss: 2.0311	LR: 0.100000
Training Epoch: 2 [31744/48750]	Loss: 2.0017	LR: 0.100000
Training Epoch: 2 [32000/48750]	Loss: 2.0668	LR: 0.100000
Training Epoch: 2 [32256/48750]	Loss: 2.0831	LR: 0.100000
Training Epoch: 2 [32512/48750]	Loss: 2.0859	LR: 0.100000
Training Epoch: 2 [32768/48750]	Loss: 2.0893	LR: 0.100000
Training Epoch: 2 [33024/48750]	Loss: 2.0718	LR: 0.100000
Training Epoch: 2 [33280/48750]	Loss: 2.0916	LR: 0.100000
Training Epoch: 2 [33536/48750]	Loss: 2.0695	LR: 0.100000
Training Epoch: 2 [33792/48750]	Loss: 2.1181	LR: 0.100000
Training Epoch: 2 [34048/48750]	Loss: 2.0744	LR: 0.100000
Training Epoch: 2 [34304/48750]	Loss: 2.1407	LR: 0.100000
Training Epoch: 2 [34560/48750]	Loss: 2.0123	LR: 0.100000
Training Epoch: 2 [34816/48750]	Loss: 2.1183	LR: 0.100000
Training Epoch: 2 [35072/48750]	Loss: 2.1409	LR: 0.100000
Training Epoch: 2 [35328/48750]	Loss: 2.0640	LR: 0.100000
Training Epoch: 2 [35584/48750]	Loss: 2.0321	LR: 0.100000
Training Epoch: 2 [35840/48750]	Loss: 1.9960	LR: 0.100000
Training Epoch: 2 [36096/48750]	Loss: 2.0822	LR: 0.100000
Training Epoch: 2 [36352/48750]	Loss: 2.1497	LR: 0.100000
Training Epoch: 2 [36608/48750]	Loss: 2.0933	LR: 0.100000
Training Epoch: 2 [36864/48750]	Loss: 2.0786	LR: 0.100000
Training Epoch: 2 [37120/48750]	Loss: 2.0882	LR: 0.100000
Training Epoch: 2 [37376/48750]	Loss: 2.0824	LR: 0.100000
Training Epoch: 2 [37632/48750]	Loss: 2.0944	LR: 0.100000
Training Epoch: 2 [37888/48750]	Loss: 2.0335	LR: 0.100000
Training Epoch: 2 [38144/48750]	Loss: 1.9910	LR: 0.100000
Training Epoch: 2 [38400/48750]	Loss: 2.1014	LR: 0.100000
Training Epoch: 2 [38656/48750]	Loss: 2.0467	LR: 0.100000
Training Epoch: 2 [38912/48750]	Loss: 1.9563	LR: 0.100000
Training Epoch: 2 [39168/48750]	Loss: 2.0498	LR: 0.100000
Training Epoch: 2 [39424/48750]	Loss: 2.0450	LR: 0.100000
Training Epoch: 2 [39680/48750]	Loss: 1.9860	LR: 0.100000
Training Epoch: 2 [39936/48750]	Loss: 2.0408	LR: 0.100000
Training Epoch: 2 [40192/48750]	Loss: 2.0216	LR: 0.100000
Training Epoch: 2 [40448/48750]	Loss: 2.0461	LR: 0.100000
Training Epoch: 2 [40704/48750]	Loss: 2.0480	LR: 0.100000
Training Epoch: 2 [40960/48750]	Loss: 2.0119	LR: 0.100000
Training Epoch: 2 [41216/48750]	Loss: 2.0207	LR: 0.100000
Training Epoch: 2 [41472/48750]	Loss: 2.0453	LR: 0.100000
Training Epoch: 2 [41728/48750]	Loss: 2.0209	LR: 0.100000
Training Epoch: 2 [41984/48750]	Loss: 2.0288	LR: 0.100000
Training Epoch: 2 [42240/48750]	Loss: 2.1466	LR: 0.100000
Training Epoch: 2 [42496/48750]	Loss: 2.0660	LR: 0.100000
Training Epoch: 2 [42752/48750]	Loss: 2.0428	LR: 0.100000
Training Epoch: 2 [43008/48750]	Loss: 1.9826	LR: 0.100000
Training Epoch: 2 [43264/48750]	Loss: 1.9868	LR: 0.100000
Training Epoch: 2 [43520/48750]	Loss: 2.0057	LR: 0.100000
Training Epoch: 2 [43776/48750]	Loss: 2.0331	LR: 0.100000
Training Epoch: 2 [44032/48750]	Loss: 2.0161	LR: 0.100000
Training Epoch: 2 [44288/48750]	Loss: 2.0973	LR: 0.100000
Training Epoch: 2 [44544/48750]	Loss: 1.9691	LR: 0.100000
Training Epoch: 2 [44800/48750]	Loss: 2.0493	LR: 0.100000
Training Epoch: 2 [45056/48750]	Loss: 1.9829	LR: 0.100000
Training Epoch: 2 [45312/48750]	Loss: 2.0485	LR: 0.100000
Training Epoch: 2 [45568/48750]	Loss: 2.1140	LR: 0.100000
Training Epoch: 2 [45824/48750]	Loss: 2.0250	LR: 0.100000
Training Epoch: 2 [46080/48750]	Loss: 2.0286	LR: 0.100000
Training Epoch: 2 [46336/48750]	Loss: 1.9610	LR: 0.100000
Training Epoch: 2 [46592/48750]	Loss: 1.9574	LR: 0.100000
Training Epoch: 2 [46848/48750]	Loss: 2.0219	LR: 0.100000
Training Epoch: 2 [47104/48750]	Loss: 1.9185	LR: 0.100000
Training Epoch: 2 [47360/48750]	Loss: 2.0170	LR: 0.100000
Training Epoch: 2 [47616/48750]	Loss: 2.0546	LR: 0.100000
Training Epoch: 2 [47872/48750]	Loss: 1.9550	LR: 0.100000
Training Epoch: 2 [48128/48750]	Loss: 1.9711	LR: 0.100000
Training Epoch: 2 [48384/48750]	Loss: 1.9723	LR: 0.100000
Training Epoch: 2 [48640/48750]	Loss: 1.9157	LR: 0.100000
Training Epoch: 2 [48750/48750]	Loss: 1.9267	LR: 0.100000
Epoch 2 - Average Train Loss: 1.2791, Train Accuracy: 0.5216
Epoch 2 training time consumed: 351.46s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0081, Accuracy: 0.2399, Time consumed:23.52s
Training Epoch: 3 [256/48750]	Loss: 1.9729	LR: 0.100000
Training Epoch: 3 [512/48750]	Loss: 2.0505	LR: 0.100000
Training Epoch: 3 [768/48750]	Loss: 2.0613	LR: 0.100000
Training Epoch: 3 [1024/48750]	Loss: 1.9993	LR: 0.100000
Training Epoch: 3 [1280/48750]	Loss: 1.9293	LR: 0.100000
Training Epoch: 3 [1536/48750]	Loss: 1.9149	LR: 0.100000
Training Epoch: 3 [1792/48750]	Loss: 1.9164	LR: 0.100000
Training Epoch: 3 [2048/48750]	Loss: 1.9603	LR: 0.100000
Training Epoch: 3 [2304/48750]	Loss: 1.9740	LR: 0.100000
Training Epoch: 3 [2560/48750]	Loss: 1.8981	LR: 0.100000
Training Epoch: 3 [2816/48750]	Loss: 1.9513	LR: 0.100000
Training Epoch: 3 [3072/48750]	Loss: 2.0317	LR: 0.100000
Training Epoch: 3 [3328/48750]	Loss: 1.9267	LR: 0.100000
Training Epoch: 3 [3584/48750]	Loss: 1.9610	LR: 0.100000
Training Epoch: 3 [3840/48750]	Loss: 1.9043	LR: 0.100000
Training Epoch: 3 [4096/48750]	Loss: 2.0162	LR: 0.100000
Training Epoch: 3 [4352/48750]	Loss: 1.9970	LR: 0.100000
Training Epoch: 3 [4608/48750]	Loss: 1.9346	LR: 0.100000
Training Epoch: 3 [4864/48750]	Loss: 2.0325	LR: 0.100000
Training Epoch: 3 [5120/48750]	Loss: 2.0503	LR: 0.100000
Training Epoch: 3 [5376/48750]	Loss: 1.9993	LR: 0.100000
Training Epoch: 3 [5632/48750]	Loss: 1.8958	LR: 0.100000
Training Epoch: 3 [5888/48750]	Loss: 1.8999	LR: 0.100000
Training Epoch: 3 [6144/48750]	Loss: 1.9609	LR: 0.100000
Training Epoch: 3 [6400/48750]	Loss: 1.9552	LR: 0.100000
Training Epoch: 3 [6656/48750]	Loss: 1.9132	LR: 0.100000
Training Epoch: 3 [6912/48750]	Loss: 2.0208	LR: 0.100000
Training Epoch: 3 [7168/48750]	Loss: 1.9886	LR: 0.100000
Training Epoch: 3 [7424/48750]	Loss: 1.9842	LR: 0.100000
Training Epoch: 3 [7680/48750]	Loss: 2.0231	LR: 0.100000
Training Epoch: 3 [7936/48750]	Loss: 1.9632	LR: 0.100000
Training Epoch: 3 [8192/48750]	Loss: 1.9773	LR: 0.100000
Training Epoch: 3 [8448/48750]	Loss: 2.0373	LR: 0.100000
Training Epoch: 3 [8704/48750]	Loss: 1.9149	LR: 0.100000
Training Epoch: 3 [8960/48750]	Loss: 1.8996	LR: 0.100000
Training Epoch: 3 [9216/48750]	Loss: 2.0562	LR: 0.100000
Training Epoch: 3 [9472/48750]	Loss: 2.0158	LR: 0.100000
Training Epoch: 3 [9728/48750]	Loss: 1.9774	LR: 0.100000
Training Epoch: 3 [9984/48750]	Loss: 1.9951	LR: 0.100000
Training Epoch: 3 [10240/48750]	Loss: 1.9550	LR: 0.100000
Training Epoch: 3 [10496/48750]	Loss: 1.9580	LR: 0.100000
Training Epoch: 3 [10752/48750]	Loss: 1.9122	LR: 0.100000
Training Epoch: 3 [11008/48750]	Loss: 1.9409	LR: 0.100000
Training Epoch: 3 [11264/48750]	Loss: 1.9426	LR: 0.100000
Training Epoch: 3 [11520/48750]	Loss: 1.8840	LR: 0.100000
Training Epoch: 3 [11776/48750]	Loss: 1.8705	LR: 0.100000
Training Epoch: 3 [12032/48750]	Loss: 1.8421	LR: 0.100000
Training Epoch: 3 [12288/48750]	Loss: 1.9147	LR: 0.100000
Training Epoch: 3 [12544/48750]	Loss: 1.9682	LR: 0.100000
Training Epoch: 3 [12800/48750]	Loss: 1.8663	LR: 0.100000
Training Epoch: 3 [13056/48750]	Loss: 1.9134	LR: 0.100000
Training Epoch: 3 [13312/48750]	Loss: 1.9389	LR: 0.100000
Training Epoch: 3 [13568/48750]	Loss: 1.9701	LR: 0.100000
Training Epoch: 3 [13824/48750]	Loss: 1.9190	LR: 0.100000
Training Epoch: 3 [14080/48750]	Loss: 1.9674	LR: 0.100000
Training Epoch: 3 [14336/48750]	Loss: 1.9697	LR: 0.100000
Training Epoch: 3 [14592/48750]	Loss: 1.8972	LR: 0.100000
Training Epoch: 3 [14848/48750]	Loss: 1.9349	LR: 0.100000
Training Epoch: 3 [15104/48750]	Loss: 1.9369	LR: 0.100000
Training Epoch: 3 [15360/48750]	Loss: 1.9889	LR: 0.100000
Training Epoch: 3 [15616/48750]	Loss: 1.9306	LR: 0.100000
Training Epoch: 3 [15872/48750]	Loss: 1.9402	LR: 0.100000
Training Epoch: 3 [16128/48750]	Loss: 1.9127	LR: 0.100000
Training Epoch: 3 [16384/48750]	Loss: 1.9080	LR: 0.100000
Training Epoch: 3 [16640/48750]	Loss: 1.8860	LR: 0.100000
Training Epoch: 3 [16896/48750]	Loss: 1.8437	LR: 0.100000
Training Epoch: 3 [17152/48750]	Loss: 1.9691	LR: 0.100000
Training Epoch: 3 [17408/48750]	Loss: 1.8807	LR: 0.100000
Training Epoch: 3 [17664/48750]	Loss: 1.8821	LR: 0.100000
Training Epoch: 3 [17920/48750]	Loss: 1.9131	LR: 0.100000
Training Epoch: 3 [18176/48750]	Loss: 1.9668	LR: 0.100000
Training Epoch: 3 [18432/48750]	Loss: 1.9668	LR: 0.100000
Training Epoch: 3 [18688/48750]	Loss: 1.9045	LR: 0.100000
Training Epoch: 3 [18944/48750]	Loss: 1.8960	LR: 0.100000
Training Epoch: 3 [19200/48750]	Loss: 1.9116	LR: 0.100000
Training Epoch: 3 [19456/48750]	Loss: 1.9886	LR: 0.100000
Training Epoch: 3 [19712/48750]	Loss: 1.7937	LR: 0.100000
Training Epoch: 3 [19968/48750]	Loss: 1.8869	LR: 0.100000
Training Epoch: 3 [20224/48750]	Loss: 1.8763	LR: 0.100000
Training Epoch: 3 [20480/48750]	Loss: 1.9119	LR: 0.100000
Training Epoch: 3 [20736/48750]	Loss: 1.8841	LR: 0.100000
Training Epoch: 3 [20992/48750]	Loss: 1.8981	LR: 0.100000
Training Epoch: 3 [21248/48750]	Loss: 2.0029	LR: 0.100000
Training Epoch: 3 [21504/48750]	Loss: 1.8741	LR: 0.100000
Training Epoch: 3 [21760/48750]	Loss: 1.9593	LR: 0.100000
Training Epoch: 3 [22016/48750]	Loss: 1.9321	LR: 0.100000
Training Epoch: 3 [22272/48750]	Loss: 1.8647	LR: 0.100000
Training Epoch: 3 [22528/48750]	Loss: 1.8393	LR: 0.100000
Training Epoch: 3 [22784/48750]	Loss: 1.8810	LR: 0.100000
Training Epoch: 3 [23040/48750]	Loss: 1.9060	LR: 0.100000
Training Epoch: 3 [23296/48750]	Loss: 1.9172	LR: 0.100000
Training Epoch: 3 [23552/48750]	Loss: 1.8703	LR: 0.100000
Training Epoch: 3 [23808/48750]	Loss: 1.8755	LR: 0.100000
Training Epoch: 3 [24064/48750]	Loss: 1.8063	LR: 0.100000
Training Epoch: 3 [24320/48750]	Loss: 1.8191	LR: 0.100000
Training Epoch: 3 [24576/48750]	Loss: 1.8282	LR: 0.100000
Training Epoch: 3 [24832/48750]	Loss: 1.9898	LR: 0.100000
Training Epoch: 3 [25088/48750]	Loss: 1.9209	LR: 0.100000
Training Epoch: 3 [25344/48750]	Loss: 1.8759	LR: 0.100000
Training Epoch: 3 [25600/48750]	Loss: 1.9626	LR: 0.100000
Training Epoch: 3 [25856/48750]	Loss: 1.8954	LR: 0.100000
Training Epoch: 3 [26112/48750]	Loss: 1.9620	LR: 0.100000
Training Epoch: 3 [26368/48750]	Loss: 1.9074	LR: 0.100000
Training Epoch: 3 [26624/48750]	Loss: 1.8890	LR: 0.100000
Training Epoch: 3 [26880/48750]	Loss: 1.8727	LR: 0.100000
Training Epoch: 3 [27136/48750]	Loss: 1.8407	LR: 0.100000
Training Epoch: 3 [27392/48750]	Loss: 1.8881	LR: 0.100000
Training Epoch: 3 [27648/48750]	Loss: 1.8699	LR: 0.100000
Training Epoch: 3 [27904/48750]	Loss: 1.9806	LR: 0.100000
Training Epoch: 3 [28160/48750]	Loss: 1.9091	LR: 0.100000
Training Epoch: 3 [28416/48750]	Loss: 1.9289	LR: 0.100000
Training Epoch: 3 [28672/48750]	Loss: 1.9753	LR: 0.100000
Training Epoch: 3 [28928/48750]	Loss: 1.9197	LR: 0.100000
Training Epoch: 3 [29184/48750]	Loss: 1.8286	LR: 0.100000
Training Epoch: 3 [29440/48750]	Loss: 1.8775	LR: 0.100000
Training Epoch: 3 [29696/48750]	Loss: 1.8847	LR: 0.100000
Training Epoch: 3 [29952/48750]	Loss: 1.8548	LR: 0.100000
Training Epoch: 3 [30208/48750]	Loss: 1.8070	LR: 0.100000
Training Epoch: 3 [30464/48750]	Loss: 1.9784	LR: 0.100000
Training Epoch: 3 [30720/48750]	Loss: 1.7951	LR: 0.100000
Training Epoch: 3 [30976/48750]	Loss: 1.9132	LR: 0.100000
Training Epoch: 3 [31232/48750]	Loss: 1.8603	LR: 0.100000
Training Epoch: 3 [31488/48750]	Loss: 1.8252	LR: 0.100000
Training Epoch: 3 [31744/48750]	Loss: 1.8793	LR: 0.100000
Training Epoch: 3 [32000/48750]	Loss: 1.8958	LR: 0.100000
Training Epoch: 3 [32256/48750]	Loss: 1.8667	LR: 0.100000
Training Epoch: 3 [32512/48750]	Loss: 1.8524	LR: 0.100000
Training Epoch: 3 [32768/48750]	Loss: 1.8557	LR: 0.100000
Training Epoch: 3 [33024/48750]	Loss: 1.8829	LR: 0.100000
Training Epoch: 3 [33280/48750]	Loss: 1.7867	LR: 0.100000
Training Epoch: 3 [33536/48750]	Loss: 1.7547	LR: 0.100000
Training Epoch: 3 [33792/48750]	Loss: 1.8203	LR: 0.100000
Training Epoch: 3 [34048/48750]	Loss: 1.8367	LR: 0.100000
Training Epoch: 3 [34304/48750]	Loss: 1.8176	LR: 0.100000
Training Epoch: 3 [34560/48750]	Loss: 1.8159	LR: 0.100000
Training Epoch: 3 [34816/48750]	Loss: 1.9130	LR: 0.100000
Training Epoch: 3 [35072/48750]	Loss: 1.8498	LR: 0.100000
Training Epoch: 3 [35328/48750]	Loss: 1.8701	LR: 0.100000
Training Epoch: 3 [35584/48750]	Loss: 1.7599	LR: 0.100000
Training Epoch: 3 [35840/48750]	Loss: 1.8846	LR: 0.100000
Training Epoch: 3 [36096/48750]	Loss: 1.8367	LR: 0.100000
Training Epoch: 3 [36352/48750]	Loss: 1.8167	LR: 0.100000
Training Epoch: 3 [36608/48750]	Loss: 1.8079	LR: 0.100000
Training Epoch: 3 [36864/48750]	Loss: 1.7911	LR: 0.100000
Training Epoch: 3 [37120/48750]	Loss: 1.8293	LR: 0.100000
Training Epoch: 3 [37376/48750]	Loss: 1.9085	LR: 0.100000
Training Epoch: 3 [37632/48750]	Loss: 1.7911	LR: 0.100000
Training Epoch: 3 [37888/48750]	Loss: 1.7091	LR: 0.100000
Training Epoch: 3 [38144/48750]	Loss: 1.7542	LR: 0.100000
Training Epoch: 3 [38400/48750]	Loss: 1.8539	LR: 0.100000
Training Epoch: 3 [38656/48750]	Loss: 1.8851	LR: 0.100000
Training Epoch: 3 [38912/48750]	Loss: 1.7578	LR: 0.100000
Training Epoch: 3 [39168/48750]	Loss: 1.7719	LR: 0.100000
Training Epoch: 3 [39424/48750]	Loss: 1.8151	LR: 0.100000
Training Epoch: 3 [39680/48750]	Loss: 1.8946	LR: 0.100000
Training Epoch: 3 [39936/48750]	Loss: 1.8780	LR: 0.100000
Training Epoch: 3 [40192/48750]	Loss: 1.7402	LR: 0.100000
Training Epoch: 3 [40448/48750]	Loss: 1.8006	LR: 0.100000
Training Epoch: 3 [40704/48750]	Loss: 1.7964	LR: 0.100000
Training Epoch: 3 [40960/48750]	Loss: 1.8897	LR: 0.100000
Training Epoch: 3 [41216/48750]	Loss: 1.8207	LR: 0.100000
Training Epoch: 3 [41472/48750]	Loss: 1.8630	LR: 0.100000
Training Epoch: 3 [41728/48750]	Loss: 1.9409	LR: 0.100000
Training Epoch: 3 [41984/48750]	Loss: 1.9237	LR: 0.100000
Training Epoch: 3 [42240/48750]	Loss: 1.8673	LR: 0.100000
Training Epoch: 3 [42496/48750]	Loss: 1.8716	LR: 0.100000
Training Epoch: 3 [42752/48750]	Loss: 1.8853	LR: 0.100000
Training Epoch: 3 [43008/48750]	Loss: 1.9402	LR: 0.100000
Training Epoch: 3 [43264/48750]	Loss: 1.8937	LR: 0.100000
Training Epoch: 3 [43520/48750]	Loss: 1.8609	LR: 0.100000
Training Epoch: 3 [43776/48750]	Loss: 1.8647	LR: 0.100000
Training Epoch: 3 [44032/48750]	Loss: 1.8399	LR: 0.100000
Training Epoch: 3 [44288/48750]	Loss: 1.8857	LR: 0.100000
Training Epoch: 3 [44544/48750]	Loss: 1.8170	LR: 0.100000
Training Epoch: 3 [44800/48750]	Loss: 1.8412	LR: 0.100000
Training Epoch: 3 [45056/48750]	Loss: 1.8312	LR: 0.100000
Training Epoch: 3 [45312/48750]	Loss: 1.8247	LR: 0.100000
Training Epoch: 3 [45568/48750]	Loss: 1.8624	LR: 0.100000
Training Epoch: 3 [45824/48750]	Loss: 1.9101	LR: 0.100000
Training Epoch: 3 [46080/48750]	Loss: 1.8499	LR: 0.100000
Training Epoch: 3 [46336/48750]	Loss: 1.8317	LR: 0.100000
Training Epoch: 3 [46592/48750]	Loss: 1.8759	LR: 0.100000
Training Epoch: 3 [46848/48750]	Loss: 1.8507	LR: 0.100000
Training Epoch: 3 [47104/48750]	Loss: 1.7838	LR: 0.100000
Training Epoch: 3 [47360/48750]	Loss: 1.8391	LR: 0.100000
Training Epoch: 3 [47616/48750]	Loss: 1.8611	LR: 0.100000
Training Epoch: 3 [47872/48750]	Loss: 1.8656	LR: 0.100000
Training Epoch: 3 [48128/48750]	Loss: 1.8780	LR: 0.100000
Training Epoch: 3 [48384/48750]	Loss: 1.8700	LR: 0.100000
Training Epoch: 3 [48640/48750]	Loss: 1.8449	LR: 0.100000
Training Epoch: 3 [48750/48750]	Loss: 1.8807	LR: 0.100000
Epoch 3 - Average Train Loss: 1.8976, Train Accuracy: 0.2928
Epoch 3 training time consumed: 351.38s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0076, Accuracy: 0.3064, Time consumed:23.48s
Training Epoch: 4 [256/48750]	Loss: 1.9077	LR: 0.100000
Training Epoch: 4 [512/48750]	Loss: 1.7992	LR: 0.100000
Training Epoch: 4 [768/48750]	Loss: 1.8348	LR: 0.100000
Training Epoch: 4 [1024/48750]	Loss: 1.7736	LR: 0.100000
Training Epoch: 4 [1280/48750]	Loss: 1.8185	LR: 0.100000
Training Epoch: 4 [1536/48750]	Loss: 1.7977	LR: 0.100000
Training Epoch: 4 [1792/48750]	Loss: 1.7283	LR: 0.100000
Training Epoch: 4 [2048/48750]	Loss: 1.8361	LR: 0.100000
Training Epoch: 4 [2304/48750]	Loss: 1.6925	LR: 0.100000
Training Epoch: 4 [2560/48750]	Loss: 1.7135	LR: 0.100000
Training Epoch: 4 [2816/48750]	Loss: 1.7989	LR: 0.100000
Training Epoch: 4 [3072/48750]	Loss: 1.8464	LR: 0.100000
Training Epoch: 4 [3328/48750]	Loss: 1.7727	LR: 0.100000
Training Epoch: 4 [3584/48750]	Loss: 1.8207	LR: 0.100000
Training Epoch: 4 [3840/48750]	Loss: 1.8028	LR: 0.100000
Training Epoch: 4 [4096/48750]	Loss: 1.6826	LR: 0.100000
Training Epoch: 4 [4352/48750]	Loss: 1.7375	LR: 0.100000
Training Epoch: 4 [4608/48750]	Loss: 1.7129	LR: 0.100000
Training Epoch: 4 [4864/48750]	Loss: 1.7335	LR: 0.100000
Training Epoch: 4 [5120/48750]	Loss: 1.7181	LR: 0.100000
Training Epoch: 4 [5376/48750]	Loss: 1.6836	LR: 0.100000
Training Epoch: 4 [5632/48750]	Loss: 1.8015	LR: 0.100000
Training Epoch: 4 [5888/48750]	Loss: 1.8171	LR: 0.100000
Training Epoch: 4 [6144/48750]	Loss: 1.7502	LR: 0.100000
Training Epoch: 4 [6400/48750]	Loss: 1.8532	LR: 0.100000
Training Epoch: 4 [6656/48750]	Loss: 1.8129	LR: 0.100000
Training Epoch: 4 [6912/48750]	Loss: 1.7642	LR: 0.100000
Training Epoch: 4 [7168/48750]	Loss: 1.8416	LR: 0.100000
Training Epoch: 4 [7424/48750]	Loss: 1.7112	LR: 0.100000
Training Epoch: 4 [7680/48750]	Loss: 1.7248	LR: 0.100000
Training Epoch: 4 [7936/48750]	Loss: 1.7057	LR: 0.100000
Training Epoch: 4 [8192/48750]	Loss: 1.7073	LR: 0.100000
Training Epoch: 4 [8448/48750]	Loss: 1.8504	LR: 0.100000
Training Epoch: 4 [8704/48750]	Loss: 1.6335	LR: 0.100000
Training Epoch: 4 [8960/48750]	Loss: 1.6897	LR: 0.100000
Training Epoch: 4 [9216/48750]	Loss: 1.7184	LR: 0.100000
Training Epoch: 4 [9472/48750]	Loss: 1.7056	LR: 0.100000
Training Epoch: 4 [9728/48750]	Loss: 1.7320	LR: 0.100000
Training Epoch: 4 [9984/48750]	Loss: 1.7277	LR: 0.100000
Training Epoch: 4 [10240/48750]	Loss: 1.7542	LR: 0.100000
Training Epoch: 4 [10496/48750]	Loss: 1.6057	LR: 0.100000
Training Epoch: 4 [10752/48750]	Loss: 1.6644	LR: 0.100000
Training Epoch: 4 [11008/48750]	Loss: 1.7055	LR: 0.100000
Training Epoch: 4 [11264/48750]	Loss: 1.7542	LR: 0.100000
Training Epoch: 4 [11520/48750]	Loss: 1.6883	LR: 0.100000
Training Epoch: 4 [11776/48750]	Loss: 1.7698	LR: 0.100000
Training Epoch: 4 [12032/48750]	Loss: 1.7180	LR: 0.100000
Training Epoch: 4 [12288/48750]	Loss: 1.6709	LR: 0.100000
Training Epoch: 4 [12544/48750]	Loss: 1.7405	LR: 0.100000
Training Epoch: 4 [12800/48750]	Loss: 1.6359	LR: 0.100000
Training Epoch: 4 [13056/48750]	Loss: 1.6455	LR: 0.100000
Training Epoch: 4 [13312/48750]	Loss: 1.6200	LR: 0.100000
Training Epoch: 4 [13568/48750]	Loss: 2.0505	LR: 0.100000
Training Epoch: 4 [13824/48750]	Loss: 1.8168	LR: 0.100000
Training Epoch: 4 [14080/48750]	Loss: 1.7882	LR: 0.100000
Training Epoch: 4 [14336/48750]	Loss: 1.6964	LR: 0.100000
Training Epoch: 4 [14592/48750]	Loss: 1.8308	LR: 0.100000
Training Epoch: 4 [14848/48750]	Loss: 1.7856	LR: 0.100000
Training Epoch: 4 [15104/48750]	Loss: 1.7612	LR: 0.100000
Training Epoch: 4 [15360/48750]	Loss: 1.8274	LR: 0.100000
Training Epoch: 4 [15616/48750]	Loss: 1.6949	LR: 0.100000
Training Epoch: 4 [15872/48750]	Loss: 1.8453	LR: 0.100000
Training Epoch: 4 [16128/48750]	Loss: 1.7421	LR: 0.100000
Training Epoch: 4 [16384/48750]	Loss: 1.7993	LR: 0.100000
Training Epoch: 4 [16640/48750]	Loss: 1.7936	LR: 0.100000
Training Epoch: 4 [16896/48750]	Loss: 1.6441	LR: 0.100000
Training Epoch: 4 [17152/48750]	Loss: 1.7491	LR: 0.100000
Training Epoch: 4 [17408/48750]	Loss: 1.7638	LR: 0.100000
Training Epoch: 4 [17664/48750]	Loss: 1.7210	LR: 0.100000
Training Epoch: 4 [17920/48750]	Loss: 1.6507	LR: 0.100000
Training Epoch: 4 [18176/48750]	Loss: 1.6970	LR: 0.100000
Training Epoch: 4 [18432/48750]	Loss: 1.7259	LR: 0.100000
Training Epoch: 4 [18688/48750]	Loss: 1.7259	LR: 0.100000
Training Epoch: 4 [18944/48750]	Loss: 1.7203	LR: 0.100000
Training Epoch: 4 [19200/48750]	Loss: 1.6899	LR: 0.100000
Training Epoch: 4 [19456/48750]	Loss: 1.7563	LR: 0.100000
Training Epoch: 4 [19712/48750]	Loss: 1.7216	LR: 0.100000
Training Epoch: 4 [19968/48750]	Loss: 1.7610	LR: 0.100000
Training Epoch: 4 [20224/48750]	Loss: 1.5544	LR: 0.100000
Training Epoch: 4 [20480/48750]	Loss: 1.6617	LR: 0.100000
Training Epoch: 4 [20736/48750]	Loss: 1.6584	LR: 0.100000
Training Epoch: 4 [20992/48750]	Loss: 1.8106	LR: 0.100000
Training Epoch: 4 [21248/48750]	Loss: 1.6753	LR: 0.100000
Training Epoch: 4 [21504/48750]	Loss: 1.7145	LR: 0.100000
Training Epoch: 4 [21760/48750]	Loss: 1.7566	LR: 0.100000
Training Epoch: 4 [22016/48750]	Loss: 1.8509	LR: 0.100000
Training Epoch: 4 [22272/48750]	Loss: 1.7323	LR: 0.100000
Training Epoch: 4 [22528/48750]	Loss: 1.6252	LR: 0.100000
Training Epoch: 4 [22784/48750]	Loss: 1.7851	LR: 0.100000
Training Epoch: 4 [23040/48750]	Loss: 1.7034	LR: 0.100000
Training Epoch: 4 [23296/48750]	Loss: 1.6325	LR: 0.100000
Training Epoch: 4 [23552/48750]	Loss: 1.6594	LR: 0.100000
Training Epoch: 4 [23808/48750]	Loss: 1.6689	LR: 0.100000
Training Epoch: 4 [24064/48750]	Loss: 1.6209	LR: 0.100000
Training Epoch: 4 [24320/48750]	Loss: 1.5900	LR: 0.100000
Training Epoch: 4 [24576/48750]	Loss: 1.5869	LR: 0.100000
Training Epoch: 4 [24832/48750]	Loss: 1.5921	LR: 0.100000
Training Epoch: 4 [25088/48750]	Loss: 1.4857	LR: 0.100000
Training Epoch: 4 [25344/48750]	Loss: 1.5643	LR: 0.100000
Training Epoch: 4 [25600/48750]	Loss: 1.5461	LR: 0.100000
Training Epoch: 4 [25856/48750]	Loss: 1.5811	LR: 0.100000
Training Epoch: 4 [26112/48750]	Loss: 1.5895	LR: 0.100000
Training Epoch: 4 [26368/48750]	Loss: 1.6047	LR: 0.100000
Training Epoch: 4 [26624/48750]	Loss: 1.4629	LR: 0.100000
Training Epoch: 4 [26880/48750]	Loss: 1.5329	LR: 0.100000
Training Epoch: 4 [27136/48750]	Loss: 1.5945	LR: 0.100000
Training Epoch: 4 [27392/48750]	Loss: 1.5889	LR: 0.100000
Training Epoch: 4 [27648/48750]	Loss: 1.6073	LR: 0.100000
Training Epoch: 4 [27904/48750]	Loss: 1.5141	LR: 0.100000
Training Epoch: 4 [28160/48750]	Loss: 1.6227	LR: 0.100000
Training Epoch: 4 [28416/48750]	Loss: 1.5848	LR: 0.100000
Training Epoch: 4 [28672/48750]	Loss: 1.5414	LR: 0.100000
Training Epoch: 4 [28928/48750]	Loss: 1.7361	LR: 0.100000
Training Epoch: 4 [29184/48750]	Loss: 1.6572	LR: 0.100000
Training Epoch: 4 [29440/48750]	Loss: 1.5557	LR: 0.100000
Training Epoch: 4 [29696/48750]	Loss: 1.6301	LR: 0.100000
Training Epoch: 4 [29952/48750]	Loss: 1.5683	LR: 0.100000
Training Epoch: 4 [30208/48750]	Loss: 1.5244	LR: 0.100000
Training Epoch: 4 [30464/48750]	Loss: 1.6301	LR: 0.100000
Training Epoch: 4 [30720/48750]	Loss: 1.6223	LR: 0.100000
Training Epoch: 4 [30976/48750]	Loss: 1.5316	LR: 0.100000
Training Epoch: 4 [31232/48750]	Loss: 1.4942	LR: 0.100000
Training Epoch: 4 [31488/48750]	Loss: 1.5886	LR: 0.100000
Training Epoch: 4 [31744/48750]	Loss: 1.5788	LR: 0.100000
Training Epoch: 4 [32000/48750]	Loss: 1.6551	LR: 0.100000
Training Epoch: 4 [32256/48750]	Loss: 1.4627	LR: 0.100000
Training Epoch: 4 [32512/48750]	Loss: 1.5796	LR: 0.100000
Training Epoch: 4 [32768/48750]	Loss: 1.4930	LR: 0.100000
Training Epoch: 4 [33024/48750]	Loss: 1.4610	LR: 0.100000
Training Epoch: 4 [33280/48750]	Loss: 1.6000	LR: 0.100000
Training Epoch: 4 [33536/48750]	Loss: 1.5095	LR: 0.100000
Training Epoch: 4 [33792/48750]	Loss: 1.5767	LR: 0.100000
Training Epoch: 4 [34048/48750]	Loss: 1.4755	LR: 0.100000
Training Epoch: 4 [34304/48750]	Loss: 1.5179	LR: 0.100000
Training Epoch: 4 [34560/48750]	Loss: 1.4789	LR: 0.100000
Training Epoch: 4 [34816/48750]	Loss: 1.4178	LR: 0.100000
Training Epoch: 4 [35072/48750]	Loss: 1.3866	LR: 0.100000
Training Epoch: 4 [35328/48750]	Loss: 1.5455	LR: 0.100000
Training Epoch: 4 [35584/48750]	Loss: 1.5618	LR: 0.100000
Training Epoch: 4 [35840/48750]	Loss: 1.5275	LR: 0.100000
Training Epoch: 4 [36096/48750]	Loss: 1.4223	LR: 0.100000
Training Epoch: 4 [36352/48750]	Loss: 1.6393	LR: 0.100000
Training Epoch: 4 [36608/48750]	Loss: 1.6058	LR: 0.100000
Training Epoch: 4 [36864/48750]	Loss: 1.4953	LR: 0.100000
Training Epoch: 4 [37120/48750]	Loss: 1.4361	LR: 0.100000
Training Epoch: 4 [37376/48750]	Loss: 1.4369	LR: 0.100000
Training Epoch: 4 [37632/48750]	Loss: 1.3976	LR: 0.100000
Training Epoch: 4 [37888/48750]	Loss: 1.5402	LR: 0.100000
Training Epoch: 4 [38144/48750]	Loss: 1.5703	LR: 0.100000
Training Epoch: 4 [38400/48750]	Loss: 1.3998	LR: 0.100000
Training Epoch: 4 [38656/48750]	Loss: 1.4734	LR: 0.100000
Training Epoch: 4 [38912/48750]	Loss: 1.4556	LR: 0.100000
Training Epoch: 4 [39168/48750]	Loss: 1.4222	LR: 0.100000
Training Epoch: 4 [39424/48750]	Loss: 1.4757	LR: 0.100000
Training Epoch: 4 [39680/48750]	Loss: 1.4209	LR: 0.100000
Training Epoch: 4 [39936/48750]	Loss: 1.4946	LR: 0.100000
Training Epoch: 4 [40192/48750]	Loss: 1.5903	LR: 0.100000
Training Epoch: 4 [40448/48750]	Loss: 1.4702	LR: 0.100000
Training Epoch: 4 [40704/48750]	Loss: 1.4746	LR: 0.100000
Training Epoch: 4 [40960/48750]	Loss: 1.4443	LR: 0.100000
Training Epoch: 4 [41216/48750]	Loss: 1.3901	LR: 0.100000
Training Epoch: 4 [41472/48750]	Loss: 1.5366	LR: 0.100000
Training Epoch: 4 [41728/48750]	Loss: 1.5032	LR: 0.100000
Training Epoch: 4 [41984/48750]	Loss: 1.3879	LR: 0.100000
Training Epoch: 4 [42240/48750]	Loss: 1.5031	LR: 0.100000
Training Epoch: 4 [42496/48750]	Loss: 1.4418	LR: 0.100000
Training Epoch: 4 [42752/48750]	Loss: 1.5060	LR: 0.100000
Training Epoch: 4 [43008/48750]	Loss: 1.5150	LR: 0.100000
Training Epoch: 4 [43264/48750]	Loss: 1.4659	LR: 0.100000
Training Epoch: 4 [43520/48750]	Loss: 1.3440	LR: 0.100000
Training Epoch: 4 [43776/48750]	Loss: 1.3600	LR: 0.100000
Training Epoch: 4 [44032/48750]	Loss: 1.4298	LR: 0.100000
Training Epoch: 4 [44288/48750]	Loss: 1.5877	LR: 0.100000
Training Epoch: 4 [44544/48750]	Loss: 1.3755	LR: 0.100000
Training Epoch: 4 [44800/48750]	Loss: 1.4581	LR: 0.100000
Training Epoch: 4 [45056/48750]	Loss: 1.4701	LR: 0.100000
Training Epoch: 4 [45312/48750]	Loss: 1.4808	LR: 0.100000
Training Epoch: 4 [45568/48750]	Loss: 1.2579	LR: 0.100000
Training Epoch: 4 [45824/48750]	Loss: 1.4253	LR: 0.100000
Training Epoch: 4 [46080/48750]	Loss: 1.3450	LR: 0.100000
Training Epoch: 4 [46336/48750]	Loss: 1.4928	LR: 0.100000
Training Epoch: 4 [46592/48750]	Loss: 1.3252	LR: 0.100000
Training Epoch: 4 [46848/48750]	Loss: 1.4453	LR: 0.100000
Training Epoch: 4 [47104/48750]	Loss: 1.4182	LR: 0.100000
Training Epoch: 4 [47360/48750]	Loss: 1.5304	LR: 0.100000
Training Epoch: 4 [47616/48750]	Loss: 1.2866	LR: 0.100000
Training Epoch: 4 [47872/48750]	Loss: 1.4754	LR: 0.100000
Training Epoch: 4 [48128/48750]	Loss: 1.6046	LR: 0.100000
Training Epoch: 4 [48384/48750]	Loss: 1.5026	LR: 0.100000
Training Epoch: 4 [48640/48750]	Loss: 1.3245	LR: 0.100000
Training Epoch: 4 [48750/48750]	Loss: 1.4349	LR: 0.100000
Epoch 4 - Average Train Loss: 1.6207, Train Accuracy: 0.4043
Epoch 4 training time consumed: 351.50s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0060, Accuracy: 0.4475, Time consumed:23.49s
Training Epoch: 5 [256/48750]	Loss: 1.4591	LR: 0.100000
Training Epoch: 5 [512/48750]	Loss: 1.4731	LR: 0.100000
Training Epoch: 5 [768/48750]	Loss: 1.4361	LR: 0.100000
Training Epoch: 5 [1024/48750]	Loss: 1.4768	LR: 0.100000
Training Epoch: 5 [1280/48750]	Loss: 1.4649	LR: 0.100000
Training Epoch: 5 [1536/48750]	Loss: 1.4905	LR: 0.100000
Training Epoch: 5 [1792/48750]	Loss: 1.3856	LR: 0.100000
Training Epoch: 5 [2048/48750]	Loss: 1.3689	LR: 0.100000
Training Epoch: 5 [2304/48750]	Loss: 1.2972	LR: 0.100000
Training Epoch: 5 [2560/48750]	Loss: 1.3706	LR: 0.100000
Training Epoch: 5 [2816/48750]	Loss: 1.3480	LR: 0.100000
Training Epoch: 5 [3072/48750]	Loss: 1.4451	LR: 0.100000
Training Epoch: 5 [3328/48750]	Loss: 1.3651	LR: 0.100000
Training Epoch: 5 [3584/48750]	Loss: 1.2365	LR: 0.100000
Training Epoch: 5 [3840/48750]	Loss: 1.2797	LR: 0.100000
Training Epoch: 5 [4096/48750]	Loss: 1.2320	LR: 0.100000
Training Epoch: 5 [4352/48750]	Loss: 1.3546	LR: 0.100000
Training Epoch: 5 [4608/48750]	Loss: 1.2891	LR: 0.100000
Training Epoch: 5 [4864/48750]	Loss: 1.2640	LR: 0.100000
Training Epoch: 5 [5120/48750]	Loss: 1.2742	LR: 0.100000
Training Epoch: 5 [5376/48750]	Loss: 1.3049	LR: 0.100000
Training Epoch: 5 [5632/48750]	Loss: 1.1300	LR: 0.100000
Training Epoch: 5 [5888/48750]	Loss: 1.2657	LR: 0.100000
Training Epoch: 5 [6144/48750]	Loss: 1.4268	LR: 0.100000
Training Epoch: 5 [6400/48750]	Loss: 1.2360	LR: 0.100000
Training Epoch: 5 [6656/48750]	Loss: 1.2774	LR: 0.100000
Training Epoch: 5 [6912/48750]	Loss: 1.2823	LR: 0.100000
Training Epoch: 5 [7168/48750]	Loss: 1.2837	LR: 0.100000
Training Epoch: 5 [7424/48750]	Loss: 1.2193	LR: 0.100000
Training Epoch: 5 [7680/48750]	Loss: 1.1882	LR: 0.100000
Training Epoch: 5 [7936/48750]	Loss: 1.2839	LR: 0.100000
Training Epoch: 5 [8192/48750]	Loss: 1.3106	LR: 0.100000
Training Epoch: 5 [8448/48750]	Loss: 1.2310	LR: 0.100000
Training Epoch: 5 [8704/48750]	Loss: 1.1976	LR: 0.100000
Training Epoch: 5 [8960/48750]	Loss: 1.0243	LR: 0.100000
Training Epoch: 5 [9216/48750]	Loss: 1.3538	LR: 0.100000
Training Epoch: 5 [9472/48750]	Loss: 1.1968	LR: 0.100000
Training Epoch: 5 [9728/48750]	Loss: 1.3451	LR: 0.100000
Training Epoch: 5 [9984/48750]	Loss: 1.3340	LR: 0.100000
Training Epoch: 5 [10240/48750]	Loss: 1.1533	LR: 0.100000
Training Epoch: 5 [10496/48750]	Loss: 1.4387	LR: 0.100000
Training Epoch: 5 [10752/48750]	Loss: 1.1981	LR: 0.100000
Training Epoch: 5 [11008/48750]	Loss: 1.1732	LR: 0.100000
Training Epoch: 5 [11264/48750]	Loss: 1.1902	LR: 0.100000
Training Epoch: 5 [11520/48750]	Loss: 1.3085	LR: 0.100000
Training Epoch: 5 [11776/48750]	Loss: 1.0813	LR: 0.100000
Training Epoch: 5 [12032/48750]	Loss: 1.1887	LR: 0.100000
Training Epoch: 5 [12288/48750]	Loss: 1.2135	LR: 0.100000
Training Epoch: 5 [12544/48750]	Loss: 1.1205	LR: 0.100000
Training Epoch: 5 [12800/48750]	Loss: 1.0762	LR: 0.100000
Training Epoch: 5 [13056/48750]	Loss: 1.0985	LR: 0.100000
Training Epoch: 5 [13312/48750]	Loss: 1.1377	LR: 0.100000
Training Epoch: 5 [13568/48750]	Loss: 1.0990	LR: 0.100000
Training Epoch: 5 [13824/48750]	Loss: 0.9854	LR: 0.100000
Training Epoch: 5 [14080/48750]	Loss: 1.1305	LR: 0.100000
Training Epoch: 5 [14336/48750]	Loss: 1.0586	LR: 0.100000
Training Epoch: 5 [14592/48750]	Loss: 1.0460	LR: 0.100000
Training Epoch: 5 [14848/48750]	Loss: 0.9937	LR: 0.100000
Training Epoch: 5 [15104/48750]	Loss: 0.9604	LR: 0.100000
Training Epoch: 5 [15360/48750]	Loss: 1.0455	LR: 0.100000
Training Epoch: 5 [15616/48750]	Loss: 0.9825	LR: 0.100000
Training Epoch: 5 [15872/48750]	Loss: 1.1170	LR: 0.100000
Training Epoch: 5 [16128/48750]	Loss: 0.9903	LR: 0.100000
Training Epoch: 5 [16384/48750]	Loss: 0.9425	LR: 0.100000
Training Epoch: 5 [16640/48750]	Loss: 0.9559	LR: 0.100000
Training Epoch: 5 [16896/48750]	Loss: 0.9286	LR: 0.100000
Training Epoch: 5 [17152/48750]	Loss: 1.0078	LR: 0.100000
Training Epoch: 5 [17408/48750]	Loss: 0.9344	LR: 0.100000
Training Epoch: 5 [17664/48750]	Loss: 0.8875	LR: 0.100000
Training Epoch: 5 [17920/48750]	Loss: 1.0248	LR: 0.100000
Training Epoch: 5 [18176/48750]	Loss: 0.7944	LR: 0.100000
Training Epoch: 5 [18432/48750]	Loss: 1.0243	LR: 0.100000
Training Epoch: 5 [18688/48750]	Loss: 0.9161	LR: 0.100000
Training Epoch: 5 [18944/48750]	Loss: 0.8262	LR: 0.100000
Training Epoch: 5 [19200/48750]	Loss: 0.9348	LR: 0.100000
Training Epoch: 5 [19456/48750]	Loss: 0.8724	LR: 0.100000
Training Epoch: 5 [19712/48750]	Loss: 0.6879	LR: 0.100000
Training Epoch: 5 [19968/48750]	Loss: 0.8167	LR: 0.100000
Training Epoch: 5 [20224/48750]	Loss: 1.0040	LR: 0.100000
Training Epoch: 5 [20480/48750]	Loss: 0.8062	LR: 0.100000
Training Epoch: 5 [20736/48750]	Loss: 1.0796	LR: 0.100000
Training Epoch: 5 [20992/48750]	Loss: 1.1541	LR: 0.100000
Training Epoch: 5 [21248/48750]	Loss: 0.9805	LR: 0.100000
Training Epoch: 5 [21504/48750]	Loss: 0.9277	LR: 0.100000
Training Epoch: 5 [21760/48750]	Loss: 1.1212	LR: 0.100000
Training Epoch: 5 [22016/48750]	Loss: 0.9999	LR: 0.100000
Training Epoch: 5 [22272/48750]	Loss: 0.9992	LR: 0.100000
Training Epoch: 5 [22528/48750]	Loss: 0.9718	LR: 0.100000
Training Epoch: 5 [22784/48750]	Loss: 1.0003	LR: 0.100000
Training Epoch: 5 [23040/48750]	Loss: 1.1284	LR: 0.100000
Training Epoch: 5 [23296/48750]	Loss: 0.8843	LR: 0.100000
Training Epoch: 5 [23552/48750]	Loss: 0.8115	LR: 0.100000
Training Epoch: 5 [23808/48750]	Loss: 0.8517	LR: 0.100000
Training Epoch: 5 [24064/48750]	Loss: 0.8008	LR: 0.100000
Training Epoch: 5 [24320/48750]	Loss: 0.7417	LR: 0.100000
Training Epoch: 5 [24576/48750]	Loss: 0.8841	LR: 0.100000
Training Epoch: 5 [24832/48750]	Loss: 0.6972	LR: 0.100000
Training Epoch: 5 [25088/48750]	Loss: 0.7762	LR: 0.100000
Training Epoch: 5 [25344/48750]	Loss: 0.7790	LR: 0.100000
Training Epoch: 5 [25600/48750]	Loss: 0.6492	LR: 0.100000
Training Epoch: 5 [25856/48750]	Loss: 0.6428	LR: 0.100000
Training Epoch: 5 [26112/48750]	Loss: 0.5746	LR: 0.100000
Training Epoch: 5 [26368/48750]	Loss: 0.6762	LR: 0.100000
Training Epoch: 5 [26624/48750]	Loss: 0.7797	LR: 0.100000
Training Epoch: 5 [26880/48750]	Loss: 0.7685	LR: 0.100000
Training Epoch: 5 [27136/48750]	Loss: 0.6563	LR: 0.100000
Training Epoch: 5 [27392/48750]	Loss: 0.6324	LR: 0.100000
Training Epoch: 5 [27648/48750]	Loss: 0.4954	LR: 0.100000
Training Epoch: 5 [27904/48750]	Loss: 0.6375	LR: 0.100000
Training Epoch: 5 [28160/48750]	Loss: 0.7618	LR: 0.100000
Training Epoch: 5 [28416/48750]	Loss: 0.6159	LR: 0.100000
Training Epoch: 5 [28672/48750]	Loss: 0.7124	LR: 0.100000
Training Epoch: 5 [28928/48750]	Loss: 0.5403	LR: 0.100000
Training Epoch: 5 [29184/48750]	Loss: 0.5166	LR: 0.100000
Training Epoch: 5 [29440/48750]	Loss: 0.6237	LR: 0.100000
Training Epoch: 5 [29696/48750]	Loss: 0.5747	LR: 0.100000
Training Epoch: 5 [29952/48750]	Loss: 0.5912	LR: 0.100000
Training Epoch: 5 [30208/48750]	Loss: 0.5310	LR: 0.100000
Training Epoch: 5 [30464/48750]	Loss: 0.6221	LR: 0.100000
Training Epoch: 5 [30720/48750]	Loss: 0.6645	LR: 0.100000
Training Epoch: 5 [30976/48750]	Loss: 1.0027	LR: 0.100000
Training Epoch: 5 [31232/48750]	Loss: 0.6089	LR: 0.100000
Training Epoch: 5 [31488/48750]	Loss: 0.6556	LR: 0.100000
Training Epoch: 5 [31744/48750]	Loss: 0.7369	LR: 0.100000
Training Epoch: 5 [32000/48750]	Loss: 0.5667	LR: 0.100000
Training Epoch: 5 [32256/48750]	Loss: 0.6101	LR: 0.100000
Training Epoch: 5 [32512/48750]	Loss: 0.6436	LR: 0.100000
Training Epoch: 5 [32768/48750]	Loss: 0.5028	LR: 0.100000
Training Epoch: 5 [33024/48750]	Loss: 0.4526	LR: 0.100000
Training Epoch: 5 [33280/48750]	Loss: 0.4582	LR: 0.100000
Training Epoch: 5 [33536/48750]	Loss: 0.4362	LR: 0.100000
Training Epoch: 5 [33792/48750]	Loss: 0.5532	LR: 0.100000
Training Epoch: 5 [34048/48750]	Loss: 0.5634	LR: 0.100000
Training Epoch: 5 [34304/48750]	Loss: 0.4362	LR: 0.100000
Training Epoch: 5 [34560/48750]	Loss: 0.4521	LR: 0.100000
Training Epoch: 5 [34816/48750]	Loss: 0.3816	LR: 0.100000
Training Epoch: 5 [35072/48750]	Loss: 0.3567	LR: 0.100000
Training Epoch: 5 [35328/48750]	Loss: 0.3847	LR: 0.100000
Training Epoch: 5 [35584/48750]	Loss: 0.4392	LR: 0.100000
Training Epoch: 5 [35840/48750]	Loss: 0.4202	LR: 0.100000
Training Epoch: 5 [36096/48750]	Loss: 0.3716	LR: 0.100000
Training Epoch: 5 [36352/48750]	Loss: 0.5727	LR: 0.100000
Training Epoch: 5 [36608/48750]	Loss: 0.6381	LR: 0.100000
Training Epoch: 5 [36864/48750]	Loss: 0.7364	LR: 0.100000
Training Epoch: 5 [37120/48750]	Loss: 0.4306	LR: 0.100000
Training Epoch: 5 [37376/48750]	Loss: 0.5506	LR: 0.100000
Training Epoch: 5 [37632/48750]	Loss: 0.5532	LR: 0.100000
Training Epoch: 5 [37888/48750]	Loss: 0.4492	LR: 0.100000
Training Epoch: 5 [38144/48750]	Loss: 0.4656	LR: 0.100000
Training Epoch: 5 [38400/48750]	Loss: 0.4439	LR: 0.100000
Training Epoch: 5 [38656/48750]	Loss: 0.4653	LR: 0.100000
Training Epoch: 5 [38912/48750]	Loss: 0.4207	LR: 0.100000
Training Epoch: 5 [39168/48750]	Loss: 0.4434	LR: 0.100000
Training Epoch: 5 [39424/48750]	Loss: 0.4380	LR: 0.100000
Training Epoch: 5 [39680/48750]	Loss: 0.3908	LR: 0.100000
Training Epoch: 5 [39936/48750]	Loss: 0.3353	LR: 0.100000
Training Epoch: 5 [40192/48750]	Loss: 0.3731	LR: 0.100000
Training Epoch: 5 [40448/48750]	Loss: 0.4818	LR: 0.100000
Training Epoch: 5 [40704/48750]	Loss: 0.3850	LR: 0.100000
Training Epoch: 5 [40960/48750]	Loss: 0.4668	LR: 0.100000
Training Epoch: 5 [41216/48750]	Loss: 0.4188	LR: 0.100000
Training Epoch: 5 [41472/48750]	Loss: 0.4246	LR: 0.100000
Training Epoch: 5 [41728/48750]	Loss: 0.3918	LR: 0.100000
Training Epoch: 5 [41984/48750]	Loss: 0.6590	LR: 0.100000
Training Epoch: 5 [42240/48750]	Loss: 0.3618	LR: 0.100000
Training Epoch: 5 [42496/48750]	Loss: 0.3721	LR: 0.100000
Training Epoch: 5 [42752/48750]	Loss: 0.4581	LR: 0.100000
Training Epoch: 5 [43008/48750]	Loss: 0.3879	LR: 0.100000
Training Epoch: 5 [43264/48750]	Loss: 0.4672	LR: 0.100000
Training Epoch: 5 [43520/48750]	Loss: 0.3290	LR: 0.100000
Training Epoch: 5 [43776/48750]	Loss: 0.4486	LR: 0.100000
Training Epoch: 5 [44032/48750]	Loss: 0.5036	LR: 0.100000
Training Epoch: 5 [44288/48750]	Loss: 0.3646	LR: 0.100000
Training Epoch: 5 [44544/48750]	Loss: 0.4900	LR: 0.100000
Training Epoch: 5 [44800/48750]	Loss: 0.3794	LR: 0.100000
Training Epoch: 5 [45056/48750]	Loss: 0.5132	LR: 0.100000
Training Epoch: 5 [45312/48750]	Loss: 0.4562	LR: 0.100000
Training Epoch: 5 [45568/48750]	Loss: 0.4856	LR: 0.100000
Training Epoch: 5 [45824/48750]	Loss: 0.3716	LR: 0.100000
Training Epoch: 5 [46080/48750]	Loss: 0.4669	LR: 0.100000
Training Epoch: 5 [46336/48750]	Loss: 0.3270	LR: 0.100000
Training Epoch: 5 [46592/48750]	Loss: 0.4330	LR: 0.100000
Training Epoch: 5 [46848/48750]	Loss: 0.3716	LR: 0.100000
Training Epoch: 5 [47104/48750]	Loss: 0.3575	LR: 0.100000
Training Epoch: 5 [47360/48750]	Loss: 0.3263	LR: 0.100000
Training Epoch: 5 [47616/48750]	Loss: 0.2549	LR: 0.100000
Training Epoch: 5 [47872/48750]	Loss: 0.3889	LR: 0.100000
Training Epoch: 5 [48128/48750]	Loss: 0.3191	LR: 0.100000
Training Epoch: 5 [48384/48750]	Loss: 0.4071	LR: 0.100000
Training Epoch: 5 [48640/48750]	Loss: 0.2777	LR: 0.100000
Training Epoch: 5 [48750/48750]	Loss: 0.2851	LR: 0.100000
Epoch 5 - Average Train Loss: 0.8225, Train Accuracy: 0.7104
Epoch 5 training time consumed: 351.57s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0010, Accuracy: 0.9159, Time consumed:23.49s
Training Epoch: 6 [256/48750]	Loss: 0.3476	LR: 0.100000
Training Epoch: 6 [512/48750]	Loss: 0.2901	LR: 0.100000
Training Epoch: 6 [768/48750]	Loss: 0.2831	LR: 0.100000
Training Epoch: 6 [1024/48750]	Loss: 0.3478	LR: 0.100000
Training Epoch: 6 [1280/48750]	Loss: 0.2810	LR: 0.100000
Training Epoch: 6 [1536/48750]	Loss: 0.3672	LR: 0.100000
Training Epoch: 6 [1792/48750]	Loss: 0.3353	LR: 0.100000
Training Epoch: 6 [2048/48750]	Loss: 0.2672	LR: 0.100000
Training Epoch: 6 [2304/48750]	Loss: 0.2344	LR: 0.100000
Training Epoch: 6 [2560/48750]	Loss: 0.3431	LR: 0.100000
Training Epoch: 6 [2816/48750]	Loss: 0.3724	LR: 0.100000
Training Epoch: 6 [3072/48750]	Loss: 0.2534	LR: 0.100000
Training Epoch: 6 [3328/48750]	Loss: 0.2237	LR: 0.100000
Training Epoch: 6 [3584/48750]	Loss: 0.2648	LR: 0.100000
Training Epoch: 6 [3840/48750]	Loss: 0.3091	LR: 0.100000
Training Epoch: 6 [4096/48750]	Loss: 0.3693	LR: 0.100000
Training Epoch: 6 [4352/48750]	Loss: 0.2723	LR: 0.100000
Training Epoch: 6 [4608/48750]	Loss: 0.2884	LR: 0.100000
Training Epoch: 6 [4864/48750]	Loss: 0.2985	LR: 0.100000
Training Epoch: 6 [5120/48750]	Loss: 0.2293	LR: 0.100000
Training Epoch: 6 [5376/48750]	Loss: 0.2573	LR: 0.100000
Training Epoch: 6 [5632/48750]	Loss: 0.3679	LR: 0.100000
Training Epoch: 6 [5888/48750]	Loss: 0.2232	LR: 0.100000
Training Epoch: 6 [6144/48750]	Loss: 0.3795	LR: 0.100000
Training Epoch: 6 [6400/48750]	Loss: 0.3181	LR: 0.100000
Training Epoch: 6 [6656/48750]	Loss: 0.2604	LR: 0.100000
Training Epoch: 6 [6912/48750]	Loss: 0.2549	LR: 0.100000
Training Epoch: 6 [7168/48750]	Loss: 0.3438	LR: 0.100000
Training Epoch: 6 [7424/48750]	Loss: 0.4214	LR: 0.100000
Training Epoch: 6 [7680/48750]	Loss: 0.2558	LR: 0.100000
Training Epoch: 6 [7936/48750]	Loss: 0.4210	LR: 0.100000
Training Epoch: 6 [8192/48750]	Loss: 0.2995	LR: 0.100000
Training Epoch: 6 [8448/48750]	Loss: 0.2422	LR: 0.100000
Training Epoch: 6 [8704/48750]	Loss: 0.2793	LR: 0.100000
Training Epoch: 6 [8960/48750]	Loss: 0.4150	LR: 0.100000
Training Epoch: 6 [9216/48750]	Loss: 0.2644	LR: 0.100000
Training Epoch: 6 [9472/48750]	Loss: 0.2360	LR: 0.100000
Training Epoch: 6 [9728/48750]	Loss: 0.3015	LR: 0.100000
Training Epoch: 6 [9984/48750]	Loss: 0.3392	LR: 0.100000
Training Epoch: 6 [10240/48750]	Loss: 0.2810	LR: 0.100000
Training Epoch: 6 [10496/48750]	Loss: 0.2863	LR: 0.100000
Training Epoch: 6 [10752/48750]	Loss: 0.3433	LR: 0.100000
Training Epoch: 6 [11008/48750]	Loss: 0.5015	LR: 0.100000
Training Epoch: 6 [11264/48750]	Loss: 0.3596	LR: 0.100000
Training Epoch: 6 [11520/48750]	Loss: 0.4660	LR: 0.100000
Training Epoch: 6 [11776/48750]	Loss: 0.3830	LR: 0.100000
Training Epoch: 6 [12032/48750]	Loss: 0.4040	LR: 0.100000
Training Epoch: 6 [12288/48750]	Loss: 0.1996	LR: 0.100000
Training Epoch: 6 [12544/48750]	Loss: 0.3776	LR: 0.100000
Training Epoch: 6 [12800/48750]	Loss: 0.3337	LR: 0.100000
Training Epoch: 6 [13056/48750]	Loss: 0.3122	LR: 0.100000
Training Epoch: 6 [13312/48750]	Loss: 0.3835	LR: 0.100000
Training Epoch: 6 [13568/48750]	Loss: 0.2726	LR: 0.100000
Training Epoch: 6 [13824/48750]	Loss: 0.3194	LR: 0.100000
Training Epoch: 6 [14080/48750]	Loss: 0.3484	LR: 0.100000
Training Epoch: 6 [14336/48750]	Loss: 0.2446	LR: 0.100000
Training Epoch: 6 [14592/48750]	Loss: 0.3637	LR: 0.100000
Training Epoch: 6 [14848/48750]	Loss: 0.3631	LR: 0.100000
Training Epoch: 6 [15104/48750]	Loss: 0.2635	LR: 0.100000
Training Epoch: 6 [15360/48750]	Loss: 0.2895	LR: 0.100000
Training Epoch: 6 [15616/48750]	Loss: 0.2356	LR: 0.100000
Training Epoch: 6 [15872/48750]	Loss: 0.3855	LR: 0.100000
Training Epoch: 6 [16128/48750]	Loss: 0.2814	LR: 0.100000
Training Epoch: 6 [16384/48750]	Loss: 0.2175	LR: 0.100000
Training Epoch: 6 [16640/48750]	Loss: 0.2794	LR: 0.100000
Training Epoch: 6 [16896/48750]	Loss: 0.2969	LR: 0.100000
Training Epoch: 6 [17152/48750]	Loss: 0.3068	LR: 0.100000
Training Epoch: 6 [17408/48750]	Loss: 0.2901	LR: 0.100000
Training Epoch: 6 [17664/48750]	Loss: 0.2472	LR: 0.100000
Training Epoch: 6 [17920/48750]	Loss: 0.3436	LR: 0.100000
Training Epoch: 6 [18176/48750]	Loss: 0.3684	LR: 0.100000
Training Epoch: 6 [18432/48750]	Loss: 0.3378	LR: 0.100000
Training Epoch: 6 [18688/48750]	Loss: 0.2312	LR: 0.100000
Training Epoch: 6 [18944/48750]	Loss: 0.2477	LR: 0.100000
Training Epoch: 6 [19200/48750]	Loss: 0.3182	LR: 0.100000
Training Epoch: 6 [19456/48750]	Loss: 0.2554	LR: 0.100000
Training Epoch: 6 [19712/48750]	Loss: 0.3322	LR: 0.100000
Training Epoch: 6 [19968/48750]	Loss: 0.2728	LR: 0.100000
Training Epoch: 6 [20224/48750]	Loss: 0.2880	LR: 0.100000
Training Epoch: 6 [20480/48750]	Loss: 0.1916	LR: 0.100000
Training Epoch: 6 [20736/48750]	Loss: 0.2427	LR: 0.100000
Training Epoch: 6 [20992/48750]	Loss: 0.2718	LR: 0.100000
Training Epoch: 6 [21248/48750]	Loss: 0.3217	LR: 0.100000
Training Epoch: 6 [21504/48750]	Loss: 0.2840	LR: 0.100000
Training Epoch: 6 [21760/48750]	Loss: 0.3364	LR: 0.100000
Training Epoch: 6 [22016/48750]	Loss: 0.2391	LR: 0.100000
Training Epoch: 6 [22272/48750]	Loss: 0.2792	LR: 0.100000
Training Epoch: 6 [22528/48750]	Loss: 0.3468	LR: 0.100000
Training Epoch: 6 [22784/48750]	Loss: 0.2500	LR: 0.100000
Training Epoch: 6 [23040/48750]	Loss: 0.2996	LR: 0.100000
Training Epoch: 6 [23296/48750]	Loss: 0.2304	LR: 0.100000
Training Epoch: 6 [23552/48750]	Loss: 0.2696	LR: 0.100000
Training Epoch: 6 [23808/48750]	Loss: 0.2149	LR: 0.100000
Training Epoch: 6 [24064/48750]	Loss: 0.1846	LR: 0.100000
Training Epoch: 6 [24320/48750]	Loss: 0.2407	LR: 0.100000
Training Epoch: 6 [24576/48750]	Loss: 0.3418	LR: 0.100000
Training Epoch: 6 [24832/48750]	Loss: 0.3926	LR: 0.100000
Training Epoch: 6 [25088/48750]	Loss: 0.2849	LR: 0.100000
Training Epoch: 6 [25344/48750]	Loss: 0.3304	LR: 0.100000
Training Epoch: 6 [25600/48750]	Loss: 0.3045	LR: 0.100000
Training Epoch: 6 [25856/48750]	Loss: 0.2950	LR: 0.100000
Training Epoch: 6 [26112/48750]	Loss: 0.2689	LR: 0.100000
Training Epoch: 6 [26368/48750]	Loss: 0.3303	LR: 0.100000
Training Epoch: 6 [26624/48750]	Loss: 0.3955	LR: 0.100000
Training Epoch: 6 [26880/48750]	Loss: 0.3071	LR: 0.100000
Training Epoch: 6 [27136/48750]	Loss: 0.3915	LR: 0.100000
Training Epoch: 6 [27392/48750]	Loss: 0.2929	LR: 0.100000
Training Epoch: 6 [27648/48750]	Loss: 0.3664	LR: 0.100000
Training Epoch: 6 [27904/48750]	Loss: 0.2963	LR: 0.100000
Training Epoch: 6 [28160/48750]	Loss: 0.2848	LR: 0.100000
Training Epoch: 6 [28416/48750]	Loss: 0.3089	LR: 0.100000
Training Epoch: 6 [28672/48750]	Loss: 0.3542	LR: 0.100000
Training Epoch: 6 [28928/48750]	Loss: 0.4295	LR: 0.100000
Training Epoch: 6 [29184/48750]	Loss: 0.2298	LR: 0.100000
Training Epoch: 6 [29440/48750]	Loss: 0.2585	LR: 0.100000
Training Epoch: 6 [29696/48750]	Loss: 0.2651	LR: 0.100000
Training Epoch: 6 [29952/48750]	Loss: 0.1534	LR: 0.100000
Training Epoch: 6 [30208/48750]	Loss: 0.3369	LR: 0.100000
Training Epoch: 6 [30464/48750]	Loss: 0.3093	LR: 0.100000
Training Epoch: 6 [30720/48750]	Loss: 0.3159	LR: 0.100000
Training Epoch: 6 [30976/48750]	Loss: 0.2690	LR: 0.100000
Training Epoch: 6 [31232/48750]	Loss: 0.2636	LR: 0.100000
Training Epoch: 6 [31488/48750]	Loss: 0.3128	LR: 0.100000
Training Epoch: 6 [31744/48750]	Loss: 0.2217	LR: 0.100000
Training Epoch: 6 [32000/48750]	Loss: 0.3160	LR: 0.100000
Training Epoch: 6 [32256/48750]	Loss: 0.2251	LR: 0.100000
Training Epoch: 6 [32512/48750]	Loss: 0.2594	LR: 0.100000
Training Epoch: 6 [32768/48750]	Loss: 0.3278	LR: 0.100000
Training Epoch: 6 [33024/48750]	Loss: 0.3952	LR: 0.100000
Training Epoch: 6 [33280/48750]	Loss: 0.2774	LR: 0.100000
Training Epoch: 6 [33536/48750]	Loss: 0.4461	LR: 0.100000
Training Epoch: 6 [33792/48750]	Loss: 0.3965	LR: 0.100000
Training Epoch: 6 [34048/48750]	Loss: 0.2370	LR: 0.100000
Training Epoch: 6 [34304/48750]	Loss: 0.2076	LR: 0.100000
Training Epoch: 6 [34560/48750]	Loss: 0.4071	LR: 0.100000
Training Epoch: 6 [34816/48750]	Loss: 0.2995	LR: 0.100000
Training Epoch: 6 [35072/48750]	Loss: 0.2437	LR: 0.100000
Training Epoch: 6 [35328/48750]	Loss: 0.2338	LR: 0.100000
Training Epoch: 6 [35584/48750]	Loss: 0.3782	LR: 0.100000
Training Epoch: 6 [35840/48750]	Loss: 0.2379	LR: 0.100000
Training Epoch: 6 [36096/48750]	Loss: 0.2455	LR: 0.100000
Training Epoch: 6 [36352/48750]	Loss: 0.3549	LR: 0.100000
Training Epoch: 6 [36608/48750]	Loss: 0.3799	LR: 0.100000
Training Epoch: 6 [36864/48750]	Loss: 0.3210	LR: 0.100000
Training Epoch: 6 [37120/48750]	Loss: 0.3440	LR: 0.100000
Training Epoch: 6 [37376/48750]	Loss: 0.2720	LR: 0.100000
Training Epoch: 6 [37632/48750]	Loss: 0.4993	LR: 0.100000
Training Epoch: 6 [37888/48750]	Loss: 0.3114	LR: 0.100000
Training Epoch: 6 [38144/48750]	Loss: 0.2902	LR: 0.100000
Training Epoch: 6 [38400/48750]	Loss: 0.4204	LR: 0.100000
Training Epoch: 6 [38656/48750]	Loss: 0.2372	LR: 0.100000
Training Epoch: 6 [38912/48750]	Loss: 0.2742	LR: 0.100000
Training Epoch: 6 [39168/48750]	Loss: 0.3794	LR: 0.100000
Training Epoch: 6 [39424/48750]	Loss: 0.3229	LR: 0.100000
Training Epoch: 6 [39680/48750]	Loss: 0.3995	LR: 0.100000
Training Epoch: 6 [39936/48750]	Loss: 0.3132	LR: 0.100000
Training Epoch: 6 [40192/48750]	Loss: 0.3506	LR: 0.100000
Training Epoch: 6 [40448/48750]	Loss: 0.5843	LR: 0.100000
Training Epoch: 6 [40704/48750]	Loss: 0.2596	LR: 0.100000
Training Epoch: 6 [40960/48750]	Loss: 0.4148	LR: 0.100000
Training Epoch: 6 [41216/48750]	Loss: 0.2992	LR: 0.100000
Training Epoch: 6 [41472/48750]	Loss: 0.3794	LR: 0.100000
Training Epoch: 6 [41728/48750]	Loss: 0.2744	LR: 0.100000
Training Epoch: 6 [41984/48750]	Loss: 0.3362	LR: 0.100000
Training Epoch: 6 [42240/48750]	Loss: 0.2376	LR: 0.100000
Training Epoch: 6 [42496/48750]	Loss: 0.3062	LR: 0.100000
Training Epoch: 6 [42752/48750]	Loss: 0.3515	LR: 0.100000
Training Epoch: 6 [43008/48750]	Loss: 0.3575	LR: 0.100000
Training Epoch: 6 [43264/48750]	Loss: 0.4295	LR: 0.100000
Training Epoch: 6 [43520/48750]	Loss: 0.4477	LR: 0.100000
Training Epoch: 6 [43776/48750]	Loss: 0.3203	LR: 0.100000
Training Epoch: 6 [44032/48750]	Loss: 0.4329	LR: 0.100000
Training Epoch: 6 [44288/48750]	Loss: 0.4021	LR: 0.100000
Training Epoch: 6 [44544/48750]	Loss: 0.3938	LR: 0.100000
Training Epoch: 6 [44800/48750]	Loss: 0.3456	LR: 0.100000
Training Epoch: 6 [45056/48750]	Loss: 0.3880	LR: 0.100000
Training Epoch: 6 [45312/48750]	Loss: 0.2894	LR: 0.100000
Training Epoch: 6 [45568/48750]	Loss: 0.3723	LR: 0.100000
Training Epoch: 6 [45824/48750]	Loss: 0.1939	LR: 0.100000
Training Epoch: 6 [46080/48750]	Loss: 0.2709	LR: 0.100000
Training Epoch: 6 [46336/48750]	Loss: 0.2553	LR: 0.100000
Training Epoch: 6 [46592/48750]	Loss: 0.3857	LR: 0.100000
Training Epoch: 6 [46848/48750]	Loss: 0.3185	LR: 0.100000
Training Epoch: 6 [47104/48750]	Loss: 0.3744	LR: 0.100000
Training Epoch: 6 [47360/48750]	Loss: 0.3048	LR: 0.100000
Training Epoch: 6 [47616/48750]	Loss: 0.3437	LR: 0.100000
Training Epoch: 6 [47872/48750]	Loss: 0.2915	LR: 0.100000
Training Epoch: 6 [48128/48750]	Loss: 0.2608	LR: 0.100000
Training Epoch: 6 [48384/48750]	Loss: 0.3358	LR: 0.100000
Training Epoch: 6 [48640/48750]	Loss: 0.2848	LR: 0.100000
Training Epoch: 6 [48750/48750]	Loss: 0.3809	LR: 0.100000
Epoch 6 - Average Train Loss: 0.3131, Train Accuracy: 0.8924
Epoch 6 training time consumed: 351.46s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0010, Accuracy: 0.9174, Time consumed:23.49s
Training Epoch: 7 [256/48750]	Loss: 0.2053	LR: 0.020000
Training Epoch: 7 [512/48750]	Loss: 0.3018	LR: 0.020000
Training Epoch: 7 [768/48750]	Loss: 0.2709	LR: 0.020000
Training Epoch: 7 [1024/48750]	Loss: 0.2457	LR: 0.020000
Training Epoch: 7 [1280/48750]	Loss: 0.2076	LR: 0.020000
Training Epoch: 7 [1536/48750]	Loss: 0.1855	LR: 0.020000
Training Epoch: 7 [1792/48750]	Loss: 0.1802	LR: 0.020000
Training Epoch: 7 [2048/48750]	Loss: 0.1575	LR: 0.020000
Training Epoch: 7 [2304/48750]	Loss: 0.1668	LR: 0.020000
Training Epoch: 7 [2560/48750]	Loss: 0.1476	LR: 0.020000
Training Epoch: 7 [2816/48750]	Loss: 0.2673	LR: 0.020000
Training Epoch: 7 [3072/48750]	Loss: 0.1593	LR: 0.020000
Training Epoch: 7 [3328/48750]	Loss: 0.1795	LR: 0.020000
Training Epoch: 7 [3584/48750]	Loss: 0.1551	LR: 0.020000
Training Epoch: 7 [3840/48750]	Loss: 0.2440	LR: 0.020000
Training Epoch: 7 [4096/48750]	Loss: 0.1728	LR: 0.020000
Training Epoch: 7 [4352/48750]	Loss: 0.1305	LR: 0.020000
Training Epoch: 7 [4608/48750]	Loss: 0.1519	LR: 0.020000
Training Epoch: 7 [4864/48750]	Loss: 0.1721	LR: 0.020000
Training Epoch: 7 [5120/48750]	Loss: 0.1309	LR: 0.020000
Training Epoch: 7 [5376/48750]	Loss: 0.1379	LR: 0.020000
Training Epoch: 7 [5632/48750]	Loss: 0.1555	LR: 0.020000
Training Epoch: 7 [5888/48750]	Loss: 0.1328	LR: 0.020000
Training Epoch: 7 [6144/48750]	Loss: 0.1596	LR: 0.020000
Training Epoch: 7 [6400/48750]	Loss: 0.1617	LR: 0.020000
Training Epoch: 7 [6656/48750]	Loss: 0.1294	LR: 0.020000
Training Epoch: 7 [6912/48750]	Loss: 0.1393	LR: 0.020000
Training Epoch: 7 [7168/48750]	Loss: 0.1261	LR: 0.020000
Training Epoch: 7 [7424/48750]	Loss: 0.1580	LR: 0.020000
Training Epoch: 7 [7680/48750]	Loss: 0.1039	LR: 0.020000
Training Epoch: 7 [7936/48750]	Loss: 0.0942	LR: 0.020000
Training Epoch: 7 [8192/48750]	Loss: 0.0998	LR: 0.020000
Training Epoch: 7 [8448/48750]	Loss: 0.1399	LR: 0.020000
Training Epoch: 7 [8704/48750]	Loss: 0.1177	LR: 0.020000
Training Epoch: 7 [8960/48750]	Loss: 0.1218	LR: 0.020000
Training Epoch: 7 [9216/48750]	Loss: 0.0787	LR: 0.020000
Training Epoch: 7 [9472/48750]	Loss: 0.0995	LR: 0.020000
Training Epoch: 7 [9728/48750]	Loss: 0.1153	LR: 0.020000
Training Epoch: 7 [9984/48750]	Loss: 0.1264	LR: 0.020000
Training Epoch: 7 [10240/48750]	Loss: 0.1160	LR: 0.020000
Training Epoch: 7 [10496/48750]	Loss: 0.1303	LR: 0.020000
Training Epoch: 7 [10752/48750]	Loss: 0.0814	LR: 0.020000
Training Epoch: 7 [11008/48750]	Loss: 0.1173	LR: 0.020000
Training Epoch: 7 [11264/48750]	Loss: 0.1285	LR: 0.020000
Training Epoch: 7 [11520/48750]	Loss: 0.1319	LR: 0.020000
Training Epoch: 7 [11776/48750]	Loss: 0.1402	LR: 0.020000
Training Epoch: 7 [12032/48750]	Loss: 0.1567	LR: 0.020000
Training Epoch: 7 [12288/48750]	Loss: 0.0975	LR: 0.020000
Training Epoch: 7 [12544/48750]	Loss: 0.1867	LR: 0.020000
Training Epoch: 7 [12800/48750]	Loss: 0.0701	LR: 0.020000
Training Epoch: 7 [13056/48750]	Loss: 0.1231	LR: 0.020000
Training Epoch: 7 [13312/48750]	Loss: 0.1693	LR: 0.020000
Training Epoch: 7 [13568/48750]	Loss: 0.1479	LR: 0.020000
Training Epoch: 7 [13824/48750]	Loss: 0.0876	LR: 0.020000
Training Epoch: 7 [14080/48750]	Loss: 0.1551	LR: 0.020000
Training Epoch: 7 [14336/48750]	Loss: 0.1142	LR: 0.020000
Training Epoch: 7 [14592/48750]	Loss: 0.0790	LR: 0.020000
Training Epoch: 7 [14848/48750]	Loss: 0.0983	LR: 0.020000
Training Epoch: 7 [15104/48750]	Loss: 0.0942	LR: 0.020000
Training Epoch: 7 [15360/48750]	Loss: 0.1687	LR: 0.020000
Training Epoch: 7 [15616/48750]	Loss: 0.0735	LR: 0.020000
Training Epoch: 7 [15872/48750]	Loss: 0.1556	LR: 0.020000
Training Epoch: 7 [16128/48750]	Loss: 0.0919	LR: 0.020000
Training Epoch: 7 [16384/48750]	Loss: 0.1484	LR: 0.020000
Training Epoch: 7 [16640/48750]	Loss: 0.1285	LR: 0.020000
Training Epoch: 7 [16896/48750]	Loss: 0.1180	LR: 0.020000
Training Epoch: 7 [17152/48750]	Loss: 0.1484	LR: 0.020000
Training Epoch: 7 [17408/48750]	Loss: 0.1481	LR: 0.020000
Training Epoch: 7 [17664/48750]	Loss: 0.1349	LR: 0.020000
Training Epoch: 7 [17920/48750]	Loss: 0.0574	LR: 0.020000
Training Epoch: 7 [18176/48750]	Loss: 0.1103	LR: 0.020000
Training Epoch: 7 [18432/48750]	Loss: 0.0802	LR: 0.020000
Training Epoch: 7 [18688/48750]	Loss: 0.0893	LR: 0.020000
Training Epoch: 7 [18944/48750]	Loss: 0.1229	LR: 0.020000
Training Epoch: 7 [19200/48750]	Loss: 0.0834	LR: 0.020000
Training Epoch: 7 [19456/48750]	Loss: 0.0743	LR: 0.020000
Training Epoch: 7 [19712/48750]	Loss: 0.1341	LR: 0.020000
Training Epoch: 7 [19968/48750]	Loss: 0.1539	LR: 0.020000
Training Epoch: 7 [20224/48750]	Loss: 0.1126	LR: 0.020000
Training Epoch: 7 [20480/48750]	Loss: 0.1518	LR: 0.020000
Training Epoch: 7 [20736/48750]	Loss: 0.1148	LR: 0.020000
Training Epoch: 7 [20992/48750]	Loss: 0.0512	LR: 0.020000
Training Epoch: 7 [21248/48750]	Loss: 0.0856	LR: 0.020000
Training Epoch: 7 [21504/48750]	Loss: 0.1102	LR: 0.020000
Training Epoch: 7 [21760/48750]	Loss: 0.1286	LR: 0.020000
Training Epoch: 7 [22016/48750]	Loss: 0.1292	LR: 0.020000
Training Epoch: 7 [22272/48750]	Loss: 0.1115	LR: 0.020000
Training Epoch: 7 [22528/48750]	Loss: 0.1229	LR: 0.020000
Training Epoch: 7 [22784/48750]	Loss: 0.1679	LR: 0.020000
Training Epoch: 7 [23040/48750]	Loss: 0.0723	LR: 0.020000
Training Epoch: 7 [23296/48750]	Loss: 0.1064	LR: 0.020000
Training Epoch: 7 [23552/48750]	Loss: 0.1723	LR: 0.020000
Training Epoch: 7 [23808/48750]	Loss: 0.1177	LR: 0.020000
Training Epoch: 7 [24064/48750]	Loss: 0.1341	LR: 0.020000
Training Epoch: 7 [24320/48750]	Loss: 0.1040	LR: 0.020000
Training Epoch: 7 [24576/48750]	Loss: 0.1073	LR: 0.020000
Training Epoch: 7 [24832/48750]	Loss: 0.0980	LR: 0.020000
Training Epoch: 7 [25088/48750]	Loss: 0.1080	LR: 0.020000
Training Epoch: 7 [25344/48750]	Loss: 0.1125	LR: 0.020000
Training Epoch: 7 [25600/48750]	Loss: 0.1516	LR: 0.020000
Training Epoch: 7 [25856/48750]	Loss: 0.1120	LR: 0.020000
Training Epoch: 7 [26112/48750]	Loss: 0.0886	LR: 0.020000
Training Epoch: 7 [26368/48750]	Loss: 0.1262	LR: 0.020000
Training Epoch: 7 [26624/48750]	Loss: 0.0821	LR: 0.020000
Training Epoch: 7 [26880/48750]	Loss: 0.1162	LR: 0.020000
Training Epoch: 7 [27136/48750]	Loss: 0.1281	LR: 0.020000
Training Epoch: 7 [27392/48750]	Loss: 0.0722	LR: 0.020000
Training Epoch: 7 [27648/48750]	Loss: 0.1369	LR: 0.020000
Training Epoch: 7 [27904/48750]	Loss: 0.0972	LR: 0.020000
Training Epoch: 7 [28160/48750]	Loss: 0.1336	LR: 0.020000
Training Epoch: 7 [28416/48750]	Loss: 0.0624	LR: 0.020000
Training Epoch: 7 [28672/48750]	Loss: 0.0725	LR: 0.020000
Training Epoch: 7 [28928/48750]	Loss: 0.0958	LR: 0.020000
Training Epoch: 7 [29184/48750]	Loss: 0.0798	LR: 0.020000
Training Epoch: 7 [29440/48750]	Loss: 0.1081	LR: 0.020000
Training Epoch: 7 [29696/48750]	Loss: 0.0960	LR: 0.020000
Training Epoch: 7 [29952/48750]	Loss: 0.0739	LR: 0.020000
Training Epoch: 7 [30208/48750]	Loss: 0.1135	LR: 0.020000
Training Epoch: 7 [30464/48750]	Loss: 0.1587	LR: 0.020000
Training Epoch: 7 [30720/48750]	Loss: 0.1049	LR: 0.020000
Training Epoch: 7 [30976/48750]	Loss: 0.1101	LR: 0.020000
Training Epoch: 7 [31232/48750]	Loss: 0.0796	LR: 0.020000
Training Epoch: 7 [31488/48750]	Loss: 0.0918	LR: 0.020000
Training Epoch: 7 [31744/48750]	Loss: 0.1326	LR: 0.020000
Training Epoch: 7 [32000/48750]	Loss: 0.1105	LR: 0.020000
Training Epoch: 7 [32256/48750]	Loss: 0.0532	LR: 0.020000
Training Epoch: 7 [32512/48750]	Loss: 0.1179	LR: 0.020000
Training Epoch: 7 [32768/48750]	Loss: 0.1320	LR: 0.020000
Training Epoch: 7 [33024/48750]	Loss: 0.0782	LR: 0.020000
Training Epoch: 7 [33280/48750]	Loss: 0.1039	LR: 0.020000
Training Epoch: 7 [33536/48750]	Loss: 0.0719	LR: 0.020000
Training Epoch: 7 [33792/48750]	Loss: 0.0954	LR: 0.020000
Training Epoch: 7 [34048/48750]	Loss: 0.0989	LR: 0.020000
Training Epoch: 7 [34304/48750]	Loss: 0.0865	LR: 0.020000
Training Epoch: 7 [34560/48750]	Loss: 0.1041	LR: 0.020000
Training Epoch: 7 [34816/48750]	Loss: 0.1036	LR: 0.020000
Training Epoch: 7 [35072/48750]	Loss: 0.1240	LR: 0.020000
Training Epoch: 7 [35328/48750]	Loss: 0.1203	LR: 0.020000
Training Epoch: 7 [35584/48750]	Loss: 0.1253	LR: 0.020000
Training Epoch: 7 [35840/48750]	Loss: 0.0455	LR: 0.020000
Training Epoch: 7 [36096/48750]	Loss: 0.1652	LR: 0.020000
Training Epoch: 7 [36352/48750]	Loss: 0.1519	LR: 0.020000
Training Epoch: 7 [36608/48750]	Loss: 0.0860	LR: 0.020000
Training Epoch: 7 [36864/48750]	Loss: 0.1210	LR: 0.020000
Training Epoch: 7 [37120/48750]	Loss: 0.1045	LR: 0.020000
Training Epoch: 7 [37376/48750]	Loss: 0.0400	LR: 0.020000
Training Epoch: 7 [37632/48750]	Loss: 0.0941	LR: 0.020000
Training Epoch: 7 [37888/48750]	Loss: 0.0771	LR: 0.020000
Training Epoch: 7 [38144/48750]	Loss: 0.1334	LR: 0.020000
Training Epoch: 7 [38400/48750]	Loss: 0.0652	LR: 0.020000
Training Epoch: 7 [38656/48750]	Loss: 0.1102	LR: 0.020000
Training Epoch: 7 [38912/48750]	Loss: 0.1313	LR: 0.020000
Training Epoch: 7 [39168/48750]	Loss: 0.1218	LR: 0.020000
Training Epoch: 7 [39424/48750]	Loss: 0.0980	LR: 0.020000
Training Epoch: 7 [39680/48750]	Loss: 0.0872	LR: 0.020000
Training Epoch: 7 [39936/48750]	Loss: 0.0703	LR: 0.020000
Training Epoch: 7 [40192/48750]	Loss: 0.1029	LR: 0.020000
Training Epoch: 7 [40448/48750]	Loss: 0.1709	LR: 0.020000
Training Epoch: 7 [40704/48750]	Loss: 0.0997	LR: 0.020000
Training Epoch: 7 [40960/48750]	Loss: 0.0948	LR: 0.020000
Training Epoch: 7 [41216/48750]	Loss: 0.0403	LR: 0.020000
Training Epoch: 7 [41472/48750]	Loss: 0.0725	LR: 0.020000
Training Epoch: 7 [41728/48750]	Loss: 0.1112	LR: 0.020000
Training Epoch: 7 [41984/48750]	Loss: 0.1073	LR: 0.020000
Training Epoch: 7 [42240/48750]	Loss: 0.0719	LR: 0.020000
Training Epoch: 7 [42496/48750]	Loss: 0.0855	LR: 0.020000
Training Epoch: 7 [42752/48750]	Loss: 0.1137	LR: 0.020000
Training Epoch: 7 [43008/48750]	Loss: 0.0752	LR: 0.020000
Training Epoch: 7 [43264/48750]	Loss: 0.0794	LR: 0.020000
Training Epoch: 7 [43520/48750]	Loss: 0.1696	LR: 0.020000
Training Epoch: 7 [43776/48750]	Loss: 0.0835	LR: 0.020000
Training Epoch: 7 [44032/48750]	Loss: 0.0716	LR: 0.020000
Training Epoch: 7 [44288/48750]	Loss: 0.0806	LR: 0.020000
Training Epoch: 7 [44544/48750]	Loss: 0.0981	LR: 0.020000
Training Epoch: 7 [44800/48750]	Loss: 0.1796	LR: 0.020000
Training Epoch: 7 [45056/48750]	Loss: 0.1395	LR: 0.020000
Training Epoch: 7 [45312/48750]	Loss: 0.0705	LR: 0.020000
Training Epoch: 7 [45568/48750]	Loss: 0.1026	LR: 0.020000
Training Epoch: 7 [45824/48750]	Loss: 0.0471	LR: 0.020000
Training Epoch: 7 [46080/48750]	Loss: 0.1555	LR: 0.020000
Training Epoch: 7 [46336/48750]	Loss: 0.0955	LR: 0.020000
Training Epoch: 7 [46592/48750]	Loss: 0.0519	LR: 0.020000
Training Epoch: 7 [46848/48750]	Loss: 0.1251	LR: 0.020000
Training Epoch: 7 [47104/48750]	Loss: 0.0912	LR: 0.020000
Training Epoch: 7 [47360/48750]	Loss: 0.1056	LR: 0.020000
Training Epoch: 7 [47616/48750]	Loss: 0.0458	LR: 0.020000
Training Epoch: 7 [47872/48750]	Loss: 0.0715	LR: 0.020000
Training Epoch: 7 [48128/48750]	Loss: 0.0769	LR: 0.020000
Training Epoch: 7 [48384/48750]	Loss: 0.1214	LR: 0.020000
Training Epoch: 7 [48640/48750]	Loss: 0.1381	LR: 0.020000
Training Epoch: 7 [48750/48750]	Loss: 0.0955	LR: 0.020000
Epoch 7 - Average Train Loss: 0.1183, Train Accuracy: 0.9597
Epoch 7 training time consumed: 351.87s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0004, Accuracy: 0.9630, Time consumed:23.47s
Saving weights file to checkpoint/retrain/ViT/Sunday_20_July_2025_00h_27m_43s/ViT-Cifar10-seed8-ret75-7-best.pth
Training Epoch: 8 [256/48750]	Loss: 0.0892	LR: 0.020000
Training Epoch: 8 [512/48750]	Loss: 0.0720	LR: 0.020000
Training Epoch: 8 [768/48750]	Loss: 0.0670	LR: 0.020000
Training Epoch: 8 [1024/48750]	Loss: 0.1180	LR: 0.020000
Training Epoch: 8 [1280/48750]	Loss: 0.1532	LR: 0.020000
Training Epoch: 8 [1536/48750]	Loss: 0.0620	LR: 0.020000
Training Epoch: 8 [1792/48750]	Loss: 0.0616	LR: 0.020000
Training Epoch: 8 [2048/48750]	Loss: 0.0581	LR: 0.020000
Training Epoch: 8 [2304/48750]	Loss: 0.0916	LR: 0.020000
Training Epoch: 8 [2560/48750]	Loss: 0.1033	LR: 0.020000
Training Epoch: 8 [2816/48750]	Loss: 0.0943	LR: 0.020000
Training Epoch: 8 [3072/48750]	Loss: 0.1505	LR: 0.020000
Training Epoch: 8 [3328/48750]	Loss: 0.1367	LR: 0.020000
Training Epoch: 8 [3584/48750]	Loss: 0.1588	LR: 0.020000
Training Epoch: 8 [3840/48750]	Loss: 0.0740	LR: 0.020000
Training Epoch: 8 [4096/48750]	Loss: 0.1110	LR: 0.020000
Training Epoch: 8 [4352/48750]	Loss: 0.0780	LR: 0.020000
Training Epoch: 8 [4608/48750]	Loss: 0.1331	LR: 0.020000
Training Epoch: 8 [4864/48750]	Loss: 0.1048	LR: 0.020000
Training Epoch: 8 [5120/48750]	Loss: 0.0745	LR: 0.020000
Training Epoch: 8 [5376/48750]	Loss: 0.1600	LR: 0.020000
Training Epoch: 8 [5632/48750]	Loss: 0.0669	LR: 0.020000
Training Epoch: 8 [5888/48750]	Loss: 0.0965	LR: 0.020000
Training Epoch: 8 [6144/48750]	Loss: 0.1078	LR: 0.020000
Training Epoch: 8 [6400/48750]	Loss: 0.0822	LR: 0.020000
Training Epoch: 8 [6656/48750]	Loss: 0.0605	LR: 0.020000
Training Epoch: 8 [6912/48750]	Loss: 0.1089	LR: 0.020000
Training Epoch: 8 [7168/48750]	Loss: 0.0846	LR: 0.020000
Training Epoch: 8 [7424/48750]	Loss: 0.0918	LR: 0.020000
Training Epoch: 8 [7680/48750]	Loss: 0.1131	LR: 0.020000
Training Epoch: 8 [7936/48750]	Loss: 0.0526	LR: 0.020000
Training Epoch: 8 [8192/48750]	Loss: 0.0816	LR: 0.020000
Training Epoch: 8 [8448/48750]	Loss: 0.0807	LR: 0.020000
Training Epoch: 8 [8704/48750]	Loss: 0.0604	LR: 0.020000
Training Epoch: 8 [8960/48750]	Loss: 0.0847	LR: 0.020000
Training Epoch: 8 [9216/48750]	Loss: 0.1066	LR: 0.020000
Training Epoch: 8 [9472/48750]	Loss: 0.0883	LR: 0.020000
Training Epoch: 8 [9728/48750]	Loss: 0.1408	LR: 0.020000
Training Epoch: 8 [9984/48750]	Loss: 0.0937	LR: 0.020000
Training Epoch: 8 [10240/48750]	Loss: 0.0484	LR: 0.020000
Training Epoch: 8 [10496/48750]	Loss: 0.0712	LR: 0.020000
Training Epoch: 8 [10752/48750]	Loss: 0.0947	LR: 0.020000
Training Epoch: 8 [11008/48750]	Loss: 0.1245	LR: 0.020000
Training Epoch: 8 [11264/48750]	Loss: 0.1285	LR: 0.020000
Training Epoch: 8 [11520/48750]	Loss: 0.1187	LR: 0.020000
Training Epoch: 8 [11776/48750]	Loss: 0.0832	LR: 0.020000
Training Epoch: 8 [12032/48750]	Loss: 0.0749	LR: 0.020000
Training Epoch: 8 [12288/48750]	Loss: 0.0621	LR: 0.020000
Training Epoch: 8 [12544/48750]	Loss: 0.0557	LR: 0.020000
Training Epoch: 8 [12800/48750]	Loss: 0.1020	LR: 0.020000
Training Epoch: 8 [13056/48750]	Loss: 0.0907	LR: 0.020000
Training Epoch: 8 [13312/48750]	Loss: 0.1019	LR: 0.020000
Training Epoch: 8 [13568/48750]	Loss: 0.1237	LR: 0.020000
Training Epoch: 8 [13824/48750]	Loss: 0.1433	LR: 0.020000
Training Epoch: 8 [14080/48750]	Loss: 0.0716	LR: 0.020000
Training Epoch: 8 [14336/48750]	Loss: 0.0699	LR: 0.020000
Training Epoch: 8 [14592/48750]	Loss: 0.0872	LR: 0.020000
Training Epoch: 8 [14848/48750]	Loss: 0.0834	LR: 0.020000
Training Epoch: 8 [15104/48750]	Loss: 0.0963	LR: 0.020000
Training Epoch: 8 [15360/48750]	Loss: 0.0816	LR: 0.020000
Training Epoch: 8 [15616/48750]	Loss: 0.1260	LR: 0.020000
Training Epoch: 8 [15872/48750]	Loss: 0.0761	LR: 0.020000
Training Epoch: 8 [16128/48750]	Loss: 0.1208	LR: 0.020000
Training Epoch: 8 [16384/48750]	Loss: 0.0858	LR: 0.020000
Training Epoch: 8 [16640/48750]	Loss: 0.1070	LR: 0.020000
Training Epoch: 8 [16896/48750]	Loss: 0.0985	LR: 0.020000
Training Epoch: 8 [17152/48750]	Loss: 0.0890	LR: 0.020000
Training Epoch: 8 [17408/48750]	Loss: 0.0711	LR: 0.020000
Training Epoch: 8 [17664/48750]	Loss: 0.0743	LR: 0.020000
Training Epoch: 8 [17920/48750]	Loss: 0.0971	LR: 0.020000
Training Epoch: 8 [18176/48750]	Loss: 0.0769	LR: 0.020000
Training Epoch: 8 [18432/48750]	Loss: 0.0798	LR: 0.020000
Training Epoch: 8 [18688/48750]	Loss: 0.0776	LR: 0.020000
Training Epoch: 8 [18944/48750]	Loss: 0.0707	LR: 0.020000
Training Epoch: 8 [19200/48750]	Loss: 0.0542	LR: 0.020000
Training Epoch: 8 [19456/48750]	Loss: 0.1161	LR: 0.020000
Training Epoch: 8 [19712/48750]	Loss: 0.0624	LR: 0.020000
Training Epoch: 8 [19968/48750]	Loss: 0.0472	LR: 0.020000
Training Epoch: 8 [20224/48750]	Loss: 0.0670	LR: 0.020000
Training Epoch: 8 [20480/48750]	Loss: 0.0812	LR: 0.020000
Training Epoch: 8 [20736/48750]	Loss: 0.0837	LR: 0.020000
Training Epoch: 8 [20992/48750]	Loss: 0.0718	LR: 0.020000
Training Epoch: 8 [21248/48750]	Loss: 0.0872	LR: 0.020000
Training Epoch: 8 [21504/48750]	Loss: 0.0910	LR: 0.020000
Training Epoch: 8 [21760/48750]	Loss: 0.0615	LR: 0.020000
Training Epoch: 8 [22016/48750]	Loss: 0.0885	LR: 0.020000
Training Epoch: 8 [22272/48750]	Loss: 0.0956	LR: 0.020000
Training Epoch: 8 [22528/48750]	Loss: 0.1112	LR: 0.020000
Training Epoch: 8 [22784/48750]	Loss: 0.0840	LR: 0.020000
Training Epoch: 8 [23040/48750]	Loss: 0.0526	LR: 0.020000
Training Epoch: 8 [23296/48750]	Loss: 0.0675	LR: 0.020000
Training Epoch: 8 [23552/48750]	Loss: 0.0990	LR: 0.020000
Training Epoch: 8 [23808/48750]	Loss: 0.1074	LR: 0.020000
Training Epoch: 8 [24064/48750]	Loss: 0.0648	LR: 0.020000
Training Epoch: 8 [24320/48750]	Loss: 0.0896	LR: 0.020000
Training Epoch: 8 [24576/48750]	Loss: 0.1188	LR: 0.020000
Training Epoch: 8 [24832/48750]	Loss: 0.1062	LR: 0.020000
Training Epoch: 8 [25088/48750]	Loss: 0.1256	LR: 0.020000
Training Epoch: 8 [25344/48750]	Loss: 0.0522	LR: 0.020000
Training Epoch: 8 [25600/48750]	Loss: 0.0828	LR: 0.020000
Training Epoch: 8 [25856/48750]	Loss: 0.1083	LR: 0.020000
Training Epoch: 8 [26112/48750]	Loss: 0.0504	LR: 0.020000
Training Epoch: 8 [26368/48750]	Loss: 0.0478	LR: 0.020000
Training Epoch: 8 [26624/48750]	Loss: 0.0592	LR: 0.020000
Training Epoch: 8 [26880/48750]	Loss: 0.0751	LR: 0.020000
Training Epoch: 8 [27136/48750]	Loss: 0.0357	LR: 0.020000
Training Epoch: 8 [27392/48750]	Loss: 0.1061	LR: 0.020000
Training Epoch: 8 [27648/48750]	Loss: 0.0558	LR: 0.020000
Training Epoch: 8 [27904/48750]	Loss: 0.0622	LR: 0.020000
Training Epoch: 8 [28160/48750]	Loss: 0.1057	LR: 0.020000
Training Epoch: 8 [28416/48750]	Loss: 0.0762	LR: 0.020000
Training Epoch: 8 [28672/48750]	Loss: 0.1281	LR: 0.020000
Training Epoch: 8 [28928/48750]	Loss: 0.0604	LR: 0.020000
Training Epoch: 8 [29184/48750]	Loss: 0.1077	LR: 0.020000
Training Epoch: 8 [29440/48750]	Loss: 0.0770	LR: 0.020000
Training Epoch: 8 [29696/48750]	Loss: 0.1061	LR: 0.020000
Training Epoch: 8 [29952/48750]	Loss: 0.0984	LR: 0.020000
Training Epoch: 8 [30208/48750]	Loss: 0.0428	LR: 0.020000
Training Epoch: 8 [30464/48750]	Loss: 0.0942	LR: 0.020000
Training Epoch: 8 [30720/48750]	Loss: 0.1213	LR: 0.020000
Training Epoch: 8 [30976/48750]	Loss: 0.0922	LR: 0.020000
Training Epoch: 8 [31232/48750]	Loss: 0.0994	LR: 0.020000
Training Epoch: 8 [31488/48750]	Loss: 0.0799	LR: 0.020000
Training Epoch: 8 [31744/48750]	Loss: 0.1098	LR: 0.020000
Training Epoch: 8 [32000/48750]	Loss: 0.0687	LR: 0.020000
Training Epoch: 8 [32256/48750]	Loss: 0.0513	LR: 0.020000
Training Epoch: 8 [32512/48750]	Loss: 0.0713	LR: 0.020000
Training Epoch: 8 [32768/48750]	Loss: 0.0823	LR: 0.020000
Training Epoch: 8 [33024/48750]	Loss: 0.0761	LR: 0.020000
Training Epoch: 8 [33280/48750]	Loss: 0.0589	LR: 0.020000
Training Epoch: 8 [33536/48750]	Loss: 0.0928	LR: 0.020000
Training Epoch: 8 [33792/48750]	Loss: 0.1028	LR: 0.020000
Training Epoch: 8 [34048/48750]	Loss: 0.0931	LR: 0.020000
Training Epoch: 8 [34304/48750]	Loss: 0.1230	LR: 0.020000
Training Epoch: 8 [34560/48750]	Loss: 0.0794	LR: 0.020000
Training Epoch: 8 [34816/48750]	Loss: 0.0879	LR: 0.020000
Training Epoch: 8 [35072/48750]	Loss: 0.1017	LR: 0.020000
Training Epoch: 8 [35328/48750]	Loss: 0.0903	LR: 0.020000
Training Epoch: 8 [35584/48750]	Loss: 0.0663	LR: 0.020000
Training Epoch: 8 [35840/48750]	Loss: 0.1026	LR: 0.020000
Training Epoch: 8 [36096/48750]	Loss: 0.0649	LR: 0.020000
Training Epoch: 8 [36352/48750]	Loss: 0.1110	LR: 0.020000
Training Epoch: 8 [36608/48750]	Loss: 0.0624	LR: 0.020000
Training Epoch: 8 [36864/48750]	Loss: 0.1175	LR: 0.020000
Training Epoch: 8 [37120/48750]	Loss: 0.1356	LR: 0.020000
Training Epoch: 8 [37376/48750]	Loss: 0.0853	LR: 0.020000
Training Epoch: 8 [37632/48750]	Loss: 0.1562	LR: 0.020000
Training Epoch: 8 [37888/48750]	Loss: 0.1151	LR: 0.020000
Training Epoch: 8 [38144/48750]	Loss: 0.0885	LR: 0.020000
Training Epoch: 8 [38400/48750]	Loss: 0.0972	LR: 0.020000
Training Epoch: 8 [38656/48750]	Loss: 0.0472	LR: 0.020000
Training Epoch: 8 [38912/48750]	Loss: 0.0935	LR: 0.020000
Training Epoch: 8 [39168/48750]	Loss: 0.1030	LR: 0.020000
Training Epoch: 8 [39424/48750]	Loss: 0.0647	LR: 0.020000
Training Epoch: 8 [39680/48750]	Loss: 0.0790	LR: 0.020000
Training Epoch: 8 [39936/48750]	Loss: 0.1096	LR: 0.020000
Training Epoch: 8 [40192/48750]	Loss: 0.0660	LR: 0.020000
Training Epoch: 8 [40448/48750]	Loss: 0.1197	LR: 0.020000
Training Epoch: 8 [40704/48750]	Loss: 0.0810	LR: 0.020000
Training Epoch: 8 [40960/48750]	Loss: 0.0497	LR: 0.020000
Training Epoch: 8 [41216/48750]	Loss: 0.0651	LR: 0.020000
Training Epoch: 8 [41472/48750]	Loss: 0.1019	LR: 0.020000
Training Epoch: 8 [41728/48750]	Loss: 0.0830	LR: 0.020000
Training Epoch: 8 [41984/48750]	Loss: 0.1014	LR: 0.020000
Training Epoch: 8 [42240/48750]	Loss: 0.0805	LR: 0.020000
Training Epoch: 8 [42496/48750]	Loss: 0.0515	LR: 0.020000
Training Epoch: 8 [42752/48750]	Loss: 0.0997	LR: 0.020000
Training Epoch: 8 [43008/48750]	Loss: 0.1085	LR: 0.020000
Training Epoch: 8 [43264/48750]	Loss: 0.0785	LR: 0.020000
Training Epoch: 8 [43520/48750]	Loss: 0.0861	LR: 0.020000
Training Epoch: 8 [43776/48750]	Loss: 0.1367	LR: 0.020000
Training Epoch: 8 [44032/48750]	Loss: 0.0829	LR: 0.020000
Training Epoch: 8 [44288/48750]	Loss: 0.0765	LR: 0.020000
Training Epoch: 8 [44544/48750]	Loss: 0.0366	LR: 0.020000
Training Epoch: 8 [44800/48750]	Loss: 0.1211	LR: 0.020000
Training Epoch: 8 [45056/48750]	Loss: 0.0547	LR: 0.020000
Training Epoch: 8 [45312/48750]	Loss: 0.0428	LR: 0.020000
Training Epoch: 8 [45568/48750]	Loss: 0.1025	LR: 0.020000
Training Epoch: 8 [45824/48750]	Loss: 0.1169	LR: 0.020000
Training Epoch: 8 [46080/48750]	Loss: 0.1005	LR: 0.020000
Training Epoch: 8 [46336/48750]	Loss: 0.0796	LR: 0.020000
Training Epoch: 8 [46592/48750]	Loss: 0.0611	LR: 0.020000
Training Epoch: 8 [46848/48750]	Loss: 0.0892	LR: 0.020000
Training Epoch: 8 [47104/48750]	Loss: 0.1016	LR: 0.020000
Training Epoch: 8 [47360/48750]	Loss: 0.1101	LR: 0.020000
Training Epoch: 8 [47616/48750]	Loss: 0.0680	LR: 0.020000
Training Epoch: 8 [47872/48750]	Loss: 0.0974	LR: 0.020000
Training Epoch: 8 [48128/48750]	Loss: 0.0839	LR: 0.020000
Training Epoch: 8 [48384/48750]	Loss: 0.1109	LR: 0.020000
Training Epoch: 8 [48640/48750]	Loss: 0.0648	LR: 0.020000
Training Epoch: 8 [48750/48750]	Loss: 0.0561	LR: 0.020000
Epoch 8 - Average Train Loss: 0.0887, Train Accuracy: 0.9682
Epoch 8 training time consumed: 351.45s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0004, Accuracy: 0.9644, Time consumed:23.48s
Saving weights file to checkpoint/retrain/ViT/Sunday_20_July_2025_00h_27m_43s/ViT-Cifar10-seed8-ret75-8-best.pth
Valid (Test) Dl:  10000
Train Dl:  50000
Retain Train Dl:  48750
Forget Train Dl:  1250
Retain Valid Dl:  48750
Forget Valid Dl:  1250
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 1250 samples
Set1 Distribution: 1250 samples
Set2 Distribution: 1250 samples
Set1 Distribution: 1250 samples
Set2 Distribution: 1250 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 96.376953125
Retain Accuracy: 97.60035705566406
Zero-Retain Forget (ZRF): 0.7827634215354919
Membership Inference Attack (MIA): 0.7592
Forget vs Retain Membership Inference Attack (MIA): 0.512
Forget vs Test Membership Inference Attack (MIA): 0.498
Test vs Retain Membership Inference Attack (MIA): 0.53075
Train vs Test Membership Inference Attack (MIA): 0.5105
Forget Set Accuracy (Df): 95.97967529296875
Method Execution Time: 5416.03 seconds
