hello
hello

📌S Retain class distribution for seed 5:
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 5:
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
hello
hello
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/45000]	Loss: 2.4270	LR: 0.000000
Training Epoch: 1 [512/45000]	Loss: 2.3746	LR: 0.000568
Training Epoch: 1 [768/45000]	Loss: 2.4260	LR: 0.001136
Training Epoch: 1 [1024/45000]	Loss: 2.3846	LR: 0.001705
Training Epoch: 1 [1280/45000]	Loss: 2.3306	LR: 0.002273
Training Epoch: 1 [1536/45000]	Loss: 2.2132	LR: 0.002841
Training Epoch: 1 [1792/45000]	Loss: 2.0911	LR: 0.003409
Training Epoch: 1 [2048/45000]	Loss: 1.8280	LR: 0.003977
Training Epoch: 1 [2304/45000]	Loss: 1.6586	LR: 0.004545
Training Epoch: 1 [2560/45000]	Loss: 1.4560	LR: 0.005114
Training Epoch: 1 [2816/45000]	Loss: 1.2199	LR: 0.005682
Training Epoch: 1 [3072/45000]	Loss: 1.0456	LR: 0.006250
Training Epoch: 1 [3328/45000]	Loss: 0.8817	LR: 0.006818
Training Epoch: 1 [3584/45000]	Loss: 0.6425	LR: 0.007386
Training Epoch: 1 [3840/45000]	Loss: 0.4990	LR: 0.007955
Training Epoch: 1 [4096/45000]	Loss: 0.3877	LR: 0.008523
Training Epoch: 1 [4352/45000]	Loss: 0.3869	LR: 0.009091
Training Epoch: 1 [4608/45000]	Loss: 0.2608	LR: 0.009659
Training Epoch: 1 [4864/45000]	Loss: 0.3174	LR: 0.010227
Training Epoch: 1 [5120/45000]	Loss: 0.2036	LR: 0.010795
Training Epoch: 1 [5376/45000]	Loss: 0.1866	LR: 0.011364
Training Epoch: 1 [5632/45000]	Loss: 0.1958	LR: 0.011932
Training Epoch: 1 [5888/45000]	Loss: 0.2698	LR: 0.012500
Training Epoch: 1 [6144/45000]	Loss: 0.1878	LR: 0.013068
Training Epoch: 1 [6400/45000]	Loss: 0.2321	LR: 0.013636
Training Epoch: 1 [6656/45000]	Loss: 0.2522	LR: 0.014205
Training Epoch: 1 [6912/45000]	Loss: 0.2390	LR: 0.014773
Training Epoch: 1 [7168/45000]	Loss: 0.2631	LR: 0.015341
Training Epoch: 1 [7424/45000]	Loss: 0.2020	LR: 0.015909
Training Epoch: 1 [7680/45000]	Loss: 0.1999	LR: 0.016477
Training Epoch: 1 [7936/45000]	Loss: 0.2850	LR: 0.017045
Training Epoch: 1 [8192/45000]	Loss: 0.1694	LR: 0.017614
Training Epoch: 1 [8448/45000]	Loss: 0.1362	LR: 0.018182
Training Epoch: 1 [8704/45000]	Loss: 0.1181	LR: 0.018750
Training Epoch: 1 [8960/45000]	Loss: 0.1729	LR: 0.019318
Training Epoch: 1 [9216/45000]	Loss: 0.1571	LR: 0.019886
Training Epoch: 1 [9472/45000]	Loss: 0.2448	LR: 0.020455
Training Epoch: 1 [9728/45000]	Loss: 0.2185	LR: 0.021023
Training Epoch: 1 [9984/45000]	Loss: 0.2693	LR: 0.021591
Training Epoch: 1 [10240/45000]	Loss: 0.1424	LR: 0.022159
Training Epoch: 1 [10496/45000]	Loss: 0.2041	LR: 0.022727
Training Epoch: 1 [10752/45000]	Loss: 0.2352	LR: 0.023295
Training Epoch: 1 [11008/45000]	Loss: 0.2719	LR: 0.023864
Training Epoch: 1 [11264/45000]	Loss: 0.1752	LR: 0.024432
Training Epoch: 1 [11520/45000]	Loss: 0.1453	LR: 0.025000
Training Epoch: 1 [11776/45000]	Loss: 0.2405	LR: 0.025568
Training Epoch: 1 [12032/45000]	Loss: 0.2167	LR: 0.026136
Training Epoch: 1 [12288/45000]	Loss: 0.3542	LR: 0.026705
Training Epoch: 1 [12544/45000]	Loss: 0.4313	LR: 0.027273
Training Epoch: 1 [12800/45000]	Loss: 0.1955	LR: 0.027841
Training Epoch: 1 [13056/45000]	Loss: 0.1426	LR: 0.028409
Training Epoch: 1 [13312/45000]	Loss: 0.2412	LR: 0.028977
Training Epoch: 1 [13568/45000]	Loss: 0.1546	LR: 0.029545
Training Epoch: 1 [13824/45000]	Loss: 0.3109	LR: 0.030114
Training Epoch: 1 [14080/45000]	Loss: 0.3407	LR: 0.030682
Training Epoch: 1 [14336/45000]	Loss: 0.2887	LR: 0.031250
Training Epoch: 1 [14592/45000]	Loss: 0.1923	LR: 0.031818
Training Epoch: 1 [14848/45000]	Loss: 0.2218	LR: 0.032386
Training Epoch: 1 [15104/45000]	Loss: 0.3210	LR: 0.032955
Training Epoch: 1 [15360/45000]	Loss: 0.4955	LR: 0.033523
Training Epoch: 1 [15616/45000]	Loss: 0.2203	LR: 0.034091
Training Epoch: 1 [15872/45000]	Loss: 0.2077	LR: 0.034659
Training Epoch: 1 [16128/45000]	Loss: 0.3216	LR: 0.035227
Training Epoch: 1 [16384/45000]	Loss: 0.4404	LR: 0.035795
Training Epoch: 1 [16640/45000]	Loss: 0.1728	LR: 0.036364
Training Epoch: 1 [16896/45000]	Loss: 0.2251	LR: 0.036932
Training Epoch: 1 [17152/45000]	Loss: 0.2539	LR: 0.037500
Training Epoch: 1 [17408/45000]	Loss: 0.2934	LR: 0.038068
Training Epoch: 1 [17664/45000]	Loss: 0.2344	LR: 0.038636
Training Epoch: 1 [17920/45000]	Loss: 0.1956	LR: 0.039205
Training Epoch: 1 [18176/45000]	Loss: 0.1358	LR: 0.039773
Training Epoch: 1 [18432/45000]	Loss: 0.2127	LR: 0.040341
Training Epoch: 1 [18688/45000]	Loss: 0.1759	LR: 0.040909
Training Epoch: 1 [18944/45000]	Loss: 0.2002	LR: 0.041477
Training Epoch: 1 [19200/45000]	Loss: 0.1618	LR: 0.042045
Training Epoch: 1 [19456/45000]	Loss: 0.2207	LR: 0.042614
Training Epoch: 1 [19712/45000]	Loss: 0.1654	LR: 0.043182
Training Epoch: 1 [19968/45000]	Loss: 0.1933	LR: 0.043750
Training Epoch: 1 [20224/45000]	Loss: 0.2347	LR: 0.044318
Training Epoch: 1 [20480/45000]	Loss: 0.1933	LR: 0.044886
Training Epoch: 1 [20736/45000]	Loss: 0.1927	LR: 0.045455
Training Epoch: 1 [20992/45000]	Loss: 0.2552	LR: 0.046023
Training Epoch: 1 [21248/45000]	Loss: 0.3735	LR: 0.046591
Training Epoch: 1 [21504/45000]	Loss: 0.3126	LR: 0.047159
Training Epoch: 1 [21760/45000]	Loss: 0.3056	LR: 0.047727
Training Epoch: 1 [22016/45000]	Loss: 0.1311	LR: 0.048295
Training Epoch: 1 [22272/45000]	Loss: 0.2512	LR: 0.048864
Training Epoch: 1 [22528/45000]	Loss: 0.1525	LR: 0.049432
Training Epoch: 1 [22784/45000]	Loss: 0.1864	LR: 0.050000
Training Epoch: 1 [23040/45000]	Loss: 0.2718	LR: 0.050568
Training Epoch: 1 [23296/45000]	Loss: 0.2145	LR: 0.051136
Training Epoch: 1 [23552/45000]	Loss: 0.2060	LR: 0.051705
Training Epoch: 1 [23808/45000]	Loss: 0.1822	LR: 0.052273
Training Epoch: 1 [24064/45000]	Loss: 0.2240	LR: 0.052841
Training Epoch: 1 [24320/45000]	Loss: 0.1536	LR: 0.053409
Training Epoch: 1 [24576/45000]	Loss: 0.2343	LR: 0.053977
Training Epoch: 1 [24832/45000]	Loss: 0.3008	LR: 0.054545
Training Epoch: 1 [25088/45000]	Loss: 0.2221	LR: 0.055114
Training Epoch: 1 [25344/45000]	Loss: 0.1608	LR: 0.055682
Training Epoch: 1 [25600/45000]	Loss: 0.1714	LR: 0.056250
Training Epoch: 1 [25856/45000]	Loss: 0.2847	LR: 0.056818
Training Epoch: 1 [26112/45000]	Loss: 0.2609	LR: 0.057386
Training Epoch: 1 [26368/45000]	Loss: 0.2181	LR: 0.057955
Training Epoch: 1 [26624/45000]	Loss: 0.1571	LR: 0.058523
Training Epoch: 1 [26880/45000]	Loss: 0.3025	LR: 0.059091
Training Epoch: 1 [27136/45000]	Loss: 0.1149	LR: 0.059659
Training Epoch: 1 [27392/45000]	Loss: 0.1376	LR: 0.060227
Training Epoch: 1 [27648/45000]	Loss: 0.2923	LR: 0.060795
Training Epoch: 1 [27904/45000]	Loss: 0.2768	LR: 0.061364
Training Epoch: 1 [28160/45000]	Loss: 0.1528	LR: 0.061932
Training Epoch: 1 [28416/45000]	Loss: 0.3019	LR: 0.062500
Training Epoch: 1 [28672/45000]	Loss: 0.1608	LR: 0.063068
Training Epoch: 1 [28928/45000]	Loss: 0.2017	LR: 0.063636
Training Epoch: 1 [29184/45000]	Loss: 0.3412	LR: 0.064205
Training Epoch: 1 [29440/45000]	Loss: 0.2655	LR: 0.064773
Training Epoch: 1 [29696/45000]	Loss: 0.3005	LR: 0.065341
Training Epoch: 1 [29952/45000]	Loss: 0.2492	LR: 0.065909
Training Epoch: 1 [30208/45000]	Loss: 0.1827	LR: 0.066477
Training Epoch: 1 [30464/45000]	Loss: 0.2758	LR: 0.067045
Training Epoch: 1 [30720/45000]	Loss: 0.1622	LR: 0.067614
Training Epoch: 1 [30976/45000]	Loss: 0.1174	LR: 0.068182
Training Epoch: 1 [31232/45000]	Loss: 0.1887	LR: 0.068750
Training Epoch: 1 [31488/45000]	Loss: 0.1989	LR: 0.069318
Training Epoch: 1 [31744/45000]	Loss: 0.1323	LR: 0.069886
Training Epoch: 1 [32000/45000]	Loss: 0.2826	LR: 0.070455
Training Epoch: 1 [32256/45000]	Loss: 0.1416	LR: 0.071023
Training Epoch: 1 [32512/45000]	Loss: 0.1001	LR: 0.071591
Training Epoch: 1 [32768/45000]	Loss: 0.2120	LR: 0.072159
Training Epoch: 1 [33024/45000]	Loss: 0.1596	LR: 0.072727
Training Epoch: 1 [33280/45000]	Loss: 0.2351	LR: 0.073295
Training Epoch: 1 [33536/45000]	Loss: 0.1643	LR: 0.073864
Training Epoch: 1 [33792/45000]	Loss: 0.2673	LR: 0.074432
Training Epoch: 1 [34048/45000]	Loss: 0.1844	LR: 0.075000
Training Epoch: 1 [34304/45000]	Loss: 0.2140	LR: 0.075568
Training Epoch: 1 [34560/45000]	Loss: 0.1472	LR: 0.076136
Training Epoch: 1 [34816/45000]	Loss: 0.2158	LR: 0.076705
Training Epoch: 1 [35072/45000]	Loss: 0.1955	LR: 0.077273
Training Epoch: 1 [35328/45000]	Loss: 0.2273	LR: 0.077841
Training Epoch: 1 [35584/45000]	Loss: 0.2545	LR: 0.078409
Training Epoch: 1 [35840/45000]	Loss: 0.1287	LR: 0.078977
Training Epoch: 1 [36096/45000]	Loss: 0.1848	LR: 0.079545
Training Epoch: 1 [36352/45000]	Loss: 0.2456	LR: 0.080114
Training Epoch: 1 [36608/45000]	Loss: 0.2558	LR: 0.080682
Training Epoch: 1 [36864/45000]	Loss: 0.2136	LR: 0.081250
Training Epoch: 1 [37120/45000]	Loss: 0.2402	LR: 0.081818
Training Epoch: 1 [37376/45000]	Loss: 0.1859	LR: 0.082386
Training Epoch: 1 [37632/45000]	Loss: 0.1685	LR: 0.082955
Training Epoch: 1 [37888/45000]	Loss: 0.2493	LR: 0.083523
Training Epoch: 1 [38144/45000]	Loss: 0.3786	LR: 0.084091
Training Epoch: 1 [38400/45000]	Loss: 0.2358	LR: 0.084659
Training Epoch: 1 [38656/45000]	Loss: 0.4065	LR: 0.085227
Training Epoch: 1 [38912/45000]	Loss: 0.1738	LR: 0.085795
Training Epoch: 1 [39168/45000]	Loss: 0.2177	LR: 0.086364
Training Epoch: 1 [39424/45000]	Loss: 0.2377	LR: 0.086932
Training Epoch: 1 [39680/45000]	Loss: 0.2518	LR: 0.087500
Training Epoch: 1 [39936/45000]	Loss: 0.2723	LR: 0.088068
Training Epoch: 1 [40192/45000]	Loss: 0.1471	LR: 0.088636
Training Epoch: 1 [40448/45000]	Loss: 0.1699	LR: 0.089205
Training Epoch: 1 [40704/45000]	Loss: 0.2435	LR: 0.089773
Training Epoch: 1 [40960/45000]	Loss: 0.1578	LR: 0.090341
Training Epoch: 1 [41216/45000]	Loss: 0.1832	LR: 0.090909
Training Epoch: 1 [41472/45000]	Loss: 0.4496	LR: 0.091477
Training Epoch: 1 [41728/45000]	Loss: 0.2100	LR: 0.092045
Training Epoch: 1 [41984/45000]	Loss: 0.3529	LR: 0.092614
Training Epoch: 1 [42240/45000]	Loss: 0.1827	LR: 0.093182
Training Epoch: 1 [42496/45000]	Loss: 0.1294	LR: 0.093750
Training Epoch: 1 [42752/45000]	Loss: 0.3603	LR: 0.094318
Training Epoch: 1 [43008/45000]	Loss: 0.2540	LR: 0.094886
Training Epoch: 1 [43264/45000]	Loss: 0.1941	LR: 0.095455
Training Epoch: 1 [43520/45000]	Loss: 0.2423	LR: 0.096023
Training Epoch: 1 [43776/45000]	Loss: 0.2917	LR: 0.096591
Training Epoch: 1 [44032/45000]	Loss: 0.2914	LR: 0.097159
Training Epoch: 1 [44288/45000]	Loss: 0.3249	LR: 0.097727
Training Epoch: 1 [44544/45000]	Loss: 0.2975	LR: 0.098295
Training Epoch: 1 [44800/45000]	Loss: 0.3173	LR: 0.098864
Training Epoch: 1 [45000/45000]	Loss: 0.2388	LR: 0.099432
Epoch 1 - Average Train Loss: 0.3563, Train Accuracy: 0.8849
Epoch 1 training time consumed: 325.58s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0008, Accuracy: 0.9311, Time consumed:23.49s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_05h_51m_14s/ViT-Cifar10-seed5-ret100-1-best.pth
Training Epoch: 2 [256/45000]	Loss: 0.2543	LR: 0.100000
Training Epoch: 2 [512/45000]	Loss: 0.1946	LR: 0.100000
Training Epoch: 2 [768/45000]	Loss: 0.2404	LR: 0.100000
Training Epoch: 2 [1024/45000]	Loss: 0.1990	LR: 0.100000
Training Epoch: 2 [1280/45000]	Loss: 0.1446	LR: 0.100000
Training Epoch: 2 [1536/45000]	Loss: 0.2134	LR: 0.100000
Training Epoch: 2 [1792/45000]	Loss: 0.1939	LR: 0.100000
Training Epoch: 2 [2048/45000]	Loss: 0.1251	LR: 0.100000
Training Epoch: 2 [2304/45000]	Loss: 0.1659	LR: 0.100000
Training Epoch: 2 [2560/45000]	Loss: 0.2122	LR: 0.100000
Training Epoch: 2 [2816/45000]	Loss: 0.1958	LR: 0.100000
Training Epoch: 2 [3072/45000]	Loss: 0.2874	LR: 0.100000
Training Epoch: 2 [3328/45000]	Loss: 0.2191	LR: 0.100000
Training Epoch: 2 [3584/45000]	Loss: 0.2611	LR: 0.100000
Training Epoch: 2 [3840/45000]	Loss: 0.2152	LR: 0.100000
Training Epoch: 2 [4096/45000]	Loss: 0.2604	LR: 0.100000
Training Epoch: 2 [4352/45000]	Loss: 0.2523	LR: 0.100000
Training Epoch: 2 [4608/45000]	Loss: 0.2704	LR: 0.100000
Training Epoch: 2 [4864/45000]	Loss: 0.2386	LR: 0.100000
Training Epoch: 2 [5120/45000]	Loss: 0.1779	LR: 0.100000
Training Epoch: 2 [5376/45000]	Loss: 0.2146	LR: 0.100000
Training Epoch: 2 [5632/45000]	Loss: 0.2344	LR: 0.100000
Training Epoch: 2 [5888/45000]	Loss: 0.1586	LR: 0.100000
Training Epoch: 2 [6144/45000]	Loss: 0.2078	LR: 0.100000
Training Epoch: 2 [6400/45000]	Loss: 0.2607	LR: 0.100000
Training Epoch: 2 [6656/45000]	Loss: 0.2634	LR: 0.100000
Training Epoch: 2 [6912/45000]	Loss: 0.2689	LR: 0.100000
Training Epoch: 2 [7168/45000]	Loss: 0.3460	LR: 0.100000
Training Epoch: 2 [7424/45000]	Loss: 0.2510	LR: 0.100000
Training Epoch: 2 [7680/45000]	Loss: 0.2169	LR: 0.100000
Training Epoch: 2 [7936/45000]	Loss: 0.2493	LR: 0.100000
Training Epoch: 2 [8192/45000]	Loss: 0.3065	LR: 0.100000
Training Epoch: 2 [8448/45000]	Loss: 0.2300	LR: 0.100000
Training Epoch: 2 [8704/45000]	Loss: 0.2705	LR: 0.100000
Training Epoch: 2 [8960/45000]	Loss: 0.1799	LR: 0.100000
Training Epoch: 2 [9216/45000]	Loss: 0.2607	LR: 0.100000
Training Epoch: 2 [9472/45000]	Loss: 0.2702	LR: 0.100000
Training Epoch: 2 [9728/45000]	Loss: 0.1823	LR: 0.100000
Training Epoch: 2 [9984/45000]	Loss: 0.1857	LR: 0.100000
Training Epoch: 2 [10240/45000]	Loss: 0.2866	LR: 0.100000
Training Epoch: 2 [10496/45000]	Loss: 0.1955	LR: 0.100000
Training Epoch: 2 [10752/45000]	Loss: 0.2370	LR: 0.100000
Training Epoch: 2 [11008/45000]	Loss: 0.1762	LR: 0.100000
Training Epoch: 2 [11264/45000]	Loss: 0.3231	LR: 0.100000
Training Epoch: 2 [11520/45000]	Loss: 0.2452	LR: 0.100000
Training Epoch: 2 [11776/45000]	Loss: 0.1938	LR: 0.100000
Training Epoch: 2 [12032/45000]	Loss: 0.2479	LR: 0.100000
Training Epoch: 2 [12288/45000]	Loss: 0.2315	LR: 0.100000
Training Epoch: 2 [12544/45000]	Loss: 0.3109	LR: 0.100000
Training Epoch: 2 [12800/45000]	Loss: 0.1678	LR: 0.100000
Training Epoch: 2 [13056/45000]	Loss: 0.2392	LR: 0.100000
Training Epoch: 2 [13312/45000]	Loss: 0.2046	LR: 0.100000
Training Epoch: 2 [13568/45000]	Loss: 0.2177	LR: 0.100000
Training Epoch: 2 [13824/45000]	Loss: 0.3157	LR: 0.100000
Training Epoch: 2 [14080/45000]	Loss: 0.2545	LR: 0.100000
Training Epoch: 2 [14336/45000]	Loss: 0.2598	LR: 0.100000
Training Epoch: 2 [14592/45000]	Loss: 0.2316	LR: 0.100000
Training Epoch: 2 [14848/45000]	Loss: 0.2628	LR: 0.100000
Training Epoch: 2 [15104/45000]	Loss: 0.2351	LR: 0.100000
Training Epoch: 2 [15360/45000]	Loss: 0.1687	LR: 0.100000
Training Epoch: 2 [15616/45000]	Loss: 0.1802	LR: 0.100000
Training Epoch: 2 [15872/45000]	Loss: 0.2401	LR: 0.100000
Training Epoch: 2 [16128/45000]	Loss: 0.2383	LR: 0.100000
Training Epoch: 2 [16384/45000]	Loss: 0.2517	LR: 0.100000
Training Epoch: 2 [16640/45000]	Loss: 0.1423	LR: 0.100000
Training Epoch: 2 [16896/45000]	Loss: 0.3835	LR: 0.100000
Training Epoch: 2 [17152/45000]	Loss: 0.2557	LR: 0.100000
Training Epoch: 2 [17408/45000]	Loss: 0.2009	LR: 0.100000
Training Epoch: 2 [17664/45000]	Loss: 0.3260	LR: 0.100000
Training Epoch: 2 [17920/45000]	Loss: 0.2584	LR: 0.100000
Training Epoch: 2 [18176/45000]	Loss: 0.1611	LR: 0.100000
Training Epoch: 2 [18432/45000]	Loss: 0.1765	LR: 0.100000
Training Epoch: 2 [18688/45000]	Loss: 0.2939	LR: 0.100000
Training Epoch: 2 [18944/45000]	Loss: 0.1570	LR: 0.100000
Training Epoch: 2 [19200/45000]	Loss: 0.2247	LR: 0.100000
Training Epoch: 2 [19456/45000]	Loss: 0.2278	LR: 0.100000
Training Epoch: 2 [19712/45000]	Loss: 0.2588	LR: 0.100000
Training Epoch: 2 [19968/45000]	Loss: 0.2086	LR: 0.100000
Training Epoch: 2 [20224/45000]	Loss: 0.2130	LR: 0.100000
Training Epoch: 2 [20480/45000]	Loss: 0.1595	LR: 0.100000
Training Epoch: 2 [20736/45000]	Loss: 0.2097	LR: 0.100000
Training Epoch: 2 [20992/45000]	Loss: 0.2037	LR: 0.100000
Training Epoch: 2 [21248/45000]	Loss: 0.1965	LR: 0.100000
Training Epoch: 2 [21504/45000]	Loss: 0.3455	LR: 0.100000
Training Epoch: 2 [21760/45000]	Loss: 0.3008	LR: 0.100000
Training Epoch: 2 [22016/45000]	Loss: 0.2517	LR: 0.100000
Training Epoch: 2 [22272/45000]	Loss: 0.3995	LR: 0.100000
Training Epoch: 2 [22528/45000]	Loss: 0.3493	LR: 0.100000
Training Epoch: 2 [22784/45000]	Loss: 0.3007	LR: 0.100000
Training Epoch: 2 [23040/45000]	Loss: 0.4487	LR: 0.100000
Training Epoch: 2 [23296/45000]	Loss: 0.2476	LR: 0.100000
Training Epoch: 2 [23552/45000]	Loss: 0.3175	LR: 0.100000
Training Epoch: 2 [23808/45000]	Loss: 0.2835	LR: 0.100000
Training Epoch: 2 [24064/45000]	Loss: 0.3048	LR: 0.100000
Training Epoch: 2 [24320/45000]	Loss: 0.1605	LR: 0.100000
Training Epoch: 2 [24576/45000]	Loss: 0.1328	LR: 0.100000
Training Epoch: 2 [24832/45000]	Loss: 0.4170	LR: 0.100000
Training Epoch: 2 [25088/45000]	Loss: 0.1925	LR: 0.100000
Training Epoch: 2 [25344/45000]	Loss: 0.1983	LR: 0.100000
Training Epoch: 2 [25600/45000]	Loss: 0.1316	LR: 0.100000
Training Epoch: 2 [25856/45000]	Loss: 0.2222	LR: 0.100000
Training Epoch: 2 [26112/45000]	Loss: 0.2972	LR: 0.100000
Training Epoch: 2 [26368/45000]	Loss: 0.1742	LR: 0.100000
Training Epoch: 2 [26624/45000]	Loss: 0.2538	LR: 0.100000
Training Epoch: 2 [26880/45000]	Loss: 0.3074	LR: 0.100000
Training Epoch: 2 [27136/45000]	Loss: 0.2491	LR: 0.100000
Training Epoch: 2 [27392/45000]	Loss: 0.2028	LR: 0.100000
Training Epoch: 2 [27648/45000]	Loss: 0.2487	LR: 0.100000
Training Epoch: 2 [27904/45000]	Loss: 0.2686	LR: 0.100000
Training Epoch: 2 [28160/45000]	Loss: 0.2030	LR: 0.100000
Training Epoch: 2 [28416/45000]	Loss: 0.1789	LR: 0.100000
Training Epoch: 2 [28672/45000]	Loss: 0.2234	LR: 0.100000
Training Epoch: 2 [28928/45000]	Loss: 0.2000	LR: 0.100000
Training Epoch: 2 [29184/45000]	Loss: 0.2894	LR: 0.100000
Training Epoch: 2 [29440/45000]	Loss: 0.2399	LR: 0.100000
Training Epoch: 2 [29696/45000]	Loss: 0.2152	LR: 0.100000
Training Epoch: 2 [29952/45000]	Loss: 0.2719	LR: 0.100000
Training Epoch: 2 [30208/45000]	Loss: 0.2198	LR: 0.100000
Training Epoch: 2 [30464/45000]	Loss: 0.2607	LR: 0.100000
Training Epoch: 2 [30720/45000]	Loss: 0.3314	LR: 0.100000
Training Epoch: 2 [30976/45000]	Loss: 0.2399	LR: 0.100000
Training Epoch: 2 [31232/45000]	Loss: 0.2643	LR: 0.100000
Training Epoch: 2 [31488/45000]	Loss: 0.2396	LR: 0.100000
Training Epoch: 2 [31744/45000]	Loss: 0.2373	LR: 0.100000
Training Epoch: 2 [32000/45000]	Loss: 0.2216	LR: 0.100000
Training Epoch: 2 [32256/45000]	Loss: 0.2550	LR: 0.100000
Training Epoch: 2 [32512/45000]	Loss: 0.2143	LR: 0.100000
Training Epoch: 2 [32768/45000]	Loss: 0.2838	LR: 0.100000
Training Epoch: 2 [33024/45000]	Loss: 0.1467	LR: 0.100000
Training Epoch: 2 [33280/45000]	Loss: 0.1876	LR: 0.100000
Training Epoch: 2 [33536/45000]	Loss: 0.2051	LR: 0.100000
Training Epoch: 2 [33792/45000]	Loss: 0.1547	LR: 0.100000
Training Epoch: 2 [34048/45000]	Loss: 0.2532	LR: 0.100000
Training Epoch: 2 [34304/45000]	Loss: 0.2658	LR: 0.100000
Training Epoch: 2 [34560/45000]	Loss: 0.1919	LR: 0.100000
Training Epoch: 2 [34816/45000]	Loss: 0.1954	LR: 0.100000
Training Epoch: 2 [35072/45000]	Loss: 0.1845	LR: 0.100000
Training Epoch: 2 [35328/45000]	Loss: 0.1755	LR: 0.100000
Training Epoch: 2 [35584/45000]	Loss: 0.2027	LR: 0.100000
Training Epoch: 2 [35840/45000]	Loss: 0.2059	LR: 0.100000
Training Epoch: 2 [36096/45000]	Loss: 0.2393	LR: 0.100000
Training Epoch: 2 [36352/45000]	Loss: 0.1654	LR: 0.100000
Training Epoch: 2 [36608/45000]	Loss: 0.1714	LR: 0.100000
Training Epoch: 2 [36864/45000]	Loss: 0.1560	LR: 0.100000
Training Epoch: 2 [37120/45000]	Loss: 0.2466	LR: 0.100000
Training Epoch: 2 [37376/45000]	Loss: 0.1964	LR: 0.100000
Training Epoch: 2 [37632/45000]	Loss: 0.2596	LR: 0.100000
Training Epoch: 2 [37888/45000]	Loss: 0.2373	LR: 0.100000
Training Epoch: 2 [38144/45000]	Loss: 0.1193	LR: 0.100000
Training Epoch: 2 [38400/45000]	Loss: 0.2759	LR: 0.100000
Training Epoch: 2 [38656/45000]	Loss: 0.1653	LR: 0.100000
Training Epoch: 2 [38912/45000]	Loss: 0.1274	LR: 0.100000
Training Epoch: 2 [39168/45000]	Loss: 0.1422	LR: 0.100000
Training Epoch: 2 [39424/45000]	Loss: 0.2011	LR: 0.100000
Training Epoch: 2 [39680/45000]	Loss: 0.1988	LR: 0.100000
Training Epoch: 2 [39936/45000]	Loss: 0.1682	LR: 0.100000
Training Epoch: 2 [40192/45000]	Loss: 0.2017	LR: 0.100000
Training Epoch: 2 [40448/45000]	Loss: 0.1823	LR: 0.100000
Training Epoch: 2 [40704/45000]	Loss: 0.1942	LR: 0.100000
Training Epoch: 2 [40960/45000]	Loss: 0.2940	LR: 0.100000
Training Epoch: 2 [41216/45000]	Loss: 0.2070	LR: 0.100000
Training Epoch: 2 [41472/45000]	Loss: 0.1721	LR: 0.100000
Training Epoch: 2 [41728/45000]	Loss: 0.2775	LR: 0.100000
Training Epoch: 2 [41984/45000]	Loss: 0.1937	LR: 0.100000
Training Epoch: 2 [42240/45000]	Loss: 0.2131	LR: 0.100000
Training Epoch: 2 [42496/45000]	Loss: 0.2023	LR: 0.100000
Training Epoch: 2 [42752/45000]	Loss: 0.2459	LR: 0.100000
Training Epoch: 2 [43008/45000]	Loss: 0.2202	LR: 0.100000
Training Epoch: 2 [43264/45000]	Loss: 0.2202	LR: 0.100000
Training Epoch: 2 [43520/45000]	Loss: 0.1922	LR: 0.100000
Training Epoch: 2 [43776/45000]	Loss: 0.2240	LR: 0.100000
Training Epoch: 2 [44032/45000]	Loss: 0.1875	LR: 0.100000
Training Epoch: 2 [44288/45000]	Loss: 0.1346	LR: 0.100000
Training Epoch: 2 [44544/45000]	Loss: 0.2532	LR: 0.100000
Training Epoch: 2 [44800/45000]	Loss: 0.2127	LR: 0.100000
Training Epoch: 2 [45000/45000]	Loss: 0.1880	LR: 0.100000
Epoch 2 - Average Train Loss: 0.2290, Train Accuracy: 0.9236
Epoch 2 training time consumed: 324.82s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0005, Accuracy: 0.9618, Time consumed:23.46s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_05h_51m_14s/ViT-Cifar10-seed5-ret100-2-best.pth
Training Epoch: 3 [256/45000]	Loss: 0.1241	LR: 0.100000
Training Epoch: 3 [512/45000]	Loss: 0.1292	LR: 0.100000
Training Epoch: 3 [768/45000]	Loss: 0.2682	LR: 0.100000
Training Epoch: 3 [1024/45000]	Loss: 0.1579	LR: 0.100000
Training Epoch: 3 [1280/45000]	Loss: 0.0981	LR: 0.100000
Training Epoch: 3 [1536/45000]	Loss: 0.1343	LR: 0.100000
Training Epoch: 3 [1792/45000]	Loss: 0.1267	LR: 0.100000
Training Epoch: 3 [2048/45000]	Loss: 0.2003	LR: 0.100000
Training Epoch: 3 [2304/45000]	Loss: 0.1083	LR: 0.100000
Training Epoch: 3 [2560/45000]	Loss: 0.1326	LR: 0.100000
Training Epoch: 3 [2816/45000]	Loss: 0.1287	LR: 0.100000
Training Epoch: 3 [3072/45000]	Loss: 0.2592	LR: 0.100000
Training Epoch: 3 [3328/45000]	Loss: 0.2404	LR: 0.100000
Training Epoch: 3 [3584/45000]	Loss: 0.2142	LR: 0.100000
Training Epoch: 3 [3840/45000]	Loss: 0.1468	LR: 0.100000
Training Epoch: 3 [4096/45000]	Loss: 0.1648	LR: 0.100000
Training Epoch: 3 [4352/45000]	Loss: 0.1747	LR: 0.100000
Training Epoch: 3 [4608/45000]	Loss: 0.2643	LR: 0.100000
Training Epoch: 3 [4864/45000]	Loss: 0.1587	LR: 0.100000
Training Epoch: 3 [5120/45000]	Loss: 0.3098	LR: 0.100000
Training Epoch: 3 [5376/45000]	Loss: 0.2232	LR: 0.100000
Training Epoch: 3 [5632/45000]	Loss: 0.1109	LR: 0.100000
Training Epoch: 3 [5888/45000]	Loss: 0.2800	LR: 0.100000
Training Epoch: 3 [6144/45000]	Loss: 0.1377	LR: 0.100000
Training Epoch: 3 [6400/45000]	Loss: 0.1539	LR: 0.100000
Training Epoch: 3 [6656/45000]	Loss: 0.1940	LR: 0.100000
Training Epoch: 3 [6912/45000]	Loss: 0.1519	LR: 0.100000
Training Epoch: 3 [7168/45000]	Loss: 0.2370	LR: 0.100000
Training Epoch: 3 [7424/45000]	Loss: 0.1396	LR: 0.100000
Training Epoch: 3 [7680/45000]	Loss: 0.1243	LR: 0.100000
Training Epoch: 3 [7936/45000]	Loss: 0.1421	LR: 0.100000
Training Epoch: 3 [8192/45000]	Loss: 0.1169	LR: 0.100000
Training Epoch: 3 [8448/45000]	Loss: 0.1390	LR: 0.100000
Training Epoch: 3 [8704/45000]	Loss: 0.2048	LR: 0.100000
Training Epoch: 3 [8960/45000]	Loss: 0.1159	LR: 0.100000
Training Epoch: 3 [9216/45000]	Loss: 0.1570	LR: 0.100000
Training Epoch: 3 [9472/45000]	Loss: 0.1411	LR: 0.100000
Training Epoch: 3 [9728/45000]	Loss: 0.2259	LR: 0.100000
Training Epoch: 3 [9984/45000]	Loss: 0.1151	LR: 0.100000
Training Epoch: 3 [10240/45000]	Loss: 0.1123	LR: 0.100000
Training Epoch: 3 [10496/45000]	Loss: 0.2096	LR: 0.100000
Training Epoch: 3 [10752/45000]	Loss: 0.1473	LR: 0.100000
Training Epoch: 3 [11008/45000]	Loss: 0.1577	LR: 0.100000
Training Epoch: 3 [11264/45000]	Loss: 0.1244	LR: 0.100000
Training Epoch: 3 [11520/45000]	Loss: 0.2089	LR: 0.100000
Training Epoch: 3 [11776/45000]	Loss: 0.2081	LR: 0.100000
Training Epoch: 3 [12032/45000]	Loss: 0.1436	LR: 0.100000
Training Epoch: 3 [12288/45000]	Loss: 0.1131	LR: 0.100000
Training Epoch: 3 [12544/45000]	Loss: 0.1221	LR: 0.100000
Training Epoch: 3 [12800/45000]	Loss: 0.1968	LR: 0.100000
Training Epoch: 3 [13056/45000]	Loss: 0.2760	LR: 0.100000
Training Epoch: 3 [13312/45000]	Loss: 0.1233	LR: 0.100000
Training Epoch: 3 [13568/45000]	Loss: 0.1167	LR: 0.100000
Training Epoch: 3 [13824/45000]	Loss: 0.2365	LR: 0.100000
Training Epoch: 3 [14080/45000]	Loss: 0.1496	LR: 0.100000
Training Epoch: 3 [14336/45000]	Loss: 0.2100	LR: 0.100000
Training Epoch: 3 [14592/45000]	Loss: 0.1874	LR: 0.100000
Training Epoch: 3 [14848/45000]	Loss: 0.1241	LR: 0.100000
Training Epoch: 3 [15104/45000]	Loss: 0.1860	LR: 0.100000
Training Epoch: 3 [15360/45000]	Loss: 0.1376	LR: 0.100000
Training Epoch: 3 [15616/45000]	Loss: 0.2033	LR: 0.100000
Training Epoch: 3 [15872/45000]	Loss: 0.1493	LR: 0.100000
Training Epoch: 3 [16128/45000]	Loss: 0.1175	LR: 0.100000
Training Epoch: 3 [16384/45000]	Loss: 0.1415	LR: 0.100000
Training Epoch: 3 [16640/45000]	Loss: 0.1880	LR: 0.100000
Training Epoch: 3 [16896/45000]	Loss: 0.1638	LR: 0.100000
Training Epoch: 3 [17152/45000]	Loss: 0.1303	LR: 0.100000
Training Epoch: 3 [17408/45000]	Loss: 0.1433	LR: 0.100000
Training Epoch: 3 [17664/45000]	Loss: 0.1217	LR: 0.100000
Training Epoch: 3 [17920/45000]	Loss: 0.1668	LR: 0.100000
Training Epoch: 3 [18176/45000]	Loss: 0.1946	LR: 0.100000
Training Epoch: 3 [18432/45000]	Loss: 0.1277	LR: 0.100000
Training Epoch: 3 [18688/45000]	Loss: 0.1384	LR: 0.100000
Training Epoch: 3 [18944/45000]	Loss: 0.1577	LR: 0.100000
Training Epoch: 3 [19200/45000]	Loss: 0.1397	LR: 0.100000
Training Epoch: 3 [19456/45000]	Loss: 0.1359	LR: 0.100000
Training Epoch: 3 [19712/45000]	Loss: 0.2356	LR: 0.100000
Training Epoch: 3 [19968/45000]	Loss: 0.1181	LR: 0.100000
Training Epoch: 3 [20224/45000]	Loss: 0.1864	LR: 0.100000
Training Epoch: 3 [20480/45000]	Loss: 0.1427	LR: 0.100000
Training Epoch: 3 [20736/45000]	Loss: 0.0789	LR: 0.100000
Training Epoch: 3 [20992/45000]	Loss: 0.0952	LR: 0.100000
Training Epoch: 3 [21248/45000]	Loss: 0.1214	LR: 0.100000
Training Epoch: 3 [21504/45000]	Loss: 0.0932	LR: 0.100000
Training Epoch: 3 [21760/45000]	Loss: 0.1080	LR: 0.100000
Training Epoch: 3 [22016/45000]	Loss: 0.2438	LR: 0.100000
Training Epoch: 3 [22272/45000]	Loss: 0.1466	LR: 0.100000
Training Epoch: 3 [22528/45000]	Loss: 0.1214	LR: 0.100000
Training Epoch: 3 [22784/45000]	Loss: 0.2398	LR: 0.100000
Training Epoch: 3 [23040/45000]	Loss: 0.1814	LR: 0.100000
Training Epoch: 3 [23296/45000]	Loss: 0.1623	LR: 0.100000
Training Epoch: 3 [23552/45000]	Loss: 0.1211	LR: 0.100000
Training Epoch: 3 [23808/45000]	Loss: 0.2223	LR: 0.100000
Training Epoch: 3 [24064/45000]	Loss: 0.1065	LR: 0.100000
Training Epoch: 3 [24320/45000]	Loss: 0.1085	LR: 0.100000
Training Epoch: 3 [24576/45000]	Loss: 0.1525	LR: 0.100000
Training Epoch: 3 [24832/45000]	Loss: 0.1039	LR: 0.100000
Training Epoch: 3 [25088/45000]	Loss: 0.1191	LR: 0.100000
Training Epoch: 3 [25344/45000]	Loss: 0.1062	LR: 0.100000
Training Epoch: 3 [25600/45000]	Loss: 0.0923	LR: 0.100000
Training Epoch: 3 [25856/45000]	Loss: 0.2088	LR: 0.100000
Training Epoch: 3 [26112/45000]	Loss: 0.1525	LR: 0.100000
Training Epoch: 3 [26368/45000]	Loss: 0.1161	LR: 0.100000
Training Epoch: 3 [26624/45000]	Loss: 0.1075	LR: 0.100000
Training Epoch: 3 [26880/45000]	Loss: 0.1183	LR: 0.100000
Training Epoch: 3 [27136/45000]	Loss: 0.1312	LR: 0.100000
Training Epoch: 3 [27392/45000]	Loss: 0.1211	LR: 0.100000
Training Epoch: 3 [27648/45000]	Loss: 0.1730	LR: 0.100000
Training Epoch: 3 [27904/45000]	Loss: 0.1228	LR: 0.100000
Training Epoch: 3 [28160/45000]	Loss: 0.1166	LR: 0.100000
Training Epoch: 3 [28416/45000]	Loss: 0.1748	LR: 0.100000
Training Epoch: 3 [28672/45000]	Loss: 0.1833	LR: 0.100000
Training Epoch: 3 [28928/45000]	Loss: 0.2262	LR: 0.100000
Training Epoch: 3 [29184/45000]	Loss: 0.1663	LR: 0.100000
Training Epoch: 3 [29440/45000]	Loss: 0.1610	LR: 0.100000
Training Epoch: 3 [29696/45000]	Loss: 0.1538	LR: 0.100000
Training Epoch: 3 [29952/45000]	Loss: 0.1164	LR: 0.100000
Training Epoch: 3 [30208/45000]	Loss: 0.1465	LR: 0.100000
Training Epoch: 3 [30464/45000]	Loss: 0.2382	LR: 0.100000
Training Epoch: 3 [30720/45000]	Loss: 0.1267	LR: 0.100000
Training Epoch: 3 [30976/45000]	Loss: 0.0722	LR: 0.100000
Training Epoch: 3 [31232/45000]	Loss: 0.1850	LR: 0.100000
Training Epoch: 3 [31488/45000]	Loss: 0.2018	LR: 0.100000
Training Epoch: 3 [31744/45000]	Loss: 0.1337	LR: 0.100000
Training Epoch: 3 [32000/45000]	Loss: 0.1287	LR: 0.100000
Training Epoch: 3 [32256/45000]	Loss: 0.1396	LR: 0.100000
Training Epoch: 3 [32512/45000]	Loss: 0.1700	LR: 0.100000
Training Epoch: 3 [32768/45000]	Loss: 0.1340	LR: 0.100000
Training Epoch: 3 [33024/45000]	Loss: 0.1457	LR: 0.100000
Training Epoch: 3 [33280/45000]	Loss: 0.1939	LR: 0.100000
Training Epoch: 3 [33536/45000]	Loss: 0.1487	LR: 0.100000
Training Epoch: 3 [33792/45000]	Loss: 0.1995	LR: 0.100000
Training Epoch: 3 [34048/45000]	Loss: 0.1394	LR: 0.100000
Training Epoch: 3 [34304/45000]	Loss: 0.2281	LR: 0.100000
Training Epoch: 3 [34560/45000]	Loss: 0.1468	LR: 0.100000
Training Epoch: 3 [34816/45000]	Loss: 0.1474	LR: 0.100000
Training Epoch: 3 [35072/45000]	Loss: 0.1818	LR: 0.100000
Training Epoch: 3 [35328/45000]	Loss: 0.1098	LR: 0.100000
Training Epoch: 3 [35584/45000]	Loss: 0.1524	LR: 0.100000
Training Epoch: 3 [35840/45000]	Loss: 0.1490	LR: 0.100000
Training Epoch: 3 [36096/45000]	Loss: 0.1425	LR: 0.100000
Training Epoch: 3 [36352/45000]	Loss: 0.1638	LR: 0.100000
Training Epoch: 3 [36608/45000]	Loss: 0.0919	LR: 0.100000
Training Epoch: 3 [36864/45000]	Loss: 0.2025	LR: 0.100000
Training Epoch: 3 [37120/45000]	Loss: 0.1278	LR: 0.100000
Training Epoch: 3 [37376/45000]	Loss: 0.1079	LR: 0.100000
Training Epoch: 3 [37632/45000]	Loss: 0.1688	LR: 0.100000
Training Epoch: 3 [37888/45000]	Loss: 0.1370	LR: 0.100000
Training Epoch: 3 [38144/45000]	Loss: 0.1555	LR: 0.100000
Training Epoch: 3 [38400/45000]	Loss: 0.0354	LR: 0.100000
Training Epoch: 3 [38656/45000]	Loss: 0.1132	LR: 0.100000
Training Epoch: 3 [38912/45000]	Loss: 0.1868	LR: 0.100000
Training Epoch: 3 [39168/45000]	Loss: 0.1040	LR: 0.100000
Training Epoch: 3 [39424/45000]	Loss: 0.1257	LR: 0.100000
Training Epoch: 3 [39680/45000]	Loss: 0.1420	LR: 0.100000
Training Epoch: 3 [39936/45000]	Loss: 0.1270	LR: 0.100000
Training Epoch: 3 [40192/45000]	Loss: 0.1673	LR: 0.100000
Training Epoch: 3 [40448/45000]	Loss: 0.1770	LR: 0.100000
Training Epoch: 3 [40704/45000]	Loss: 0.1375	LR: 0.100000
Training Epoch: 3 [40960/45000]	Loss: 0.1870	LR: 0.100000
Training Epoch: 3 [41216/45000]	Loss: 0.1452	LR: 0.100000
Training Epoch: 3 [41472/45000]	Loss: 0.1739	LR: 0.100000
Training Epoch: 3 [41728/45000]	Loss: 0.1671	LR: 0.100000
Training Epoch: 3 [41984/45000]	Loss: 0.1820	LR: 0.100000
Training Epoch: 3 [42240/45000]	Loss: 0.2174	LR: 0.100000
Training Epoch: 3 [42496/45000]	Loss: 0.1614	LR: 0.100000
Training Epoch: 3 [42752/45000]	Loss: 0.2302	LR: 0.100000
Training Epoch: 3 [43008/45000]	Loss: 0.2040	LR: 0.100000
Training Epoch: 3 [43264/45000]	Loss: 0.1919	LR: 0.100000
Training Epoch: 3 [43520/45000]	Loss: 0.1426	LR: 0.100000
Training Epoch: 3 [43776/45000]	Loss: 0.1836	LR: 0.100000
Training Epoch: 3 [44032/45000]	Loss: 0.1058	LR: 0.100000
Training Epoch: 3 [44288/45000]	Loss: 0.1400	LR: 0.100000
Training Epoch: 3 [44544/45000]	Loss: 0.1661	LR: 0.100000
Training Epoch: 3 [44800/45000]	Loss: 0.1619	LR: 0.100000
Training Epoch: 3 [45000/45000]	Loss: 0.1990	LR: 0.100000
Epoch 3 - Average Train Loss: 0.1574, Train Accuracy: 0.9470
Epoch 3 training time consumed: 325.12s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0005, Accuracy: 0.9589, Time consumed:23.45s
Training Epoch: 4 [256/45000]	Loss: 0.1251	LR: 0.100000
Training Epoch: 4 [512/45000]	Loss: 0.1291	LR: 0.100000
Training Epoch: 4 [768/45000]	Loss: 0.1574	LR: 0.100000
Training Epoch: 4 [1024/45000]	Loss: 0.1090	LR: 0.100000
Training Epoch: 4 [1280/45000]	Loss: 0.1247	LR: 0.100000
Training Epoch: 4 [1536/45000]	Loss: 0.1184	LR: 0.100000
Training Epoch: 4 [1792/45000]	Loss: 0.0893	LR: 0.100000
Training Epoch: 4 [2048/45000]	Loss: 0.0837	LR: 0.100000
Training Epoch: 4 [2304/45000]	Loss: 0.1286	LR: 0.100000
Training Epoch: 4 [2560/45000]	Loss: 0.1594	LR: 0.100000
Training Epoch: 4 [2816/45000]	Loss: 0.0899	LR: 0.100000
Training Epoch: 4 [3072/45000]	Loss: 0.0794	LR: 0.100000
Training Epoch: 4 [3328/45000]	Loss: 0.2236	LR: 0.100000
Training Epoch: 4 [3584/45000]	Loss: 0.1207	LR: 0.100000
Training Epoch: 4 [3840/45000]	Loss: 0.1073	LR: 0.100000
Training Epoch: 4 [4096/45000]	Loss: 0.2055	LR: 0.100000
Training Epoch: 4 [4352/45000]	Loss: 0.1506	LR: 0.100000
Training Epoch: 4 [4608/45000]	Loss: 0.1347	LR: 0.100000
Training Epoch: 4 [4864/45000]	Loss: 0.2703	LR: 0.100000
Training Epoch: 4 [5120/45000]	Loss: 0.1941	LR: 0.100000
Training Epoch: 4 [5376/45000]	Loss: 0.1644	LR: 0.100000
Training Epoch: 4 [5632/45000]	Loss: 0.1501	LR: 0.100000
Training Epoch: 4 [5888/45000]	Loss: 0.1975	LR: 0.100000
Training Epoch: 4 [6144/45000]	Loss: 0.2152	LR: 0.100000
Training Epoch: 4 [6400/45000]	Loss: 0.1796	LR: 0.100000
Training Epoch: 4 [6656/45000]	Loss: 0.1466	LR: 0.100000
Training Epoch: 4 [6912/45000]	Loss: 0.1275	LR: 0.100000
Training Epoch: 4 [7168/45000]	Loss: 0.1646	LR: 0.100000
Training Epoch: 4 [7424/45000]	Loss: 0.0777	LR: 0.100000
Training Epoch: 4 [7680/45000]	Loss: 0.1462	LR: 0.100000
Training Epoch: 4 [7936/45000]	Loss: 0.1599	LR: 0.100000
Training Epoch: 4 [8192/45000]	Loss: 0.1907	LR: 0.100000
Training Epoch: 4 [8448/45000]	Loss: 0.0948	LR: 0.100000
Training Epoch: 4 [8704/45000]	Loss: 0.1818	LR: 0.100000
Training Epoch: 4 [8960/45000]	Loss: 0.1484	LR: 0.100000
Training Epoch: 4 [9216/45000]	Loss: 0.1369	LR: 0.100000
Training Epoch: 4 [9472/45000]	Loss: 0.1096	LR: 0.100000
Training Epoch: 4 [9728/45000]	Loss: 0.1873	LR: 0.100000
Training Epoch: 4 [9984/45000]	Loss: 0.1962	LR: 0.100000
Training Epoch: 4 [10240/45000]	Loss: 0.1240	LR: 0.100000
Training Epoch: 4 [10496/45000]	Loss: 0.1775	LR: 0.100000
Training Epoch: 4 [10752/45000]	Loss: 0.1958	LR: 0.100000
Training Epoch: 4 [11008/45000]	Loss: 0.1765	LR: 0.100000
Training Epoch: 4 [11264/45000]	Loss: 0.1312	LR: 0.100000
Training Epoch: 4 [11520/45000]	Loss: 0.1937	LR: 0.100000
Training Epoch: 4 [11776/45000]	Loss: 0.2006	LR: 0.100000
Training Epoch: 4 [12032/45000]	Loss: 0.1812	LR: 0.100000
Training Epoch: 4 [12288/45000]	Loss: 0.1730	LR: 0.100000
Training Epoch: 4 [12544/45000]	Loss: 0.0955	LR: 0.100000
Training Epoch: 4 [12800/45000]	Loss: 0.1912	LR: 0.100000
Training Epoch: 4 [13056/45000]	Loss: 0.1393	LR: 0.100000
Training Epoch: 4 [13312/45000]	Loss: 0.1335	LR: 0.100000
Training Epoch: 4 [13568/45000]	Loss: 0.1024	LR: 0.100000
Training Epoch: 4 [13824/45000]	Loss: 0.0687	LR: 0.100000
Training Epoch: 4 [14080/45000]	Loss: 0.1870	LR: 0.100000
Training Epoch: 4 [14336/45000]	Loss: 0.1749	LR: 0.100000
Training Epoch: 4 [14592/45000]	Loss: 0.1951	LR: 0.100000
Training Epoch: 4 [14848/45000]	Loss: 0.1332	LR: 0.100000
Training Epoch: 4 [15104/45000]	Loss: 0.1819	LR: 0.100000
Training Epoch: 4 [15360/45000]	Loss: 0.1509	LR: 0.100000
Training Epoch: 4 [15616/45000]	Loss: 0.1886	LR: 0.100000
Training Epoch: 4 [15872/45000]	Loss: 0.1406	LR: 0.100000
Training Epoch: 4 [16128/45000]	Loss: 0.1076	LR: 0.100000
Training Epoch: 4 [16384/45000]	Loss: 0.1229	LR: 0.100000
Training Epoch: 4 [16640/45000]	Loss: 0.1511	LR: 0.100000
Training Epoch: 4 [16896/45000]	Loss: 0.2528	LR: 0.100000
Training Epoch: 4 [17152/45000]	Loss: 0.1236	LR: 0.100000
Training Epoch: 4 [17408/45000]	Loss: 0.1500	LR: 0.100000
Training Epoch: 4 [17664/45000]	Loss: 0.1723	LR: 0.100000
Training Epoch: 4 [17920/45000]	Loss: 0.1576	LR: 0.100000
Training Epoch: 4 [18176/45000]	Loss: 0.2192	LR: 0.100000
Training Epoch: 4 [18432/45000]	Loss: 0.1708	LR: 0.100000
Training Epoch: 4 [18688/45000]	Loss: 0.1818	LR: 0.100000
Training Epoch: 4 [18944/45000]	Loss: 0.1442	LR: 0.100000
Training Epoch: 4 [19200/45000]	Loss: 0.1353	LR: 0.100000
Training Epoch: 4 [19456/45000]	Loss: 0.1665	LR: 0.100000
Training Epoch: 4 [19712/45000]	Loss: 0.1434	LR: 0.100000
Training Epoch: 4 [19968/45000]	Loss: 0.1990	LR: 0.100000
Training Epoch: 4 [20224/45000]	Loss: 0.0851	LR: 0.100000
Training Epoch: 4 [20480/45000]	Loss: 0.0951	LR: 0.100000
Training Epoch: 4 [20736/45000]	Loss: 0.2012	LR: 0.100000
Training Epoch: 4 [20992/45000]	Loss: 0.1142	LR: 0.100000
Training Epoch: 4 [21248/45000]	Loss: 0.1728	LR: 0.100000
Training Epoch: 4 [21504/45000]	Loss: 0.1721	LR: 0.100000
Training Epoch: 4 [21760/45000]	Loss: 0.1496	LR: 0.100000
Training Epoch: 4 [22016/45000]	Loss: 0.2126	LR: 0.100000
Training Epoch: 4 [22272/45000]	Loss: 0.1614	LR: 0.100000
Training Epoch: 4 [22528/45000]	Loss: 0.1636	LR: 0.100000
Training Epoch: 4 [22784/45000]	Loss: 0.1482	LR: 0.100000
Training Epoch: 4 [23040/45000]	Loss: 0.1637	LR: 0.100000
Training Epoch: 4 [23296/45000]	Loss: 0.2400	LR: 0.100000
Training Epoch: 4 [23552/45000]	Loss: 0.0823	LR: 0.100000
Training Epoch: 4 [23808/45000]	Loss: 0.1536	LR: 0.100000
Training Epoch: 4 [24064/45000]	Loss: 0.1903	LR: 0.100000
Training Epoch: 4 [24320/45000]	Loss: 0.1751	LR: 0.100000
Training Epoch: 4 [24576/45000]	Loss: 0.1558	LR: 0.100000
Training Epoch: 4 [24832/45000]	Loss: 0.1748	LR: 0.100000
Training Epoch: 4 [25088/45000]	Loss: 0.1170	LR: 0.100000
Training Epoch: 4 [25344/45000]	Loss: 0.1931	LR: 0.100000
Training Epoch: 4 [25600/45000]	Loss: 0.1327	LR: 0.100000
Training Epoch: 4 [25856/45000]	Loss: 0.1082	LR: 0.100000
Training Epoch: 4 [26112/45000]	Loss: 0.2222	LR: 0.100000
Training Epoch: 4 [26368/45000]	Loss: 0.1562	LR: 0.100000
Training Epoch: 4 [26624/45000]	Loss: 0.1599	LR: 0.100000
Training Epoch: 4 [26880/45000]	Loss: 0.2170	LR: 0.100000
Training Epoch: 4 [27136/45000]	Loss: 0.1257	LR: 0.100000
Training Epoch: 4 [27392/45000]	Loss: 0.1847	LR: 0.100000
Training Epoch: 4 [27648/45000]	Loss: 0.0686	LR: 0.100000
Training Epoch: 4 [27904/45000]	Loss: 0.1563	LR: 0.100000
Training Epoch: 4 [28160/45000]	Loss: 0.1978	LR: 0.100000
Training Epoch: 4 [28416/45000]	Loss: 0.1711	LR: 0.100000
Training Epoch: 4 [28672/45000]	Loss: 0.1172	LR: 0.100000
Training Epoch: 4 [28928/45000]	Loss: 0.1439	LR: 0.100000
Training Epoch: 4 [29184/45000]	Loss: 0.1074	LR: 0.100000
Training Epoch: 4 [29440/45000]	Loss: 0.1048	LR: 0.100000
Training Epoch: 4 [29696/45000]	Loss: 0.1309	LR: 0.100000
Training Epoch: 4 [29952/45000]	Loss: 0.2122	LR: 0.100000
Training Epoch: 4 [30208/45000]	Loss: 0.1091	LR: 0.100000
Training Epoch: 4 [30464/45000]	Loss: 0.1419	LR: 0.100000
Training Epoch: 4 [30720/45000]	Loss: 0.1231	LR: 0.100000
Training Epoch: 4 [30976/45000]	Loss: 0.2779	LR: 0.100000
Training Epoch: 4 [31232/45000]	Loss: 0.1044	LR: 0.100000
Training Epoch: 4 [31488/45000]	Loss: 0.2188	LR: 0.100000
Training Epoch: 4 [31744/45000]	Loss: 0.2752	LR: 0.100000
Training Epoch: 4 [32000/45000]	Loss: 0.2163	LR: 0.100000
Training Epoch: 4 [32256/45000]	Loss: 0.1785	LR: 0.100000
Training Epoch: 4 [32512/45000]	Loss: 0.2996	LR: 0.100000
Training Epoch: 4 [32768/45000]	Loss: 0.1234	LR: 0.100000
Training Epoch: 4 [33024/45000]	Loss: 0.1588	LR: 0.100000
Training Epoch: 4 [33280/45000]	Loss: 0.2586	LR: 0.100000
Training Epoch: 4 [33536/45000]	Loss: 0.1395	LR: 0.100000
Training Epoch: 4 [33792/45000]	Loss: 0.1928	LR: 0.100000
Training Epoch: 4 [34048/45000]	Loss: 0.0952	LR: 0.100000
Training Epoch: 4 [34304/45000]	Loss: 0.2915	LR: 0.100000
Training Epoch: 4 [34560/45000]	Loss: 0.0874	LR: 0.100000
Training Epoch: 4 [34816/45000]	Loss: 0.1918	LR: 0.100000
Training Epoch: 4 [35072/45000]	Loss: 0.1257	LR: 0.100000
Training Epoch: 4 [35328/45000]	Loss: 0.1186	LR: 0.100000
Training Epoch: 4 [35584/45000]	Loss: 0.0937	LR: 0.100000
Training Epoch: 4 [35840/45000]	Loss: 0.1878	LR: 0.100000
Training Epoch: 4 [36096/45000]	Loss: 0.1205	LR: 0.100000
Training Epoch: 4 [36352/45000]	Loss: 0.1880	LR: 0.100000
Training Epoch: 4 [36608/45000]	Loss: 0.1890	LR: 0.100000
Training Epoch: 4 [36864/45000]	Loss: 0.0777	LR: 0.100000
Training Epoch: 4 [37120/45000]	Loss: 0.1660	LR: 0.100000
Training Epoch: 4 [37376/45000]	Loss: 0.1713	LR: 0.100000
Training Epoch: 4 [37632/45000]	Loss: 0.2639	LR: 0.100000
Training Epoch: 4 [37888/45000]	Loss: 0.1588	LR: 0.100000
Training Epoch: 4 [38144/45000]	Loss: 0.1386	LR: 0.100000
Training Epoch: 4 [38400/45000]	Loss: 0.1834	LR: 0.100000
Training Epoch: 4 [38656/45000]	Loss: 0.1040	LR: 0.100000
Training Epoch: 4 [38912/45000]	Loss: 0.1676	LR: 0.100000
Training Epoch: 4 [39168/45000]	Loss: 0.1393	LR: 0.100000
Training Epoch: 4 [39424/45000]	Loss: 0.1047	LR: 0.100000
Training Epoch: 4 [39680/45000]	Loss: 0.1749	LR: 0.100000
Training Epoch: 4 [39936/45000]	Loss: 0.1603	LR: 0.100000
Training Epoch: 4 [40192/45000]	Loss: 0.1473	LR: 0.100000
Training Epoch: 4 [40448/45000]	Loss: 0.2437	LR: 0.100000
Training Epoch: 4 [40704/45000]	Loss: 0.1204	LR: 0.100000
Training Epoch: 4 [40960/45000]	Loss: 0.0827	LR: 0.100000
Training Epoch: 4 [41216/45000]	Loss: 0.1652	LR: 0.100000
Training Epoch: 4 [41472/45000]	Loss: 0.1837	LR: 0.100000
Training Epoch: 4 [41728/45000]	Loss: 0.0994	LR: 0.100000
Training Epoch: 4 [41984/45000]	Loss: 0.1546	LR: 0.100000
Training Epoch: 4 [42240/45000]	Loss: 0.1781	LR: 0.100000
Training Epoch: 4 [42496/45000]	Loss: 0.1530	LR: 0.100000
Training Epoch: 4 [42752/45000]	Loss: 0.1813	LR: 0.100000
Training Epoch: 4 [43008/45000]	Loss: 0.1627	LR: 0.100000
Training Epoch: 4 [43264/45000]	Loss: 0.1118	LR: 0.100000
Training Epoch: 4 [43520/45000]	Loss: 0.1191	LR: 0.100000
Training Epoch: 4 [43776/45000]	Loss: 0.0814	LR: 0.100000
Training Epoch: 4 [44032/45000]	Loss: 0.1005	LR: 0.100000
Training Epoch: 4 [44288/45000]	Loss: 0.1759	LR: 0.100000
Training Epoch: 4 [44544/45000]	Loss: 0.1514	LR: 0.100000
Training Epoch: 4 [44800/45000]	Loss: 0.1230	LR: 0.100000
Training Epoch: 4 [45000/45000]	Loss: 0.0996	LR: 0.100000
Epoch 4 - Average Train Loss: 0.1558, Train Accuracy: 0.9460
Epoch 4 training time consumed: 324.76s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0006, Accuracy: 0.9507, Time consumed:23.48s
Training Epoch: 5 [256/45000]	Loss: 0.1759	LR: 0.100000
Training Epoch: 5 [512/45000]	Loss: 0.0801	LR: 0.100000
Training Epoch: 5 [768/45000]	Loss: 0.1991	LR: 0.100000
Training Epoch: 5 [1024/45000]	Loss: 0.2390	LR: 0.100000
Training Epoch: 5 [1280/45000]	Loss: 0.1015	LR: 0.100000
Training Epoch: 5 [1536/45000]	Loss: 0.1849	LR: 0.100000
Training Epoch: 5 [1792/45000]	Loss: 0.2227	LR: 0.100000
Training Epoch: 5 [2048/45000]	Loss: 0.1977	LR: 0.100000
Training Epoch: 5 [2304/45000]	Loss: 0.1259	LR: 0.100000
Training Epoch: 5 [2560/45000]	Loss: 0.0844	LR: 0.100000
Training Epoch: 5 [2816/45000]	Loss: 0.2613	LR: 0.100000
Training Epoch: 5 [3072/45000]	Loss: 0.1836	LR: 0.100000
Training Epoch: 5 [3328/45000]	Loss: 0.1758	LR: 0.100000
Training Epoch: 5 [3584/45000]	Loss: 0.2518	LR: 0.100000
Training Epoch: 5 [3840/45000]	Loss: 0.1719	LR: 0.100000
Training Epoch: 5 [4096/45000]	Loss: 0.1060	LR: 0.100000
Training Epoch: 5 [4352/45000]	Loss: 0.1472	LR: 0.100000
Training Epoch: 5 [4608/45000]	Loss: 0.1627	LR: 0.100000
Training Epoch: 5 [4864/45000]	Loss: 0.1041	LR: 0.100000
Training Epoch: 5 [5120/45000]	Loss: 0.1589	LR: 0.100000
Training Epoch: 5 [5376/45000]	Loss: 0.1077	LR: 0.100000
Training Epoch: 5 [5632/45000]	Loss: 0.1809	LR: 0.100000
Training Epoch: 5 [5888/45000]	Loss: 0.1516	LR: 0.100000
Training Epoch: 5 [6144/45000]	Loss: 0.1271	LR: 0.100000
Training Epoch: 5 [6400/45000]	Loss: 0.1370	LR: 0.100000
Training Epoch: 5 [6656/45000]	Loss: 0.1083	LR: 0.100000
Training Epoch: 5 [6912/45000]	Loss: 0.1915	LR: 0.100000
Training Epoch: 5 [7168/45000]	Loss: 0.1183	LR: 0.100000
Training Epoch: 5 [7424/45000]	Loss: 0.1147	LR: 0.100000
Training Epoch: 5 [7680/45000]	Loss: 0.1397	LR: 0.100000
Training Epoch: 5 [7936/45000]	Loss: 0.1875	LR: 0.100000
Training Epoch: 5 [8192/45000]	Loss: 0.1206	LR: 0.100000
Training Epoch: 5 [8448/45000]	Loss: 0.0871	LR: 0.100000
Training Epoch: 5 [8704/45000]	Loss: 0.1891	LR: 0.100000
Training Epoch: 5 [8960/45000]	Loss: 0.1847	LR: 0.100000
Training Epoch: 5 [9216/45000]	Loss: 0.1902	LR: 0.100000
Training Epoch: 5 [9472/45000]	Loss: 0.1550	LR: 0.100000
Training Epoch: 5 [9728/45000]	Loss: 0.1708	LR: 0.100000
Training Epoch: 5 [9984/45000]	Loss: 0.1451	LR: 0.100000
Training Epoch: 5 [10240/45000]	Loss: 0.1191	LR: 0.100000
Training Epoch: 5 [10496/45000]	Loss: 0.1954	LR: 0.100000
Training Epoch: 5 [10752/45000]	Loss: 0.0997	LR: 0.100000
Training Epoch: 5 [11008/45000]	Loss: 0.1533	LR: 0.100000
Training Epoch: 5 [11264/45000]	Loss: 0.1343	LR: 0.100000
Training Epoch: 5 [11520/45000]	Loss: 0.1183	LR: 0.100000
Training Epoch: 5 [11776/45000]	Loss: 0.0931	LR: 0.100000
Training Epoch: 5 [12032/45000]	Loss: 0.1009	LR: 0.100000
Training Epoch: 5 [12288/45000]	Loss: 0.1610	LR: 0.100000
Training Epoch: 5 [12544/45000]	Loss: 0.1250	LR: 0.100000
Training Epoch: 5 [12800/45000]	Loss: 0.0969	LR: 0.100000
Training Epoch: 5 [13056/45000]	Loss: 0.1980	LR: 0.100000
Training Epoch: 5 [13312/45000]	Loss: 0.1516	LR: 0.100000
Training Epoch: 5 [13568/45000]	Loss: 0.1524	LR: 0.100000
Training Epoch: 5 [13824/45000]	Loss: 0.2146	LR: 0.100000
Training Epoch: 5 [14080/45000]	Loss: 0.1722	LR: 0.100000
Training Epoch: 5 [14336/45000]	Loss: 0.1259	LR: 0.100000
Training Epoch: 5 [14592/45000]	Loss: 0.1224	LR: 0.100000
Training Epoch: 5 [14848/45000]	Loss: 0.1784	LR: 0.100000
Training Epoch: 5 [15104/45000]	Loss: 0.1136	LR: 0.100000
Training Epoch: 5 [15360/45000]	Loss: 0.0818	LR: 0.100000
Training Epoch: 5 [15616/45000]	Loss: 0.1574	LR: 0.100000
Training Epoch: 5 [15872/45000]	Loss: 0.2315	LR: 0.100000
Training Epoch: 5 [16128/45000]	Loss: 0.1596	LR: 0.100000
Training Epoch: 5 [16384/45000]	Loss: 0.1608	LR: 0.100000
Training Epoch: 5 [16640/45000]	Loss: 0.0804	LR: 0.100000
Training Epoch: 5 [16896/45000]	Loss: 0.1647	LR: 0.100000
Training Epoch: 5 [17152/45000]	Loss: 0.1693	LR: 0.100000
Training Epoch: 5 [17408/45000]	Loss: 0.1891	LR: 0.100000
Training Epoch: 5 [17664/45000]	Loss: 0.1369	LR: 0.100000
Training Epoch: 5 [17920/45000]	Loss: 0.1505	LR: 0.100000
Training Epoch: 5 [18176/45000]	Loss: 0.1659	LR: 0.100000
Training Epoch: 5 [18432/45000]	Loss: 0.1225	LR: 0.100000
Training Epoch: 5 [18688/45000]	Loss: 0.1696	LR: 0.100000
Training Epoch: 5 [18944/45000]	Loss: 0.1726	LR: 0.100000
Training Epoch: 5 [19200/45000]	Loss: 0.1413	LR: 0.100000
Training Epoch: 5 [19456/45000]	Loss: 0.1588	LR: 0.100000
Training Epoch: 5 [19712/45000]	Loss: 0.1001	LR: 0.100000
Training Epoch: 5 [19968/45000]	Loss: 0.1229	LR: 0.100000
Training Epoch: 5 [20224/45000]	Loss: 0.1772	LR: 0.100000
Training Epoch: 5 [20480/45000]	Loss: 0.1323	LR: 0.100000
Training Epoch: 5 [20736/45000]	Loss: 0.1281	LR: 0.100000
Training Epoch: 5 [20992/45000]	Loss: 0.1757	LR: 0.100000
Training Epoch: 5 [21248/45000]	Loss: 0.1562	LR: 0.100000
Training Epoch: 5 [21504/45000]	Loss: 0.1402	LR: 0.100000
Training Epoch: 5 [21760/45000]	Loss: 0.1847	LR: 0.100000
Training Epoch: 5 [22016/45000]	Loss: 0.1161	LR: 0.100000
Training Epoch: 5 [22272/45000]	Loss: 0.1675	LR: 0.100000
Training Epoch: 5 [22528/45000]	Loss: 0.1662	LR: 0.100000
Training Epoch: 5 [22784/45000]	Loss: 0.1908	LR: 0.100000
Training Epoch: 5 [23040/45000]	Loss: 0.1086	LR: 0.100000
Training Epoch: 5 [23296/45000]	Loss: 0.1450	LR: 0.100000
Training Epoch: 5 [23552/45000]	Loss: 0.2434	LR: 0.100000
Training Epoch: 5 [23808/45000]	Loss: 0.1791	LR: 0.100000
Training Epoch: 5 [24064/45000]	Loss: 0.1461	LR: 0.100000
Training Epoch: 5 [24320/45000]	Loss: 0.1465	LR: 0.100000
Training Epoch: 5 [24576/45000]	Loss: 0.2453	LR: 0.100000
Training Epoch: 5 [24832/45000]	Loss: 0.1102	LR: 0.100000
Training Epoch: 5 [25088/45000]	Loss: 0.1241	LR: 0.100000
Training Epoch: 5 [25344/45000]	Loss: 0.1562	LR: 0.100000
Training Epoch: 5 [25600/45000]	Loss: 0.1842	LR: 0.100000
Training Epoch: 5 [25856/45000]	Loss: 0.0878	LR: 0.100000
Training Epoch: 5 [26112/45000]	Loss: 0.1111	LR: 0.100000
Training Epoch: 5 [26368/45000]	Loss: 0.0902	LR: 0.100000
Training Epoch: 5 [26624/45000]	Loss: 0.1422	LR: 0.100000
Training Epoch: 5 [26880/45000]	Loss: 0.1472	LR: 0.100000
Training Epoch: 5 [27136/45000]	Loss: 0.1014	LR: 0.100000
Training Epoch: 5 [27392/45000]	Loss: 0.1642	LR: 0.100000
Training Epoch: 5 [27648/45000]	Loss: 0.0363	LR: 0.100000
Training Epoch: 5 [27904/45000]	Loss: 0.1483	LR: 0.100000
Training Epoch: 5 [28160/45000]	Loss: 0.1571	LR: 0.100000
Training Epoch: 5 [28416/45000]	Loss: 0.1116	LR: 0.100000
Training Epoch: 5 [28672/45000]	Loss: 0.1149	LR: 0.100000
Training Epoch: 5 [28928/45000]	Loss: 0.1981	LR: 0.100000
Training Epoch: 5 [29184/45000]	Loss: 0.1663	LR: 0.100000
Training Epoch: 5 [29440/45000]	Loss: 0.1541	LR: 0.100000
Training Epoch: 5 [29696/45000]	Loss: 0.1393	LR: 0.100000
Training Epoch: 5 [29952/45000]	Loss: 0.1053	LR: 0.100000
Training Epoch: 5 [30208/45000]	Loss: 0.2262	LR: 0.100000
Training Epoch: 5 [30464/45000]	Loss: 0.1352	LR: 0.100000
Training Epoch: 5 [30720/45000]	Loss: 0.2706	LR: 0.100000
Training Epoch: 5 [30976/45000]	Loss: 0.1283	LR: 0.100000
Training Epoch: 5 [31232/45000]	Loss: 0.1606	LR: 0.100000
Training Epoch: 5 [31488/45000]	Loss: 0.1655	LR: 0.100000
Training Epoch: 5 [31744/45000]	Loss: 0.1956	LR: 0.100000
Training Epoch: 5 [32000/45000]	Loss: 0.1705	LR: 0.100000
Training Epoch: 5 [32256/45000]	Loss: 0.1572	LR: 0.100000
Training Epoch: 5 [32512/45000]	Loss: 0.1015	LR: 0.100000
Training Epoch: 5 [32768/45000]	Loss: 0.1529	LR: 0.100000
Training Epoch: 5 [33024/45000]	Loss: 0.2169	LR: 0.100000
Training Epoch: 5 [33280/45000]	Loss: 0.1802	LR: 0.100000
Training Epoch: 5 [33536/45000]	Loss: 0.2090	LR: 0.100000
Training Epoch: 5 [33792/45000]	Loss: 0.2248	LR: 0.100000
Training Epoch: 5 [34048/45000]	Loss: 0.1721	LR: 0.100000
Training Epoch: 5 [34304/45000]	Loss: 0.1368	LR: 0.100000
Training Epoch: 5 [34560/45000]	Loss: 0.1457	LR: 0.100000
Training Epoch: 5 [34816/45000]	Loss: 0.1909	LR: 0.100000
Training Epoch: 5 [35072/45000]	Loss: 0.2067	LR: 0.100000
Training Epoch: 5 [35328/45000]	Loss: 0.1672	LR: 0.100000
Training Epoch: 5 [35584/45000]	Loss: 0.1189	LR: 0.100000
Training Epoch: 5 [35840/45000]	Loss: 0.1594	LR: 0.100000
Training Epoch: 5 [36096/45000]	Loss: 0.1212	LR: 0.100000
Training Epoch: 5 [36352/45000]	Loss: 0.1392	LR: 0.100000
Training Epoch: 5 [36608/45000]	Loss: 0.1386	LR: 0.100000
Training Epoch: 5 [36864/45000]	Loss: 0.1594	LR: 0.100000
Training Epoch: 5 [37120/45000]	Loss: 0.1564	LR: 0.100000
Training Epoch: 5 [37376/45000]	Loss: 0.1606	LR: 0.100000
Training Epoch: 5 [37632/45000]	Loss: 0.2378	LR: 0.100000
Training Epoch: 5 [37888/45000]	Loss: 0.1045	LR: 0.100000
Training Epoch: 5 [38144/45000]	Loss: 0.1935	LR: 0.100000
Training Epoch: 5 [38400/45000]	Loss: 0.2934	LR: 0.100000
Training Epoch: 5 [38656/45000]	Loss: 0.1475	LR: 0.100000
Training Epoch: 5 [38912/45000]	Loss: 0.1662	LR: 0.100000
Training Epoch: 5 [39168/45000]	Loss: 0.1929	LR: 0.100000
Training Epoch: 5 [39424/45000]	Loss: 0.2873	LR: 0.100000
Training Epoch: 5 [39680/45000]	Loss: 0.2282	LR: 0.100000
Training Epoch: 5 [39936/45000]	Loss: 0.0946	LR: 0.100000
Training Epoch: 5 [40192/45000]	Loss: 0.2278	LR: 0.100000
Training Epoch: 5 [40448/45000]	Loss: 0.2111	LR: 0.100000
Training Epoch: 5 [40704/45000]	Loss: 0.2859	LR: 0.100000
Training Epoch: 5 [40960/45000]	Loss: 0.1681	LR: 0.100000
Training Epoch: 5 [41216/45000]	Loss: 0.1532	LR: 0.100000
Training Epoch: 5 [41472/45000]	Loss: 0.1754	LR: 0.100000
Training Epoch: 5 [41728/45000]	Loss: 0.1899	LR: 0.100000
Training Epoch: 5 [41984/45000]	Loss: 0.1582	LR: 0.100000
Training Epoch: 5 [42240/45000]	Loss: 0.1771	LR: 0.100000
Training Epoch: 5 [42496/45000]	Loss: 0.1594	LR: 0.100000
Training Epoch: 5 [42752/45000]	Loss: 0.1071	LR: 0.100000
Training Epoch: 5 [43008/45000]	Loss: 0.1139	LR: 0.100000
Training Epoch: 5 [43264/45000]	Loss: 0.2341	LR: 0.100000
Training Epoch: 5 [43520/45000]	Loss: 0.2191	LR: 0.100000
Training Epoch: 5 [43776/45000]	Loss: 0.1595	LR: 0.100000
Training Epoch: 5 [44032/45000]	Loss: 0.1798	LR: 0.100000
Training Epoch: 5 [44288/45000]	Loss: 0.1503	LR: 0.100000
Training Epoch: 5 [44544/45000]	Loss: 0.2552	LR: 0.100000
Training Epoch: 5 [44800/45000]	Loss: 0.2530	LR: 0.100000
Training Epoch: 5 [45000/45000]	Loss: 0.1815	LR: 0.100000
Epoch 5 - Average Train Loss: 0.1595, Train Accuracy: 0.9456
Epoch 5 training time consumed: 324.42s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0008, Accuracy: 0.9324, Time consumed:23.47s
Training Epoch: 6 [256/45000]	Loss: 0.2044	LR: 0.100000
Training Epoch: 6 [512/45000]	Loss: 0.1632	LR: 0.100000
Training Epoch: 6 [768/45000]	Loss: 0.1461	LR: 0.100000
Training Epoch: 6 [1024/45000]	Loss: 0.1292	LR: 0.100000
Training Epoch: 6 [1280/45000]	Loss: 0.0785	LR: 0.100000
Training Epoch: 6 [1536/45000]	Loss: 0.1158	LR: 0.100000
Training Epoch: 6 [1792/45000]	Loss: 0.1924	LR: 0.100000
Training Epoch: 6 [2048/45000]	Loss: 0.1058	LR: 0.100000
Training Epoch: 6 [2304/45000]	Loss: 0.1151	LR: 0.100000
Training Epoch: 6 [2560/45000]	Loss: 0.1341	LR: 0.100000
Training Epoch: 6 [2816/45000]	Loss: 0.1828	LR: 0.100000
Training Epoch: 6 [3072/45000]	Loss: 0.0949	LR: 0.100000
Training Epoch: 6 [3328/45000]	Loss: 0.0782	LR: 0.100000
Training Epoch: 6 [3584/45000]	Loss: 0.0910	LR: 0.100000
Training Epoch: 6 [3840/45000]	Loss: 0.1061	LR: 0.100000
Training Epoch: 6 [4096/45000]	Loss: 0.1383	LR: 0.100000
Training Epoch: 6 [4352/45000]	Loss: 0.1739	LR: 0.100000
Training Epoch: 6 [4608/45000]	Loss: 0.1725	LR: 0.100000
Training Epoch: 6 [4864/45000]	Loss: 0.1539	LR: 0.100000
Training Epoch: 6 [5120/45000]	Loss: 0.1166	LR: 0.100000
Training Epoch: 6 [5376/45000]	Loss: 0.2125	LR: 0.100000
Training Epoch: 6 [5632/45000]	Loss: 0.1506	LR: 0.100000
Training Epoch: 6 [5888/45000]	Loss: 0.2442	LR: 0.100000
Training Epoch: 6 [6144/45000]	Loss: 0.1722	LR: 0.100000
Training Epoch: 6 [6400/45000]	Loss: 0.2078	LR: 0.100000
Training Epoch: 6 [6656/45000]	Loss: 0.1119	LR: 0.100000
Training Epoch: 6 [6912/45000]	Loss: 0.1328	LR: 0.100000
Training Epoch: 6 [7168/45000]	Loss: 0.1379	LR: 0.100000
Training Epoch: 6 [7424/45000]	Loss: 0.1817	LR: 0.100000
Training Epoch: 6 [7680/45000]	Loss: 0.2319	LR: 0.100000
Training Epoch: 6 [7936/45000]	Loss: 0.1461	LR: 0.100000
Training Epoch: 6 [8192/45000]	Loss: 0.1666	LR: 0.100000
Training Epoch: 6 [8448/45000]	Loss: 0.1429	LR: 0.100000
Training Epoch: 6 [8704/45000]	Loss: 0.1283	LR: 0.100000
Training Epoch: 6 [8960/45000]	Loss: 0.1210	LR: 0.100000
Training Epoch: 6 [9216/45000]	Loss: 0.1339	LR: 0.100000
Training Epoch: 6 [9472/45000]	Loss: 0.1172	LR: 0.100000
Training Epoch: 6 [9728/45000]	Loss: 0.1576	LR: 0.100000
Training Epoch: 6 [9984/45000]	Loss: 0.1806	LR: 0.100000
Training Epoch: 6 [10240/45000]	Loss: 0.1677	LR: 0.100000
Training Epoch: 6 [10496/45000]	Loss: 0.0873	LR: 0.100000
Training Epoch: 6 [10752/45000]	Loss: 0.1812	LR: 0.100000
Training Epoch: 6 [11008/45000]	Loss: 0.1175	LR: 0.100000
Training Epoch: 6 [11264/45000]	Loss: 0.1541	LR: 0.100000
Training Epoch: 6 [11520/45000]	Loss: 0.1425	LR: 0.100000
Training Epoch: 6 [11776/45000]	Loss: 0.1715	LR: 0.100000
Training Epoch: 6 [12032/45000]	Loss: 0.2022	LR: 0.100000
Training Epoch: 6 [12288/45000]	Loss: 0.1541	LR: 0.100000
Training Epoch: 6 [12544/45000]	Loss: 0.1495	LR: 0.100000
Training Epoch: 6 [12800/45000]	Loss: 0.2314	LR: 0.100000
Training Epoch: 6 [13056/45000]	Loss: 0.1514	LR: 0.100000
Training Epoch: 6 [13312/45000]	Loss: 0.1226	LR: 0.100000
Training Epoch: 6 [13568/45000]	Loss: 0.1508	LR: 0.100000
Training Epoch: 6 [13824/45000]	Loss: 0.1612	LR: 0.100000
Training Epoch: 6 [14080/45000]	Loss: 0.1817	LR: 0.100000
Training Epoch: 6 [14336/45000]	Loss: 0.1415	LR: 0.100000
Training Epoch: 6 [14592/45000]	Loss: 0.2303	LR: 0.100000
Training Epoch: 6 [14848/45000]	Loss: 0.2255	LR: 0.100000
Training Epoch: 6 [15104/45000]	Loss: 0.1369	LR: 0.100000
Training Epoch: 6 [15360/45000]	Loss: 0.0926	LR: 0.100000
Training Epoch: 6 [15616/45000]	Loss: 0.3569	LR: 0.100000
Training Epoch: 6 [15872/45000]	Loss: 0.2173	LR: 0.100000
Training Epoch: 6 [16128/45000]	Loss: 0.1334	LR: 0.100000
Training Epoch: 6 [16384/45000]	Loss: 0.2625	LR: 0.100000
Training Epoch: 6 [16640/45000]	Loss: 0.1776	LR: 0.100000
Training Epoch: 6 [16896/45000]	Loss: 0.1788	LR: 0.100000
Training Epoch: 6 [17152/45000]	Loss: 0.1985	LR: 0.100000
Training Epoch: 6 [17408/45000]	Loss: 0.2545	LR: 0.100000
Training Epoch: 6 [17664/45000]	Loss: 0.1852	LR: 0.100000
Training Epoch: 6 [17920/45000]	Loss: 0.0959	LR: 0.100000
Training Epoch: 6 [18176/45000]	Loss: 0.1535	LR: 0.100000
Training Epoch: 6 [18432/45000]	Loss: 0.1339	LR: 0.100000
Training Epoch: 6 [18688/45000]	Loss: 0.1677	LR: 0.100000
Training Epoch: 6 [18944/45000]	Loss: 0.1254	LR: 0.100000
Training Epoch: 6 [19200/45000]	Loss: 0.1863	LR: 0.100000
Training Epoch: 6 [19456/45000]	Loss: 0.1548	LR: 0.100000
Training Epoch: 6 [19712/45000]	Loss: 0.1510	LR: 0.100000
Training Epoch: 6 [19968/45000]	Loss: 0.2196	LR: 0.100000
Training Epoch: 6 [20224/45000]	Loss: 0.1670	LR: 0.100000
Training Epoch: 6 [20480/45000]	Loss: 0.2697	LR: 0.100000
Training Epoch: 6 [20736/45000]	Loss: 0.1306	LR: 0.100000
Training Epoch: 6 [20992/45000]	Loss: 0.3595	LR: 0.100000
Training Epoch: 6 [21248/45000]	Loss: 0.3600	LR: 0.100000
Training Epoch: 6 [21504/45000]	Loss: 0.4589	LR: 0.100000
Training Epoch: 6 [21760/45000]	Loss: 0.0986	LR: 0.100000
Training Epoch: 6 [22016/45000]	Loss: 0.2753	LR: 0.100000
Training Epoch: 6 [22272/45000]	Loss: 0.3829	LR: 0.100000
Training Epoch: 6 [22528/45000]	Loss: 0.3895	LR: 0.100000
Training Epoch: 6 [22784/45000]	Loss: 0.2790	LR: 0.100000
Training Epoch: 6 [23040/45000]	Loss: 0.2531	LR: 0.100000
Training Epoch: 6 [23296/45000]	Loss: 0.1943	LR: 0.100000
Training Epoch: 6 [23552/45000]	Loss: 0.1894	LR: 0.100000
Training Epoch: 6 [23808/45000]	Loss: 0.2092	LR: 0.100000
Training Epoch: 6 [24064/45000]	Loss: 0.2121	LR: 0.100000
Training Epoch: 6 [24320/45000]	Loss: 0.1971	LR: 0.100000
Training Epoch: 6 [24576/45000]	Loss: 0.2428	LR: 0.100000
Training Epoch: 6 [24832/45000]	Loss: 0.1834	LR: 0.100000
Training Epoch: 6 [25088/45000]	Loss: 0.1288	LR: 0.100000
Training Epoch: 6 [25344/45000]	Loss: 0.2702	LR: 0.100000
Training Epoch: 6 [25600/45000]	Loss: 0.2482	LR: 0.100000
Training Epoch: 6 [25856/45000]	Loss: 0.2330	LR: 0.100000
Training Epoch: 6 [26112/45000]	Loss: 0.3788	LR: 0.100000
Training Epoch: 6 [26368/45000]	Loss: 0.2753	LR: 0.100000
Training Epoch: 6 [26624/45000]	Loss: 0.2395	LR: 0.100000
Training Epoch: 6 [26880/45000]	Loss: 0.2492	LR: 0.100000
Training Epoch: 6 [27136/45000]	Loss: 0.2587	LR: 0.100000
Training Epoch: 6 [27392/45000]	Loss: 0.2224	LR: 0.100000
Training Epoch: 6 [27648/45000]	Loss: 0.1888	LR: 0.100000
Training Epoch: 6 [27904/45000]	Loss: 0.2489	LR: 0.100000
Training Epoch: 6 [28160/45000]	Loss: 0.1561	LR: 0.100000
Training Epoch: 6 [28416/45000]	Loss: 0.2288	LR: 0.100000
Training Epoch: 6 [28672/45000]	Loss: 0.1987	LR: 0.100000
Training Epoch: 6 [28928/45000]	Loss: 0.1645	LR: 0.100000
Training Epoch: 6 [29184/45000]	Loss: 0.1500	LR: 0.100000
Training Epoch: 6 [29440/45000]	Loss: 0.1680	LR: 0.100000
Training Epoch: 6 [29696/45000]	Loss: 0.1526	LR: 0.100000
Training Epoch: 6 [29952/45000]	Loss: 0.3179	LR: 0.100000
Training Epoch: 6 [30208/45000]	Loss: 0.2249	LR: 0.100000
Training Epoch: 6 [30464/45000]	Loss: 0.2126	LR: 0.100000
Training Epoch: 6 [30720/45000]	Loss: 0.2873	LR: 0.100000
Training Epoch: 6 [30976/45000]	Loss: 0.1975	LR: 0.100000
Training Epoch: 6 [31232/45000]	Loss: 0.2184	LR: 0.100000
Training Epoch: 6 [31488/45000]	Loss: 0.2598	LR: 0.100000
Training Epoch: 6 [31744/45000]	Loss: 0.2243	LR: 0.100000
Training Epoch: 6 [32000/45000]	Loss: 0.1912	LR: 0.100000
Training Epoch: 6 [32256/45000]	Loss: 0.2615	LR: 0.100000
Training Epoch: 6 [32512/45000]	Loss: 0.2591	LR: 0.100000
Training Epoch: 6 [32768/45000]	Loss: 0.2437	LR: 0.100000
Training Epoch: 6 [33024/45000]	Loss: 0.2656	LR: 0.100000
Training Epoch: 6 [33280/45000]	Loss: 0.2611	LR: 0.100000
Training Epoch: 6 [33536/45000]	Loss: 0.2589	LR: 0.100000
Training Epoch: 6 [33792/45000]	Loss: 0.1999	LR: 0.100000
Training Epoch: 6 [34048/45000]	Loss: 0.2016	LR: 0.100000
Training Epoch: 6 [34304/45000]	Loss: 0.2274	LR: 0.100000
Training Epoch: 6 [34560/45000]	Loss: 0.2398	LR: 0.100000
Training Epoch: 6 [34816/45000]	Loss: 0.1825	LR: 0.100000
Training Epoch: 6 [35072/45000]	Loss: 0.1796	LR: 0.100000
Training Epoch: 6 [35328/45000]	Loss: 0.1682	LR: 0.100000
Training Epoch: 6 [35584/45000]	Loss: 0.1515	LR: 0.100000
Training Epoch: 6 [35840/45000]	Loss: 0.2540	LR: 0.100000
Training Epoch: 6 [36096/45000]	Loss: 0.1226	LR: 0.100000
Training Epoch: 6 [36352/45000]	Loss: 0.1485	LR: 0.100000
Training Epoch: 6 [36608/45000]	Loss: 0.1505	LR: 0.100000
Training Epoch: 6 [36864/45000]	Loss: 0.2186	LR: 0.100000
Training Epoch: 6 [37120/45000]	Loss: 0.1834	LR: 0.100000
Training Epoch: 6 [37376/45000]	Loss: 0.2104	LR: 0.100000
Training Epoch: 6 [37632/45000]	Loss: 0.1590	LR: 0.100000
Training Epoch: 6 [37888/45000]	Loss: 0.1813	LR: 0.100000
Training Epoch: 6 [38144/45000]	Loss: 0.3188	LR: 0.100000
Training Epoch: 6 [38400/45000]	Loss: 0.2568	LR: 0.100000
Training Epoch: 6 [38656/45000]	Loss: 0.1139	LR: 0.100000
Training Epoch: 6 [38912/45000]	Loss: 0.1593	LR: 0.100000
Training Epoch: 6 [39168/45000]	Loss: 0.1755	LR: 0.100000
Training Epoch: 6 [39424/45000]	Loss: 0.1683	LR: 0.100000
Training Epoch: 6 [39680/45000]	Loss: 0.0940	LR: 0.100000
Training Epoch: 6 [39936/45000]	Loss: 0.1006	LR: 0.100000
Training Epoch: 6 [40192/45000]	Loss: 0.1932	LR: 0.100000
Training Epoch: 6 [40448/45000]	Loss: 0.1295	LR: 0.100000
Training Epoch: 6 [40704/45000]	Loss: 0.1263	LR: 0.100000
Training Epoch: 6 [40960/45000]	Loss: 0.1292	LR: 0.100000
Training Epoch: 6 [41216/45000]	Loss: 0.1155	LR: 0.100000
Training Epoch: 6 [41472/45000]	Loss: 0.1691	LR: 0.100000
Training Epoch: 6 [41728/45000]	Loss: 0.1803	LR: 0.100000
Training Epoch: 6 [41984/45000]	Loss: 0.1516	LR: 0.100000
Training Epoch: 6 [42240/45000]	Loss: 0.1231	LR: 0.100000
Training Epoch: 6 [42496/45000]	Loss: 0.0918	LR: 0.100000
Training Epoch: 6 [42752/45000]	Loss: 0.2586	LR: 0.100000
Training Epoch: 6 [43008/45000]	Loss: 0.1353	LR: 0.100000
Training Epoch: 6 [43264/45000]	Loss: 0.1759	LR: 0.100000
Training Epoch: 6 [43520/45000]	Loss: 0.1425	LR: 0.100000
Training Epoch: 6 [43776/45000]	Loss: 0.3328	LR: 0.100000
Training Epoch: 6 [44032/45000]	Loss: 0.1504	LR: 0.100000
Training Epoch: 6 [44288/45000]	Loss: 0.1504	LR: 0.100000
Training Epoch: 6 [44544/45000]	Loss: 0.2030	LR: 0.100000
Training Epoch: 6 [44800/45000]	Loss: 0.1938	LR: 0.100000
Training Epoch: 6 [45000/45000]	Loss: 0.1633	LR: 0.100000
Epoch 6 - Average Train Loss: 0.1878, Train Accuracy: 0.9356
Epoch 6 training time consumed: 324.71s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0008, Accuracy: 0.9246, Time consumed:23.44s
Training Epoch: 7 [256/45000]	Loss: 0.1929	LR: 0.020000
Training Epoch: 7 [512/45000]	Loss: 0.1610	LR: 0.020000
Training Epoch: 7 [768/45000]	Loss: 0.1749	LR: 0.020000
Training Epoch: 7 [1024/45000]	Loss: 0.0990	LR: 0.020000
Training Epoch: 7 [1280/45000]	Loss: 0.1558	LR: 0.020000
Training Epoch: 7 [1536/45000]	Loss: 0.1087	LR: 0.020000
Training Epoch: 7 [1792/45000]	Loss: 0.1776	LR: 0.020000
Training Epoch: 7 [2048/45000]	Loss: 0.0811	LR: 0.020000
Training Epoch: 7 [2304/45000]	Loss: 0.0899	LR: 0.020000
Training Epoch: 7 [2560/45000]	Loss: 0.0917	LR: 0.020000
Training Epoch: 7 [2816/45000]	Loss: 0.0782	LR: 0.020000
Training Epoch: 7 [3072/45000]	Loss: 0.0983	LR: 0.020000
Training Epoch: 7 [3328/45000]	Loss: 0.1089	LR: 0.020000
Training Epoch: 7 [3584/45000]	Loss: 0.0536	LR: 0.020000
Training Epoch: 7 [3840/45000]	Loss: 0.1239	LR: 0.020000
Training Epoch: 7 [4096/45000]	Loss: 0.0990	LR: 0.020000
Training Epoch: 7 [4352/45000]	Loss: 0.0983	LR: 0.020000
Training Epoch: 7 [4608/45000]	Loss: 0.0836	LR: 0.020000
Training Epoch: 7 [4864/45000]	Loss: 0.0655	LR: 0.020000
Training Epoch: 7 [5120/45000]	Loss: 0.0669	LR: 0.020000
Training Epoch: 7 [5376/45000]	Loss: 0.0548	LR: 0.020000
Training Epoch: 7 [5632/45000]	Loss: 0.1263	LR: 0.020000
Training Epoch: 7 [5888/45000]	Loss: 0.1235	LR: 0.020000
Training Epoch: 7 [6144/45000]	Loss: 0.0729	LR: 0.020000
Training Epoch: 7 [6400/45000]	Loss: 0.0627	LR: 0.020000
Training Epoch: 7 [6656/45000]	Loss: 0.0525	LR: 0.020000
Training Epoch: 7 [6912/45000]	Loss: 0.0608	LR: 0.020000
Training Epoch: 7 [7168/45000]	Loss: 0.0724	LR: 0.020000
Training Epoch: 7 [7424/45000]	Loss: 0.0956	LR: 0.020000
Training Epoch: 7 [7680/45000]	Loss: 0.0885	LR: 0.020000
Training Epoch: 7 [7936/45000]	Loss: 0.0594	LR: 0.020000
Training Epoch: 7 [8192/45000]	Loss: 0.0606	LR: 0.020000
Training Epoch: 7 [8448/45000]	Loss: 0.0412	LR: 0.020000
Training Epoch: 7 [8704/45000]	Loss: 0.0461	LR: 0.020000
Training Epoch: 7 [8960/45000]	Loss: 0.0542	LR: 0.020000
Training Epoch: 7 [9216/45000]	Loss: 0.0762	LR: 0.020000
Training Epoch: 7 [9472/45000]	Loss: 0.0399	LR: 0.020000
Training Epoch: 7 [9728/45000]	Loss: 0.0950	LR: 0.020000
Training Epoch: 7 [9984/45000]	Loss: 0.0644	LR: 0.020000
Training Epoch: 7 [10240/45000]	Loss: 0.0818	LR: 0.020000
Training Epoch: 7 [10496/45000]	Loss: 0.0333	LR: 0.020000
Training Epoch: 7 [10752/45000]	Loss: 0.0811	LR: 0.020000
Training Epoch: 7 [11008/45000]	Loss: 0.0880	LR: 0.020000
Training Epoch: 7 [11264/45000]	Loss: 0.0663	LR: 0.020000
Training Epoch: 7 [11520/45000]	Loss: 0.0649	LR: 0.020000
Training Epoch: 7 [11776/45000]	Loss: 0.1009	LR: 0.020000
Training Epoch: 7 [12032/45000]	Loss: 0.0647	LR: 0.020000
Training Epoch: 7 [12288/45000]	Loss: 0.0379	LR: 0.020000
Training Epoch: 7 [12544/45000]	Loss: 0.0634	LR: 0.020000
Training Epoch: 7 [12800/45000]	Loss: 0.0898	LR: 0.020000
Training Epoch: 7 [13056/45000]	Loss: 0.0423	LR: 0.020000
Training Epoch: 7 [13312/45000]	Loss: 0.0590	LR: 0.020000
Training Epoch: 7 [13568/45000]	Loss: 0.0353	LR: 0.020000
Training Epoch: 7 [13824/45000]	Loss: 0.0350	LR: 0.020000
Training Epoch: 7 [14080/45000]	Loss: 0.0679	LR: 0.020000
Training Epoch: 7 [14336/45000]	Loss: 0.0981	LR: 0.020000
Training Epoch: 7 [14592/45000]	Loss: 0.0347	LR: 0.020000
Training Epoch: 7 [14848/45000]	Loss: 0.0282	LR: 0.020000
Training Epoch: 7 [15104/45000]	Loss: 0.0385	LR: 0.020000
Training Epoch: 7 [15360/45000]	Loss: 0.0581	LR: 0.020000
Training Epoch: 7 [15616/45000]	Loss: 0.0975	LR: 0.020000
Training Epoch: 7 [15872/45000]	Loss: 0.0338	LR: 0.020000
Training Epoch: 7 [16128/45000]	Loss: 0.0391	LR: 0.020000
Training Epoch: 7 [16384/45000]	Loss: 0.0321	LR: 0.020000
Training Epoch: 7 [16640/45000]	Loss: 0.0728	LR: 0.020000
Training Epoch: 7 [16896/45000]	Loss: 0.0304	LR: 0.020000
Training Epoch: 7 [17152/45000]	Loss: 0.0419	LR: 0.020000
Training Epoch: 7 [17408/45000]	Loss: 0.0645	LR: 0.020000
Training Epoch: 7 [17664/45000]	Loss: 0.0373	LR: 0.020000
Training Epoch: 7 [17920/45000]	Loss: 0.0482	LR: 0.020000
Training Epoch: 7 [18176/45000]	Loss: 0.0440	LR: 0.020000
Training Epoch: 7 [18432/45000]	Loss: 0.0720	LR: 0.020000
Training Epoch: 7 [18688/45000]	Loss: 0.0297	LR: 0.020000
Training Epoch: 7 [18944/45000]	Loss: 0.0807	LR: 0.020000
Training Epoch: 7 [19200/45000]	Loss: 0.0839	LR: 0.020000
Training Epoch: 7 [19456/45000]	Loss: 0.0610	LR: 0.020000
Training Epoch: 7 [19712/45000]	Loss: 0.0702	LR: 0.020000
Training Epoch: 7 [19968/45000]	Loss: 0.0251	LR: 0.020000
Training Epoch: 7 [20224/45000]	Loss: 0.0564	LR: 0.020000
Training Epoch: 7 [20480/45000]	Loss: 0.0593	LR: 0.020000
Training Epoch: 7 [20736/45000]	Loss: 0.0316	LR: 0.020000
Training Epoch: 7 [20992/45000]	Loss: 0.0349	LR: 0.020000
Training Epoch: 7 [21248/45000]	Loss: 0.0804	LR: 0.020000
Training Epoch: 7 [21504/45000]	Loss: 0.0085	LR: 0.020000
Training Epoch: 7 [21760/45000]	Loss: 0.0656	LR: 0.020000
Training Epoch: 7 [22016/45000]	Loss: 0.0529	LR: 0.020000
Training Epoch: 7 [22272/45000]	Loss: 0.0381	LR: 0.020000
Training Epoch: 7 [22528/45000]	Loss: 0.0551	LR: 0.020000
Training Epoch: 7 [22784/45000]	Loss: 0.0667	LR: 0.020000
Training Epoch: 7 [23040/45000]	Loss: 0.0887	LR: 0.020000
Training Epoch: 7 [23296/45000]	Loss: 0.0461	LR: 0.020000
Training Epoch: 7 [23552/45000]	Loss: 0.0509	LR: 0.020000
Training Epoch: 7 [23808/45000]	Loss: 0.0387	LR: 0.020000
Training Epoch: 7 [24064/45000]	Loss: 0.0426	LR: 0.020000
Training Epoch: 7 [24320/45000]	Loss: 0.0549	LR: 0.020000
Training Epoch: 7 [24576/45000]	Loss: 0.0397	LR: 0.020000
Training Epoch: 7 [24832/45000]	Loss: 0.0498	LR: 0.020000
Training Epoch: 7 [25088/45000]	Loss: 0.0178	LR: 0.020000
Training Epoch: 7 [25344/45000]	Loss: 0.0461	LR: 0.020000
Training Epoch: 7 [25600/45000]	Loss: 0.0362	LR: 0.020000
Training Epoch: 7 [25856/45000]	Loss: 0.0767	LR: 0.020000
Training Epoch: 7 [26112/45000]	Loss: 0.0476	LR: 0.020000
Training Epoch: 7 [26368/45000]	Loss: 0.0694	LR: 0.020000
Training Epoch: 7 [26624/45000]	Loss: 0.0731	LR: 0.020000
Training Epoch: 7 [26880/45000]	Loss: 0.0421	LR: 0.020000
Training Epoch: 7 [27136/45000]	Loss: 0.0319	LR: 0.020000
Training Epoch: 7 [27392/45000]	Loss: 0.0131	LR: 0.020000
Training Epoch: 7 [27648/45000]	Loss: 0.0436	LR: 0.020000
Training Epoch: 7 [27904/45000]	Loss: 0.0314	LR: 0.020000
Training Epoch: 7 [28160/45000]	Loss: 0.0609	LR: 0.020000
Training Epoch: 7 [28416/45000]	Loss: 0.0240	LR: 0.020000
Training Epoch: 7 [28672/45000]	Loss: 0.0281	LR: 0.020000
Training Epoch: 7 [28928/45000]	Loss: 0.0509	LR: 0.020000
Training Epoch: 7 [29184/45000]	Loss: 0.0355	LR: 0.020000
Training Epoch: 7 [29440/45000]	Loss: 0.0298	LR: 0.020000
Training Epoch: 7 [29696/45000]	Loss: 0.0827	LR: 0.020000
Training Epoch: 7 [29952/45000]	Loss: 0.0962	LR: 0.020000
Training Epoch: 7 [30208/45000]	Loss: 0.0326	LR: 0.020000
Training Epoch: 7 [30464/45000]	Loss: 0.0571	LR: 0.020000
Training Epoch: 7 [30720/45000]	Loss: 0.0267	LR: 0.020000
Training Epoch: 7 [30976/45000]	Loss: 0.0677	LR: 0.020000
Training Epoch: 7 [31232/45000]	Loss: 0.0397	LR: 0.020000
Training Epoch: 7 [31488/45000]	Loss: 0.0920	LR: 0.020000
Training Epoch: 7 [31744/45000]	Loss: 0.0585	LR: 0.020000
Training Epoch: 7 [32000/45000]	Loss: 0.0415	LR: 0.020000
Training Epoch: 7 [32256/45000]	Loss: 0.0519	LR: 0.020000
Training Epoch: 7 [32512/45000]	Loss: 0.0735	LR: 0.020000
Training Epoch: 7 [32768/45000]	Loss: 0.0805	LR: 0.020000
Training Epoch: 7 [33024/45000]	Loss: 0.0627	LR: 0.020000
Training Epoch: 7 [33280/45000]	Loss: 0.0498	LR: 0.020000
Training Epoch: 7 [33536/45000]	Loss: 0.0534	LR: 0.020000
Training Epoch: 7 [33792/45000]	Loss: 0.0602	LR: 0.020000
Training Epoch: 7 [34048/45000]	Loss: 0.0152	LR: 0.020000
Training Epoch: 7 [34304/45000]	Loss: 0.0580	LR: 0.020000
Training Epoch: 7 [34560/45000]	Loss: 0.0659	LR: 0.020000
Training Epoch: 7 [34816/45000]	Loss: 0.0970	LR: 0.020000
Training Epoch: 7 [35072/45000]	Loss: 0.0574	LR: 0.020000
Training Epoch: 7 [35328/45000]	Loss: 0.0252	LR: 0.020000
Training Epoch: 7 [35584/45000]	Loss: 0.0534	LR: 0.020000
Training Epoch: 7 [35840/45000]	Loss: 0.0301	LR: 0.020000
Training Epoch: 7 [36096/45000]	Loss: 0.0707	LR: 0.020000
Training Epoch: 7 [36352/45000]	Loss: 0.0685	LR: 0.020000
Training Epoch: 7 [36608/45000]	Loss: 0.0577	LR: 0.020000
Training Epoch: 7 [36864/45000]	Loss: 0.0379	LR: 0.020000
Training Epoch: 7 [37120/45000]	Loss: 0.0789	LR: 0.020000
Training Epoch: 7 [37376/45000]	Loss: 0.0236	LR: 0.020000
Training Epoch: 7 [37632/45000]	Loss: 0.0634	LR: 0.020000
Training Epoch: 7 [37888/45000]	Loss: 0.0134	LR: 0.020000
Training Epoch: 7 [38144/45000]	Loss: 0.0365	LR: 0.020000
Training Epoch: 7 [38400/45000]	Loss: 0.0528	LR: 0.020000
Training Epoch: 7 [38656/45000]	Loss: 0.0742	LR: 0.020000
Training Epoch: 7 [38912/45000]	Loss: 0.0432	LR: 0.020000
Training Epoch: 7 [39168/45000]	Loss: 0.0208	LR: 0.020000
Training Epoch: 7 [39424/45000]	Loss: 0.0428	LR: 0.020000
Training Epoch: 7 [39680/45000]	Loss: 0.0881	LR: 0.020000
Training Epoch: 7 [39936/45000]	Loss: 0.0591	LR: 0.020000
Training Epoch: 7 [40192/45000]	Loss: 0.0375	LR: 0.020000
Training Epoch: 7 [40448/45000]	Loss: 0.0199	LR: 0.020000
Training Epoch: 7 [40704/45000]	Loss: 0.0591	LR: 0.020000
Training Epoch: 7 [40960/45000]	Loss: 0.0381	LR: 0.020000
Training Epoch: 7 [41216/45000]	Loss: 0.0554	LR: 0.020000
Training Epoch: 7 [41472/45000]	Loss: 0.0439	LR: 0.020000
Training Epoch: 7 [41728/45000]	Loss: 0.0320	LR: 0.020000
Training Epoch: 7 [41984/45000]	Loss: 0.0451	LR: 0.020000
Training Epoch: 7 [42240/45000]	Loss: 0.0482	LR: 0.020000
Training Epoch: 7 [42496/45000]	Loss: 0.0578	LR: 0.020000
Training Epoch: 7 [42752/45000]	Loss: 0.0630	LR: 0.020000
Training Epoch: 7 [43008/45000]	Loss: 0.0771	LR: 0.020000
Training Epoch: 7 [43264/45000]	Loss: 0.0413	LR: 0.020000
Training Epoch: 7 [43520/45000]	Loss: 0.0659	LR: 0.020000
Training Epoch: 7 [43776/45000]	Loss: 0.0665	LR: 0.020000
Training Epoch: 7 [44032/45000]	Loss: 0.0453	LR: 0.020000
Training Epoch: 7 [44288/45000]	Loss: 0.0610	LR: 0.020000
Training Epoch: 7 [44544/45000]	Loss: 0.0358	LR: 0.020000
Training Epoch: 7 [44800/45000]	Loss: 0.0546	LR: 0.020000
Training Epoch: 7 [45000/45000]	Loss: 0.0317	LR: 0.020000
Epoch 7 - Average Train Loss: 0.0611, Train Accuracy: 0.9790
Epoch 7 training time consumed: 324.93s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0004, Accuracy: 0.9678, Time consumed:23.46s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_05h_51m_14s/ViT-Cifar10-seed5-ret100-7-best.pth
Training Epoch: 8 [256/45000]	Loss: 0.0451	LR: 0.020000
Training Epoch: 8 [512/45000]	Loss: 0.0655	LR: 0.020000
Training Epoch: 8 [768/45000]	Loss: 0.0595	LR: 0.020000
Training Epoch: 8 [1024/45000]	Loss: 0.0308	LR: 0.020000
Training Epoch: 8 [1280/45000]	Loss: 0.0317	LR: 0.020000
Training Epoch: 8 [1536/45000]	Loss: 0.0746	LR: 0.020000
Training Epoch: 8 [1792/45000]	Loss: 0.0744	LR: 0.020000
Training Epoch: 8 [2048/45000]	Loss: 0.0438	LR: 0.020000
Training Epoch: 8 [2304/45000]	Loss: 0.0355	LR: 0.020000
Training Epoch: 8 [2560/45000]	Loss: 0.0208	LR: 0.020000
Training Epoch: 8 [2816/45000]	Loss: 0.0420	LR: 0.020000
Training Epoch: 8 [3072/45000]	Loss: 0.0170	LR: 0.020000
Training Epoch: 8 [3328/45000]	Loss: 0.0472	LR: 0.020000
Training Epoch: 8 [3584/45000]	Loss: 0.0360	LR: 0.020000
Training Epoch: 8 [3840/45000]	Loss: 0.0458	LR: 0.020000
Training Epoch: 8 [4096/45000]	Loss: 0.0685	LR: 0.020000
Training Epoch: 8 [4352/45000]	Loss: 0.0651	LR: 0.020000
Training Epoch: 8 [4608/45000]	Loss: 0.0395	LR: 0.020000
Training Epoch: 8 [4864/45000]	Loss: 0.0203	LR: 0.020000
Training Epoch: 8 [5120/45000]	Loss: 0.0310	LR: 0.020000
Training Epoch: 8 [5376/45000]	Loss: 0.0382	LR: 0.020000
Training Epoch: 8 [5632/45000]	Loss: 0.0301	LR: 0.020000
Training Epoch: 8 [5888/45000]	Loss: 0.0142	LR: 0.020000
Training Epoch: 8 [6144/45000]	Loss: 0.0212	LR: 0.020000
Training Epoch: 8 [6400/45000]	Loss: 0.0211	LR: 0.020000
Training Epoch: 8 [6656/45000]	Loss: 0.0406	LR: 0.020000
Training Epoch: 8 [6912/45000]	Loss: 0.0224	LR: 0.020000
Training Epoch: 8 [7168/45000]	Loss: 0.0336	LR: 0.020000
Training Epoch: 8 [7424/45000]	Loss: 0.0499	LR: 0.020000
Training Epoch: 8 [7680/45000]	Loss: 0.0241	LR: 0.020000
Training Epoch: 8 [7936/45000]	Loss: 0.0562	LR: 0.020000
Training Epoch: 8 [8192/45000]	Loss: 0.0257	LR: 0.020000
Training Epoch: 8 [8448/45000]	Loss: 0.0360	LR: 0.020000
Training Epoch: 8 [8704/45000]	Loss: 0.0207	LR: 0.020000
Training Epoch: 8 [8960/45000]	Loss: 0.0299	LR: 0.020000
Training Epoch: 8 [9216/45000]	Loss: 0.0465	LR: 0.020000
Training Epoch: 8 [9472/45000]	Loss: 0.0505	LR: 0.020000
Training Epoch: 8 [9728/45000]	Loss: 0.0752	LR: 0.020000
Training Epoch: 8 [9984/45000]	Loss: 0.0345	LR: 0.020000
Training Epoch: 8 [10240/45000]	Loss: 0.0156	LR: 0.020000
Training Epoch: 8 [10496/45000]	Loss: 0.0557	LR: 0.020000
Training Epoch: 8 [10752/45000]	Loss: 0.0353	LR: 0.020000
Training Epoch: 8 [11008/45000]	Loss: 0.0584	LR: 0.020000
Training Epoch: 8 [11264/45000]	Loss: 0.0590	LR: 0.020000
Training Epoch: 8 [11520/45000]	Loss: 0.0130	LR: 0.020000
Training Epoch: 8 [11776/45000]	Loss: 0.0579	LR: 0.020000
Training Epoch: 8 [12032/45000]	Loss: 0.0475	LR: 0.020000
Training Epoch: 8 [12288/45000]	Loss: 0.0596	LR: 0.020000
Training Epoch: 8 [12544/45000]	Loss: 0.0207	LR: 0.020000
Training Epoch: 8 [12800/45000]	Loss: 0.0559	LR: 0.020000
Training Epoch: 8 [13056/45000]	Loss: 0.0192	LR: 0.020000
Training Epoch: 8 [13312/45000]	Loss: 0.0462	LR: 0.020000
Training Epoch: 8 [13568/45000]	Loss: 0.0157	LR: 0.020000
Training Epoch: 8 [13824/45000]	Loss: 0.0232	LR: 0.020000
Training Epoch: 8 [14080/45000]	Loss: 0.0207	LR: 0.020000
Training Epoch: 8 [14336/45000]	Loss: 0.0595	LR: 0.020000
Training Epoch: 8 [14592/45000]	Loss: 0.0271	LR: 0.020000
Training Epoch: 8 [14848/45000]	Loss: 0.0372	LR: 0.020000
Training Epoch: 8 [15104/45000]	Loss: 0.0506	LR: 0.020000
Training Epoch: 8 [15360/45000]	Loss: 0.0410	LR: 0.020000
Training Epoch: 8 [15616/45000]	Loss: 0.0353	LR: 0.020000
Training Epoch: 8 [15872/45000]	Loss: 0.0200	LR: 0.020000
Training Epoch: 8 [16128/45000]	Loss: 0.0567	LR: 0.020000
Training Epoch: 8 [16384/45000]	Loss: 0.0740	LR: 0.020000
Training Epoch: 8 [16640/45000]	Loss: 0.0255	LR: 0.020000
Training Epoch: 8 [16896/45000]	Loss: 0.0387	LR: 0.020000
Training Epoch: 8 [17152/45000]	Loss: 0.0481	LR: 0.020000
Training Epoch: 8 [17408/45000]	Loss: 0.0114	LR: 0.020000
Training Epoch: 8 [17664/45000]	Loss: 0.0573	LR: 0.020000
Training Epoch: 8 [17920/45000]	Loss: 0.0296	LR: 0.020000
Training Epoch: 8 [18176/45000]	Loss: 0.0365	LR: 0.020000
Training Epoch: 8 [18432/45000]	Loss: 0.0226	LR: 0.020000
Training Epoch: 8 [18688/45000]	Loss: 0.0422	LR: 0.020000
Training Epoch: 8 [18944/45000]	Loss: 0.0465	LR: 0.020000
Training Epoch: 8 [19200/45000]	Loss: 0.0604	LR: 0.020000
Training Epoch: 8 [19456/45000]	Loss: 0.0419	LR: 0.020000
Training Epoch: 8 [19712/45000]	Loss: 0.0350	LR: 0.020000
Training Epoch: 8 [19968/45000]	Loss: 0.0401	LR: 0.020000
Training Epoch: 8 [20224/45000]	Loss: 0.0409	LR: 0.020000
Training Epoch: 8 [20480/45000]	Loss: 0.0416	LR: 0.020000
Training Epoch: 8 [20736/45000]	Loss: 0.0943	LR: 0.020000
Training Epoch: 8 [20992/45000]	Loss: 0.0513	LR: 0.020000
Training Epoch: 8 [21248/45000]	Loss: 0.0263	LR: 0.020000
Training Epoch: 8 [21504/45000]	Loss: 0.0439	LR: 0.020000
Training Epoch: 8 [21760/45000]	Loss: 0.0523	LR: 0.020000
Training Epoch: 8 [22016/45000]	Loss: 0.0301	LR: 0.020000
Training Epoch: 8 [22272/45000]	Loss: 0.0163	LR: 0.020000
Training Epoch: 8 [22528/45000]	Loss: 0.0342	LR: 0.020000
Training Epoch: 8 [22784/45000]	Loss: 0.0248	LR: 0.020000
Training Epoch: 8 [23040/45000]	Loss: 0.0468	LR: 0.020000
Training Epoch: 8 [23296/45000]	Loss: 0.0350	LR: 0.020000
Training Epoch: 8 [23552/45000]	Loss: 0.0886	LR: 0.020000
Training Epoch: 8 [23808/45000]	Loss: 0.0305	LR: 0.020000
Training Epoch: 8 [24064/45000]	Loss: 0.0370	LR: 0.020000
Training Epoch: 8 [24320/45000]	Loss: 0.0271	LR: 0.020000
Training Epoch: 8 [24576/45000]	Loss: 0.0394	LR: 0.020000
Training Epoch: 8 [24832/45000]	Loss: 0.0383	LR: 0.020000
Training Epoch: 8 [25088/45000]	Loss: 0.0416	LR: 0.020000
Training Epoch: 8 [25344/45000]	Loss: 0.0473	LR: 0.020000
Training Epoch: 8 [25600/45000]	Loss: 0.0364	LR: 0.020000
Training Epoch: 8 [25856/45000]	Loss: 0.0171	LR: 0.020000
Training Epoch: 8 [26112/45000]	Loss: 0.0653	LR: 0.020000
Training Epoch: 8 [26368/45000]	Loss: 0.0477	LR: 0.020000
Training Epoch: 8 [26624/45000]	Loss: 0.0502	LR: 0.020000
Training Epoch: 8 [26880/45000]	Loss: 0.0448	LR: 0.020000
Training Epoch: 8 [27136/45000]	Loss: 0.0409	LR: 0.020000
Training Epoch: 8 [27392/45000]	Loss: 0.0570	LR: 0.020000
Training Epoch: 8 [27648/45000]	Loss: 0.0446	LR: 0.020000
Training Epoch: 8 [27904/45000]	Loss: 0.0275	LR: 0.020000
Training Epoch: 8 [28160/45000]	Loss: 0.0264	LR: 0.020000
Training Epoch: 8 [28416/45000]	Loss: 0.0220	LR: 0.020000
Training Epoch: 8 [28672/45000]	Loss: 0.0304	LR: 0.020000
Training Epoch: 8 [28928/45000]	Loss: 0.0227	LR: 0.020000
Training Epoch: 8 [29184/45000]	Loss: 0.0508	LR: 0.020000
Training Epoch: 8 [29440/45000]	Loss: 0.0502	LR: 0.020000
Training Epoch: 8 [29696/45000]	Loss: 0.0361	LR: 0.020000
Training Epoch: 8 [29952/45000]	Loss: 0.0458	LR: 0.020000
Training Epoch: 8 [30208/45000]	Loss: 0.0687	LR: 0.020000
Training Epoch: 8 [30464/45000]	Loss: 0.0190	LR: 0.020000
Training Epoch: 8 [30720/45000]	Loss: 0.0525	LR: 0.020000
Training Epoch: 8 [30976/45000]	Loss: 0.0202	LR: 0.020000
Training Epoch: 8 [31232/45000]	Loss: 0.0168	LR: 0.020000
Training Epoch: 8 [31488/45000]	Loss: 0.0442	LR: 0.020000
Training Epoch: 8 [31744/45000]	Loss: 0.0435	LR: 0.020000
Training Epoch: 8 [32000/45000]	Loss: 0.0642	LR: 0.020000
Training Epoch: 8 [32256/45000]	Loss: 0.0488	LR: 0.020000
Training Epoch: 8 [32512/45000]	Loss: 0.0834	LR: 0.020000
Training Epoch: 8 [32768/45000]	Loss: 0.0394	LR: 0.020000
Training Epoch: 8 [33024/45000]	Loss: 0.0772	LR: 0.020000
Training Epoch: 8 [33280/45000]	Loss: 0.0966	LR: 0.020000
Training Epoch: 8 [33536/45000]	Loss: 0.0321	LR: 0.020000
Training Epoch: 8 [33792/45000]	Loss: 0.0492	LR: 0.020000
Training Epoch: 8 [34048/45000]	Loss: 0.0279	LR: 0.020000
Training Epoch: 8 [34304/45000]	Loss: 0.0172	LR: 0.020000
Training Epoch: 8 [34560/45000]	Loss: 0.0256	LR: 0.020000
Training Epoch: 8 [34816/45000]	Loss: 0.0441	LR: 0.020000
Training Epoch: 8 [35072/45000]	Loss: 0.0257	LR: 0.020000
Training Epoch: 8 [35328/45000]	Loss: 0.0125	LR: 0.020000
Training Epoch: 8 [35584/45000]	Loss: 0.0552	LR: 0.020000
Training Epoch: 8 [35840/45000]	Loss: 0.0209	LR: 0.020000
Training Epoch: 8 [36096/45000]	Loss: 0.0537	LR: 0.020000
Training Epoch: 8 [36352/45000]	Loss: 0.0374	LR: 0.020000
Training Epoch: 8 [36608/45000]	Loss: 0.0312	LR: 0.020000
Training Epoch: 8 [36864/45000]	Loss: 0.0405	LR: 0.020000
Training Epoch: 8 [37120/45000]	Loss: 0.0181	LR: 0.020000
Training Epoch: 8 [37376/45000]	Loss: 0.0205	LR: 0.020000
Training Epoch: 8 [37632/45000]	Loss: 0.0248	LR: 0.020000
Training Epoch: 8 [37888/45000]	Loss: 0.0443	LR: 0.020000
Training Epoch: 8 [38144/45000]	Loss: 0.0425	LR: 0.020000
Training Epoch: 8 [38400/45000]	Loss: 0.0506	LR: 0.020000
Training Epoch: 8 [38656/45000]	Loss: 0.0314	LR: 0.020000
Training Epoch: 8 [38912/45000]	Loss: 0.0663	LR: 0.020000
Training Epoch: 8 [39168/45000]	Loss: 0.0282	LR: 0.020000
Training Epoch: 8 [39424/45000]	Loss: 0.0243	LR: 0.020000
Training Epoch: 8 [39680/45000]	Loss: 0.0258	LR: 0.020000
Training Epoch: 8 [39936/45000]	Loss: 0.0071	LR: 0.020000
Training Epoch: 8 [40192/45000]	Loss: 0.0372	LR: 0.020000
Training Epoch: 8 [40448/45000]	Loss: 0.0120	LR: 0.020000
Training Epoch: 8 [40704/45000]	Loss: 0.0317	LR: 0.020000
Training Epoch: 8 [40960/45000]	Loss: 0.0202	LR: 0.020000
Training Epoch: 8 [41216/45000]	Loss: 0.0568	LR: 0.020000
Training Epoch: 8 [41472/45000]	Loss: 0.0554	LR: 0.020000
Training Epoch: 8 [41728/45000]	Loss: 0.0253	LR: 0.020000
Training Epoch: 8 [41984/45000]	Loss: 0.0243	LR: 0.020000
Training Epoch: 8 [42240/45000]	Loss: 0.0177	LR: 0.020000
Training Epoch: 8 [42496/45000]	Loss: 0.0474	LR: 0.020000
Training Epoch: 8 [42752/45000]	Loss: 0.0359	LR: 0.020000
Training Epoch: 8 [43008/45000]	Loss: 0.0144	LR: 0.020000
Training Epoch: 8 [43264/45000]	Loss: 0.0689	LR: 0.020000
Training Epoch: 8 [43520/45000]	Loss: 0.0640	LR: 0.020000
Training Epoch: 8 [43776/45000]	Loss: 0.0476	LR: 0.020000
Training Epoch: 8 [44032/45000]	Loss: 0.0340	LR: 0.020000
Training Epoch: 8 [44288/45000]	Loss: 0.0511	LR: 0.020000
Training Epoch: 8 [44544/45000]	Loss: 0.0166	LR: 0.020000
Training Epoch: 8 [44800/45000]	Loss: 0.0152	LR: 0.020000
Training Epoch: 8 [45000/45000]	Loss: 0.0370	LR: 0.020000
Epoch 8 - Average Train Loss: 0.0395, Train Accuracy: 0.9866
Epoch 8 training time consumed: 324.48s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0003, Accuracy: 0.9742, Time consumed:23.44s
Saving weights file to checkpoint/retrain/ViT/Thursday_17_July_2025_05h_51m_14s/ViT-Cifar10-seed5-ret100-8-best.pth
Valid (Test) Dl:  10000
Train Dl:  50000
Retain Train Dl:  45000
Forget Train Dl:  5000
Retain Valid Dl:  45000
Forget Valid Dl:  5000
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 5000 samples
Set1 Distribution: 5000 samples
Set2 Distribution: 5000 samples
Set1 Distribution: 5000 samples
Set2 Distribution: 5000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 97.48046875
Retain Accuracy: 99.11096954345703
Zero-Retain Forget (ZRF): 0.7615729570388794
Membership Inference Attack (MIA): 0.8374
Forget vs Retain Membership Inference Attack (MIA): 0.521
Forget vs Test Membership Inference Attack (MIA): 0.5295
Test vs Retain Membership Inference Attack (MIA): 0.50525
Train vs Test Membership Inference Attack (MIA): 0.51125
Forget Set Accuracy (Df): 96.48092651367188
Method Execution Time: 5192.08 seconds
