hello
hello

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

📊 Updated class distribution:
Retain set:
  Class 0: 4750
  Class 1: 4750
  Class 2: 4750
  Class 3: 4750
  Class 4: 4750
  Class 5: 4750
  Class 6: 4750
  Class 7: 4750
  Class 8: 4750
  Class 9: 4750
Forget set:
  Class 0: 250
  Class 1: 250
  Class 2: 250
  Class 3: 250
  Class 4: 250
  Class 5: 250
  Class 6: 250
  Class 7: 250
  Class 8: 250
  Class 9: 250
hello
hello
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/47500]	Loss: 2.5096	LR: 0.000000
Training Epoch: 1 [512/47500]	Loss: 2.5071	LR: 0.000538
Training Epoch: 1 [768/47500]	Loss: 2.4451	LR: 0.001075
Training Epoch: 1 [1024/47500]	Loss: 2.4852	LR: 0.001613
Training Epoch: 1 [1280/47500]	Loss: 2.3635	LR: 0.002151
Training Epoch: 1 [1536/47500]	Loss: 2.2610	LR: 0.002688
Training Epoch: 1 [1792/47500]	Loss: 2.1231	LR: 0.003226
Training Epoch: 1 [2048/47500]	Loss: 2.0267	LR: 0.003763
Training Epoch: 1 [2304/47500]	Loss: 1.7508	LR: 0.004301
Training Epoch: 1 [2560/47500]	Loss: 1.5360	LR: 0.004839
Training Epoch: 1 [2816/47500]	Loss: 1.3586	LR: 0.005376
Training Epoch: 1 [3072/47500]	Loss: 1.0797	LR: 0.005914
Training Epoch: 1 [3328/47500]	Loss: 0.8647	LR: 0.006452
Training Epoch: 1 [3584/47500]	Loss: 0.7356	LR: 0.006989
Training Epoch: 1 [3840/47500]	Loss: 0.6194	LR: 0.007527
Training Epoch: 1 [4096/47500]	Loss: 0.3979	LR: 0.008065
Training Epoch: 1 [4352/47500]	Loss: 0.4088	LR: 0.008602
Training Epoch: 1 [4608/47500]	Loss: 0.2657	LR: 0.009140
Training Epoch: 1 [4864/47500]	Loss: 0.2146	LR: 0.009677
Training Epoch: 1 [5120/47500]	Loss: 0.2384	LR: 0.010215
Training Epoch: 1 [5376/47500]	Loss: 0.3065	LR: 0.010753
Training Epoch: 1 [5632/47500]	Loss: 0.1579	LR: 0.011290
Training Epoch: 1 [5888/47500]	Loss: 0.3098	LR: 0.011828
Training Epoch: 1 [6144/47500]	Loss: 0.1771	LR: 0.012366
Training Epoch: 1 [6400/47500]	Loss: 0.2378	LR: 0.012903
Training Epoch: 1 [6656/47500]	Loss: 0.2233	LR: 0.013441
Training Epoch: 1 [6912/47500]	Loss: 0.2495	LR: 0.013978
Training Epoch: 1 [7168/47500]	Loss: 0.1535	LR: 0.014516
Training Epoch: 1 [7424/47500]	Loss: 0.2329	LR: 0.015054
Training Epoch: 1 [7680/47500]	Loss: 0.2386	LR: 0.015591
Training Epoch: 1 [7936/47500]	Loss: 0.1315	LR: 0.016129
Training Epoch: 1 [8192/47500]	Loss: 0.3302	LR: 0.016667
Training Epoch: 1 [8448/47500]	Loss: 0.2757	LR: 0.017204
Training Epoch: 1 [8704/47500]	Loss: 0.0967	LR: 0.017742
Training Epoch: 1 [8960/47500]	Loss: 0.1745	LR: 0.018280
Training Epoch: 1 [9216/47500]	Loss: 0.1757	LR: 0.018817
Training Epoch: 1 [9472/47500]	Loss: 0.2490	LR: 0.019355
Training Epoch: 1 [9728/47500]	Loss: 0.2341	LR: 0.019892
Training Epoch: 1 [9984/47500]	Loss: 0.2360	LR: 0.020430
Training Epoch: 1 [10240/47500]	Loss: 0.1909	LR: 0.020968
Training Epoch: 1 [10496/47500]	Loss: 0.2807	LR: 0.021505
Training Epoch: 1 [10752/47500]	Loss: 0.2155	LR: 0.022043
Training Epoch: 1 [11008/47500]	Loss: 0.1760	LR: 0.022581
Training Epoch: 1 [11264/47500]	Loss: 0.2779	LR: 0.023118
Training Epoch: 1 [11520/47500]	Loss: 0.2269	LR: 0.023656
Training Epoch: 1 [11776/47500]	Loss: 0.1764	LR: 0.024194
Training Epoch: 1 [12032/47500]	Loss: 0.3107	LR: 0.024731
Training Epoch: 1 [12288/47500]	Loss: 0.2222	LR: 0.025269
Training Epoch: 1 [12544/47500]	Loss: 0.1859	LR: 0.025806
Training Epoch: 1 [12800/47500]	Loss: 0.2968	LR: 0.026344
Training Epoch: 1 [13056/47500]	Loss: 0.2634	LR: 0.026882
Training Epoch: 1 [13312/47500]	Loss: 0.2167	LR: 0.027419
Training Epoch: 1 [13568/47500]	Loss: 0.2588	LR: 0.027957
Training Epoch: 1 [13824/47500]	Loss: 0.2748	LR: 0.028495
Training Epoch: 1 [14080/47500]	Loss: 0.4229	LR: 0.029032
Training Epoch: 1 [14336/47500]	Loss: 0.1181	LR: 0.029570
Training Epoch: 1 [14592/47500]	Loss: 0.4965	LR: 0.030108
Training Epoch: 1 [14848/47500]	Loss: 0.3556	LR: 0.030645
Training Epoch: 1 [15104/47500]	Loss: 0.3871	LR: 0.031183
Training Epoch: 1 [15360/47500]	Loss: 0.2389	LR: 0.031720
Training Epoch: 1 [15616/47500]	Loss: 0.3346	LR: 0.032258
Training Epoch: 1 [15872/47500]	Loss: 0.2525	LR: 0.032796
Training Epoch: 1 [16128/47500]	Loss: 0.2250	LR: 0.033333
Training Epoch: 1 [16384/47500]	Loss: 0.3330	LR: 0.033871
Training Epoch: 1 [16640/47500]	Loss: 0.1935	LR: 0.034409
Training Epoch: 1 [16896/47500]	Loss: 0.1538	LR: 0.034946
Training Epoch: 1 [17152/47500]	Loss: 0.2362	LR: 0.035484
Training Epoch: 1 [17408/47500]	Loss: 0.2757	LR: 0.036022
Training Epoch: 1 [17664/47500]	Loss: 0.2546	LR: 0.036559
Training Epoch: 1 [17920/47500]	Loss: 0.1518	LR: 0.037097
Training Epoch: 1 [18176/47500]	Loss: 0.1776	LR: 0.037634
Training Epoch: 1 [18432/47500]	Loss: 0.2648	LR: 0.038172
Training Epoch: 1 [18688/47500]	Loss: 0.1525	LR: 0.038710
Training Epoch: 1 [18944/47500]	Loss: 0.2130	LR: 0.039247
Training Epoch: 1 [19200/47500]	Loss: 0.1778	LR: 0.039785
Training Epoch: 1 [19456/47500]	Loss: 0.1346	LR: 0.040323
Training Epoch: 1 [19712/47500]	Loss: 0.1858	LR: 0.040860
Training Epoch: 1 [19968/47500]	Loss: 0.3449	LR: 0.041398
Training Epoch: 1 [20224/47500]	Loss: 0.1599	LR: 0.041935
Training Epoch: 1 [20480/47500]	Loss: 0.1753	LR: 0.042473
Training Epoch: 1 [20736/47500]	Loss: 0.2063	LR: 0.043011
Training Epoch: 1 [20992/47500]	Loss: 0.2585	LR: 0.043548
Training Epoch: 1 [21248/47500]	Loss: 0.2228	LR: 0.044086
Training Epoch: 1 [21504/47500]	Loss: 0.2001	LR: 0.044624
Training Epoch: 1 [21760/47500]	Loss: 0.2054	LR: 0.045161
Training Epoch: 1 [22016/47500]	Loss: 0.1799	LR: 0.045699
Training Epoch: 1 [22272/47500]	Loss: 0.2839	LR: 0.046237
Training Epoch: 1 [22528/47500]	Loss: 0.1831	LR: 0.046774
Training Epoch: 1 [22784/47500]	Loss: 0.2670	LR: 0.047312
Training Epoch: 1 [23040/47500]	Loss: 0.3239	LR: 0.047849
Training Epoch: 1 [23296/47500]	Loss: 0.1938	LR: 0.048387
Training Epoch: 1 [23552/47500]	Loss: 0.2080	LR: 0.048925
Training Epoch: 1 [23808/47500]	Loss: 0.2017	LR: 0.049462
Training Epoch: 1 [24064/47500]	Loss: 0.2506	LR: 0.050000
Training Epoch: 1 [24320/47500]	Loss: 0.1726	LR: 0.050538
Training Epoch: 1 [24576/47500]	Loss: 0.2062	LR: 0.051075
Training Epoch: 1 [24832/47500]	Loss: 0.2657	LR: 0.051613
Training Epoch: 1 [25088/47500]	Loss: 0.3363	LR: 0.052151
Training Epoch: 1 [25344/47500]	Loss: 0.2689	LR: 0.052688
Training Epoch: 1 [25600/47500]	Loss: 0.1397	LR: 0.053226
Training Epoch: 1 [25856/47500]	Loss: 0.3230	LR: 0.053763
Training Epoch: 1 [26112/47500]	Loss: 0.2399	LR: 0.054301
Training Epoch: 1 [26368/47500]	Loss: 0.3484	LR: 0.054839
Training Epoch: 1 [26624/47500]	Loss: 0.3299	LR: 0.055376
Training Epoch: 1 [26880/47500]	Loss: 0.3187	LR: 0.055914
Training Epoch: 1 [27136/47500]	Loss: 0.2863	LR: 0.056452
Training Epoch: 1 [27392/47500]	Loss: 0.3438	LR: 0.056989
Training Epoch: 1 [27648/47500]	Loss: 0.2552	LR: 0.057527
Training Epoch: 1 [27904/47500]	Loss: 0.2498	LR: 0.058065
Training Epoch: 1 [28160/47500]	Loss: 0.2800	LR: 0.058602
Training Epoch: 1 [28416/47500]	Loss: 0.3275	LR: 0.059140
Training Epoch: 1 [28672/47500]	Loss: 0.2724	LR: 0.059677
Training Epoch: 1 [28928/47500]	Loss: 0.2472	LR: 0.060215
Training Epoch: 1 [29184/47500]	Loss: 0.1659	LR: 0.060753
Training Epoch: 1 [29440/47500]	Loss: 0.2283	LR: 0.061290
Training Epoch: 1 [29696/47500]	Loss: 0.1673	LR: 0.061828
Training Epoch: 1 [29952/47500]	Loss: 0.0559	LR: 0.062366
Training Epoch: 1 [30208/47500]	Loss: 0.1752	LR: 0.062903
Training Epoch: 1 [30464/47500]	Loss: 0.2428	LR: 0.063441
Training Epoch: 1 [30720/47500]	Loss: 0.1765	LR: 0.063978
Training Epoch: 1 [30976/47500]	Loss: 0.2057	LR: 0.064516
Training Epoch: 1 [31232/47500]	Loss: 0.2219	LR: 0.065054
Training Epoch: 1 [31488/47500]	Loss: 0.2480	LR: 0.065591
Training Epoch: 1 [31744/47500]	Loss: 0.1913	LR: 0.066129
Training Epoch: 1 [32000/47500]	Loss: 0.2904	LR: 0.066667
Training Epoch: 1 [32256/47500]	Loss: 0.2427	LR: 0.067204
Training Epoch: 1 [32512/47500]	Loss: 0.1669	LR: 0.067742
Training Epoch: 1 [32768/47500]	Loss: 0.2758	LR: 0.068280
Training Epoch: 1 [33024/47500]	Loss: 0.2098	LR: 0.068817
Training Epoch: 1 [33280/47500]	Loss: 0.1782	LR: 0.069355
Training Epoch: 1 [33536/47500]	Loss: 0.1904	LR: 0.069892
Training Epoch: 1 [33792/47500]	Loss: 0.2980	LR: 0.070430
Training Epoch: 1 [34048/47500]	Loss: 0.2680	LR: 0.070968
Training Epoch: 1 [34304/47500]	Loss: 0.2555	LR: 0.071505
Training Epoch: 1 [34560/47500]	Loss: 0.2354	LR: 0.072043
Training Epoch: 1 [34816/47500]	Loss: 0.2111	LR: 0.072581
Training Epoch: 1 [35072/47500]	Loss: 0.4116	LR: 0.073118
Training Epoch: 1 [35328/47500]	Loss: 0.2301	LR: 0.073656
Training Epoch: 1 [35584/47500]	Loss: 0.2972	LR: 0.074194
Training Epoch: 1 [35840/47500]	Loss: 0.3774	LR: 0.074731
Training Epoch: 1 [36096/47500]	Loss: 0.2437	LR: 0.075269
Training Epoch: 1 [36352/47500]	Loss: 0.1642	LR: 0.075806
Training Epoch: 1 [36608/47500]	Loss: 0.1389	LR: 0.076344
Training Epoch: 1 [36864/47500]	Loss: 0.1860	LR: 0.076882
Training Epoch: 1 [37120/47500]	Loss: 0.2736	LR: 0.077419
Training Epoch: 1 [37376/47500]	Loss: 0.2922	LR: 0.077957
Training Epoch: 1 [37632/47500]	Loss: 0.2669	LR: 0.078495
Training Epoch: 1 [37888/47500]	Loss: 0.2725	LR: 0.079032
Training Epoch: 1 [38144/47500]	Loss: 0.2653	LR: 0.079570
Training Epoch: 1 [38400/47500]	Loss: 0.2301	LR: 0.080108
Training Epoch: 1 [38656/47500]	Loss: 0.2795	LR: 0.080645
Training Epoch: 1 [38912/47500]	Loss: 0.2240	LR: 0.081183
Training Epoch: 1 [39168/47500]	Loss: 0.2092	LR: 0.081720
Training Epoch: 1 [39424/47500]	Loss: 0.2395	LR: 0.082258
Training Epoch: 1 [39680/47500]	Loss: 0.2094	LR: 0.082796
Training Epoch: 1 [39936/47500]	Loss: 0.1602	LR: 0.083333
Training Epoch: 1 [40192/47500]	Loss: 0.2547	LR: 0.083871
Training Epoch: 1 [40448/47500]	Loss: 0.2052	LR: 0.084409
Training Epoch: 1 [40704/47500]	Loss: 0.2376	LR: 0.084946
Training Epoch: 1 [40960/47500]	Loss: 0.2511	LR: 0.085484
Training Epoch: 1 [41216/47500]	Loss: 0.1268	LR: 0.086022
Training Epoch: 1 [41472/47500]	Loss: 0.1801	LR: 0.086559
Training Epoch: 1 [41728/47500]	Loss: 0.2507	LR: 0.087097
Training Epoch: 1 [41984/47500]	Loss: 0.1439	LR: 0.087634
Training Epoch: 1 [42240/47500]	Loss: 0.2168	LR: 0.088172
Training Epoch: 1 [42496/47500]	Loss: 0.2154	LR: 0.088710
Training Epoch: 1 [42752/47500]	Loss: 0.2504	LR: 0.089247
Training Epoch: 1 [43008/47500]	Loss: 0.2415	LR: 0.089785
Training Epoch: 1 [43264/47500]	Loss: 0.2765	LR: 0.090323
Training Epoch: 1 [43520/47500]	Loss: 0.1840	LR: 0.090860
Training Epoch: 1 [43776/47500]	Loss: 0.3240	LR: 0.091398
Training Epoch: 1 [44032/47500]	Loss: 0.2984	LR: 0.091935
Training Epoch: 1 [44288/47500]	Loss: 0.1481	LR: 0.092473
Training Epoch: 1 [44544/47500]	Loss: 0.1261	LR: 0.093011
Training Epoch: 1 [44800/47500]	Loss: 0.3053	LR: 0.093548
Training Epoch: 1 [45056/47500]	Loss: 0.2418	LR: 0.094086
Training Epoch: 1 [45312/47500]	Loss: 0.2414	LR: 0.094624
Training Epoch: 1 [45568/47500]	Loss: 0.4630	LR: 0.095161
Training Epoch: 1 [45824/47500]	Loss: 0.2441	LR: 0.095699
Training Epoch: 1 [46080/47500]	Loss: 0.2884	LR: 0.096237
Training Epoch: 1 [46336/47500]	Loss: 0.3546	LR: 0.096774
Training Epoch: 1 [46592/47500]	Loss: 0.3099	LR: 0.097312
Training Epoch: 1 [46848/47500]	Loss: 0.2474	LR: 0.097849
Training Epoch: 1 [47104/47500]	Loss: 0.3624	LR: 0.098387
Training Epoch: 1 [47360/47500]	Loss: 0.4176	LR: 0.098925
Training Epoch: 1 [47500/47500]	Loss: 0.2846	LR: 0.099462
Epoch 1 - Average Train Loss: 0.3676, Train Accuracy: 0.8797
Epoch 1 training time consumed: 344.10s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0011, Accuracy: 0.9148, Time consumed:23.52s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-1-best.pth
Training Epoch: 2 [256/47500]	Loss: 0.3446	LR: 0.100000
Training Epoch: 2 [512/47500]	Loss: 0.3327	LR: 0.100000
Training Epoch: 2 [768/47500]	Loss: 0.2565	LR: 0.100000
Training Epoch: 2 [1024/47500]	Loss: 0.2917	LR: 0.100000
Training Epoch: 2 [1280/47500]	Loss: 0.2497	LR: 0.100000
Training Epoch: 2 [1536/47500]	Loss: 0.3348	LR: 0.100000
Training Epoch: 2 [1792/47500]	Loss: 0.2393	LR: 0.100000
Training Epoch: 2 [2048/47500]	Loss: 0.3620	LR: 0.100000
Training Epoch: 2 [2304/47500]	Loss: 0.3450	LR: 0.100000
Training Epoch: 2 [2560/47500]	Loss: 0.2593	LR: 0.100000
Training Epoch: 2 [2816/47500]	Loss: 0.3432	LR: 0.100000
Training Epoch: 2 [3072/47500]	Loss: 0.2543	LR: 0.100000
Training Epoch: 2 [3328/47500]	Loss: 0.2473	LR: 0.100000
Training Epoch: 2 [3584/47500]	Loss: 0.3110	LR: 0.100000
Training Epoch: 2 [3840/47500]	Loss: 0.2278	LR: 0.100000
Training Epoch: 2 [4096/47500]	Loss: 0.2100	LR: 0.100000
Training Epoch: 2 [4352/47500]	Loss: 0.2797	LR: 0.100000
Training Epoch: 2 [4608/47500]	Loss: 0.1219	LR: 0.100000
Training Epoch: 2 [4864/47500]	Loss: 0.2253	LR: 0.100000
Training Epoch: 2 [5120/47500]	Loss: 0.1685	LR: 0.100000
Training Epoch: 2 [5376/47500]	Loss: 0.1966	LR: 0.100000
Training Epoch: 2 [5632/47500]	Loss: 0.2194	LR: 0.100000
Training Epoch: 2 [5888/47500]	Loss: 0.1439	LR: 0.100000
Training Epoch: 2 [6144/47500]	Loss: 0.2176	LR: 0.100000
Training Epoch: 2 [6400/47500]	Loss: 0.2692	LR: 0.100000
Training Epoch: 2 [6656/47500]	Loss: 0.1817	LR: 0.100000
Training Epoch: 2 [6912/47500]	Loss: 0.2018	LR: 0.100000
Training Epoch: 2 [7168/47500]	Loss: 0.1361	LR: 0.100000
Training Epoch: 2 [7424/47500]	Loss: 0.1698	LR: 0.100000
Training Epoch: 2 [7680/47500]	Loss: 0.2776	LR: 0.100000
Training Epoch: 2 [7936/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 2 [8192/47500]	Loss: 0.2452	LR: 0.100000
Training Epoch: 2 [8448/47500]	Loss: 0.2278	LR: 0.100000
Training Epoch: 2 [8704/47500]	Loss: 0.2828	LR: 0.100000
Training Epoch: 2 [8960/47500]	Loss: 0.1948	LR: 0.100000
Training Epoch: 2 [9216/47500]	Loss: 0.3180	LR: 0.100000
Training Epoch: 2 [9472/47500]	Loss: 0.1325	LR: 0.100000
Training Epoch: 2 [9728/47500]	Loss: 0.2577	LR: 0.100000
Training Epoch: 2 [9984/47500]	Loss: 0.2125	LR: 0.100000
Training Epoch: 2 [10240/47500]	Loss: 0.2622	LR: 0.100000
Training Epoch: 2 [10496/47500]	Loss: 0.2375	LR: 0.100000
Training Epoch: 2 [10752/47500]	Loss: 0.2477	LR: 0.100000
Training Epoch: 2 [11008/47500]	Loss: 0.1998	LR: 0.100000
Training Epoch: 2 [11264/47500]	Loss: 0.3036	LR: 0.100000
Training Epoch: 2 [11520/47500]	Loss: 0.2645	LR: 0.100000
Training Epoch: 2 [11776/47500]	Loss: 0.2460	LR: 0.100000
Training Epoch: 2 [12032/47500]	Loss: 0.2792	LR: 0.100000
Training Epoch: 2 [12288/47500]	Loss: 0.2017	LR: 0.100000
Training Epoch: 2 [12544/47500]	Loss: 0.1403	LR: 0.100000
Training Epoch: 2 [12800/47500]	Loss: 0.2354	LR: 0.100000
Training Epoch: 2 [13056/47500]	Loss: 0.2121	LR: 0.100000
Training Epoch: 2 [13312/47500]	Loss: 0.2525	LR: 0.100000
Training Epoch: 2 [13568/47500]	Loss: 0.1868	LR: 0.100000
Training Epoch: 2 [13824/47500]	Loss: 0.2490	LR: 0.100000
Training Epoch: 2 [14080/47500]	Loss: 0.1961	LR: 0.100000
Training Epoch: 2 [14336/47500]	Loss: 0.1758	LR: 0.100000
Training Epoch: 2 [14592/47500]	Loss: 0.1849	LR: 0.100000
Training Epoch: 2 [14848/47500]	Loss: 0.1721	LR: 0.100000
Training Epoch: 2 [15104/47500]	Loss: 0.2090	LR: 0.100000
Training Epoch: 2 [15360/47500]	Loss: 0.1823	LR: 0.100000
Training Epoch: 2 [15616/47500]	Loss: 0.2363	LR: 0.100000
Training Epoch: 2 [15872/47500]	Loss: 0.2808	LR: 0.100000
Training Epoch: 2 [16128/47500]	Loss: 0.1905	LR: 0.100000
Training Epoch: 2 [16384/47500]	Loss: 0.2352	LR: 0.100000
Training Epoch: 2 [16640/47500]	Loss: 0.2401	LR: 0.100000
Training Epoch: 2 [16896/47500]	Loss: 0.1937	LR: 0.100000
Training Epoch: 2 [17152/47500]	Loss: 0.1961	LR: 0.100000
Training Epoch: 2 [17408/47500]	Loss: 0.2102	LR: 0.100000
Training Epoch: 2 [17664/47500]	Loss: 0.1311	LR: 0.100000
Training Epoch: 2 [17920/47500]	Loss: 0.1924	LR: 0.100000
Training Epoch: 2 [18176/47500]	Loss: 0.1482	LR: 0.100000
Training Epoch: 2 [18432/47500]	Loss: 0.2092	LR: 0.100000
Training Epoch: 2 [18688/47500]	Loss: 0.1978	LR: 0.100000
Training Epoch: 2 [18944/47500]	Loss: 0.1615	LR: 0.100000
Training Epoch: 2 [19200/47500]	Loss: 0.2517	LR: 0.100000
Training Epoch: 2 [19456/47500]	Loss: 0.1742	LR: 0.100000
Training Epoch: 2 [19712/47500]	Loss: 0.1851	LR: 0.100000
Training Epoch: 2 [19968/47500]	Loss: 0.1265	LR: 0.100000
Training Epoch: 2 [20224/47500]	Loss: 0.1250	LR: 0.100000
Training Epoch: 2 [20480/47500]	Loss: 0.1487	LR: 0.100000
Training Epoch: 2 [20736/47500]	Loss: 0.1484	LR: 0.100000
Training Epoch: 2 [20992/47500]	Loss: 0.1206	LR: 0.100000
Training Epoch: 2 [21248/47500]	Loss: 0.1963	LR: 0.100000
Training Epoch: 2 [21504/47500]	Loss: 0.1974	LR: 0.100000
Training Epoch: 2 [21760/47500]	Loss: 0.2494	LR: 0.100000
Training Epoch: 2 [22016/47500]	Loss: 0.1374	LR: 0.100000
Training Epoch: 2 [22272/47500]	Loss: 0.1259	LR: 0.100000
Training Epoch: 2 [22528/47500]	Loss: 0.2113	LR: 0.100000
Training Epoch: 2 [22784/47500]	Loss: 0.1524	LR: 0.100000
Training Epoch: 2 [23040/47500]	Loss: 0.2021	LR: 0.100000
Training Epoch: 2 [23296/47500]	Loss: 0.2136	LR: 0.100000
Training Epoch: 2 [23552/47500]	Loss: 0.2567	LR: 0.100000
Training Epoch: 2 [23808/47500]	Loss: 0.1948	LR: 0.100000
Training Epoch: 2 [24064/47500]	Loss: 0.2080	LR: 0.100000
Training Epoch: 2 [24320/47500]	Loss: 0.1796	LR: 0.100000
Training Epoch: 2 [24576/47500]	Loss: 0.2018	LR: 0.100000
Training Epoch: 2 [24832/47500]	Loss: 0.2324	LR: 0.100000
Training Epoch: 2 [25088/47500]	Loss: 0.1642	LR: 0.100000
Training Epoch: 2 [25344/47500]	Loss: 0.2384	LR: 0.100000
Training Epoch: 2 [25600/47500]	Loss: 0.2467	LR: 0.100000
Training Epoch: 2 [25856/47500]	Loss: 0.2099	LR: 0.100000
Training Epoch: 2 [26112/47500]	Loss: 0.2511	LR: 0.100000
Training Epoch: 2 [26368/47500]	Loss: 0.3244	LR: 0.100000
Training Epoch: 2 [26624/47500]	Loss: 0.2545	LR: 0.100000
Training Epoch: 2 [26880/47500]	Loss: 0.3336	LR: 0.100000
Training Epoch: 2 [27136/47500]	Loss: 0.2429	LR: 0.100000
Training Epoch: 2 [27392/47500]	Loss: 0.1208	LR: 0.100000
Training Epoch: 2 [27648/47500]	Loss: 0.1445	LR: 0.100000
Training Epoch: 2 [27904/47500]	Loss: 0.2997	LR: 0.100000
Training Epoch: 2 [28160/47500]	Loss: 0.1962	LR: 0.100000
Training Epoch: 2 [28416/47500]	Loss: 0.1789	LR: 0.100000
Training Epoch: 2 [28672/47500]	Loss: 0.2078	LR: 0.100000
Training Epoch: 2 [28928/47500]	Loss: 0.1313	LR: 0.100000
Training Epoch: 2 [29184/47500]	Loss: 0.2007	LR: 0.100000
Training Epoch: 2 [29440/47500]	Loss: 0.1683	LR: 0.100000
Training Epoch: 2 [29696/47500]	Loss: 0.2359	LR: 0.100000
Training Epoch: 2 [29952/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 2 [30208/47500]	Loss: 0.2713	LR: 0.100000
Training Epoch: 2 [30464/47500]	Loss: 0.2762	LR: 0.100000
Training Epoch: 2 [30720/47500]	Loss: 0.1852	LR: 0.100000
Training Epoch: 2 [30976/47500]	Loss: 0.2420	LR: 0.100000
Training Epoch: 2 [31232/47500]	Loss: 0.2337	LR: 0.100000
Training Epoch: 2 [31488/47500]	Loss: 0.2174	LR: 0.100000
Training Epoch: 2 [31744/47500]	Loss: 0.2452	LR: 0.100000
Training Epoch: 2 [32000/47500]	Loss: 0.2560	LR: 0.100000
Training Epoch: 2 [32256/47500]	Loss: 0.2119	LR: 0.100000
Training Epoch: 2 [32512/47500]	Loss: 0.3038	LR: 0.100000
Training Epoch: 2 [32768/47500]	Loss: 0.2515	LR: 0.100000
Training Epoch: 2 [33024/47500]	Loss: 0.1361	LR: 0.100000
Training Epoch: 2 [33280/47500]	Loss: 0.1462	LR: 0.100000
Training Epoch: 2 [33536/47500]	Loss: 0.1687	LR: 0.100000
Training Epoch: 2 [33792/47500]	Loss: 0.1855	LR: 0.100000
Training Epoch: 2 [34048/47500]	Loss: 0.1770	LR: 0.100000
Training Epoch: 2 [34304/47500]	Loss: 0.2410	LR: 0.100000
Training Epoch: 2 [34560/47500]	Loss: 0.1489	LR: 0.100000
Training Epoch: 2 [34816/47500]	Loss: 0.1120	LR: 0.100000
Training Epoch: 2 [35072/47500]	Loss: 0.0945	LR: 0.100000
Training Epoch: 2 [35328/47500]	Loss: 0.3378	LR: 0.100000
Training Epoch: 2 [35584/47500]	Loss: 0.2534	LR: 0.100000
Training Epoch: 2 [35840/47500]	Loss: 0.2597	LR: 0.100000
Training Epoch: 2 [36096/47500]	Loss: 0.2089	LR: 0.100000
Training Epoch: 2 [36352/47500]	Loss: 0.2495	LR: 0.100000
Training Epoch: 2 [36608/47500]	Loss: 0.2058	LR: 0.100000
Training Epoch: 2 [36864/47500]	Loss: 0.3452	LR: 0.100000
Training Epoch: 2 [37120/47500]	Loss: 0.1951	LR: 0.100000
Training Epoch: 2 [37376/47500]	Loss: 0.2087	LR: 0.100000
Training Epoch: 2 [37632/47500]	Loss: 0.2447	LR: 0.100000
Training Epoch: 2 [37888/47500]	Loss: 0.2203	LR: 0.100000
Training Epoch: 2 [38144/47500]	Loss: 0.1623	LR: 0.100000
Training Epoch: 2 [38400/47500]	Loss: 0.1256	LR: 0.100000
Training Epoch: 2 [38656/47500]	Loss: 0.2093	LR: 0.100000
Training Epoch: 2 [38912/47500]	Loss: 0.1280	LR: 0.100000
Training Epoch: 2 [39168/47500]	Loss: 0.2429	LR: 0.100000
Training Epoch: 2 [39424/47500]	Loss: 0.1873	LR: 0.100000
Training Epoch: 2 [39680/47500]	Loss: 0.2227	LR: 0.100000
Training Epoch: 2 [39936/47500]	Loss: 0.1641	LR: 0.100000
Training Epoch: 2 [40192/47500]	Loss: 0.1648	LR: 0.100000
Training Epoch: 2 [40448/47500]	Loss: 0.1339	LR: 0.100000
Training Epoch: 2 [40704/47500]	Loss: 0.2342	LR: 0.100000
Training Epoch: 2 [40960/47500]	Loss: 0.1632	LR: 0.100000
Training Epoch: 2 [41216/47500]	Loss: 0.1036	LR: 0.100000
Training Epoch: 2 [41472/47500]	Loss: 0.1172	LR: 0.100000
Training Epoch: 2 [41728/47500]	Loss: 0.1420	LR: 0.100000
Training Epoch: 2 [41984/47500]	Loss: 0.2024	LR: 0.100000
Training Epoch: 2 [42240/47500]	Loss: 0.1151	LR: 0.100000
Training Epoch: 2 [42496/47500]	Loss: 0.1927	LR: 0.100000
Training Epoch: 2 [42752/47500]	Loss: 0.1742	LR: 0.100000
Training Epoch: 2 [43008/47500]	Loss: 0.1640	LR: 0.100000
Training Epoch: 2 [43264/47500]	Loss: 0.1232	LR: 0.100000
Training Epoch: 2 [43520/47500]	Loss: 0.1961	LR: 0.100000
Training Epoch: 2 [43776/47500]	Loss: 0.1900	LR: 0.100000
Training Epoch: 2 [44032/47500]	Loss: 0.2535	LR: 0.100000
Training Epoch: 2 [44288/47500]	Loss: 0.1745	LR: 0.100000
Training Epoch: 2 [44544/47500]	Loss: 0.2421	LR: 0.100000
Training Epoch: 2 [44800/47500]	Loss: 0.1935	LR: 0.100000
Training Epoch: 2 [45056/47500]	Loss: 0.2019	LR: 0.100000
Training Epoch: 2 [45312/47500]	Loss: 0.1540	LR: 0.100000
Training Epoch: 2 [45568/47500]	Loss: 0.1563	LR: 0.100000
Training Epoch: 2 [45824/47500]	Loss: 0.1943	LR: 0.100000
Training Epoch: 2 [46080/47500]	Loss: 0.2581	LR: 0.100000
Training Epoch: 2 [46336/47500]	Loss: 0.2974	LR: 0.100000
Training Epoch: 2 [46592/47500]	Loss: 0.1880	LR: 0.100000
Training Epoch: 2 [46848/47500]	Loss: 0.2022	LR: 0.100000
Training Epoch: 2 [47104/47500]	Loss: 0.1731	LR: 0.100000
Training Epoch: 2 [47360/47500]	Loss: 0.1918	LR: 0.100000
Training Epoch: 2 [47500/47500]	Loss: 0.2821	LR: 0.100000
Epoch 2 - Average Train Loss: 0.2119, Train Accuracy: 0.9279
Epoch 2 training time consumed: 343.46s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0006, Accuracy: 0.9465, Time consumed:23.48s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-2-best.pth
Training Epoch: 3 [256/47500]	Loss: 0.1284	LR: 0.100000
Training Epoch: 3 [512/47500]	Loss: 0.1881	LR: 0.100000
Training Epoch: 3 [768/47500]	Loss: 0.1964	LR: 0.100000
Training Epoch: 3 [1024/47500]	Loss: 0.2312	LR: 0.100000
Training Epoch: 3 [1280/47500]	Loss: 0.2225	LR: 0.100000
Training Epoch: 3 [1536/47500]	Loss: 0.1603	LR: 0.100000
Training Epoch: 3 [1792/47500]	Loss: 0.1029	LR: 0.100000
Training Epoch: 3 [2048/47500]	Loss: 0.1520	LR: 0.100000
Training Epoch: 3 [2304/47500]	Loss: 0.1710	LR: 0.100000
Training Epoch: 3 [2560/47500]	Loss: 0.1163	LR: 0.100000
Training Epoch: 3 [2816/47500]	Loss: 0.1146	LR: 0.100000
Training Epoch: 3 [3072/47500]	Loss: 0.1199	LR: 0.100000
Training Epoch: 3 [3328/47500]	Loss: 0.0851	LR: 0.100000
Training Epoch: 3 [3584/47500]	Loss: 0.1777	LR: 0.100000
Training Epoch: 3 [3840/47500]	Loss: 0.2057	LR: 0.100000
Training Epoch: 3 [4096/47500]	Loss: 0.1023	LR: 0.100000
Training Epoch: 3 [4352/47500]	Loss: 0.0879	LR: 0.100000
Training Epoch: 3 [4608/47500]	Loss: 0.0833	LR: 0.100000
Training Epoch: 3 [4864/47500]	Loss: 0.1570	LR: 0.100000
Training Epoch: 3 [5120/47500]	Loss: 0.1841	LR: 0.100000
Training Epoch: 3 [5376/47500]	Loss: 0.1193	LR: 0.100000
Training Epoch: 3 [5632/47500]	Loss: 0.0852	LR: 0.100000
Training Epoch: 3 [5888/47500]	Loss: 0.1286	LR: 0.100000
Training Epoch: 3 [6144/47500]	Loss: 0.1654	LR: 0.100000
Training Epoch: 3 [6400/47500]	Loss: 0.2038	LR: 0.100000
Training Epoch: 3 [6656/47500]	Loss: 0.1550	LR: 0.100000
Training Epoch: 3 [6912/47500]	Loss: 0.1179	LR: 0.100000
Training Epoch: 3 [7168/47500]	Loss: 0.1533	LR: 0.100000
Training Epoch: 3 [7424/47500]	Loss: 0.2225	LR: 0.100000
Training Epoch: 3 [7680/47500]	Loss: 0.0970	LR: 0.100000
Training Epoch: 3 [7936/47500]	Loss: 0.2448	LR: 0.100000
Training Epoch: 3 [8192/47500]	Loss: 0.1740	LR: 0.100000
Training Epoch: 3 [8448/47500]	Loss: 0.2375	LR: 0.100000
Training Epoch: 3 [8704/47500]	Loss: 0.1581	LR: 0.100000
Training Epoch: 3 [8960/47500]	Loss: 0.1592	LR: 0.100000
Training Epoch: 3 [9216/47500]	Loss: 0.1811	LR: 0.100000
Training Epoch: 3 [9472/47500]	Loss: 0.2277	LR: 0.100000
Training Epoch: 3 [9728/47500]	Loss: 0.1490	LR: 0.100000
Training Epoch: 3 [9984/47500]	Loss: 0.1973	LR: 0.100000
Training Epoch: 3 [10240/47500]	Loss: 0.2355	LR: 0.100000
Training Epoch: 3 [10496/47500]	Loss: 0.2441	LR: 0.100000
Training Epoch: 3 [10752/47500]	Loss: 0.1730	LR: 0.100000
Training Epoch: 3 [11008/47500]	Loss: 0.1584	LR: 0.100000
Training Epoch: 3 [11264/47500]	Loss: 0.2002	LR: 0.100000
Training Epoch: 3 [11520/47500]	Loss: 0.2150	LR: 0.100000
Training Epoch: 3 [11776/47500]	Loss: 0.1464	LR: 0.100000
Training Epoch: 3 [12032/47500]	Loss: 0.1335	LR: 0.100000
Training Epoch: 3 [12288/47500]	Loss: 0.1838	LR: 0.100000
Training Epoch: 3 [12544/47500]	Loss: 0.2545	LR: 0.100000
Training Epoch: 3 [12800/47500]	Loss: 0.1269	LR: 0.100000
Training Epoch: 3 [13056/47500]	Loss: 0.1032	LR: 0.100000
Training Epoch: 3 [13312/47500]	Loss: 0.1439	LR: 0.100000
Training Epoch: 3 [13568/47500]	Loss: 0.1713	LR: 0.100000
Training Epoch: 3 [13824/47500]	Loss: 0.1998	LR: 0.100000
Training Epoch: 3 [14080/47500]	Loss: 0.2068	LR: 0.100000
Training Epoch: 3 [14336/47500]	Loss: 0.1545	LR: 0.100000
Training Epoch: 3 [14592/47500]	Loss: 0.2360	LR: 0.100000
Training Epoch: 3 [14848/47500]	Loss: 0.1139	LR: 0.100000
Training Epoch: 3 [15104/47500]	Loss: 0.2580	LR: 0.100000
Training Epoch: 3 [15360/47500]	Loss: 0.1320	LR: 0.100000
Training Epoch: 3 [15616/47500]	Loss: 0.0938	LR: 0.100000
Training Epoch: 3 [15872/47500]	Loss: 0.0803	LR: 0.100000
Training Epoch: 3 [16128/47500]	Loss: 0.1950	LR: 0.100000
Training Epoch: 3 [16384/47500]	Loss: 0.1157	LR: 0.100000
Training Epoch: 3 [16640/47500]	Loss: 0.2347	LR: 0.100000
Training Epoch: 3 [16896/47500]	Loss: 0.2288	LR: 0.100000
Training Epoch: 3 [17152/47500]	Loss: 0.2280	LR: 0.100000
Training Epoch: 3 [17408/47500]	Loss: 0.1762	LR: 0.100000
Training Epoch: 3 [17664/47500]	Loss: 0.1833	LR: 0.100000
Training Epoch: 3 [17920/47500]	Loss: 0.1868	LR: 0.100000
Training Epoch: 3 [18176/47500]	Loss: 0.1437	LR: 0.100000
Training Epoch: 3 [18432/47500]	Loss: 0.1100	LR: 0.100000
Training Epoch: 3 [18688/47500]	Loss: 0.2059	LR: 0.100000
Training Epoch: 3 [18944/47500]	Loss: 0.1874	LR: 0.100000
Training Epoch: 3 [19200/47500]	Loss: 0.1435	LR: 0.100000
Training Epoch: 3 [19456/47500]	Loss: 0.2548	LR: 0.100000
Training Epoch: 3 [19712/47500]	Loss: 0.1094	LR: 0.100000
Training Epoch: 3 [19968/47500]	Loss: 0.1294	LR: 0.100000
Training Epoch: 3 [20224/47500]	Loss: 0.1047	LR: 0.100000
Training Epoch: 3 [20480/47500]	Loss: 0.1210	LR: 0.100000
Training Epoch: 3 [20736/47500]	Loss: 0.1791	LR: 0.100000
Training Epoch: 3 [20992/47500]	Loss: 0.2324	LR: 0.100000
Training Epoch: 3 [21248/47500]	Loss: 0.1582	LR: 0.100000
Training Epoch: 3 [21504/47500]	Loss: 0.1510	LR: 0.100000
Training Epoch: 3 [21760/47500]	Loss: 0.1125	LR: 0.100000
Training Epoch: 3 [22016/47500]	Loss: 0.1088	LR: 0.100000
Training Epoch: 3 [22272/47500]	Loss: 0.1136	LR: 0.100000
Training Epoch: 3 [22528/47500]	Loss: 0.1223	LR: 0.100000
Training Epoch: 3 [22784/47500]	Loss: 0.1642	LR: 0.100000
Training Epoch: 3 [23040/47500]	Loss: 0.1492	LR: 0.100000
Training Epoch: 3 [23296/47500]	Loss: 0.1724	LR: 0.100000
Training Epoch: 3 [23552/47500]	Loss: 0.1443	LR: 0.100000
Training Epoch: 3 [23808/47500]	Loss: 0.1705	LR: 0.100000
Training Epoch: 3 [24064/47500]	Loss: 0.1421	LR: 0.100000
Training Epoch: 3 [24320/47500]	Loss: 0.1748	LR: 0.100000
Training Epoch: 3 [24576/47500]	Loss: 0.1135	LR: 0.100000
Training Epoch: 3 [24832/47500]	Loss: 0.1677	LR: 0.100000
Training Epoch: 3 [25088/47500]	Loss: 0.3176	LR: 0.100000
Training Epoch: 3 [25344/47500]	Loss: 0.1462	LR: 0.100000
Training Epoch: 3 [25600/47500]	Loss: 0.2195	LR: 0.100000
Training Epoch: 3 [25856/47500]	Loss: 0.1721	LR: 0.100000
Training Epoch: 3 [26112/47500]	Loss: 0.1367	LR: 0.100000
Training Epoch: 3 [26368/47500]	Loss: 0.1553	LR: 0.100000
Training Epoch: 3 [26624/47500]	Loss: 0.1180	LR: 0.100000
Training Epoch: 3 [26880/47500]	Loss: 0.3073	LR: 0.100000
Training Epoch: 3 [27136/47500]	Loss: 0.1246	LR: 0.100000
Training Epoch: 3 [27392/47500]	Loss: 0.1342	LR: 0.100000
Training Epoch: 3 [27648/47500]	Loss: 0.1305	LR: 0.100000
Training Epoch: 3 [27904/47500]	Loss: 0.2453	LR: 0.100000
Training Epoch: 3 [28160/47500]	Loss: 0.1817	LR: 0.100000
Training Epoch: 3 [28416/47500]	Loss: 0.1755	LR: 0.100000
Training Epoch: 3 [28672/47500]	Loss: 0.1675	LR: 0.100000
Training Epoch: 3 [28928/47500]	Loss: 0.1508	LR: 0.100000
Training Epoch: 3 [29184/47500]	Loss: 0.1498	LR: 0.100000
Training Epoch: 3 [29440/47500]	Loss: 0.1764	LR: 0.100000
Training Epoch: 3 [29696/47500]	Loss: 0.1607	LR: 0.100000
Training Epoch: 3 [29952/47500]	Loss: 0.1993	LR: 0.100000
Training Epoch: 3 [30208/47500]	Loss: 0.1874	LR: 0.100000
Training Epoch: 3 [30464/47500]	Loss: 0.1541	LR: 0.100000
Training Epoch: 3 [30720/47500]	Loss: 0.2704	LR: 0.100000
Training Epoch: 3 [30976/47500]	Loss: 0.2662	LR: 0.100000
Training Epoch: 3 [31232/47500]	Loss: 0.2599	LR: 0.100000
Training Epoch: 3 [31488/47500]	Loss: 0.2761	LR: 0.100000
Training Epoch: 3 [31744/47500]	Loss: 0.2702	LR: 0.100000
Training Epoch: 3 [32000/47500]	Loss: 0.2081	LR: 0.100000
Training Epoch: 3 [32256/47500]	Loss: 0.2992	LR: 0.100000
Training Epoch: 3 [32512/47500]	Loss: 0.2401	LR: 0.100000
Training Epoch: 3 [32768/47500]	Loss: 0.2033	LR: 0.100000
Training Epoch: 3 [33024/47500]	Loss: 0.2939	LR: 0.100000
Training Epoch: 3 [33280/47500]	Loss: 0.1814	LR: 0.100000
Training Epoch: 3 [33536/47500]	Loss: 0.1662	LR: 0.100000
Training Epoch: 3 [33792/47500]	Loss: 0.1714	LR: 0.100000
Training Epoch: 3 [34048/47500]	Loss: 0.1043	LR: 0.100000
Training Epoch: 3 [34304/47500]	Loss: 0.1358	LR: 0.100000
Training Epoch: 3 [34560/47500]	Loss: 0.1555	LR: 0.100000
Training Epoch: 3 [34816/47500]	Loss: 0.3007	LR: 0.100000
Training Epoch: 3 [35072/47500]	Loss: 0.2248	LR: 0.100000
Training Epoch: 3 [35328/47500]	Loss: 0.2641	LR: 0.100000
Training Epoch: 3 [35584/47500]	Loss: 0.1865	LR: 0.100000
Training Epoch: 3 [35840/47500]	Loss: 0.2109	LR: 0.100000
Training Epoch: 3 [36096/47500]	Loss: 0.2484	LR: 0.100000
Training Epoch: 3 [36352/47500]	Loss: 0.1835	LR: 0.100000
Training Epoch: 3 [36608/47500]	Loss: 0.2552	LR: 0.100000
Training Epoch: 3 [36864/47500]	Loss: 0.1560	LR: 0.100000
Training Epoch: 3 [37120/47500]	Loss: 0.1976	LR: 0.100000
Training Epoch: 3 [37376/47500]	Loss: 0.2010	LR: 0.100000
Training Epoch: 3 [37632/47500]	Loss: 0.2344	LR: 0.100000
Training Epoch: 3 [37888/47500]	Loss: 0.1811	LR: 0.100000
Training Epoch: 3 [38144/47500]	Loss: 0.2010	LR: 0.100000
Training Epoch: 3 [38400/47500]	Loss: 0.2492	LR: 0.100000
Training Epoch: 3 [38656/47500]	Loss: 0.1625	LR: 0.100000
Training Epoch: 3 [38912/47500]	Loss: 0.1385	LR: 0.100000
Training Epoch: 3 [39168/47500]	Loss: 0.2553	LR: 0.100000
Training Epoch: 3 [39424/47500]	Loss: 0.1982	LR: 0.100000
Training Epoch: 3 [39680/47500]	Loss: 0.1487	LR: 0.100000
Training Epoch: 3 [39936/47500]	Loss: 0.2473	LR: 0.100000
Training Epoch: 3 [40192/47500]	Loss: 0.1937	LR: 0.100000
Training Epoch: 3 [40448/47500]	Loss: 0.2042	LR: 0.100000
Training Epoch: 3 [40704/47500]	Loss: 0.2443	LR: 0.100000
Training Epoch: 3 [40960/47500]	Loss: 0.1937	LR: 0.100000
Training Epoch: 3 [41216/47500]	Loss: 0.1691	LR: 0.100000
Training Epoch: 3 [41472/47500]	Loss: 0.1488	LR: 0.100000
Training Epoch: 3 [41728/47500]	Loss: 0.1999	LR: 0.100000
Training Epoch: 3 [41984/47500]	Loss: 0.1511	LR: 0.100000
Training Epoch: 3 [42240/47500]	Loss: 0.1430	LR: 0.100000
Training Epoch: 3 [42496/47500]	Loss: 0.2188	LR: 0.100000
Training Epoch: 3 [42752/47500]	Loss: 0.1172	LR: 0.100000
Training Epoch: 3 [43008/47500]	Loss: 0.2009	LR: 0.100000
Training Epoch: 3 [43264/47500]	Loss: 0.1660	LR: 0.100000
Training Epoch: 3 [43520/47500]	Loss: 0.1328	LR: 0.100000
Training Epoch: 3 [43776/47500]	Loss: 0.1888	LR: 0.100000
Training Epoch: 3 [44032/47500]	Loss: 0.1377	LR: 0.100000
Training Epoch: 3 [44288/47500]	Loss: 0.1965	LR: 0.100000
Training Epoch: 3 [44544/47500]	Loss: 0.2092	LR: 0.100000
Training Epoch: 3 [44800/47500]	Loss: 0.2811	LR: 0.100000
Training Epoch: 3 [45056/47500]	Loss: 0.1705	LR: 0.100000
Training Epoch: 3 [45312/47500]	Loss: 0.1269	LR: 0.100000
Training Epoch: 3 [45568/47500]	Loss: 0.1898	LR: 0.100000
Training Epoch: 3 [45824/47500]	Loss: 0.1780	LR: 0.100000
Training Epoch: 3 [46080/47500]	Loss: 0.2034	LR: 0.100000
Training Epoch: 3 [46336/47500]	Loss: 0.2520	LR: 0.100000
Training Epoch: 3 [46592/47500]	Loss: 0.1143	LR: 0.100000
Training Epoch: 3 [46848/47500]	Loss: 0.1612	LR: 0.100000
Training Epoch: 3 [47104/47500]	Loss: 0.1500	LR: 0.100000
Training Epoch: 3 [47360/47500]	Loss: 0.2689	LR: 0.100000
Training Epoch: 3 [47500/47500]	Loss: 0.1567	LR: 0.100000
Epoch 3 - Average Train Loss: 0.1780, Train Accuracy: 0.9399
Epoch 3 training time consumed: 343.52s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0005, Accuracy: 0.9528, Time consumed:23.47s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-3-best.pth
Training Epoch: 4 [256/47500]	Loss: 0.1289	LR: 0.100000
Training Epoch: 4 [512/47500]	Loss: 0.1062	LR: 0.100000
Training Epoch: 4 [768/47500]	Loss: 0.1296	LR: 0.100000
Training Epoch: 4 [1024/47500]	Loss: 0.1557	LR: 0.100000
Training Epoch: 4 [1280/47500]	Loss: 0.1019	LR: 0.100000
Training Epoch: 4 [1536/47500]	Loss: 0.1721	LR: 0.100000
Training Epoch: 4 [1792/47500]	Loss: 0.1556	LR: 0.100000
Training Epoch: 4 [2048/47500]	Loss: 0.1914	LR: 0.100000
Training Epoch: 4 [2304/47500]	Loss: 0.1788	LR: 0.100000
Training Epoch: 4 [2560/47500]	Loss: 0.2359	LR: 0.100000
Training Epoch: 4 [2816/47500]	Loss: 0.1956	LR: 0.100000
Training Epoch: 4 [3072/47500]	Loss: 0.0858	LR: 0.100000
Training Epoch: 4 [3328/47500]	Loss: 0.2187	LR: 0.100000
Training Epoch: 4 [3584/47500]	Loss: 0.1363	LR: 0.100000
Training Epoch: 4 [3840/47500]	Loss: 0.1413	LR: 0.100000
Training Epoch: 4 [4096/47500]	Loss: 0.1617	LR: 0.100000
Training Epoch: 4 [4352/47500]	Loss: 0.1656	LR: 0.100000
Training Epoch: 4 [4608/47500]	Loss: 0.1677	LR: 0.100000
Training Epoch: 4 [4864/47500]	Loss: 0.1909	LR: 0.100000
Training Epoch: 4 [5120/47500]	Loss: 0.1478	LR: 0.100000
Training Epoch: 4 [5376/47500]	Loss: 0.1511	LR: 0.100000
Training Epoch: 4 [5632/47500]	Loss: 0.1635	LR: 0.100000
Training Epoch: 4 [5888/47500]	Loss: 0.2007	LR: 0.100000
Training Epoch: 4 [6144/47500]	Loss: 0.1643	LR: 0.100000
Training Epoch: 4 [6400/47500]	Loss: 0.0450	LR: 0.100000
Training Epoch: 4 [6656/47500]	Loss: 0.1168	LR: 0.100000
Training Epoch: 4 [6912/47500]	Loss: 0.1045	LR: 0.100000
Training Epoch: 4 [7168/47500]	Loss: 0.1159	LR: 0.100000
Training Epoch: 4 [7424/47500]	Loss: 0.1399	LR: 0.100000
Training Epoch: 4 [7680/47500]	Loss: 0.1602	LR: 0.100000
Training Epoch: 4 [7936/47500]	Loss: 0.1426	LR: 0.100000
Training Epoch: 4 [8192/47500]	Loss: 0.1076	LR: 0.100000
Training Epoch: 4 [8448/47500]	Loss: 0.1721	LR: 0.100000
Training Epoch: 4 [8704/47500]	Loss: 0.1445	LR: 0.100000
Training Epoch: 4 [8960/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 4 [9216/47500]	Loss: 0.0813	LR: 0.100000
Training Epoch: 4 [9472/47500]	Loss: 0.1912	LR: 0.100000
Training Epoch: 4 [9728/47500]	Loss: 0.1313	LR: 0.100000
Training Epoch: 4 [9984/47500]	Loss: 0.1594	LR: 0.100000
Training Epoch: 4 [10240/47500]	Loss: 0.1803	LR: 0.100000
Training Epoch: 4 [10496/47500]	Loss: 0.1305	LR: 0.100000
Training Epoch: 4 [10752/47500]	Loss: 0.1184	LR: 0.100000
Training Epoch: 4 [11008/47500]	Loss: 0.0881	LR: 0.100000
Training Epoch: 4 [11264/47500]	Loss: 0.0755	LR: 0.100000
Training Epoch: 4 [11520/47500]	Loss: 0.1748	LR: 0.100000
Training Epoch: 4 [11776/47500]	Loss: 0.1234	LR: 0.100000
Training Epoch: 4 [12032/47500]	Loss: 0.0895	LR: 0.100000
Training Epoch: 4 [12288/47500]	Loss: 0.0961	LR: 0.100000
Training Epoch: 4 [12544/47500]	Loss: 0.0654	LR: 0.100000
Training Epoch: 4 [12800/47500]	Loss: 0.2008	LR: 0.100000
Training Epoch: 4 [13056/47500]	Loss: 0.1227	LR: 0.100000
Training Epoch: 4 [13312/47500]	Loss: 0.0787	LR: 0.100000
Training Epoch: 4 [13568/47500]	Loss: 0.1706	LR: 0.100000
Training Epoch: 4 [13824/47500]	Loss: 0.2214	LR: 0.100000
Training Epoch: 4 [14080/47500]	Loss: 0.1745	LR: 0.100000
Training Epoch: 4 [14336/47500]	Loss: 0.1631	LR: 0.100000
Training Epoch: 4 [14592/47500]	Loss: 0.1390	LR: 0.100000
Training Epoch: 4 [14848/47500]	Loss: 0.1958	LR: 0.100000
Training Epoch: 4 [15104/47500]	Loss: 0.1410	LR: 0.100000
Training Epoch: 4 [15360/47500]	Loss: 0.1213	LR: 0.100000
Training Epoch: 4 [15616/47500]	Loss: 0.1370	LR: 0.100000
Training Epoch: 4 [15872/47500]	Loss: 0.2070	LR: 0.100000
Training Epoch: 4 [16128/47500]	Loss: 0.1725	LR: 0.100000
Training Epoch: 4 [16384/47500]	Loss: 0.1778	LR: 0.100000
Training Epoch: 4 [16640/47500]	Loss: 0.0920	LR: 0.100000
Training Epoch: 4 [16896/47500]	Loss: 0.1174	LR: 0.100000
Training Epoch: 4 [17152/47500]	Loss: 0.1019	LR: 0.100000
Training Epoch: 4 [17408/47500]	Loss: 0.1095	LR: 0.100000
Training Epoch: 4 [17664/47500]	Loss: 0.1501	LR: 0.100000
Training Epoch: 4 [17920/47500]	Loss: 0.1403	LR: 0.100000
Training Epoch: 4 [18176/47500]	Loss: 0.1475	LR: 0.100000
Training Epoch: 4 [18432/47500]	Loss: 0.1154	LR: 0.100000
Training Epoch: 4 [18688/47500]	Loss: 0.1152	LR: 0.100000
Training Epoch: 4 [18944/47500]	Loss: 0.1129	LR: 0.100000
Training Epoch: 4 [19200/47500]	Loss: 0.0822	LR: 0.100000
Training Epoch: 4 [19456/47500]	Loss: 0.0932	LR: 0.100000
Training Epoch: 4 [19712/47500]	Loss: 0.0803	LR: 0.100000
Training Epoch: 4 [19968/47500]	Loss: 0.0731	LR: 0.100000
Training Epoch: 4 [20224/47500]	Loss: 0.2054	LR: 0.100000
Training Epoch: 4 [20480/47500]	Loss: 0.1469	LR: 0.100000
Training Epoch: 4 [20736/47500]	Loss: 0.1193	LR: 0.100000
Training Epoch: 4 [20992/47500]	Loss: 0.2113	LR: 0.100000
Training Epoch: 4 [21248/47500]	Loss: 0.1191	LR: 0.100000
Training Epoch: 4 [21504/47500]	Loss: 0.2300	LR: 0.100000
Training Epoch: 4 [21760/47500]	Loss: 0.1747	LR: 0.100000
Training Epoch: 4 [22016/47500]	Loss: 0.1337	LR: 0.100000
Training Epoch: 4 [22272/47500]	Loss: 0.1335	LR: 0.100000
Training Epoch: 4 [22528/47500]	Loss: 0.1117	LR: 0.100000
Training Epoch: 4 [22784/47500]	Loss: 0.0675	LR: 0.100000
Training Epoch: 4 [23040/47500]	Loss: 0.1331	LR: 0.100000
Training Epoch: 4 [23296/47500]	Loss: 0.2129	LR: 0.100000
Training Epoch: 4 [23552/47500]	Loss: 0.1266	LR: 0.100000
Training Epoch: 4 [23808/47500]	Loss: 0.1815	LR: 0.100000
Training Epoch: 4 [24064/47500]	Loss: 0.1272	LR: 0.100000
Training Epoch: 4 [24320/47500]	Loss: 0.1307	LR: 0.100000
Training Epoch: 4 [24576/47500]	Loss: 0.1078	LR: 0.100000
Training Epoch: 4 [24832/47500]	Loss: 0.1334	LR: 0.100000
Training Epoch: 4 [25088/47500]	Loss: 0.1056	LR: 0.100000
Training Epoch: 4 [25344/47500]	Loss: 0.1439	LR: 0.100000
Training Epoch: 4 [25600/47500]	Loss: 0.1079	LR: 0.100000
Training Epoch: 4 [25856/47500]	Loss: 0.1344	LR: 0.100000
Training Epoch: 4 [26112/47500]	Loss: 0.1959	LR: 0.100000
Training Epoch: 4 [26368/47500]	Loss: 0.2305	LR: 0.100000
Training Epoch: 4 [26624/47500]	Loss: 0.1279	LR: 0.100000
Training Epoch: 4 [26880/47500]	Loss: 0.1453	LR: 0.100000
Training Epoch: 4 [27136/47500]	Loss: 0.1525	LR: 0.100000
Training Epoch: 4 [27392/47500]	Loss: 0.1389	LR: 0.100000
Training Epoch: 4 [27648/47500]	Loss: 0.1104	LR: 0.100000
Training Epoch: 4 [27904/47500]	Loss: 0.1820	LR: 0.100000
Training Epoch: 4 [28160/47500]	Loss: 0.1240	LR: 0.100000
Training Epoch: 4 [28416/47500]	Loss: 0.1472	LR: 0.100000
Training Epoch: 4 [28672/47500]	Loss: 0.1853	LR: 0.100000
Training Epoch: 4 [28928/47500]	Loss: 0.1450	LR: 0.100000
Training Epoch: 4 [29184/47500]	Loss: 0.1368	LR: 0.100000
Training Epoch: 4 [29440/47500]	Loss: 0.1098	LR: 0.100000
Training Epoch: 4 [29696/47500]	Loss: 0.2202	LR: 0.100000
Training Epoch: 4 [29952/47500]	Loss: 0.1574	LR: 0.100000
Training Epoch: 4 [30208/47500]	Loss: 0.2099	LR: 0.100000
Training Epoch: 4 [30464/47500]	Loss: 0.1700	LR: 0.100000
Training Epoch: 4 [30720/47500]	Loss: 0.1482	LR: 0.100000
Training Epoch: 4 [30976/47500]	Loss: 0.1565	LR: 0.100000
Training Epoch: 4 [31232/47500]	Loss: 0.1148	LR: 0.100000
Training Epoch: 4 [31488/47500]	Loss: 0.1202	LR: 0.100000
Training Epoch: 4 [31744/47500]	Loss: 0.1000	LR: 0.100000
Training Epoch: 4 [32000/47500]	Loss: 0.1936	LR: 0.100000
Training Epoch: 4 [32256/47500]	Loss: 0.1205	LR: 0.100000
Training Epoch: 4 [32512/47500]	Loss: 0.0900	LR: 0.100000
Training Epoch: 4 [32768/47500]	Loss: 0.1465	LR: 0.100000
Training Epoch: 4 [33024/47500]	Loss: 0.1550	LR: 0.100000
Training Epoch: 4 [33280/47500]	Loss: 0.0564	LR: 0.100000
Training Epoch: 4 [33536/47500]	Loss: 0.1491	LR: 0.100000
Training Epoch: 4 [33792/47500]	Loss: 0.1038	LR: 0.100000
Training Epoch: 4 [34048/47500]	Loss: 0.1978	LR: 0.100000
Training Epoch: 4 [34304/47500]	Loss: 0.1324	LR: 0.100000
Training Epoch: 4 [34560/47500]	Loss: 0.1226	LR: 0.100000
Training Epoch: 4 [34816/47500]	Loss: 0.0812	LR: 0.100000
Training Epoch: 4 [35072/47500]	Loss: 0.2244	LR: 0.100000
Training Epoch: 4 [35328/47500]	Loss: 0.1234	LR: 0.100000
Training Epoch: 4 [35584/47500]	Loss: 0.1477	LR: 0.100000
Training Epoch: 4 [35840/47500]	Loss: 0.1171	LR: 0.100000
Training Epoch: 4 [36096/47500]	Loss: 0.2046	LR: 0.100000
Training Epoch: 4 [36352/47500]	Loss: 0.1859	LR: 0.100000
Training Epoch: 4 [36608/47500]	Loss: 0.2068	LR: 0.100000
Training Epoch: 4 [36864/47500]	Loss: 0.1570	LR: 0.100000
Training Epoch: 4 [37120/47500]	Loss: 0.1392	LR: 0.100000
Training Epoch: 4 [37376/47500]	Loss: 0.1930	LR: 0.100000
Training Epoch: 4 [37632/47500]	Loss: 0.1456	LR: 0.100000
Training Epoch: 4 [37888/47500]	Loss: 0.0988	LR: 0.100000
Training Epoch: 4 [38144/47500]	Loss: 0.1552	LR: 0.100000
Training Epoch: 4 [38400/47500]	Loss: 0.1205	LR: 0.100000
Training Epoch: 4 [38656/47500]	Loss: 0.1875	LR: 0.100000
Training Epoch: 4 [38912/47500]	Loss: 0.0785	LR: 0.100000
Training Epoch: 4 [39168/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 4 [39424/47500]	Loss: 0.2039	LR: 0.100000
Training Epoch: 4 [39680/47500]	Loss: 0.1549	LR: 0.100000
Training Epoch: 4 [39936/47500]	Loss: 0.1968	LR: 0.100000
Training Epoch: 4 [40192/47500]	Loss: 0.1298	LR: 0.100000
Training Epoch: 4 [40448/47500]	Loss: 0.1678	LR: 0.100000
Training Epoch: 4 [40704/47500]	Loss: 0.1369	LR: 0.100000
Training Epoch: 4 [40960/47500]	Loss: 0.1358	LR: 0.100000
Training Epoch: 4 [41216/47500]	Loss: 0.1112	LR: 0.100000
Training Epoch: 4 [41472/47500]	Loss: 0.0869	LR: 0.100000
Training Epoch: 4 [41728/47500]	Loss: 0.1862	LR: 0.100000
Training Epoch: 4 [41984/47500]	Loss: 0.0755	LR: 0.100000
Training Epoch: 4 [42240/47500]	Loss: 0.1638	LR: 0.100000
Training Epoch: 4 [42496/47500]	Loss: 0.1593	LR: 0.100000
Training Epoch: 4 [42752/47500]	Loss: 0.1646	LR: 0.100000
Training Epoch: 4 [43008/47500]	Loss: 0.1781	LR: 0.100000
Training Epoch: 4 [43264/47500]	Loss: 0.0791	LR: 0.100000
Training Epoch: 4 [43520/47500]	Loss: 0.1437	LR: 0.100000
Training Epoch: 4 [43776/47500]	Loss: 0.1896	LR: 0.100000
Training Epoch: 4 [44032/47500]	Loss: 0.1701	LR: 0.100000
Training Epoch: 4 [44288/47500]	Loss: 0.1687	LR: 0.100000
Training Epoch: 4 [44544/47500]	Loss: 0.2035	LR: 0.100000
Training Epoch: 4 [44800/47500]	Loss: 0.1394	LR: 0.100000
Training Epoch: 4 [45056/47500]	Loss: 0.1069	LR: 0.100000
Training Epoch: 4 [45312/47500]	Loss: 0.1294	LR: 0.100000
Training Epoch: 4 [45568/47500]	Loss: 0.2088	LR: 0.100000
Training Epoch: 4 [45824/47500]	Loss: 0.1532	LR: 0.100000
Training Epoch: 4 [46080/47500]	Loss: 0.2039	LR: 0.100000
Training Epoch: 4 [46336/47500]	Loss: 0.1484	LR: 0.100000
Training Epoch: 4 [46592/47500]	Loss: 0.1750	LR: 0.100000
Training Epoch: 4 [46848/47500]	Loss: 0.1738	LR: 0.100000
Training Epoch: 4 [47104/47500]	Loss: 0.1662	LR: 0.100000
Training Epoch: 4 [47360/47500]	Loss: 0.1246	LR: 0.100000
Training Epoch: 4 [47500/47500]	Loss: 0.1283	LR: 0.100000
Epoch 4 - Average Train Loss: 0.1459, Train Accuracy: 0.9505
Epoch 4 training time consumed: 343.38s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0005, Accuracy: 0.9588, Time consumed:23.49s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-4-best.pth
Training Epoch: 5 [256/47500]	Loss: 0.1961	LR: 0.100000
Training Epoch: 5 [512/47500]	Loss: 0.1326	LR: 0.100000
Training Epoch: 5 [768/47500]	Loss: 0.0899	LR: 0.100000
Training Epoch: 5 [1024/47500]	Loss: 0.1102	LR: 0.100000
Training Epoch: 5 [1280/47500]	Loss: 0.1026	LR: 0.100000
Training Epoch: 5 [1536/47500]	Loss: 0.0788	LR: 0.100000
Training Epoch: 5 [1792/47500]	Loss: 0.1124	LR: 0.100000
Training Epoch: 5 [2048/47500]	Loss: 0.1608	LR: 0.100000
Training Epoch: 5 [2304/47500]	Loss: 0.1453	LR: 0.100000
Training Epoch: 5 [2560/47500]	Loss: 0.0962	LR: 0.100000
Training Epoch: 5 [2816/47500]	Loss: 0.1579	LR: 0.100000
Training Epoch: 5 [3072/47500]	Loss: 0.1462	LR: 0.100000
Training Epoch: 5 [3328/47500]	Loss: 0.1564	LR: 0.100000
Training Epoch: 5 [3584/47500]	Loss: 0.2038	LR: 0.100000
Training Epoch: 5 [3840/47500]	Loss: 0.1972	LR: 0.100000
Training Epoch: 5 [4096/47500]	Loss: 0.1229	LR: 0.100000
Training Epoch: 5 [4352/47500]	Loss: 0.1540	LR: 0.100000
Training Epoch: 5 [4608/47500]	Loss: 0.1651	LR: 0.100000
Training Epoch: 5 [4864/47500]	Loss: 0.0987	LR: 0.100000
Training Epoch: 5 [5120/47500]	Loss: 0.1756	LR: 0.100000
Training Epoch: 5 [5376/47500]	Loss: 0.1824	LR: 0.100000
Training Epoch: 5 [5632/47500]	Loss: 0.1517	LR: 0.100000
Training Epoch: 5 [5888/47500]	Loss: 0.2122	LR: 0.100000
Training Epoch: 5 [6144/47500]	Loss: 0.1721	LR: 0.100000
Training Epoch: 5 [6400/47500]	Loss: 0.1616	LR: 0.100000
Training Epoch: 5 [6656/47500]	Loss: 0.1596	LR: 0.100000
Training Epoch: 5 [6912/47500]	Loss: 0.1501	LR: 0.100000
Training Epoch: 5 [7168/47500]	Loss: 0.1084	LR: 0.100000
Training Epoch: 5 [7424/47500]	Loss: 0.1985	LR: 0.100000
Training Epoch: 5 [7680/47500]	Loss: 0.1497	LR: 0.100000
Training Epoch: 5 [7936/47500]	Loss: 0.1696	LR: 0.100000
Training Epoch: 5 [8192/47500]	Loss: 0.1289	LR: 0.100000
Training Epoch: 5 [8448/47500]	Loss: 0.1626	LR: 0.100000
Training Epoch: 5 [8704/47500]	Loss: 0.1264	LR: 0.100000
Training Epoch: 5 [8960/47500]	Loss: 0.1767	LR: 0.100000
Training Epoch: 5 [9216/47500]	Loss: 0.1329	LR: 0.100000
Training Epoch: 5 [9472/47500]	Loss: 0.1034	LR: 0.100000
Training Epoch: 5 [9728/47500]	Loss: 0.1420	LR: 0.100000
Training Epoch: 5 [9984/47500]	Loss: 0.2127	LR: 0.100000
Training Epoch: 5 [10240/47500]	Loss: 0.0826	LR: 0.100000
Training Epoch: 5 [10496/47500]	Loss: 0.0899	LR: 0.100000
Training Epoch: 5 [10752/47500]	Loss: 0.1225	LR: 0.100000
Training Epoch: 5 [11008/47500]	Loss: 0.2194	LR: 0.100000
Training Epoch: 5 [11264/47500]	Loss: 0.1780	LR: 0.100000
Training Epoch: 5 [11520/47500]	Loss: 0.0698	LR: 0.100000
Training Epoch: 5 [11776/47500]	Loss: 0.1068	LR: 0.100000
Training Epoch: 5 [12032/47500]	Loss: 0.1671	LR: 0.100000
Training Epoch: 5 [12288/47500]	Loss: 0.1258	LR: 0.100000
Training Epoch: 5 [12544/47500]	Loss: 0.2702	LR: 0.100000
Training Epoch: 5 [12800/47500]	Loss: 0.1665	LR: 0.100000
Training Epoch: 5 [13056/47500]	Loss: 0.1364	LR: 0.100000
Training Epoch: 5 [13312/47500]	Loss: 0.1830	LR: 0.100000
Training Epoch: 5 [13568/47500]	Loss: 0.2295	LR: 0.100000
Training Epoch: 5 [13824/47500]	Loss: 0.1462	LR: 0.100000
Training Epoch: 5 [14080/47500]	Loss: 0.1723	LR: 0.100000
Training Epoch: 5 [14336/47500]	Loss: 0.1285	LR: 0.100000
Training Epoch: 5 [14592/47500]	Loss: 0.1705	LR: 0.100000
Training Epoch: 5 [14848/47500]	Loss: 0.1550	LR: 0.100000
Training Epoch: 5 [15104/47500]	Loss: 0.1845	LR: 0.100000
Training Epoch: 5 [15360/47500]	Loss: 0.1209	LR: 0.100000
Training Epoch: 5 [15616/47500]	Loss: 0.1947	LR: 0.100000
Training Epoch: 5 [15872/47500]	Loss: 0.1642	LR: 0.100000
Training Epoch: 5 [16128/47500]	Loss: 0.1128	LR: 0.100000
Training Epoch: 5 [16384/47500]	Loss: 0.1629	LR: 0.100000
Training Epoch: 5 [16640/47500]	Loss: 0.1768	LR: 0.100000
Training Epoch: 5 [16896/47500]	Loss: 0.1094	LR: 0.100000
Training Epoch: 5 [17152/47500]	Loss: 0.1075	LR: 0.100000
Training Epoch: 5 [17408/47500]	Loss: 0.0881	LR: 0.100000
Training Epoch: 5 [17664/47500]	Loss: 0.1986	LR: 0.100000
Training Epoch: 5 [17920/47500]	Loss: 0.1954	LR: 0.100000
Training Epoch: 5 [18176/47500]	Loss: 0.1357	LR: 0.100000
Training Epoch: 5 [18432/47500]	Loss: 0.2055	LR: 0.100000
Training Epoch: 5 [18688/47500]	Loss: 0.1990	LR: 0.100000
Training Epoch: 5 [18944/47500]	Loss: 0.0741	LR: 0.100000
Training Epoch: 5 [19200/47500]	Loss: 0.0921	LR: 0.100000
Training Epoch: 5 [19456/47500]	Loss: 0.1156	LR: 0.100000
Training Epoch: 5 [19712/47500]	Loss: 0.1457	LR: 0.100000
Training Epoch: 5 [19968/47500]	Loss: 0.1680	LR: 0.100000
Training Epoch: 5 [20224/47500]	Loss: 0.1240	LR: 0.100000
Training Epoch: 5 [20480/47500]	Loss: 0.1518	LR: 0.100000
Training Epoch: 5 [20736/47500]	Loss: 0.2135	LR: 0.100000
Training Epoch: 5 [20992/47500]	Loss: 0.2190	LR: 0.100000
Training Epoch: 5 [21248/47500]	Loss: 0.1701	LR: 0.100000
Training Epoch: 5 [21504/47500]	Loss: 0.1287	LR: 0.100000
Training Epoch: 5 [21760/47500]	Loss: 0.1143	LR: 0.100000
Training Epoch: 5 [22016/47500]	Loss: 0.1845	LR: 0.100000
Training Epoch: 5 [22272/47500]	Loss: 0.1170	LR: 0.100000
Training Epoch: 5 [22528/47500]	Loss: 0.0660	LR: 0.100000
Training Epoch: 5 [22784/47500]	Loss: 0.1912	LR: 0.100000
Training Epoch: 5 [23040/47500]	Loss: 0.1430	LR: 0.100000
Training Epoch: 5 [23296/47500]	Loss: 0.1417	LR: 0.100000
Training Epoch: 5 [23552/47500]	Loss: 0.2466	LR: 0.100000
Training Epoch: 5 [23808/47500]	Loss: 0.1356	LR: 0.100000
Training Epoch: 5 [24064/47500]	Loss: 0.1527	LR: 0.100000
Training Epoch: 5 [24320/47500]	Loss: 0.1391	LR: 0.100000
Training Epoch: 5 [24576/47500]	Loss: 0.1231	LR: 0.100000
Training Epoch: 5 [24832/47500]	Loss: 0.2622	LR: 0.100000
Training Epoch: 5 [25088/47500]	Loss: 0.1467	LR: 0.100000
Training Epoch: 5 [25344/47500]	Loss: 0.2327	LR: 0.100000
Training Epoch: 5 [25600/47500]	Loss: 0.2126	LR: 0.100000
Training Epoch: 5 [25856/47500]	Loss: 0.2207	LR: 0.100000
Training Epoch: 5 [26112/47500]	Loss: 0.1267	LR: 0.100000
Training Epoch: 5 [26368/47500]	Loss: 0.1878	LR: 0.100000
Training Epoch: 5 [26624/47500]	Loss: 0.1492	LR: 0.100000
Training Epoch: 5 [26880/47500]	Loss: 0.1340	LR: 0.100000
Training Epoch: 5 [27136/47500]	Loss: 0.1548	LR: 0.100000
Training Epoch: 5 [27392/47500]	Loss: 0.1901	LR: 0.100000
Training Epoch: 5 [27648/47500]	Loss: 0.1248	LR: 0.100000
Training Epoch: 5 [27904/47500]	Loss: 0.2397	LR: 0.100000
Training Epoch: 5 [28160/47500]	Loss: 0.1367	LR: 0.100000
Training Epoch: 5 [28416/47500]	Loss: 0.1803	LR: 0.100000
Training Epoch: 5 [28672/47500]	Loss: 0.1058	LR: 0.100000
Training Epoch: 5 [28928/47500]	Loss: 0.1186	LR: 0.100000
Training Epoch: 5 [29184/47500]	Loss: 0.2161	LR: 0.100000
Training Epoch: 5 [29440/47500]	Loss: 0.1280	LR: 0.100000
Training Epoch: 5 [29696/47500]	Loss: 0.1501	LR: 0.100000
Training Epoch: 5 [29952/47500]	Loss: 0.1151	LR: 0.100000
Training Epoch: 5 [30208/47500]	Loss: 0.0945	LR: 0.100000
Training Epoch: 5 [30464/47500]	Loss: 0.1520	LR: 0.100000
Training Epoch: 5 [30720/47500]	Loss: 0.0748	LR: 0.100000
Training Epoch: 5 [30976/47500]	Loss: 0.1473	LR: 0.100000
Training Epoch: 5 [31232/47500]	Loss: 0.1810	LR: 0.100000
Training Epoch: 5 [31488/47500]	Loss: 0.1768	LR: 0.100000
Training Epoch: 5 [31744/47500]	Loss: 0.1564	LR: 0.100000
Training Epoch: 5 [32000/47500]	Loss: 0.2297	LR: 0.100000
Training Epoch: 5 [32256/47500]	Loss: 0.2076	LR: 0.100000
Training Epoch: 5 [32512/47500]	Loss: 0.1097	LR: 0.100000
Training Epoch: 5 [32768/47500]	Loss: 0.1852	LR: 0.100000
Training Epoch: 5 [33024/47500]	Loss: 0.2356	LR: 0.100000
Training Epoch: 5 [33280/47500]	Loss: 0.2231	LR: 0.100000
Training Epoch: 5 [33536/47500]	Loss: 0.2529	LR: 0.100000
Training Epoch: 5 [33792/47500]	Loss: 0.1828	LR: 0.100000
Training Epoch: 5 [34048/47500]	Loss: 0.1725	LR: 0.100000
Training Epoch: 5 [34304/47500]	Loss: 0.1417	LR: 0.100000
Training Epoch: 5 [34560/47500]	Loss: 0.1161	LR: 0.100000
Training Epoch: 5 [34816/47500]	Loss: 0.2044	LR: 0.100000
Training Epoch: 5 [35072/47500]	Loss: 0.2651	LR: 0.100000
Training Epoch: 5 [35328/47500]	Loss: 0.1672	LR: 0.100000
Training Epoch: 5 [35584/47500]	Loss: 0.1789	LR: 0.100000
Training Epoch: 5 [35840/47500]	Loss: 0.2073	LR: 0.100000
Training Epoch: 5 [36096/47500]	Loss: 0.1522	LR: 0.100000
Training Epoch: 5 [36352/47500]	Loss: 0.1008	LR: 0.100000
Training Epoch: 5 [36608/47500]	Loss: 0.1658	LR: 0.100000
Training Epoch: 5 [36864/47500]	Loss: 0.1789	LR: 0.100000
Training Epoch: 5 [37120/47500]	Loss: 0.1652	LR: 0.100000
Training Epoch: 5 [37376/47500]	Loss: 0.1085	LR: 0.100000
Training Epoch: 5 [37632/47500]	Loss: 0.1153	LR: 0.100000
Training Epoch: 5 [37888/47500]	Loss: 0.0863	LR: 0.100000
Training Epoch: 5 [38144/47500]	Loss: 0.1033	LR: 0.100000
Training Epoch: 5 [38400/47500]	Loss: 0.1207	LR: 0.100000
Training Epoch: 5 [38656/47500]	Loss: 0.2335	LR: 0.100000
Training Epoch: 5 [38912/47500]	Loss: 0.1389	LR: 0.100000
Training Epoch: 5 [39168/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 5 [39424/47500]	Loss: 0.1357	LR: 0.100000
Training Epoch: 5 [39680/47500]	Loss: 0.1911	LR: 0.100000
Training Epoch: 5 [39936/47500]	Loss: 0.2206	LR: 0.100000
Training Epoch: 5 [40192/47500]	Loss: 0.1561	LR: 0.100000
Training Epoch: 5 [40448/47500]	Loss: 0.3101	LR: 0.100000
Training Epoch: 5 [40704/47500]	Loss: 0.1940	LR: 0.100000
Training Epoch: 5 [40960/47500]	Loss: 0.1249	LR: 0.100000
Training Epoch: 5 [41216/47500]	Loss: 0.1821	LR: 0.100000
Training Epoch: 5 [41472/47500]	Loss: 0.2019	LR: 0.100000
Training Epoch: 5 [41728/47500]	Loss: 0.1488	LR: 0.100000
Training Epoch: 5 [41984/47500]	Loss: 0.1773	LR: 0.100000
Training Epoch: 5 [42240/47500]	Loss: 0.1679	LR: 0.100000
Training Epoch: 5 [42496/47500]	Loss: 0.2248	LR: 0.100000
Training Epoch: 5 [42752/47500]	Loss: 0.0928	LR: 0.100000
Training Epoch: 5 [43008/47500]	Loss: 0.2234	LR: 0.100000
Training Epoch: 5 [43264/47500]	Loss: 0.2181	LR: 0.100000
Training Epoch: 5 [43520/47500]	Loss: 0.1468	LR: 0.100000
Training Epoch: 5 [43776/47500]	Loss: 0.3149	LR: 0.100000
Training Epoch: 5 [44032/47500]	Loss: 0.1727	LR: 0.100000
Training Epoch: 5 [44288/47500]	Loss: 0.2549	LR: 0.100000
Training Epoch: 5 [44544/47500]	Loss: 0.1713	LR: 0.100000
Training Epoch: 5 [44800/47500]	Loss: 0.2132	LR: 0.100000
Training Epoch: 5 [45056/47500]	Loss: 0.1862	LR: 0.100000
Training Epoch: 5 [45312/47500]	Loss: 0.1415	LR: 0.100000
Training Epoch: 5 [45568/47500]	Loss: 0.2326	LR: 0.100000
Training Epoch: 5 [45824/47500]	Loss: 0.1948	LR: 0.100000
Training Epoch: 5 [46080/47500]	Loss: 0.1543	LR: 0.100000
Training Epoch: 5 [46336/47500]	Loss: 0.1675	LR: 0.100000
Training Epoch: 5 [46592/47500]	Loss: 0.2036	LR: 0.100000
Training Epoch: 5 [46848/47500]	Loss: 0.3060	LR: 0.100000
Training Epoch: 5 [47104/47500]	Loss: 0.1500	LR: 0.100000
Training Epoch: 5 [47360/47500]	Loss: 0.1739	LR: 0.100000
Training Epoch: 5 [47500/47500]	Loss: 0.1680	LR: 0.100000
Epoch 5 - Average Train Loss: 0.1626, Train Accuracy: 0.9444
Epoch 5 training time consumed: 343.51s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0008, Accuracy: 0.9306, Time consumed:23.48s
Training Epoch: 6 [256/47500]	Loss: 0.2421	LR: 0.100000
Training Epoch: 6 [512/47500]	Loss: 0.1972	LR: 0.100000
Training Epoch: 6 [768/47500]	Loss: 0.1231	LR: 0.100000
Training Epoch: 6 [1024/47500]	Loss: 0.1965	LR: 0.100000
Training Epoch: 6 [1280/47500]	Loss: 0.1784	LR: 0.100000
Training Epoch: 6 [1536/47500]	Loss: 0.2220	LR: 0.100000
Training Epoch: 6 [1792/47500]	Loss: 0.1929	LR: 0.100000
Training Epoch: 6 [2048/47500]	Loss: 0.1878	LR: 0.100000
Training Epoch: 6 [2304/47500]	Loss: 0.2248	LR: 0.100000
Training Epoch: 6 [2560/47500]	Loss: 0.1832	LR: 0.100000
Training Epoch: 6 [2816/47500]	Loss: 0.1686	LR: 0.100000
Training Epoch: 6 [3072/47500]	Loss: 0.1923	LR: 0.100000
Training Epoch: 6 [3328/47500]	Loss: 0.3039	LR: 0.100000
Training Epoch: 6 [3584/47500]	Loss: 0.1076	LR: 0.100000
Training Epoch: 6 [3840/47500]	Loss: 0.2106	LR: 0.100000
Training Epoch: 6 [4096/47500]	Loss: 0.1488	LR: 0.100000
Training Epoch: 6 [4352/47500]	Loss: 0.1605	LR: 0.100000
Training Epoch: 6 [4608/47500]	Loss: 0.1430	LR: 0.100000
Training Epoch: 6 [4864/47500]	Loss: 0.1296	LR: 0.100000
Training Epoch: 6 [5120/47500]	Loss: 0.1242	LR: 0.100000
Training Epoch: 6 [5376/47500]	Loss: 0.2374	LR: 0.100000
Training Epoch: 6 [5632/47500]	Loss: 0.1977	LR: 0.100000
Training Epoch: 6 [5888/47500]	Loss: 0.1346	LR: 0.100000
Training Epoch: 6 [6144/47500]	Loss: 0.1848	LR: 0.100000
Training Epoch: 6 [6400/47500]	Loss: 0.2684	LR: 0.100000
Training Epoch: 6 [6656/47500]	Loss: 0.2252	LR: 0.100000
Training Epoch: 6 [6912/47500]	Loss: 0.1881	LR: 0.100000
Training Epoch: 6 [7168/47500]	Loss: 0.1962	LR: 0.100000
Training Epoch: 6 [7424/47500]	Loss: 0.2212	LR: 0.100000
Training Epoch: 6 [7680/47500]	Loss: 0.2064	LR: 0.100000
Training Epoch: 6 [7936/47500]	Loss: 0.1209	LR: 0.100000
Training Epoch: 6 [8192/47500]	Loss: 0.1723	LR: 0.100000
Training Epoch: 6 [8448/47500]	Loss: 0.1586	LR: 0.100000
Training Epoch: 6 [8704/47500]	Loss: 0.1828	LR: 0.100000
Training Epoch: 6 [8960/47500]	Loss: 0.2287	LR: 0.100000
Training Epoch: 6 [9216/47500]	Loss: 0.2001	LR: 0.100000
Training Epoch: 6 [9472/47500]	Loss: 0.1273	LR: 0.100000
Training Epoch: 6 [9728/47500]	Loss: 0.1974	LR: 0.100000
Training Epoch: 6 [9984/47500]	Loss: 0.1847	LR: 0.100000
Training Epoch: 6 [10240/47500]	Loss: 0.1803	LR: 0.100000
Training Epoch: 6 [10496/47500]	Loss: 0.1773	LR: 0.100000
Training Epoch: 6 [10752/47500]	Loss: 0.1770	LR: 0.100000
Training Epoch: 6 [11008/47500]	Loss: 0.1881	LR: 0.100000
Training Epoch: 6 [11264/47500]	Loss: 0.1696	LR: 0.100000
Training Epoch: 6 [11520/47500]	Loss: 0.2004	LR: 0.100000
Training Epoch: 6 [11776/47500]	Loss: 0.2423	LR: 0.100000
Training Epoch: 6 [12032/47500]	Loss: 0.1586	LR: 0.100000
Training Epoch: 6 [12288/47500]	Loss: 0.2143	LR: 0.100000
Training Epoch: 6 [12544/47500]	Loss: 0.2233	LR: 0.100000
Training Epoch: 6 [12800/47500]	Loss: 0.0987	LR: 0.100000
Training Epoch: 6 [13056/47500]	Loss: 0.0863	LR: 0.100000
Training Epoch: 6 [13312/47500]	Loss: 0.1588	LR: 0.100000
Training Epoch: 6 [13568/47500]	Loss: 0.1334	LR: 0.100000
Training Epoch: 6 [13824/47500]	Loss: 0.1178	LR: 0.100000
Training Epoch: 6 [14080/47500]	Loss: 0.1917	LR: 0.100000
Training Epoch: 6 [14336/47500]	Loss: 0.1945	LR: 0.100000
Training Epoch: 6 [14592/47500]	Loss: 0.1451	LR: 0.100000
Training Epoch: 6 [14848/47500]	Loss: 0.1658	LR: 0.100000
Training Epoch: 6 [15104/47500]	Loss: 0.1336	LR: 0.100000
Training Epoch: 6 [15360/47500]	Loss: 0.3701	LR: 0.100000
Training Epoch: 6 [15616/47500]	Loss: 0.1363	LR: 0.100000
Training Epoch: 6 [15872/47500]	Loss: 0.1936	LR: 0.100000
Training Epoch: 6 [16128/47500]	Loss: 0.2583	LR: 0.100000
Training Epoch: 6 [16384/47500]	Loss: 0.2353	LR: 0.100000
Training Epoch: 6 [16640/47500]	Loss: 0.2140	LR: 0.100000
Training Epoch: 6 [16896/47500]	Loss: 0.2366	LR: 0.100000
Training Epoch: 6 [17152/47500]	Loss: 0.2150	LR: 0.100000
Training Epoch: 6 [17408/47500]	Loss: 0.2723	LR: 0.100000
Training Epoch: 6 [17664/47500]	Loss: 0.1537	LR: 0.100000
Training Epoch: 6 [17920/47500]	Loss: 0.1880	LR: 0.100000
Training Epoch: 6 [18176/47500]	Loss: 0.2391	LR: 0.100000
Training Epoch: 6 [18432/47500]	Loss: 0.1099	LR: 0.100000
Training Epoch: 6 [18688/47500]	Loss: 0.2289	LR: 0.100000
Training Epoch: 6 [18944/47500]	Loss: 0.1657	LR: 0.100000
Training Epoch: 6 [19200/47500]	Loss: 0.1786	LR: 0.100000
Training Epoch: 6 [19456/47500]	Loss: 0.1720	LR: 0.100000
Training Epoch: 6 [19712/47500]	Loss: 0.1858	LR: 0.100000
Training Epoch: 6 [19968/47500]	Loss: 0.1594	LR: 0.100000
Training Epoch: 6 [20224/47500]	Loss: 0.1011	LR: 0.100000
Training Epoch: 6 [20480/47500]	Loss: 0.1949	LR: 0.100000
Training Epoch: 6 [20736/47500]	Loss: 0.1892	LR: 0.100000
Training Epoch: 6 [20992/47500]	Loss: 0.1436	LR: 0.100000
Training Epoch: 6 [21248/47500]	Loss: 0.1839	LR: 0.100000
Training Epoch: 6 [21504/47500]	Loss: 0.1528	LR: 0.100000
Training Epoch: 6 [21760/47500]	Loss: 0.2460	LR: 0.100000
Training Epoch: 6 [22016/47500]	Loss: 0.1522	LR: 0.100000
Training Epoch: 6 [22272/47500]	Loss: 0.1889	LR: 0.100000
Training Epoch: 6 [22528/47500]	Loss: 0.2957	LR: 0.100000
Training Epoch: 6 [22784/47500]	Loss: 0.0991	LR: 0.100000
Training Epoch: 6 [23040/47500]	Loss: 0.2793	LR: 0.100000
Training Epoch: 6 [23296/47500]	Loss: 0.2797	LR: 0.100000
Training Epoch: 6 [23552/47500]	Loss: 0.0938	LR: 0.100000
Training Epoch: 6 [23808/47500]	Loss: 0.1469	LR: 0.100000
Training Epoch: 6 [24064/47500]	Loss: 0.1923	LR: 0.100000
Training Epoch: 6 [24320/47500]	Loss: 0.1662	LR: 0.100000
Training Epoch: 6 [24576/47500]	Loss: 0.1762	LR: 0.100000
Training Epoch: 6 [24832/47500]	Loss: 0.1534	LR: 0.100000
Training Epoch: 6 [25088/47500]	Loss: 0.1313	LR: 0.100000
Training Epoch: 6 [25344/47500]	Loss: 0.1272	LR: 0.100000
Training Epoch: 6 [25600/47500]	Loss: 0.1182	LR: 0.100000
Training Epoch: 6 [25856/47500]	Loss: 0.2013	LR: 0.100000
Training Epoch: 6 [26112/47500]	Loss: 0.1610	LR: 0.100000
Training Epoch: 6 [26368/47500]	Loss: 0.2202	LR: 0.100000
Training Epoch: 6 [26624/47500]	Loss: 0.1443	LR: 0.100000
Training Epoch: 6 [26880/47500]	Loss: 0.1710	LR: 0.100000
Training Epoch: 6 [27136/47500]	Loss: 0.1731	LR: 0.100000
Training Epoch: 6 [27392/47500]	Loss: 0.2544	LR: 0.100000
Training Epoch: 6 [27648/47500]	Loss: 0.2428	LR: 0.100000
Training Epoch: 6 [27904/47500]	Loss: 0.0955	LR: 0.100000
Training Epoch: 6 [28160/47500]	Loss: 0.2152	LR: 0.100000
Training Epoch: 6 [28416/47500]	Loss: 0.2535	LR: 0.100000
Training Epoch: 6 [28672/47500]	Loss: 0.2056	LR: 0.100000
Training Epoch: 6 [28928/47500]	Loss: 0.1365	LR: 0.100000
Training Epoch: 6 [29184/47500]	Loss: 0.1202	LR: 0.100000
Training Epoch: 6 [29440/47500]	Loss: 0.2302	LR: 0.100000
Training Epoch: 6 [29696/47500]	Loss: 0.2522	LR: 0.100000
Training Epoch: 6 [29952/47500]	Loss: 0.1631	LR: 0.100000
Training Epoch: 6 [30208/47500]	Loss: 0.2106	LR: 0.100000
Training Epoch: 6 [30464/47500]	Loss: 0.1510	LR: 0.100000
Training Epoch: 6 [30720/47500]	Loss: 0.2838	LR: 0.100000
Training Epoch: 6 [30976/47500]	Loss: 0.1414	LR: 0.100000
Training Epoch: 6 [31232/47500]	Loss: 0.1601	LR: 0.100000
Training Epoch: 6 [31488/47500]	Loss: 0.3045	LR: 0.100000
Training Epoch: 6 [31744/47500]	Loss: 0.2493	LR: 0.100000
Training Epoch: 6 [32000/47500]	Loss: 0.3674	LR: 0.100000
Training Epoch: 6 [32256/47500]	Loss: 0.1269	LR: 0.100000
Training Epoch: 6 [32512/47500]	Loss: 0.1568	LR: 0.100000
Training Epoch: 6 [32768/47500]	Loss: 0.1830	LR: 0.100000
Training Epoch: 6 [33024/47500]	Loss: 0.2345	LR: 0.100000
Training Epoch: 6 [33280/47500]	Loss: 0.1560	LR: 0.100000
Training Epoch: 6 [33536/47500]	Loss: 0.2104	LR: 0.100000
Training Epoch: 6 [33792/47500]	Loss: 0.1982	LR: 0.100000
Training Epoch: 6 [34048/47500]	Loss: 0.1873	LR: 0.100000
Training Epoch: 6 [34304/47500]	Loss: 0.1966	LR: 0.100000
Training Epoch: 6 [34560/47500]	Loss: 0.1547	LR: 0.100000
Training Epoch: 6 [34816/47500]	Loss: 0.1773	LR: 0.100000
Training Epoch: 6 [35072/47500]	Loss: 0.1799	LR: 0.100000
Training Epoch: 6 [35328/47500]	Loss: 0.1416	LR: 0.100000
Training Epoch: 6 [35584/47500]	Loss: 0.1780	LR: 0.100000
Training Epoch: 6 [35840/47500]	Loss: 0.1401	LR: 0.100000
Training Epoch: 6 [36096/47500]	Loss: 0.1763	LR: 0.100000
Training Epoch: 6 [36352/47500]	Loss: 0.1460	LR: 0.100000
Training Epoch: 6 [36608/47500]	Loss: 0.1867	LR: 0.100000
Training Epoch: 6 [36864/47500]	Loss: 0.2282	LR: 0.100000
Training Epoch: 6 [37120/47500]	Loss: 0.1228	LR: 0.100000
Training Epoch: 6 [37376/47500]	Loss: 0.1891	LR: 0.100000
Training Epoch: 6 [37632/47500]	Loss: 0.1758	LR: 0.100000
Training Epoch: 6 [37888/47500]	Loss: 0.2638	LR: 0.100000
Training Epoch: 6 [38144/47500]	Loss: 0.1591	LR: 0.100000
Training Epoch: 6 [38400/47500]	Loss: 0.2392	LR: 0.100000
Training Epoch: 6 [38656/47500]	Loss: 0.1659	LR: 0.100000
Training Epoch: 6 [38912/47500]	Loss: 0.2267	LR: 0.100000
Training Epoch: 6 [39168/47500]	Loss: 0.2022	LR: 0.100000
Training Epoch: 6 [39424/47500]	Loss: 0.1753	LR: 0.100000
Training Epoch: 6 [39680/47500]	Loss: 0.3279	LR: 0.100000
Training Epoch: 6 [39936/47500]	Loss: 0.2508	LR: 0.100000
Training Epoch: 6 [40192/47500]	Loss: 0.1766	LR: 0.100000
Training Epoch: 6 [40448/47500]	Loss: 0.2054	LR: 0.100000
Training Epoch: 6 [40704/47500]	Loss: 0.2126	LR: 0.100000
Training Epoch: 6 [40960/47500]	Loss: 0.2963	LR: 0.100000
Training Epoch: 6 [41216/47500]	Loss: 0.1797	LR: 0.100000
Training Epoch: 6 [41472/47500]	Loss: 0.1411	LR: 0.100000
Training Epoch: 6 [41728/47500]	Loss: 0.1805	LR: 0.100000
Training Epoch: 6 [41984/47500]	Loss: 0.2051	LR: 0.100000
Training Epoch: 6 [42240/47500]	Loss: 0.2015	LR: 0.100000
Training Epoch: 6 [42496/47500]	Loss: 0.2048	LR: 0.100000
Training Epoch: 6 [42752/47500]	Loss: 0.3165	LR: 0.100000
Training Epoch: 6 [43008/47500]	Loss: 0.2070	LR: 0.100000
Training Epoch: 6 [43264/47500]	Loss: 0.2722	LR: 0.100000
Training Epoch: 6 [43520/47500]	Loss: 0.2207	LR: 0.100000
Training Epoch: 6 [43776/47500]	Loss: 0.3068	LR: 0.100000
Training Epoch: 6 [44032/47500]	Loss: 0.2514	LR: 0.100000
Training Epoch: 6 [44288/47500]	Loss: 0.2214	LR: 0.100000
Training Epoch: 6 [44544/47500]	Loss: 0.2035	LR: 0.100000
Training Epoch: 6 [44800/47500]	Loss: 0.3299	LR: 0.100000
Training Epoch: 6 [45056/47500]	Loss: 0.1792	LR: 0.100000
Training Epoch: 6 [45312/47500]	Loss: 0.1558	LR: 0.100000
Training Epoch: 6 [45568/47500]	Loss: 0.1776	LR: 0.100000
Training Epoch: 6 [45824/47500]	Loss: 0.1859	LR: 0.100000
Training Epoch: 6 [46080/47500]	Loss: 0.1466	LR: 0.100000
Training Epoch: 6 [46336/47500]	Loss: 0.1832	LR: 0.100000
Training Epoch: 6 [46592/47500]	Loss: 0.3053	LR: 0.100000
Training Epoch: 6 [46848/47500]	Loss: 0.2005	LR: 0.100000
Training Epoch: 6 [47104/47500]	Loss: 0.2561	LR: 0.100000
Training Epoch: 6 [47360/47500]	Loss: 0.2176	LR: 0.100000
Training Epoch: 6 [47500/47500]	Loss: 0.2202	LR: 0.100000
Epoch 6 - Average Train Loss: 0.1928, Train Accuracy: 0.9346
Epoch 6 training time consumed: 343.68s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0007, Accuracy: 0.9394, Time consumed:23.48s
Training Epoch: 7 [256/47500]	Loss: 0.1175	LR: 0.020000
Training Epoch: 7 [512/47500]	Loss: 0.1880	LR: 0.020000
Training Epoch: 7 [768/47500]	Loss: 0.1080	LR: 0.020000
Training Epoch: 7 [1024/47500]	Loss: 0.1090	LR: 0.020000
Training Epoch: 7 [1280/47500]	Loss: 0.1087	LR: 0.020000
Training Epoch: 7 [1536/47500]	Loss: 0.1169	LR: 0.020000
Training Epoch: 7 [1792/47500]	Loss: 0.0877	LR: 0.020000
Training Epoch: 7 [2048/47500]	Loss: 0.1160	LR: 0.020000
Training Epoch: 7 [2304/47500]	Loss: 0.0844	LR: 0.020000
Training Epoch: 7 [2560/47500]	Loss: 0.1333	LR: 0.020000
Training Epoch: 7 [2816/47500]	Loss: 0.0676	LR: 0.020000
Training Epoch: 7 [3072/47500]	Loss: 0.0816	LR: 0.020000
Training Epoch: 7 [3328/47500]	Loss: 0.0839	LR: 0.020000
Training Epoch: 7 [3584/47500]	Loss: 0.0812	LR: 0.020000
Training Epoch: 7 [3840/47500]	Loss: 0.0865	LR: 0.020000
Training Epoch: 7 [4096/47500]	Loss: 0.0417	LR: 0.020000
Training Epoch: 7 [4352/47500]	Loss: 0.0912	LR: 0.020000
Training Epoch: 7 [4608/47500]	Loss: 0.0664	LR: 0.020000
Training Epoch: 7 [4864/47500]	Loss: 0.0958	LR: 0.020000
Training Epoch: 7 [5120/47500]	Loss: 0.0744	LR: 0.020000
Training Epoch: 7 [5376/47500]	Loss: 0.0861	LR: 0.020000
Training Epoch: 7 [5632/47500]	Loss: 0.0816	LR: 0.020000
Training Epoch: 7 [5888/47500]	Loss: 0.0840	LR: 0.020000
Training Epoch: 7 [6144/47500]	Loss: 0.0884	LR: 0.020000
Training Epoch: 7 [6400/47500]	Loss: 0.0760	LR: 0.020000
Training Epoch: 7 [6656/47500]	Loss: 0.0674	LR: 0.020000
Training Epoch: 7 [6912/47500]	Loss: 0.0853	LR: 0.020000
Training Epoch: 7 [7168/47500]	Loss: 0.0864	LR: 0.020000
Training Epoch: 7 [7424/47500]	Loss: 0.0759	LR: 0.020000
Training Epoch: 7 [7680/47500]	Loss: 0.0777	LR: 0.020000
Training Epoch: 7 [7936/47500]	Loss: 0.0946	LR: 0.020000
Training Epoch: 7 [8192/47500]	Loss: 0.0671	LR: 0.020000
Training Epoch: 7 [8448/47500]	Loss: 0.0954	LR: 0.020000
Training Epoch: 7 [8704/47500]	Loss: 0.0859	LR: 0.020000
Training Epoch: 7 [8960/47500]	Loss: 0.0561	LR: 0.020000
Training Epoch: 7 [9216/47500]	Loss: 0.0508	LR: 0.020000
Training Epoch: 7 [9472/47500]	Loss: 0.0597	LR: 0.020000
Training Epoch: 7 [9728/47500]	Loss: 0.0498	LR: 0.020000
Training Epoch: 7 [9984/47500]	Loss: 0.1005	LR: 0.020000
Training Epoch: 7 [10240/47500]	Loss: 0.0821	LR: 0.020000
Training Epoch: 7 [10496/47500]	Loss: 0.0486	LR: 0.020000
Training Epoch: 7 [10752/47500]	Loss: 0.0589	LR: 0.020000
Training Epoch: 7 [11008/47500]	Loss: 0.0451	LR: 0.020000
Training Epoch: 7 [11264/47500]	Loss: 0.0433	LR: 0.020000
Training Epoch: 7 [11520/47500]	Loss: 0.1369	LR: 0.020000
Training Epoch: 7 [11776/47500]	Loss: 0.0505	LR: 0.020000
Training Epoch: 7 [12032/47500]	Loss: 0.0506	LR: 0.020000
Training Epoch: 7 [12288/47500]	Loss: 0.1240	LR: 0.020000
Training Epoch: 7 [12544/47500]	Loss: 0.1454	LR: 0.020000
Training Epoch: 7 [12800/47500]	Loss: 0.0511	LR: 0.020000
Training Epoch: 7 [13056/47500]	Loss: 0.0596	LR: 0.020000
Training Epoch: 7 [13312/47500]	Loss: 0.0565	LR: 0.020000
Training Epoch: 7 [13568/47500]	Loss: 0.0719	LR: 0.020000
Training Epoch: 7 [13824/47500]	Loss: 0.0988	LR: 0.020000
Training Epoch: 7 [14080/47500]	Loss: 0.0391	LR: 0.020000
Training Epoch: 7 [14336/47500]	Loss: 0.0682	LR: 0.020000
Training Epoch: 7 [14592/47500]	Loss: 0.0631	LR: 0.020000
Training Epoch: 7 [14848/47500]	Loss: 0.0894	LR: 0.020000
Training Epoch: 7 [15104/47500]	Loss: 0.0556	LR: 0.020000
Training Epoch: 7 [15360/47500]	Loss: 0.0658	LR: 0.020000
Training Epoch: 7 [15616/47500]	Loss: 0.0838	LR: 0.020000
Training Epoch: 7 [15872/47500]	Loss: 0.0805	LR: 0.020000
Training Epoch: 7 [16128/47500]	Loss: 0.0601	LR: 0.020000
Training Epoch: 7 [16384/47500]	Loss: 0.0813	LR: 0.020000
Training Epoch: 7 [16640/47500]	Loss: 0.0560	LR: 0.020000
Training Epoch: 7 [16896/47500]	Loss: 0.0707	LR: 0.020000
Training Epoch: 7 [17152/47500]	Loss: 0.0779	LR: 0.020000
Training Epoch: 7 [17408/47500]	Loss: 0.0582	LR: 0.020000
Training Epoch: 7 [17664/47500]	Loss: 0.0288	LR: 0.020000
Training Epoch: 7 [17920/47500]	Loss: 0.0893	LR: 0.020000
Training Epoch: 7 [18176/47500]	Loss: 0.0397	LR: 0.020000
Training Epoch: 7 [18432/47500]	Loss: 0.0590	LR: 0.020000
Training Epoch: 7 [18688/47500]	Loss: 0.0284	LR: 0.020000
Training Epoch: 7 [18944/47500]	Loss: 0.0430	LR: 0.020000
Training Epoch: 7 [19200/47500]	Loss: 0.0536	LR: 0.020000
Training Epoch: 7 [19456/47500]	Loss: 0.0180	LR: 0.020000
Training Epoch: 7 [19712/47500]	Loss: 0.0776	LR: 0.020000
Training Epoch: 7 [19968/47500]	Loss: 0.0739	LR: 0.020000
Training Epoch: 7 [20224/47500]	Loss: 0.0510	LR: 0.020000
Training Epoch: 7 [20480/47500]	Loss: 0.0653	LR: 0.020000
Training Epoch: 7 [20736/47500]	Loss: 0.0389	LR: 0.020000
Training Epoch: 7 [20992/47500]	Loss: 0.0801	LR: 0.020000
Training Epoch: 7 [21248/47500]	Loss: 0.0777	LR: 0.020000
Training Epoch: 7 [21504/47500]	Loss: 0.0646	LR: 0.020000
Training Epoch: 7 [21760/47500]	Loss: 0.0435	LR: 0.020000
Training Epoch: 7 [22016/47500]	Loss: 0.0766	LR: 0.020000
Training Epoch: 7 [22272/47500]	Loss: 0.0630	LR: 0.020000
Training Epoch: 7 [22528/47500]	Loss: 0.0593	LR: 0.020000
Training Epoch: 7 [22784/47500]	Loss: 0.0322	LR: 0.020000
Training Epoch: 7 [23040/47500]	Loss: 0.0392	LR: 0.020000
Training Epoch: 7 [23296/47500]	Loss: 0.0384	LR: 0.020000
Training Epoch: 7 [23552/47500]	Loss: 0.0798	LR: 0.020000
Training Epoch: 7 [23808/47500]	Loss: 0.0702	LR: 0.020000
Training Epoch: 7 [24064/47500]	Loss: 0.0546	LR: 0.020000
Training Epoch: 7 [24320/47500]	Loss: 0.0559	LR: 0.020000
Training Epoch: 7 [24576/47500]	Loss: 0.0539	LR: 0.020000
Training Epoch: 7 [24832/47500]	Loss: 0.0585	LR: 0.020000
Training Epoch: 7 [25088/47500]	Loss: 0.0299	LR: 0.020000
Training Epoch: 7 [25344/47500]	Loss: 0.0682	LR: 0.020000
Training Epoch: 7 [25600/47500]	Loss: 0.0814	LR: 0.020000
Training Epoch: 7 [25856/47500]	Loss: 0.0241	LR: 0.020000
Training Epoch: 7 [26112/47500]	Loss: 0.0288	LR: 0.020000
Training Epoch: 7 [26368/47500]	Loss: 0.0412	LR: 0.020000
Training Epoch: 7 [26624/47500]	Loss: 0.0186	LR: 0.020000
Training Epoch: 7 [26880/47500]	Loss: 0.0375	LR: 0.020000
Training Epoch: 7 [27136/47500]	Loss: 0.0944	LR: 0.020000
Training Epoch: 7 [27392/47500]	Loss: 0.0151	LR: 0.020000
Training Epoch: 7 [27648/47500]	Loss: 0.0409	LR: 0.020000
Training Epoch: 7 [27904/47500]	Loss: 0.0353	LR: 0.020000
Training Epoch: 7 [28160/47500]	Loss: 0.0178	LR: 0.020000
Training Epoch: 7 [28416/47500]	Loss: 0.0375	LR: 0.020000
Training Epoch: 7 [28672/47500]	Loss: 0.0300	LR: 0.020000
Training Epoch: 7 [28928/47500]	Loss: 0.0485	LR: 0.020000
Training Epoch: 7 [29184/47500]	Loss: 0.0334	LR: 0.020000
Training Epoch: 7 [29440/47500]	Loss: 0.0599	LR: 0.020000
Training Epoch: 7 [29696/47500]	Loss: 0.0714	LR: 0.020000
Training Epoch: 7 [29952/47500]	Loss: 0.0326	LR: 0.020000
Training Epoch: 7 [30208/47500]	Loss: 0.0391	LR: 0.020000
Training Epoch: 7 [30464/47500]	Loss: 0.0352	LR: 0.020000
Training Epoch: 7 [30720/47500]	Loss: 0.0328	LR: 0.020000
Training Epoch: 7 [30976/47500]	Loss: 0.0198	LR: 0.020000
Training Epoch: 7 [31232/47500]	Loss: 0.0597	LR: 0.020000
Training Epoch: 7 [31488/47500]	Loss: 0.0653	LR: 0.020000
Training Epoch: 7 [31744/47500]	Loss: 0.0540	LR: 0.020000
Training Epoch: 7 [32000/47500]	Loss: 0.0439	LR: 0.020000
Training Epoch: 7 [32256/47500]	Loss: 0.0532	LR: 0.020000
Training Epoch: 7 [32512/47500]	Loss: 0.0267	LR: 0.020000
Training Epoch: 7 [32768/47500]	Loss: 0.0352	LR: 0.020000
Training Epoch: 7 [33024/47500]	Loss: 0.0542	LR: 0.020000
Training Epoch: 7 [33280/47500]	Loss: 0.0398	LR: 0.020000
Training Epoch: 7 [33536/47500]	Loss: 0.0676	LR: 0.020000
Training Epoch: 7 [33792/47500]	Loss: 0.0305	LR: 0.020000
Training Epoch: 7 [34048/47500]	Loss: 0.0561	LR: 0.020000
Training Epoch: 7 [34304/47500]	Loss: 0.1059	LR: 0.020000
Training Epoch: 7 [34560/47500]	Loss: 0.0426	LR: 0.020000
Training Epoch: 7 [34816/47500]	Loss: 0.0680	LR: 0.020000
Training Epoch: 7 [35072/47500]	Loss: 0.0898	LR: 0.020000
Training Epoch: 7 [35328/47500]	Loss: 0.0240	LR: 0.020000
Training Epoch: 7 [35584/47500]	Loss: 0.0540	LR: 0.020000
Training Epoch: 7 [35840/47500]	Loss: 0.0478	LR: 0.020000
Training Epoch: 7 [36096/47500]	Loss: 0.0650	LR: 0.020000
Training Epoch: 7 [36352/47500]	Loss: 0.0705	LR: 0.020000
Training Epoch: 7 [36608/47500]	Loss: 0.0611	LR: 0.020000
Training Epoch: 7 [36864/47500]	Loss: 0.0229	LR: 0.020000
Training Epoch: 7 [37120/47500]	Loss: 0.0710	LR: 0.020000
Training Epoch: 7 [37376/47500]	Loss: 0.0471	LR: 0.020000
Training Epoch: 7 [37632/47500]	Loss: 0.0306	LR: 0.020000
Training Epoch: 7 [37888/47500]	Loss: 0.0576	LR: 0.020000
Training Epoch: 7 [38144/47500]	Loss: 0.0442	LR: 0.020000
Training Epoch: 7 [38400/47500]	Loss: 0.0378	LR: 0.020000
Training Epoch: 7 [38656/47500]	Loss: 0.0327	LR: 0.020000
Training Epoch: 7 [38912/47500]	Loss: 0.0447	LR: 0.020000
Training Epoch: 7 [39168/47500]	Loss: 0.0233	LR: 0.020000
Training Epoch: 7 [39424/47500]	Loss: 0.0254	LR: 0.020000
Training Epoch: 7 [39680/47500]	Loss: 0.0090	LR: 0.020000
Training Epoch: 7 [39936/47500]	Loss: 0.0527	LR: 0.020000
Training Epoch: 7 [40192/47500]	Loss: 0.0326	LR: 0.020000
Training Epoch: 7 [40448/47500]	Loss: 0.0501	LR: 0.020000
Training Epoch: 7 [40704/47500]	Loss: 0.0569	LR: 0.020000
Training Epoch: 7 [40960/47500]	Loss: 0.0381	LR: 0.020000
Training Epoch: 7 [41216/47500]	Loss: 0.0388	LR: 0.020000
Training Epoch: 7 [41472/47500]	Loss: 0.0336	LR: 0.020000
Training Epoch: 7 [41728/47500]	Loss: 0.0957	LR: 0.020000
Training Epoch: 7 [41984/47500]	Loss: 0.0450	LR: 0.020000
Training Epoch: 7 [42240/47500]	Loss: 0.0413	LR: 0.020000
Training Epoch: 7 [42496/47500]	Loss: 0.0146	LR: 0.020000
Training Epoch: 7 [42752/47500]	Loss: 0.0731	LR: 0.020000
Training Epoch: 7 [43008/47500]	Loss: 0.0644	LR: 0.020000
Training Epoch: 7 [43264/47500]	Loss: 0.0472	LR: 0.020000
Training Epoch: 7 [43520/47500]	Loss: 0.0365	LR: 0.020000
Training Epoch: 7 [43776/47500]	Loss: 0.0233	LR: 0.020000
Training Epoch: 7 [44032/47500]	Loss: 0.0656	LR: 0.020000
Training Epoch: 7 [44288/47500]	Loss: 0.0547	LR: 0.020000
Training Epoch: 7 [44544/47500]	Loss: 0.0562	LR: 0.020000
Training Epoch: 7 [44800/47500]	Loss: 0.0370	LR: 0.020000
Training Epoch: 7 [45056/47500]	Loss: 0.0661	LR: 0.020000
Training Epoch: 7 [45312/47500]	Loss: 0.0331	LR: 0.020000
Training Epoch: 7 [45568/47500]	Loss: 0.0580	LR: 0.020000
Training Epoch: 7 [45824/47500]	Loss: 0.0244	LR: 0.020000
Training Epoch: 7 [46080/47500]	Loss: 0.0440	LR: 0.020000
Training Epoch: 7 [46336/47500]	Loss: 0.0870	LR: 0.020000
Training Epoch: 7 [46592/47500]	Loss: 0.0192	LR: 0.020000
Training Epoch: 7 [46848/47500]	Loss: 0.0750	LR: 0.020000
Training Epoch: 7 [47104/47500]	Loss: 0.0289	LR: 0.020000
Training Epoch: 7 [47360/47500]	Loss: 0.0677	LR: 0.020000
Training Epoch: 7 [47500/47500]	Loss: 0.1238	LR: 0.020000
Epoch 7 - Average Train Loss: 0.0607, Train Accuracy: 0.9788
Epoch 7 training time consumed: 343.44s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0004, Accuracy: 0.9706, Time consumed:23.46s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-7-best.pth
Training Epoch: 8 [256/47500]	Loss: 0.0319	LR: 0.020000
Training Epoch: 8 [512/47500]	Loss: 0.0455	LR: 0.020000
Training Epoch: 8 [768/47500]	Loss: 0.0510	LR: 0.020000
Training Epoch: 8 [1024/47500]	Loss: 0.0411	LR: 0.020000
Training Epoch: 8 [1280/47500]	Loss: 0.1044	LR: 0.020000
Training Epoch: 8 [1536/47500]	Loss: 0.0486	LR: 0.020000
Training Epoch: 8 [1792/47500]	Loss: 0.0136	LR: 0.020000
Training Epoch: 8 [2048/47500]	Loss: 0.0425	LR: 0.020000
Training Epoch: 8 [2304/47500]	Loss: 0.0222	LR: 0.020000
Training Epoch: 8 [2560/47500]	Loss: 0.0317	LR: 0.020000
Training Epoch: 8 [2816/47500]	Loss: 0.0758	LR: 0.020000
Training Epoch: 8 [3072/47500]	Loss: 0.0571	LR: 0.020000
Training Epoch: 8 [3328/47500]	Loss: 0.0626	LR: 0.020000
Training Epoch: 8 [3584/47500]	Loss: 0.0432	LR: 0.020000
Training Epoch: 8 [3840/47500]	Loss: 0.0300	LR: 0.020000
Training Epoch: 8 [4096/47500]	Loss: 0.0290	LR: 0.020000
Training Epoch: 8 [4352/47500]	Loss: 0.0613	LR: 0.020000
Training Epoch: 8 [4608/47500]	Loss: 0.0275	LR: 0.020000
Training Epoch: 8 [4864/47500]	Loss: 0.0532	LR: 0.020000
Training Epoch: 8 [5120/47500]	Loss: 0.0349	LR: 0.020000
Training Epoch: 8 [5376/47500]	Loss: 0.0279	LR: 0.020000
Training Epoch: 8 [5632/47500]	Loss: 0.0341	LR: 0.020000
Training Epoch: 8 [5888/47500]	Loss: 0.0592	LR: 0.020000
Training Epoch: 8 [6144/47500]	Loss: 0.0621	LR: 0.020000
Training Epoch: 8 [6400/47500]	Loss: 0.0699	LR: 0.020000
Training Epoch: 8 [6656/47500]	Loss: 0.0586	LR: 0.020000
Training Epoch: 8 [6912/47500]	Loss: 0.0151	LR: 0.020000
Training Epoch: 8 [7168/47500]	Loss: 0.0217	LR: 0.020000
Training Epoch: 8 [7424/47500]	Loss: 0.0551	LR: 0.020000
Training Epoch: 8 [7680/47500]	Loss: 0.0315	LR: 0.020000
Training Epoch: 8 [7936/47500]	Loss: 0.0227	LR: 0.020000
Training Epoch: 8 [8192/47500]	Loss: 0.0235	LR: 0.020000
Training Epoch: 8 [8448/47500]	Loss: 0.0954	LR: 0.020000
Training Epoch: 8 [8704/47500]	Loss: 0.0313	LR: 0.020000
Training Epoch: 8 [8960/47500]	Loss: 0.0552	LR: 0.020000
Training Epoch: 8 [9216/47500]	Loss: 0.0196	LR: 0.020000
Training Epoch: 8 [9472/47500]	Loss: 0.0443	LR: 0.020000
Training Epoch: 8 [9728/47500]	Loss: 0.0212	LR: 0.020000
Training Epoch: 8 [9984/47500]	Loss: 0.0197	LR: 0.020000
Training Epoch: 8 [10240/47500]	Loss: 0.0215	LR: 0.020000
Training Epoch: 8 [10496/47500]	Loss: 0.0147	LR: 0.020000
Training Epoch: 8 [10752/47500]	Loss: 0.0155	LR: 0.020000
Training Epoch: 8 [11008/47500]	Loss: 0.0284	LR: 0.020000
Training Epoch: 8 [11264/47500]	Loss: 0.0266	LR: 0.020000
Training Epoch: 8 [11520/47500]	Loss: 0.0604	LR: 0.020000
Training Epoch: 8 [11776/47500]	Loss: 0.0508	LR: 0.020000
Training Epoch: 8 [12032/47500]	Loss: 0.0140	LR: 0.020000
Training Epoch: 8 [12288/47500]	Loss: 0.0289	LR: 0.020000
Training Epoch: 8 [12544/47500]	Loss: 0.0319	LR: 0.020000
Training Epoch: 8 [12800/47500]	Loss: 0.0658	LR: 0.020000
Training Epoch: 8 [13056/47500]	Loss: 0.0418	LR: 0.020000
Training Epoch: 8 [13312/47500]	Loss: 0.0311	LR: 0.020000
Training Epoch: 8 [13568/47500]	Loss: 0.0365	LR: 0.020000
Training Epoch: 8 [13824/47500]	Loss: 0.0219	LR: 0.020000
Training Epoch: 8 [14080/47500]	Loss: 0.0351	LR: 0.020000
Training Epoch: 8 [14336/47500]	Loss: 0.0157	LR: 0.020000
Training Epoch: 8 [14592/47500]	Loss: 0.0734	LR: 0.020000
Training Epoch: 8 [14848/47500]	Loss: 0.0163	LR: 0.020000
Training Epoch: 8 [15104/47500]	Loss: 0.0244	LR: 0.020000
Training Epoch: 8 [15360/47500]	Loss: 0.0645	LR: 0.020000
Training Epoch: 8 [15616/47500]	Loss: 0.0361	LR: 0.020000
Training Epoch: 8 [15872/47500]	Loss: 0.0248	LR: 0.020000
Training Epoch: 8 [16128/47500]	Loss: 0.0517	LR: 0.020000
Training Epoch: 8 [16384/47500]	Loss: 0.0823	LR: 0.020000
Training Epoch: 8 [16640/47500]	Loss: 0.0287	LR: 0.020000
Training Epoch: 8 [16896/47500]	Loss: 0.0436	LR: 0.020000
Training Epoch: 8 [17152/47500]	Loss: 0.0225	LR: 0.020000
Training Epoch: 8 [17408/47500]	Loss: 0.0350	LR: 0.020000
Training Epoch: 8 [17664/47500]	Loss: 0.0433	LR: 0.020000
Training Epoch: 8 [17920/47500]	Loss: 0.0348	LR: 0.020000
Training Epoch: 8 [18176/47500]	Loss: 0.0219	LR: 0.020000
Training Epoch: 8 [18432/47500]	Loss: 0.0257	LR: 0.020000
Training Epoch: 8 [18688/47500]	Loss: 0.0612	LR: 0.020000
Training Epoch: 8 [18944/47500]	Loss: 0.0324	LR: 0.020000
Training Epoch: 8 [19200/47500]	Loss: 0.0836	LR: 0.020000
Training Epoch: 8 [19456/47500]	Loss: 0.0361	LR: 0.020000
Training Epoch: 8 [19712/47500]	Loss: 0.0314	LR: 0.020000
Training Epoch: 8 [19968/47500]	Loss: 0.0485	LR: 0.020000
Training Epoch: 8 [20224/47500]	Loss: 0.0229	LR: 0.020000
Training Epoch: 8 [20480/47500]	Loss: 0.0383	LR: 0.020000
Training Epoch: 8 [20736/47500]	Loss: 0.0489	LR: 0.020000
Training Epoch: 8 [20992/47500]	Loss: 0.0393	LR: 0.020000
Training Epoch: 8 [21248/47500]	Loss: 0.0128	LR: 0.020000
Training Epoch: 8 [21504/47500]	Loss: 0.0130	LR: 0.020000
Training Epoch: 8 [21760/47500]	Loss: 0.0406	LR: 0.020000
Training Epoch: 8 [22016/47500]	Loss: 0.0159	LR: 0.020000
Training Epoch: 8 [22272/47500]	Loss: 0.0537	LR: 0.020000
Training Epoch: 8 [22528/47500]	Loss: 0.0449	LR: 0.020000
Training Epoch: 8 [22784/47500]	Loss: 0.0604	LR: 0.020000
Training Epoch: 8 [23040/47500]	Loss: 0.0418	LR: 0.020000
Training Epoch: 8 [23296/47500]	Loss: 0.0240	LR: 0.020000
Training Epoch: 8 [23552/47500]	Loss: 0.0544	LR: 0.020000
Training Epoch: 8 [23808/47500]	Loss: 0.0402	LR: 0.020000
Training Epoch: 8 [24064/47500]	Loss: 0.0538	LR: 0.020000
Training Epoch: 8 [24320/47500]	Loss: 0.0426	LR: 0.020000
Training Epoch: 8 [24576/47500]	Loss: 0.0561	LR: 0.020000
Training Epoch: 8 [24832/47500]	Loss: 0.0384	LR: 0.020000
Training Epoch: 8 [25088/47500]	Loss: 0.0464	LR: 0.020000
Training Epoch: 8 [25344/47500]	Loss: 0.0280	LR: 0.020000
Training Epoch: 8 [25600/47500]	Loss: 0.0320	LR: 0.020000
Training Epoch: 8 [25856/47500]	Loss: 0.0430	LR: 0.020000
Training Epoch: 8 [26112/47500]	Loss: 0.0371	LR: 0.020000
Training Epoch: 8 [26368/47500]	Loss: 0.0157	LR: 0.020000
Training Epoch: 8 [26624/47500]	Loss: 0.0234	LR: 0.020000
Training Epoch: 8 [26880/47500]	Loss: 0.0404	LR: 0.020000
Training Epoch: 8 [27136/47500]	Loss: 0.0248	LR: 0.020000
Training Epoch: 8 [27392/47500]	Loss: 0.0485	LR: 0.020000
Training Epoch: 8 [27648/47500]	Loss: 0.0376	LR: 0.020000
Training Epoch: 8 [27904/47500]	Loss: 0.0758	LR: 0.020000
Training Epoch: 8 [28160/47500]	Loss: 0.0362	LR: 0.020000
Training Epoch: 8 [28416/47500]	Loss: 0.0315	LR: 0.020000
Training Epoch: 8 [28672/47500]	Loss: 0.0487	LR: 0.020000
Training Epoch: 8 [28928/47500]	Loss: 0.0315	LR: 0.020000
Training Epoch: 8 [29184/47500]	Loss: 0.0209	LR: 0.020000
Training Epoch: 8 [29440/47500]	Loss: 0.0255	LR: 0.020000
Training Epoch: 8 [29696/47500]	Loss: 0.0573	LR: 0.020000
Training Epoch: 8 [29952/47500]	Loss: 0.0433	LR: 0.020000
Training Epoch: 8 [30208/47500]	Loss: 0.0290	LR: 0.020000
Training Epoch: 8 [30464/47500]	Loss: 0.0228	LR: 0.020000
Training Epoch: 8 [30720/47500]	Loss: 0.0353	LR: 0.020000
Training Epoch: 8 [30976/47500]	Loss: 0.1008	LR: 0.020000
Training Epoch: 8 [31232/47500]	Loss: 0.0524	LR: 0.020000
Training Epoch: 8 [31488/47500]	Loss: 0.0215	LR: 0.020000
Training Epoch: 8 [31744/47500]	Loss: 0.0314	LR: 0.020000
Training Epoch: 8 [32000/47500]	Loss: 0.0699	LR: 0.020000
Training Epoch: 8 [32256/47500]	Loss: 0.0638	LR: 0.020000
Training Epoch: 8 [32512/47500]	Loss: 0.0631	LR: 0.020000
Training Epoch: 8 [32768/47500]	Loss: 0.0611	LR: 0.020000
Training Epoch: 8 [33024/47500]	Loss: 0.0409	LR: 0.020000
Training Epoch: 8 [33280/47500]	Loss: 0.0449	LR: 0.020000
Training Epoch: 8 [33536/47500]	Loss: 0.0518	LR: 0.020000
Training Epoch: 8 [33792/47500]	Loss: 0.0152	LR: 0.020000
Training Epoch: 8 [34048/47500]	Loss: 0.0494	LR: 0.020000
Training Epoch: 8 [34304/47500]	Loss: 0.0421	LR: 0.020000
Training Epoch: 8 [34560/47500]	Loss: 0.0454	LR: 0.020000
Training Epoch: 8 [34816/47500]	Loss: 0.0325	LR: 0.020000
Training Epoch: 8 [35072/47500]	Loss: 0.0371	LR: 0.020000
Training Epoch: 8 [35328/47500]	Loss: 0.0137	LR: 0.020000
Training Epoch: 8 [35584/47500]	Loss: 0.0345	LR: 0.020000
Training Epoch: 8 [35840/47500]	Loss: 0.0553	LR: 0.020000
Training Epoch: 8 [36096/47500]	Loss: 0.0422	LR: 0.020000
Training Epoch: 8 [36352/47500]	Loss: 0.0282	LR: 0.020000
Training Epoch: 8 [36608/47500]	Loss: 0.0204	LR: 0.020000
Training Epoch: 8 [36864/47500]	Loss: 0.0200	LR: 0.020000
Training Epoch: 8 [37120/47500]	Loss: 0.0545	LR: 0.020000
Training Epoch: 8 [37376/47500]	Loss: 0.0139	LR: 0.020000
Training Epoch: 8 [37632/47500]	Loss: 0.0729	LR: 0.020000
Training Epoch: 8 [37888/47500]	Loss: 0.0366	LR: 0.020000
Training Epoch: 8 [38144/47500]	Loss: 0.0416	LR: 0.020000
Training Epoch: 8 [38400/47500]	Loss: 0.0366	LR: 0.020000
Training Epoch: 8 [38656/47500]	Loss: 0.0530	LR: 0.020000
Training Epoch: 8 [38912/47500]	Loss: 0.0689	LR: 0.020000
Training Epoch: 8 [39168/47500]	Loss: 0.0356	LR: 0.020000
Training Epoch: 8 [39424/47500]	Loss: 0.0469	LR: 0.020000
Training Epoch: 8 [39680/47500]	Loss: 0.0387	LR: 0.020000
Training Epoch: 8 [39936/47500]	Loss: 0.0249	LR: 0.020000
Training Epoch: 8 [40192/47500]	Loss: 0.0167	LR: 0.020000
Training Epoch: 8 [40448/47500]	Loss: 0.0635	LR: 0.020000
Training Epoch: 8 [40704/47500]	Loss: 0.0436	LR: 0.020000
Training Epoch: 8 [40960/47500]	Loss: 0.0384	LR: 0.020000
Training Epoch: 8 [41216/47500]	Loss: 0.0368	LR: 0.020000
Training Epoch: 8 [41472/47500]	Loss: 0.0626	LR: 0.020000
Training Epoch: 8 [41728/47500]	Loss: 0.0540	LR: 0.020000
Training Epoch: 8 [41984/47500]	Loss: 0.0224	LR: 0.020000
Training Epoch: 8 [42240/47500]	Loss: 0.0403	LR: 0.020000
Training Epoch: 8 [42496/47500]	Loss: 0.0898	LR: 0.020000
Training Epoch: 8 [42752/47500]	Loss: 0.0336	LR: 0.020000
Training Epoch: 8 [43008/47500]	Loss: 0.0421	LR: 0.020000
Training Epoch: 8 [43264/47500]	Loss: 0.0300	LR: 0.020000
Training Epoch: 8 [43520/47500]	Loss: 0.0264	LR: 0.020000
Training Epoch: 8 [43776/47500]	Loss: 0.0470	LR: 0.020000
Training Epoch: 8 [44032/47500]	Loss: 0.0377	LR: 0.020000
Training Epoch: 8 [44288/47500]	Loss: 0.0847	LR: 0.020000
Training Epoch: 8 [44544/47500]	Loss: 0.0518	LR: 0.020000
Training Epoch: 8 [44800/47500]	Loss: 0.0289	LR: 0.020000
Training Epoch: 8 [45056/47500]	Loss: 0.0276	LR: 0.020000
Training Epoch: 8 [45312/47500]	Loss: 0.0215	LR: 0.020000
Training Epoch: 8 [45568/47500]	Loss: 0.0621	LR: 0.020000
Training Epoch: 8 [45824/47500]	Loss: 0.0451	LR: 0.020000
Training Epoch: 8 [46080/47500]	Loss: 0.0437	LR: 0.020000
Training Epoch: 8 [46336/47500]	Loss: 0.0448	LR: 0.020000
Training Epoch: 8 [46592/47500]	Loss: 0.0262	LR: 0.020000
Training Epoch: 8 [46848/47500]	Loss: 0.0173	LR: 0.020000
Training Epoch: 8 [47104/47500]	Loss: 0.0528	LR: 0.020000
Training Epoch: 8 [47360/47500]	Loss: 0.0368	LR: 0.020000
Training Epoch: 8 [47500/47500]	Loss: 0.0668	LR: 0.020000
Epoch 8 - Average Train Loss: 0.0406, Train Accuracy: 0.9863
Epoch 8 training time consumed: 343.24s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0004, Accuracy: 0.9726, Time consumed:23.48s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_18h_43m_07s/ViT-Cifar10-seed3-ret50-8-best.pth
Valid (Test) Dl:  10000
Train Dl:  50000
Retain Train Dl:  47500
Forget Train Dl:  2500
Retain Valid Dl:  47500
Forget Valid Dl:  2500
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 2500 samples
Set1 Distribution: 2500 samples
Set2 Distribution: 2500 samples
Set1 Distribution: 2500 samples
Set2 Distribution: 2500 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 97.32421875
Retain Accuracy: 98.88134002685547
Zero-Retain Forget (ZRF): 0.7739262580871582
Membership Inference Attack (MIA): 0.8284
Forget vs Retain Membership Inference Attack (MIA): 0.491
Forget vs Test Membership Inference Attack (MIA): 0.518
Test vs Retain Membership Inference Attack (MIA): 0.514
Train vs Test Membership Inference Attack (MIA): 0.51425
Forget Set Accuracy (Df): 96.5808334350586
Method Execution Time: 5366.12 seconds
