hello
hello

📌S Retain class distribution for seed 4:
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 4:
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: 2.4712	LR: 0.000000
Training Epoch: 1 [512/47500]	Loss: 2.4658	LR: 0.000538
Training Epoch: 1 [768/47500]	Loss: 2.4767	LR: 0.001075
Training Epoch: 1 [1024/47500]	Loss: 2.4274	LR: 0.001613
Training Epoch: 1 [1280/47500]	Loss: 2.3800	LR: 0.002151
Training Epoch: 1 [1536/47500]	Loss: 2.2577	LR: 0.002688
Training Epoch: 1 [1792/47500]	Loss: 2.1463	LR: 0.003226
Training Epoch: 1 [2048/47500]	Loss: 1.9574	LR: 0.003763
Training Epoch: 1 [2304/47500]	Loss: 1.7416	LR: 0.004301
Training Epoch: 1 [2560/47500]	Loss: 1.4865	LR: 0.004839
Training Epoch: 1 [2816/47500]	Loss: 1.3324	LR: 0.005376
Training Epoch: 1 [3072/47500]	Loss: 1.1635	LR: 0.005914
Training Epoch: 1 [3328/47500]	Loss: 0.8874	LR: 0.006452
Training Epoch: 1 [3584/47500]	Loss: 0.7506	LR: 0.006989
Training Epoch: 1 [3840/47500]	Loss: 0.5031	LR: 0.007527
Training Epoch: 1 [4096/47500]	Loss: 0.4300	LR: 0.008065
Training Epoch: 1 [4352/47500]	Loss: 0.4471	LR: 0.008602
Training Epoch: 1 [4608/47500]	Loss: 0.2560	LR: 0.009140
Training Epoch: 1 [4864/47500]	Loss: 0.2750	LR: 0.009677
Training Epoch: 1 [5120/47500]	Loss: 0.2761	LR: 0.010215
Training Epoch: 1 [5376/47500]	Loss: 0.2273	LR: 0.010753
Training Epoch: 1 [5632/47500]	Loss: 0.1741	LR: 0.011290
Training Epoch: 1 [5888/47500]	Loss: 0.1815	LR: 0.011828
Training Epoch: 1 [6144/47500]	Loss: 0.2128	LR: 0.012366
Training Epoch: 1 [6400/47500]	Loss: 0.2310	LR: 0.012903
Training Epoch: 1 [6656/47500]	Loss: 0.2777	LR: 0.013441
Training Epoch: 1 [6912/47500]	Loss: 0.2166	LR: 0.013978
Training Epoch: 1 [7168/47500]	Loss: 0.1166	LR: 0.014516
Training Epoch: 1 [7424/47500]	Loss: 0.2411	LR: 0.015054
Training Epoch: 1 [7680/47500]	Loss: 0.2358	LR: 0.015591
Training Epoch: 1 [7936/47500]	Loss: 0.2446	LR: 0.016129
Training Epoch: 1 [8192/47500]	Loss: 0.2308	LR: 0.016667
Training Epoch: 1 [8448/47500]	Loss: 0.1385	LR: 0.017204
Training Epoch: 1 [8704/47500]	Loss: 0.1912	LR: 0.017742
Training Epoch: 1 [8960/47500]	Loss: 0.2946	LR: 0.018280
Training Epoch: 1 [9216/47500]	Loss: 0.2433	LR: 0.018817
Training Epoch: 1 [9472/47500]	Loss: 0.2663	LR: 0.019355
Training Epoch: 1 [9728/47500]	Loss: 0.2455	LR: 0.019892
Training Epoch: 1 [9984/47500]	Loss: 0.1742	LR: 0.020430
Training Epoch: 1 [10240/47500]	Loss: 0.3121	LR: 0.020968
Training Epoch: 1 [10496/47500]	Loss: 0.3264	LR: 0.021505
Training Epoch: 1 [10752/47500]	Loss: 0.2272	LR: 0.022043
Training Epoch: 1 [11008/47500]	Loss: 0.1432	LR: 0.022581
Training Epoch: 1 [11264/47500]	Loss: 0.2613	LR: 0.023118
Training Epoch: 1 [11520/47500]	Loss: 0.3046	LR: 0.023656
Training Epoch: 1 [11776/47500]	Loss: 0.1326	LR: 0.024194
Training Epoch: 1 [12032/47500]	Loss: 0.2287	LR: 0.024731
Training Epoch: 1 [12288/47500]	Loss: 0.2595	LR: 0.025269
Training Epoch: 1 [12544/47500]	Loss: 0.2653	LR: 0.025806
Training Epoch: 1 [12800/47500]	Loss: 0.2029	LR: 0.026344
Training Epoch: 1 [13056/47500]	Loss: 0.2445	LR: 0.026882
Training Epoch: 1 [13312/47500]	Loss: 0.2325	LR: 0.027419
Training Epoch: 1 [13568/47500]	Loss: 0.2685	LR: 0.027957
Training Epoch: 1 [13824/47500]	Loss: 0.1958	LR: 0.028495
Training Epoch: 1 [14080/47500]	Loss: 0.1773	LR: 0.029032
Training Epoch: 1 [14336/47500]	Loss: 0.1761	LR: 0.029570
Training Epoch: 1 [14592/47500]	Loss: 0.2085	LR: 0.030108
Training Epoch: 1 [14848/47500]	Loss: 0.3790	LR: 0.030645
Training Epoch: 1 [15104/47500]	Loss: 0.2328	LR: 0.031183
Training Epoch: 1 [15360/47500]	Loss: 0.2850	LR: 0.031720
Training Epoch: 1 [15616/47500]	Loss: 0.2136	LR: 0.032258
Training Epoch: 1 [15872/47500]	Loss: 0.1681	LR: 0.032796
Training Epoch: 1 [16128/47500]	Loss: 0.2076	LR: 0.033333
Training Epoch: 1 [16384/47500]	Loss: 0.2643	LR: 0.033871
Training Epoch: 1 [16640/47500]	Loss: 0.2413	LR: 0.034409
Training Epoch: 1 [16896/47500]	Loss: 0.3014	LR: 0.034946
Training Epoch: 1 [17152/47500]	Loss: 0.1531	LR: 0.035484
Training Epoch: 1 [17408/47500]	Loss: 0.2623	LR: 0.036022
Training Epoch: 1 [17664/47500]	Loss: 0.1592	LR: 0.036559
Training Epoch: 1 [17920/47500]	Loss: 0.2118	LR: 0.037097
Training Epoch: 1 [18176/47500]	Loss: 0.2058	LR: 0.037634
Training Epoch: 1 [18432/47500]	Loss: 0.1052	LR: 0.038172
Training Epoch: 1 [18688/47500]	Loss: 0.1788	LR: 0.038710
Training Epoch: 1 [18944/47500]	Loss: 0.0915	LR: 0.039247
Training Epoch: 1 [19200/47500]	Loss: 0.2066	LR: 0.039785
Training Epoch: 1 [19456/47500]	Loss: 0.2847	LR: 0.040323
Training Epoch: 1 [19712/47500]	Loss: 0.1816	LR: 0.040860
Training Epoch: 1 [19968/47500]	Loss: 0.1832	LR: 0.041398
Training Epoch: 1 [20224/47500]	Loss: 0.2562	LR: 0.041935
Training Epoch: 1 [20480/47500]	Loss: 0.2872	LR: 0.042473
Training Epoch: 1 [20736/47500]	Loss: 0.1690	LR: 0.043011
Training Epoch: 1 [20992/47500]	Loss: 0.1650	LR: 0.043548
Training Epoch: 1 [21248/47500]	Loss: 0.2534	LR: 0.044086
Training Epoch: 1 [21504/47500]	Loss: 0.2182	LR: 0.044624
Training Epoch: 1 [21760/47500]	Loss: 0.2381	LR: 0.045161
Training Epoch: 1 [22016/47500]	Loss: 0.2311	LR: 0.045699
Training Epoch: 1 [22272/47500]	Loss: 0.2697	LR: 0.046237
Training Epoch: 1 [22528/47500]	Loss: 0.1348	LR: 0.046774
Training Epoch: 1 [22784/47500]	Loss: 0.3126	LR: 0.047312
Training Epoch: 1 [23040/47500]	Loss: 1.0583	LR: 0.047849
Training Epoch: 1 [23296/47500]	Loss: 2.7084	LR: 0.048387
Training Epoch: 1 [23552/47500]	Loss: 2.6629	LR: 0.048925
Training Epoch: 1 [23808/47500]	Loss: 2.5026	LR: 0.049462
Training Epoch: 1 [24064/47500]	Loss: 2.3453	LR: 0.050000
Training Epoch: 1 [24320/47500]	Loss: 2.4065	LR: 0.050538
Training Epoch: 1 [24576/47500]	Loss: 2.3303	LR: 0.051075
Training Epoch: 1 [24832/47500]	Loss: 2.5219	LR: 0.051613
Training Epoch: 1 [25088/47500]	Loss: 2.3501	LR: 0.052151
Training Epoch: 1 [25344/47500]	Loss: 2.3212	LR: 0.052688
Training Epoch: 1 [25600/47500]	Loss: 2.4018	LR: 0.053226
Training Epoch: 1 [25856/47500]	Loss: 2.3554	LR: 0.053763
Training Epoch: 1 [26112/47500]	Loss: 2.4860	LR: 0.054301
Training Epoch: 1 [26368/47500]	Loss: 2.4890	LR: 0.054839
Training Epoch: 1 [26624/47500]	Loss: 2.3512	LR: 0.055376
Training Epoch: 1 [26880/47500]	Loss: 2.3592	LR: 0.055914
Training Epoch: 1 [27136/47500]	Loss: 2.3721	LR: 0.056452
Training Epoch: 1 [27392/47500]	Loss: 2.3243	LR: 0.056989
Training Epoch: 1 [27648/47500]	Loss: 2.4334	LR: 0.057527
Training Epoch: 1 [27904/47500]	Loss: 2.3734	LR: 0.058065
Training Epoch: 1 [28160/47500]	Loss: 2.3787	LR: 0.058602
Training Epoch: 1 [28416/47500]	Loss: 2.3347	LR: 0.059140
Training Epoch: 1 [28672/47500]	Loss: 2.3427	LR: 0.059677
Training Epoch: 1 [28928/47500]	Loss: 2.3239	LR: 0.060215
Training Epoch: 1 [29184/47500]	Loss: 2.3442	LR: 0.060753
Training Epoch: 1 [29440/47500]	Loss: 2.3475	LR: 0.061290
Training Epoch: 1 [29696/47500]	Loss: 2.4013	LR: 0.061828
Training Epoch: 1 [29952/47500]	Loss: 2.3904	LR: 0.062366
Training Epoch: 1 [30208/47500]	Loss: 2.3376	LR: 0.062903
Training Epoch: 1 [30464/47500]	Loss: 2.4273	LR: 0.063441
Training Epoch: 1 [30720/47500]	Loss: 2.6271	LR: 0.063978
Training Epoch: 1 [30976/47500]	Loss: 2.4805	LR: 0.064516
Training Epoch: 1 [31232/47500]	Loss: 2.4927	LR: 0.065054
Training Epoch: 1 [31488/47500]	Loss: 2.8013	LR: 0.065591
Training Epoch: 1 [31744/47500]	Loss: 2.5780	LR: 0.066129
Training Epoch: 1 [32000/47500]	Loss: 2.4550	LR: 0.066667
Training Epoch: 1 [32256/47500]	Loss: 2.4145	LR: 0.067204
Training Epoch: 1 [32512/47500]	Loss: 2.4129	LR: 0.067742
Training Epoch: 1 [32768/47500]	Loss: 2.4905	LR: 0.068280
Training Epoch: 1 [33024/47500]	Loss: 2.3389	LR: 0.068817
Training Epoch: 1 [33280/47500]	Loss: 2.4121	LR: 0.069355
Training Epoch: 1 [33536/47500]	Loss: 2.4008	LR: 0.069892
Training Epoch: 1 [33792/47500]	Loss: 2.4516	LR: 0.070430
Training Epoch: 1 [34048/47500]	Loss: 2.4215	LR: 0.070968
Training Epoch: 1 [34304/47500]	Loss: 2.3960	LR: 0.071505
Training Epoch: 1 [34560/47500]	Loss: 2.3476	LR: 0.072043
Training Epoch: 1 [34816/47500]	Loss: 2.3687	LR: 0.072581
Training Epoch: 1 [35072/47500]	Loss: 2.3665	LR: 0.073118
Training Epoch: 1 [35328/47500]	Loss: 2.3537	LR: 0.073656
Training Epoch: 1 [35584/47500]	Loss: 2.3975	LR: 0.074194
Training Epoch: 1 [35840/47500]	Loss: 2.3513	LR: 0.074731
Training Epoch: 1 [36096/47500]	Loss: 2.3397	LR: 0.075269
Training Epoch: 1 [36352/47500]	Loss: 2.3050	LR: 0.075806
Training Epoch: 1 [36608/47500]	Loss: 2.3212	LR: 0.076344
Training Epoch: 1 [36864/47500]	Loss: 2.2947	LR: 0.076882
Training Epoch: 1 [37120/47500]	Loss: 2.3024	LR: 0.077419
Training Epoch: 1 [37376/47500]	Loss: 2.3373	LR: 0.077957
Training Epoch: 1 [37632/47500]	Loss: 2.3205	LR: 0.078495
Training Epoch: 1 [37888/47500]	Loss: 2.3309	LR: 0.079032
Training Epoch: 1 [38144/47500]	Loss: 2.2905	LR: 0.079570
Training Epoch: 1 [38400/47500]	Loss: 2.2871	LR: 0.080108
Training Epoch: 1 [38656/47500]	Loss: 2.2947	LR: 0.080645
Training Epoch: 1 [38912/47500]	Loss: 2.3203	LR: 0.081183
Training Epoch: 1 [39168/47500]	Loss: 2.2996	LR: 0.081720
Training Epoch: 1 [39424/47500]	Loss: 2.2750	LR: 0.082258
Training Epoch: 1 [39680/47500]	Loss: 2.2953	LR: 0.082796
Training Epoch: 1 [39936/47500]	Loss: 2.2998	LR: 0.083333
Training Epoch: 1 [40192/47500]	Loss: 2.3149	LR: 0.083871
Training Epoch: 1 [40448/47500]	Loss: 2.2895	LR: 0.084409
Training Epoch: 1 [40704/47500]	Loss: 2.2891	LR: 0.084946
Training Epoch: 1 [40960/47500]	Loss: 2.3047	LR: 0.085484
Training Epoch: 1 [41216/47500]	Loss: 2.2992	LR: 0.086022
Training Epoch: 1 [41472/47500]	Loss: 2.3185	LR: 0.086559
Training Epoch: 1 [41728/47500]	Loss: 2.2938	LR: 0.087097
Training Epoch: 1 [41984/47500]	Loss: 2.2948	LR: 0.087634
Training Epoch: 1 [42240/47500]	Loss: 2.2995	LR: 0.088172
Training Epoch: 1 [42496/47500]	Loss: 2.2931	LR: 0.088710
Training Epoch: 1 [42752/47500]	Loss: 2.2662	LR: 0.089247
Training Epoch: 1 [43008/47500]	Loss: 2.2827	LR: 0.089785
Training Epoch: 1 [43264/47500]	Loss: 2.2912	LR: 0.090323
Training Epoch: 1 [43520/47500]	Loss: 2.2827	LR: 0.090860
Training Epoch: 1 [43776/47500]	Loss: 2.2998	LR: 0.091398
Training Epoch: 1 [44032/47500]	Loss: 2.2805	LR: 0.091935
Training Epoch: 1 [44288/47500]	Loss: 2.2890	LR: 0.092473
Training Epoch: 1 [44544/47500]	Loss: 2.3059	LR: 0.093011
Training Epoch: 1 [44800/47500]	Loss: 2.2750	LR: 0.093548
Training Epoch: 1 [45056/47500]	Loss: 2.3067	LR: 0.094086
Training Epoch: 1 [45312/47500]	Loss: 2.3101	LR: 0.094624
Training Epoch: 1 [45568/47500]	Loss: 2.3240	LR: 0.095161
Training Epoch: 1 [45824/47500]	Loss: 2.2845	LR: 0.095699
Training Epoch: 1 [46080/47500]	Loss: 2.2796	LR: 0.096237
Training Epoch: 1 [46336/47500]	Loss: 2.3075	LR: 0.096774
Training Epoch: 1 [46592/47500]	Loss: 2.3532	LR: 0.097312
Training Epoch: 1 [46848/47500]	Loss: 2.2989	LR: 0.097849
Training Epoch: 1 [47104/47500]	Loss: 2.2912	LR: 0.098387
Training Epoch: 1 [47360/47500]	Loss: 2.3078	LR: 0.098925
Training Epoch: 1 [47500/47500]	Loss: 2.3047	LR: 0.099462
Epoch 1 - Average Train Loss: 1.4575, Train Accuracy: 0.4660
Epoch 1 training time consumed: 344.42s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0092, Accuracy: 0.1345, Time consumed:23.50s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-1-best.pth
Training Epoch: 2 [256/47500]	Loss: 2.2921	LR: 0.100000
Training Epoch: 2 [512/47500]	Loss: 2.3033	LR: 0.100000
Training Epoch: 2 [768/47500]	Loss: 2.2904	LR: 0.100000
Training Epoch: 2 [1024/47500]	Loss: 2.2799	LR: 0.100000
Training Epoch: 2 [1280/47500]	Loss: 2.3000	LR: 0.100000
Training Epoch: 2 [1536/47500]	Loss: 2.2709	LR: 0.100000
Training Epoch: 2 [1792/47500]	Loss: 2.2966	LR: 0.100000
Training Epoch: 2 [2048/47500]	Loss: 2.2470	LR: 0.100000
Training Epoch: 2 [2304/47500]	Loss: 2.2780	LR: 0.100000
Training Epoch: 2 [2560/47500]	Loss: 2.3155	LR: 0.100000
Training Epoch: 2 [2816/47500]	Loss: 2.3538	LR: 0.100000
Training Epoch: 2 [3072/47500]	Loss: 2.2738	LR: 0.100000
Training Epoch: 2 [3328/47500]	Loss: 2.2730	LR: 0.100000
Training Epoch: 2 [3584/47500]	Loss: 2.3130	LR: 0.100000
Training Epoch: 2 [3840/47500]	Loss: 2.2357	LR: 0.100000
Training Epoch: 2 [4096/47500]	Loss: 2.2430	LR: 0.100000
Training Epoch: 2 [4352/47500]	Loss: 2.2381	LR: 0.100000
Training Epoch: 2 [4608/47500]	Loss: 2.2253	LR: 0.100000
Training Epoch: 2 [4864/47500]	Loss: 2.2013	LR: 0.100000
Training Epoch: 2 [5120/47500]	Loss: 2.2091	LR: 0.100000
Training Epoch: 2 [5376/47500]	Loss: 2.1783	LR: 0.100000
Training Epoch: 2 [5632/47500]	Loss: 2.2047	LR: 0.100000
Training Epoch: 2 [5888/47500]	Loss: 2.2102	LR: 0.100000
Training Epoch: 2 [6144/47500]	Loss: 2.1993	LR: 0.100000
Training Epoch: 2 [6400/47500]	Loss: 2.1917	LR: 0.100000
Training Epoch: 2 [6656/47500]	Loss: 2.1795	LR: 0.100000
Training Epoch: 2 [6912/47500]	Loss: 2.2048	LR: 0.100000
Training Epoch: 2 [7168/47500]	Loss: 2.1945	LR: 0.100000
Training Epoch: 2 [7424/47500]	Loss: 2.1459	LR: 0.100000
Training Epoch: 2 [7680/47500]	Loss: 2.2392	LR: 0.100000
Training Epoch: 2 [7936/47500]	Loss: 2.1267	LR: 0.100000
Training Epoch: 2 [8192/47500]	Loss: 2.2236	LR: 0.100000
Training Epoch: 2 [8448/47500]	Loss: 2.1771	LR: 0.100000
Training Epoch: 2 [8704/47500]	Loss: 2.1879	LR: 0.100000
Training Epoch: 2 [8960/47500]	Loss: 2.1879	LR: 0.100000
Training Epoch: 2 [9216/47500]	Loss: 2.1549	LR: 0.100000
Training Epoch: 2 [9472/47500]	Loss: 2.1727	LR: 0.100000
Training Epoch: 2 [9728/47500]	Loss: 2.0933	LR: 0.100000
Training Epoch: 2 [9984/47500]	Loss: 2.1383	LR: 0.100000
Training Epoch: 2 [10240/47500]	Loss: 2.1816	LR: 0.100000
Training Epoch: 2 [10496/47500]	Loss: 2.2120	LR: 0.100000
Training Epoch: 2 [10752/47500]	Loss: 2.1318	LR: 0.100000
Training Epoch: 2 [11008/47500]	Loss: 2.2048	LR: 0.100000
Training Epoch: 2 [11264/47500]	Loss: 2.1226	LR: 0.100000
Training Epoch: 2 [11520/47500]	Loss: 2.1530	LR: 0.100000
Training Epoch: 2 [11776/47500]	Loss: 2.0903	LR: 0.100000
Training Epoch: 2 [12032/47500]	Loss: 2.1830	LR: 0.100000
Training Epoch: 2 [12288/47500]	Loss: 2.1378	LR: 0.100000
Training Epoch: 2 [12544/47500]	Loss: 2.2021	LR: 0.100000
Training Epoch: 2 [12800/47500]	Loss: 2.1479	LR: 0.100000
Training Epoch: 2 [13056/47500]	Loss: 2.2370	LR: 0.100000
Training Epoch: 2 [13312/47500]	Loss: 2.2079	LR: 0.100000
Training Epoch: 2 [13568/47500]	Loss: 2.1040	LR: 0.100000
Training Epoch: 2 [13824/47500]	Loss: 2.1273	LR: 0.100000
Training Epoch: 2 [14080/47500]	Loss: 2.0974	LR: 0.100000
Training Epoch: 2 [14336/47500]	Loss: 2.1519	LR: 0.100000
Training Epoch: 2 [14592/47500]	Loss: 2.1056	LR: 0.100000
Training Epoch: 2 [14848/47500]	Loss: 2.1495	LR: 0.100000
Training Epoch: 2 [15104/47500]	Loss: 2.1726	LR: 0.100000
Training Epoch: 2 [15360/47500]	Loss: 2.1406	LR: 0.100000
Training Epoch: 2 [15616/47500]	Loss: 2.1969	LR: 0.100000
Training Epoch: 2 [15872/47500]	Loss: 2.1384	LR: 0.100000
Training Epoch: 2 [16128/47500]	Loss: 2.1424	LR: 0.100000
Training Epoch: 2 [16384/47500]	Loss: 2.0873	LR: 0.100000
Training Epoch: 2 [16640/47500]	Loss: 2.1967	LR: 0.100000
Training Epoch: 2 [16896/47500]	Loss: 2.1933	LR: 0.100000
Training Epoch: 2 [17152/47500]	Loss: 2.1792	LR: 0.100000
Training Epoch: 2 [17408/47500]	Loss: 2.1387	LR: 0.100000
Training Epoch: 2 [17664/47500]	Loss: 2.1831	LR: 0.100000
Training Epoch: 2 [17920/47500]	Loss: 2.1088	LR: 0.100000
Training Epoch: 2 [18176/47500]	Loss: 2.1528	LR: 0.100000
Training Epoch: 2 [18432/47500]	Loss: 2.1854	LR: 0.100000
Training Epoch: 2 [18688/47500]	Loss: 2.2235	LR: 0.100000
Training Epoch: 2 [18944/47500]	Loss: 2.1004	LR: 0.100000
Training Epoch: 2 [19200/47500]	Loss: 2.1090	LR: 0.100000
Training Epoch: 2 [19456/47500]	Loss: 2.1428	LR: 0.100000
Training Epoch: 2 [19712/47500]	Loss: 2.1105	LR: 0.100000
Training Epoch: 2 [19968/47500]	Loss: 2.0782	LR: 0.100000
Training Epoch: 2 [20224/47500]	Loss: 2.1010	LR: 0.100000
Training Epoch: 2 [20480/47500]	Loss: 2.1223	LR: 0.100000
Training Epoch: 2 [20736/47500]	Loss: 2.1057	LR: 0.100000
Training Epoch: 2 [20992/47500]	Loss: 2.1111	LR: 0.100000
Training Epoch: 2 [21248/47500]	Loss: 2.0897	LR: 0.100000
Training Epoch: 2 [21504/47500]	Loss: 2.1350	LR: 0.100000
Training Epoch: 2 [21760/47500]	Loss: 2.1163	LR: 0.100000
Training Epoch: 2 [22016/47500]	Loss: 2.1515	LR: 0.100000
Training Epoch: 2 [22272/47500]	Loss: 2.1260	LR: 0.100000
Training Epoch: 2 [22528/47500]	Loss: 2.1161	LR: 0.100000
Training Epoch: 2 [22784/47500]	Loss: 2.2010	LR: 0.100000
Training Epoch: 2 [23040/47500]	Loss: 2.0924	LR: 0.100000
Training Epoch: 2 [23296/47500]	Loss: 2.1371	LR: 0.100000
Training Epoch: 2 [23552/47500]	Loss: 2.1276	LR: 0.100000
Training Epoch: 2 [23808/47500]	Loss: 2.1192	LR: 0.100000
Training Epoch: 2 [24064/47500]	Loss: 2.1224	LR: 0.100000
Training Epoch: 2 [24320/47500]	Loss: 2.1380	LR: 0.100000
Training Epoch: 2 [24576/47500]	Loss: 2.1471	LR: 0.100000
Training Epoch: 2 [24832/47500]	Loss: 2.1505	LR: 0.100000
Training Epoch: 2 [25088/47500]	Loss: 2.0589	LR: 0.100000
Training Epoch: 2 [25344/47500]	Loss: 2.0983	LR: 0.100000
Training Epoch: 2 [25600/47500]	Loss: 2.1126	LR: 0.100000
Training Epoch: 2 [25856/47500]	Loss: 2.1015	LR: 0.100000
Training Epoch: 2 [26112/47500]	Loss: 2.0450	LR: 0.100000
Training Epoch: 2 [26368/47500]	Loss: 2.1498	LR: 0.100000
Training Epoch: 2 [26624/47500]	Loss: 2.0622	LR: 0.100000
Training Epoch: 2 [26880/47500]	Loss: 2.1140	LR: 0.100000
Training Epoch: 2 [27136/47500]	Loss: 2.1441	LR: 0.100000
Training Epoch: 2 [27392/47500]	Loss: 2.0120	LR: 0.100000
Training Epoch: 2 [27648/47500]	Loss: 2.1334	LR: 0.100000
Training Epoch: 2 [27904/47500]	Loss: 1.9824	LR: 0.100000
Training Epoch: 2 [28160/47500]	Loss: 2.0900	LR: 0.100000
Training Epoch: 2 [28416/47500]	Loss: 2.0782	LR: 0.100000
Training Epoch: 2 [28672/47500]	Loss: 2.2136	LR: 0.100000
Training Epoch: 2 [28928/47500]	Loss: 2.1390	LR: 0.100000
Training Epoch: 2 [29184/47500]	Loss: 2.1889	LR: 0.100000
Training Epoch: 2 [29440/47500]	Loss: 1.9989	LR: 0.100000
Training Epoch: 2 [29696/47500]	Loss: 2.1240	LR: 0.100000
Training Epoch: 2 [29952/47500]	Loss: 2.1084	LR: 0.100000
Training Epoch: 2 [30208/47500]	Loss: 2.1291	LR: 0.100000
Training Epoch: 2 [30464/47500]	Loss: 2.0463	LR: 0.100000
Training Epoch: 2 [30720/47500]	Loss: 2.0704	LR: 0.100000
Training Epoch: 2 [30976/47500]	Loss: 2.1591	LR: 0.100000
Training Epoch: 2 [31232/47500]	Loss: 2.1498	LR: 0.100000
Training Epoch: 2 [31488/47500]	Loss: 2.0352	LR: 0.100000
Training Epoch: 2 [31744/47500]	Loss: 2.1274	LR: 0.100000
Training Epoch: 2 [32000/47500]	Loss: 2.1084	LR: 0.100000
Training Epoch: 2 [32256/47500]	Loss: 2.1187	LR: 0.100000
Training Epoch: 2 [32512/47500]	Loss: 2.1757	LR: 0.100000
Training Epoch: 2 [32768/47500]	Loss: 2.1363	LR: 0.100000
Training Epoch: 2 [33024/47500]	Loss: 2.1257	LR: 0.100000
Training Epoch: 2 [33280/47500]	Loss: 2.0818	LR: 0.100000
Training Epoch: 2 [33536/47500]	Loss: 2.1763	LR: 0.100000
Training Epoch: 2 [33792/47500]	Loss: 2.1539	LR: 0.100000
Training Epoch: 2 [34048/47500]	Loss: 2.1076	LR: 0.100000
Training Epoch: 2 [34304/47500]	Loss: 2.1313	LR: 0.100000
Training Epoch: 2 [34560/47500]	Loss: 2.1154	LR: 0.100000
Training Epoch: 2 [34816/47500]	Loss: 2.0715	LR: 0.100000
Training Epoch: 2 [35072/47500]	Loss: 2.1045	LR: 0.100000
Training Epoch: 2 [35328/47500]	Loss: 2.1055	LR: 0.100000
Training Epoch: 2 [35584/47500]	Loss: 2.1062	LR: 0.100000
Training Epoch: 2 [35840/47500]	Loss: 2.1377	LR: 0.100000
Training Epoch: 2 [36096/47500]	Loss: 2.0784	LR: 0.100000
Training Epoch: 2 [36352/47500]	Loss: 2.0796	LR: 0.100000
Training Epoch: 2 [36608/47500]	Loss: 2.0993	LR: 0.100000
Training Epoch: 2 [36864/47500]	Loss: 2.1149	LR: 0.100000
Training Epoch: 2 [37120/47500]	Loss: 2.1382	LR: 0.100000
Training Epoch: 2 [37376/47500]	Loss: 2.0811	LR: 0.100000
Training Epoch: 2 [37632/47500]	Loss: 2.1317	LR: 0.100000
Training Epoch: 2 [37888/47500]	Loss: 2.1824	LR: 0.100000
Training Epoch: 2 [38144/47500]	Loss: 2.1011	LR: 0.100000
Training Epoch: 2 [38400/47500]	Loss: 2.1308	LR: 0.100000
Training Epoch: 2 [38656/47500]	Loss: 2.1333	LR: 0.100000
Training Epoch: 2 [38912/47500]	Loss: 2.0682	LR: 0.100000
Training Epoch: 2 [39168/47500]	Loss: 2.0961	LR: 0.100000
Training Epoch: 2 [39424/47500]	Loss: 2.0829	LR: 0.100000
Training Epoch: 2 [39680/47500]	Loss: 2.1045	LR: 0.100000
Training Epoch: 2 [39936/47500]	Loss: 2.1754	LR: 0.100000
Training Epoch: 2 [40192/47500]	Loss: 2.1092	LR: 0.100000
Training Epoch: 2 [40448/47500]	Loss: 2.1318	LR: 0.100000
Training Epoch: 2 [40704/47500]	Loss: 2.1097	LR: 0.100000
Training Epoch: 2 [40960/47500]	Loss: 2.1144	LR: 0.100000
Training Epoch: 2 [41216/47500]	Loss: 2.0537	LR: 0.100000
Training Epoch: 2 [41472/47500]	Loss: 2.1488	LR: 0.100000
Training Epoch: 2 [41728/47500]	Loss: 2.1281	LR: 0.100000
Training Epoch: 2 [41984/47500]	Loss: 2.0836	LR: 0.100000
Training Epoch: 2 [42240/47500]	Loss: 2.0932	LR: 0.100000
Training Epoch: 2 [42496/47500]	Loss: 2.0976	LR: 0.100000
Training Epoch: 2 [42752/47500]	Loss: 2.2477	LR: 0.100000
Training Epoch: 2 [43008/47500]	Loss: 2.0540	LR: 0.100000
Training Epoch: 2 [43264/47500]	Loss: 2.1445	LR: 0.100000
Training Epoch: 2 [43520/47500]	Loss: 2.1653	LR: 0.100000
Training Epoch: 2 [43776/47500]	Loss: 2.0267	LR: 0.100000
Training Epoch: 2 [44032/47500]	Loss: 2.0754	LR: 0.100000
Training Epoch: 2 [44288/47500]	Loss: 2.0934	LR: 0.100000
Training Epoch: 2 [44544/47500]	Loss: 2.0882	LR: 0.100000
Training Epoch: 2 [44800/47500]	Loss: 2.0922	LR: 0.100000
Training Epoch: 2 [45056/47500]	Loss: 2.0609	LR: 0.100000
Training Epoch: 2 [45312/47500]	Loss: 2.1061	LR: 0.100000
Training Epoch: 2 [45568/47500]	Loss: 2.0695	LR: 0.100000
Training Epoch: 2 [45824/47500]	Loss: 2.0784	LR: 0.100000
Training Epoch: 2 [46080/47500]	Loss: 2.0607	LR: 0.100000
Training Epoch: 2 [46336/47500]	Loss: 2.0195	LR: 0.100000
Training Epoch: 2 [46592/47500]	Loss: 2.0637	LR: 0.100000
Training Epoch: 2 [46848/47500]	Loss: 2.0690	LR: 0.100000
Training Epoch: 2 [47104/47500]	Loss: 2.1430	LR: 0.100000
Training Epoch: 2 [47360/47500]	Loss: 2.0866	LR: 0.100000
Training Epoch: 2 [47500/47500]	Loss: 2.0459	LR: 0.100000
Epoch 2 - Average Train Loss: 2.1426, Train Accuracy: 0.1895
Epoch 2 training time consumed: 342.92s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0083, Accuracy: 0.2318, Time consumed:23.51s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-2-best.pth
Training Epoch: 3 [256/47500]	Loss: 2.0420	LR: 0.100000
Training Epoch: 3 [512/47500]	Loss: 2.0933	LR: 0.100000
Training Epoch: 3 [768/47500]	Loss: 2.1208	LR: 0.100000
Training Epoch: 3 [1024/47500]	Loss: 2.0551	LR: 0.100000
Training Epoch: 3 [1280/47500]	Loss: 2.1553	LR: 0.100000
Training Epoch: 3 [1536/47500]	Loss: 2.0575	LR: 0.100000
Training Epoch: 3 [1792/47500]	Loss: 2.0385	LR: 0.100000
Training Epoch: 3 [2048/47500]	Loss: 2.1587	LR: 0.100000
Training Epoch: 3 [2304/47500]	Loss: 2.0915	LR: 0.100000
Training Epoch: 3 [2560/47500]	Loss: 2.0822	LR: 0.100000
Training Epoch: 3 [2816/47500]	Loss: 2.1494	LR: 0.100000
Training Epoch: 3 [3072/47500]	Loss: 2.1734	LR: 0.100000
Training Epoch: 3 [3328/47500]	Loss: 2.0751	LR: 0.100000
Training Epoch: 3 [3584/47500]	Loss: 2.1073	LR: 0.100000
Training Epoch: 3 [3840/47500]	Loss: 2.1144	LR: 0.100000
Training Epoch: 3 [4096/47500]	Loss: 2.1025	LR: 0.100000
Training Epoch: 3 [4352/47500]	Loss: 2.1046	LR: 0.100000
Training Epoch: 3 [4608/47500]	Loss: 2.0393	LR: 0.100000
Training Epoch: 3 [4864/47500]	Loss: 2.0709	LR: 0.100000
Training Epoch: 3 [5120/47500]	Loss: 2.0991	LR: 0.100000
Training Epoch: 3 [5376/47500]	Loss: 2.0339	LR: 0.100000
Training Epoch: 3 [5632/47500]	Loss: 2.0849	LR: 0.100000
Training Epoch: 3 [5888/47500]	Loss: 2.0788	LR: 0.100000
Training Epoch: 3 [6144/47500]	Loss: 1.9709	LR: 0.100000
Training Epoch: 3 [6400/47500]	Loss: 2.0453	LR: 0.100000
Training Epoch: 3 [6656/47500]	Loss: 2.0768	LR: 0.100000
Training Epoch: 3 [6912/47500]	Loss: 2.1846	LR: 0.100000
Training Epoch: 3 [7168/47500]	Loss: 2.1406	LR: 0.100000
Training Epoch: 3 [7424/47500]	Loss: 1.9954	LR: 0.100000
Training Epoch: 3 [7680/47500]	Loss: 2.0204	LR: 0.100000
Training Epoch: 3 [7936/47500]	Loss: 2.0763	LR: 0.100000
Training Epoch: 3 [8192/47500]	Loss: 2.0372	LR: 0.100000
Training Epoch: 3 [8448/47500]	Loss: 2.0873	LR: 0.100000
Training Epoch: 3 [8704/47500]	Loss: 2.1122	LR: 0.100000
Training Epoch: 3 [8960/47500]	Loss: 2.1326	LR: 0.100000
Training Epoch: 3 [9216/47500]	Loss: 2.0881	LR: 0.100000
Training Epoch: 3 [9472/47500]	Loss: 2.0579	LR: 0.100000
Training Epoch: 3 [9728/47500]	Loss: 2.0907	LR: 0.100000
Training Epoch: 3 [9984/47500]	Loss: 2.1378	LR: 0.100000
Training Epoch: 3 [10240/47500]	Loss: 2.1355	LR: 0.100000
Training Epoch: 3 [10496/47500]	Loss: 2.1457	LR: 0.100000
Training Epoch: 3 [10752/47500]	Loss: 2.0992	LR: 0.100000
Training Epoch: 3 [11008/47500]	Loss: 2.1440	LR: 0.100000
Training Epoch: 3 [11264/47500]	Loss: 2.1932	LR: 0.100000
Training Epoch: 3 [11520/47500]	Loss: 2.0739	LR: 0.100000
Training Epoch: 3 [11776/47500]	Loss: 2.0665	LR: 0.100000
Training Epoch: 3 [12032/47500]	Loss: 2.0839	LR: 0.100000
Training Epoch: 3 [12288/47500]	Loss: 2.1308	LR: 0.100000
Training Epoch: 3 [12544/47500]	Loss: 2.0178	LR: 0.100000
Training Epoch: 3 [12800/47500]	Loss: 2.1533	LR: 0.100000
Training Epoch: 3 [13056/47500]	Loss: 2.1214	LR: 0.100000
Training Epoch: 3 [13312/47500]	Loss: 2.1674	LR: 0.100000
Training Epoch: 3 [13568/47500]	Loss: 2.0389	LR: 0.100000
Training Epoch: 3 [13824/47500]	Loss: 2.1070	LR: 0.100000
Training Epoch: 3 [14080/47500]	Loss: 2.0980	LR: 0.100000
Training Epoch: 3 [14336/47500]	Loss: 2.1146	LR: 0.100000
Training Epoch: 3 [14592/47500]	Loss: 2.0900	LR: 0.100000
Training Epoch: 3 [14848/47500]	Loss: 2.1541	LR: 0.100000
Training Epoch: 3 [15104/47500]	Loss: 2.1494	LR: 0.100000
Training Epoch: 3 [15360/47500]	Loss: 2.0795	LR: 0.100000
Training Epoch: 3 [15616/47500]	Loss: 2.0816	LR: 0.100000
Training Epoch: 3 [15872/47500]	Loss: 2.1260	LR: 0.100000
Training Epoch: 3 [16128/47500]	Loss: 2.1474	LR: 0.100000
Training Epoch: 3 [16384/47500]	Loss: 2.0319	LR: 0.100000
Training Epoch: 3 [16640/47500]	Loss: 2.0678	LR: 0.100000
Training Epoch: 3 [16896/47500]	Loss: 2.0996	LR: 0.100000
Training Epoch: 3 [17152/47500]	Loss: 2.0762	LR: 0.100000
Training Epoch: 3 [17408/47500]	Loss: 2.0688	LR: 0.100000
Training Epoch: 3 [17664/47500]	Loss: 2.0609	LR: 0.100000
Training Epoch: 3 [17920/47500]	Loss: 2.1079	LR: 0.100000
Training Epoch: 3 [18176/47500]	Loss: 2.1180	LR: 0.100000
Training Epoch: 3 [18432/47500]	Loss: 2.0119	LR: 0.100000
Training Epoch: 3 [18688/47500]	Loss: 2.1113	LR: 0.100000
Training Epoch: 3 [18944/47500]	Loss: 1.9899	LR: 0.100000
Training Epoch: 3 [19200/47500]	Loss: 2.1516	LR: 0.100000
Training Epoch: 3 [19456/47500]	Loss: 2.0507	LR: 0.100000
Training Epoch: 3 [19712/47500]	Loss: 2.0874	LR: 0.100000
Training Epoch: 3 [19968/47500]	Loss: 2.0149	LR: 0.100000
Training Epoch: 3 [20224/47500]	Loss: 2.1000	LR: 0.100000
Training Epoch: 3 [20480/47500]	Loss: 2.0693	LR: 0.100000
Training Epoch: 3 [20736/47500]	Loss: 2.0449	LR: 0.100000
Training Epoch: 3 [20992/47500]	Loss: 2.0819	LR: 0.100000
Training Epoch: 3 [21248/47500]	Loss: 2.0635	LR: 0.100000
Training Epoch: 3 [21504/47500]	Loss: 2.0832	LR: 0.100000
Training Epoch: 3 [21760/47500]	Loss: 2.0481	LR: 0.100000
Training Epoch: 3 [22016/47500]	Loss: 2.0364	LR: 0.100000
Training Epoch: 3 [22272/47500]	Loss: 2.1116	LR: 0.100000
Training Epoch: 3 [22528/47500]	Loss: 2.1052	LR: 0.100000
Training Epoch: 3 [22784/47500]	Loss: 2.0503	LR: 0.100000
Training Epoch: 3 [23040/47500]	Loss: 2.0183	LR: 0.100000
Training Epoch: 3 [23296/47500]	Loss: 2.1403	LR: 0.100000
Training Epoch: 3 [23552/47500]	Loss: 2.1287	LR: 0.100000
Training Epoch: 3 [23808/47500]	Loss: 2.0592	LR: 0.100000
Training Epoch: 3 [24064/47500]	Loss: 2.0015	LR: 0.100000
Training Epoch: 3 [24320/47500]	Loss: 2.1259	LR: 0.100000
Training Epoch: 3 [24576/47500]	Loss: 2.1570	LR: 0.100000
Training Epoch: 3 [24832/47500]	Loss: 2.0704	LR: 0.100000
Training Epoch: 3 [25088/47500]	Loss: 2.0636	LR: 0.100000
Training Epoch: 3 [25344/47500]	Loss: 2.0459	LR: 0.100000
Training Epoch: 3 [25600/47500]	Loss: 2.1021	LR: 0.100000
Training Epoch: 3 [25856/47500]	Loss: 2.0247	LR: 0.100000
Training Epoch: 3 [26112/47500]	Loss: 2.1145	LR: 0.100000
Training Epoch: 3 [26368/47500]	Loss: 2.0224	LR: 0.100000
Training Epoch: 3 [26624/47500]	Loss: 2.0410	LR: 0.100000
Training Epoch: 3 [26880/47500]	Loss: 2.1021	LR: 0.100000
Training Epoch: 3 [27136/47500]	Loss: 2.1204	LR: 0.100000
Training Epoch: 3 [27392/47500]	Loss: 2.0855	LR: 0.100000
Training Epoch: 3 [27648/47500]	Loss: 2.0590	LR: 0.100000
Training Epoch: 3 [27904/47500]	Loss: 2.0417	LR: 0.100000
Training Epoch: 3 [28160/47500]	Loss: 2.0320	LR: 0.100000
Training Epoch: 3 [28416/47500]	Loss: 2.0877	LR: 0.100000
Training Epoch: 3 [28672/47500]	Loss: 2.1753	LR: 0.100000
Training Epoch: 3 [28928/47500]	Loss: 2.0172	LR: 0.100000
Training Epoch: 3 [29184/47500]	Loss: 1.9907	LR: 0.100000
Training Epoch: 3 [29440/47500]	Loss: 2.0639	LR: 0.100000
Training Epoch: 3 [29696/47500]	Loss: 2.0400	LR: 0.100000
Training Epoch: 3 [29952/47500]	Loss: 2.1628	LR: 0.100000
Training Epoch: 3 [30208/47500]	Loss: 2.1029	LR: 0.100000
Training Epoch: 3 [30464/47500]	Loss: 2.0934	LR: 0.100000
Training Epoch: 3 [30720/47500]	Loss: 2.1530	LR: 0.100000
Training Epoch: 3 [30976/47500]	Loss: 2.1192	LR: 0.100000
Training Epoch: 3 [31232/47500]	Loss: 2.0943	LR: 0.100000
Training Epoch: 3 [31488/47500]	Loss: 2.0824	LR: 0.100000
Training Epoch: 3 [31744/47500]	Loss: 2.0843	LR: 0.100000
Training Epoch: 3 [32000/47500]	Loss: 2.0989	LR: 0.100000
Training Epoch: 3 [32256/47500]	Loss: 2.1174	LR: 0.100000
Training Epoch: 3 [32512/47500]	Loss: 2.0763	LR: 0.100000
Training Epoch: 3 [32768/47500]	Loss: 2.1148	LR: 0.100000
Training Epoch: 3 [33024/47500]	Loss: 2.1483	LR: 0.100000
Training Epoch: 3 [33280/47500]	Loss: 2.0967	LR: 0.100000
Training Epoch: 3 [33536/47500]	Loss: 2.1361	LR: 0.100000
Training Epoch: 3 [33792/47500]	Loss: 2.0790	LR: 0.100000
Training Epoch: 3 [34048/47500]	Loss: 2.0949	LR: 0.100000
Training Epoch: 3 [34304/47500]	Loss: 2.0646	LR: 0.100000
Training Epoch: 3 [34560/47500]	Loss: 2.0452	LR: 0.100000
Training Epoch: 3 [34816/47500]	Loss: 2.0785	LR: 0.100000
Training Epoch: 3 [35072/47500]	Loss: 2.0868	LR: 0.100000
Training Epoch: 3 [35328/47500]	Loss: 2.0151	LR: 0.100000
Training Epoch: 3 [35584/47500]	Loss: 2.1184	LR: 0.100000
Training Epoch: 3 [35840/47500]	Loss: 2.1129	LR: 0.100000
Training Epoch: 3 [36096/47500]	Loss: 2.1091	LR: 0.100000
Training Epoch: 3 [36352/47500]	Loss: 2.0222	LR: 0.100000
Training Epoch: 3 [36608/47500]	Loss: 2.0978	LR: 0.100000
Training Epoch: 3 [36864/47500]	Loss: 2.1258	LR: 0.100000
Training Epoch: 3 [37120/47500]	Loss: 2.0993	LR: 0.100000
Training Epoch: 3 [37376/47500]	Loss: 2.0686	LR: 0.100000
Training Epoch: 3 [37632/47500]	Loss: 2.0718	LR: 0.100000
Training Epoch: 3 [37888/47500]	Loss: 2.1136	LR: 0.100000
Training Epoch: 3 [38144/47500]	Loss: 2.0831	LR: 0.100000
Training Epoch: 3 [38400/47500]	Loss: 2.0663	LR: 0.100000
Training Epoch: 3 [38656/47500]	Loss: 2.1543	LR: 0.100000
Training Epoch: 3 [38912/47500]	Loss: 2.1207	LR: 0.100000
Training Epoch: 3 [39168/47500]	Loss: 2.1021	LR: 0.100000
Training Epoch: 3 [39424/47500]	Loss: 2.1643	LR: 0.100000
Training Epoch: 3 [39680/47500]	Loss: 2.0743	LR: 0.100000
Training Epoch: 3 [39936/47500]	Loss: 2.0733	LR: 0.100000
Training Epoch: 3 [40192/47500]	Loss: 2.1275	LR: 0.100000
Training Epoch: 3 [40448/47500]	Loss: 2.2124	LR: 0.100000
Training Epoch: 3 [40704/47500]	Loss: 2.1810	LR: 0.100000
Training Epoch: 3 [40960/47500]	Loss: 2.1432	LR: 0.100000
Training Epoch: 3 [41216/47500]	Loss: 2.1631	LR: 0.100000
Training Epoch: 3 [41472/47500]	Loss: 2.1152	LR: 0.100000
Training Epoch: 3 [41728/47500]	Loss: 2.0256	LR: 0.100000
Training Epoch: 3 [41984/47500]	Loss: 2.1649	LR: 0.100000
Training Epoch: 3 [42240/47500]	Loss: 2.0766	LR: 0.100000
Training Epoch: 3 [42496/47500]	Loss: 2.0596	LR: 0.100000
Training Epoch: 3 [42752/47500]	Loss: 2.1001	LR: 0.100000
Training Epoch: 3 [43008/47500]	Loss: 2.0768	LR: 0.100000
Training Epoch: 3 [43264/47500]	Loss: 2.0419	LR: 0.100000
Training Epoch: 3 [43520/47500]	Loss: 2.0845	LR: 0.100000
Training Epoch: 3 [43776/47500]	Loss: 2.1337	LR: 0.100000
Training Epoch: 3 [44032/47500]	Loss: 2.0638	LR: 0.100000
Training Epoch: 3 [44288/47500]	Loss: 2.1807	LR: 0.100000
Training Epoch: 3 [44544/47500]	Loss: 2.0638	LR: 0.100000
Training Epoch: 3 [44800/47500]	Loss: 2.1078	LR: 0.100000
Training Epoch: 3 [45056/47500]	Loss: 2.0488	LR: 0.100000
Training Epoch: 3 [45312/47500]	Loss: 2.0996	LR: 0.100000
Training Epoch: 3 [45568/47500]	Loss: 2.0354	LR: 0.100000
Training Epoch: 3 [45824/47500]	Loss: 2.0786	LR: 0.100000
Training Epoch: 3 [46080/47500]	Loss: 2.0786	LR: 0.100000
Training Epoch: 3 [46336/47500]	Loss: 2.0824	LR: 0.100000
Training Epoch: 3 [46592/47500]	Loss: 2.0816	LR: 0.100000
Training Epoch: 3 [46848/47500]	Loss: 1.9807	LR: 0.100000
Training Epoch: 3 [47104/47500]	Loss: 2.0271	LR: 0.100000
Training Epoch: 3 [47360/47500]	Loss: 2.0959	LR: 0.100000
Training Epoch: 3 [47500/47500]	Loss: 2.0760	LR: 0.100000
Epoch 3 - Average Train Loss: 2.0893, Train Accuracy: 0.2120
Epoch 3 training time consumed: 343.59s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0085, Accuracy: 0.2044, Time consumed:23.49s
Training Epoch: 4 [256/47500]	Loss: 1.9948	LR: 0.100000
Training Epoch: 4 [512/47500]	Loss: 2.0883	LR: 0.100000
Training Epoch: 4 [768/47500]	Loss: 2.1304	LR: 0.100000
Training Epoch: 4 [1024/47500]	Loss: 2.2136	LR: 0.100000
Training Epoch: 4 [1280/47500]	Loss: 2.0677	LR: 0.100000
Training Epoch: 4 [1536/47500]	Loss: 2.1103	LR: 0.100000
Training Epoch: 4 [1792/47500]	Loss: 2.0681	LR: 0.100000
Training Epoch: 4 [2048/47500]	Loss: 2.1555	LR: 0.100000
Training Epoch: 4 [2304/47500]	Loss: 2.0402	LR: 0.100000
Training Epoch: 4 [2560/47500]	Loss: 2.0834	LR: 0.100000
Training Epoch: 4 [2816/47500]	Loss: 2.0271	LR: 0.100000
Training Epoch: 4 [3072/47500]	Loss: 2.1039	LR: 0.100000
Training Epoch: 4 [3328/47500]	Loss: 2.0739	LR: 0.100000
Training Epoch: 4 [3584/47500]	Loss: 2.0996	LR: 0.100000
Training Epoch: 4 [3840/47500]	Loss: 1.9966	LR: 0.100000
Training Epoch: 4 [4096/47500]	Loss: 2.1451	LR: 0.100000
Training Epoch: 4 [4352/47500]	Loss: 2.0613	LR: 0.100000
Training Epoch: 4 [4608/47500]	Loss: 2.1003	LR: 0.100000
Training Epoch: 4 [4864/47500]	Loss: 2.1747	LR: 0.100000
Training Epoch: 4 [5120/47500]	Loss: 2.0690	LR: 0.100000
Training Epoch: 4 [5376/47500]	Loss: 2.0246	LR: 0.100000
Training Epoch: 4 [5632/47500]	Loss: 2.0689	LR: 0.100000
Training Epoch: 4 [5888/47500]	Loss: 2.0714	LR: 0.100000
Training Epoch: 4 [6144/47500]	Loss: 2.0858	LR: 0.100000
Training Epoch: 4 [6400/47500]	Loss: 2.1357	LR: 0.100000
Training Epoch: 4 [6656/47500]	Loss: 2.1194	LR: 0.100000
Training Epoch: 4 [6912/47500]	Loss: 2.1797	LR: 0.100000
Training Epoch: 4 [7168/47500]	Loss: 2.0709	LR: 0.100000
Training Epoch: 4 [7424/47500]	Loss: 2.0559	LR: 0.100000
Training Epoch: 4 [7680/47500]	Loss: 2.0899	LR: 0.100000
Training Epoch: 4 [7936/47500]	Loss: 2.0672	LR: 0.100000
Training Epoch: 4 [8192/47500]	Loss: 2.0270	LR: 0.100000
Training Epoch: 4 [8448/47500]	Loss: 2.0506	LR: 0.100000
Training Epoch: 4 [8704/47500]	Loss: 1.9996	LR: 0.100000
Training Epoch: 4 [8960/47500]	Loss: 2.0968	LR: 0.100000
Training Epoch: 4 [9216/47500]	Loss: 2.0579	LR: 0.100000
Training Epoch: 4 [9472/47500]	Loss: 2.0359	LR: 0.100000
Training Epoch: 4 [9728/47500]	Loss: 2.0993	LR: 0.100000
Training Epoch: 4 [9984/47500]	Loss: 2.1146	LR: 0.100000
Training Epoch: 4 [10240/47500]	Loss: 2.0409	LR: 0.100000
Training Epoch: 4 [10496/47500]	Loss: 2.1238	LR: 0.100000
Training Epoch: 4 [10752/47500]	Loss: 1.9753	LR: 0.100000
Training Epoch: 4 [11008/47500]	Loss: 2.0636	LR: 0.100000
Training Epoch: 4 [11264/47500]	Loss: 2.1025	LR: 0.100000
Training Epoch: 4 [11520/47500]	Loss: 2.0474	LR: 0.100000
Training Epoch: 4 [11776/47500]	Loss: 2.0487	LR: 0.100000
Training Epoch: 4 [12032/47500]	Loss: 2.0858	LR: 0.100000
Training Epoch: 4 [12288/47500]	Loss: 2.0508	LR: 0.100000
Training Epoch: 4 [12544/47500]	Loss: 2.0542	LR: 0.100000
Training Epoch: 4 [12800/47500]	Loss: 2.0482	LR: 0.100000
Training Epoch: 4 [13056/47500]	Loss: 2.0746	LR: 0.100000
Training Epoch: 4 [13312/47500]	Loss: 2.0902	LR: 0.100000
Training Epoch: 4 [13568/47500]	Loss: 1.9244	LR: 0.100000
Training Epoch: 4 [13824/47500]	Loss: 2.0902	LR: 0.100000
Training Epoch: 4 [14080/47500]	Loss: 2.1025	LR: 0.100000
Training Epoch: 4 [14336/47500]	Loss: 2.0701	LR: 0.100000
Training Epoch: 4 [14592/47500]	Loss: 1.9626	LR: 0.100000
Training Epoch: 4 [14848/47500]	Loss: 2.0645	LR: 0.100000
Training Epoch: 4 [15104/47500]	Loss: 2.1384	LR: 0.100000
Training Epoch: 4 [15360/47500]	Loss: 2.0558	LR: 0.100000
Training Epoch: 4 [15616/47500]	Loss: 2.0990	LR: 0.100000
Training Epoch: 4 [15872/47500]	Loss: 2.0974	LR: 0.100000
Training Epoch: 4 [16128/47500]	Loss: 2.1865	LR: 0.100000
Training Epoch: 4 [16384/47500]	Loss: 2.0678	LR: 0.100000
Training Epoch: 4 [16640/47500]	Loss: 2.0762	LR: 0.100000
Training Epoch: 4 [16896/47500]	Loss: 2.0279	LR: 0.100000
Training Epoch: 4 [17152/47500]	Loss: 2.1109	LR: 0.100000
Training Epoch: 4 [17408/47500]	Loss: 2.0710	LR: 0.100000
Training Epoch: 4 [17664/47500]	Loss: 2.0631	LR: 0.100000
Training Epoch: 4 [17920/47500]	Loss: 2.0599	LR: 0.100000
Training Epoch: 4 [18176/47500]	Loss: 2.1105	LR: 0.100000
Training Epoch: 4 [18432/47500]	Loss: 2.1203	LR: 0.100000
Training Epoch: 4 [18688/47500]	Loss: 2.0681	LR: 0.100000
Training Epoch: 4 [18944/47500]	Loss: 2.0719	LR: 0.100000
Training Epoch: 4 [19200/47500]	Loss: 2.0417	LR: 0.100000
Training Epoch: 4 [19456/47500]	Loss: 2.1301	LR: 0.100000
Training Epoch: 4 [19712/47500]	Loss: 2.0312	LR: 0.100000
Training Epoch: 4 [19968/47500]	Loss: 2.0858	LR: 0.100000
Training Epoch: 4 [20224/47500]	Loss: 2.0642	LR: 0.100000
Training Epoch: 4 [20480/47500]	Loss: 2.0757	LR: 0.100000
Training Epoch: 4 [20736/47500]	Loss: 2.0009	LR: 0.100000
Training Epoch: 4 [20992/47500]	Loss: 2.0506	LR: 0.100000
Training Epoch: 4 [21248/47500]	Loss: 2.0721	LR: 0.100000
Training Epoch: 4 [21504/47500]	Loss: 2.0473	LR: 0.100000
Training Epoch: 4 [21760/47500]	Loss: 2.1095	LR: 0.100000
Training Epoch: 4 [22016/47500]	Loss: 2.0679	LR: 0.100000
Training Epoch: 4 [22272/47500]	Loss: 2.0320	LR: 0.100000
Training Epoch: 4 [22528/47500]	Loss: 2.0304	LR: 0.100000
Training Epoch: 4 [22784/47500]	Loss: 2.0380	LR: 0.100000
Training Epoch: 4 [23040/47500]	Loss: 2.1193	LR: 0.100000
Training Epoch: 4 [23296/47500]	Loss: 2.0297	LR: 0.100000
Training Epoch: 4 [23552/47500]	Loss: 2.0672	LR: 0.100000
Training Epoch: 4 [23808/47500]	Loss: 1.9644	LR: 0.100000
Training Epoch: 4 [24064/47500]	Loss: 1.9344	LR: 0.100000
Training Epoch: 4 [24320/47500]	Loss: 2.0310	LR: 0.100000
Training Epoch: 4 [24576/47500]	Loss: 2.0035	LR: 0.100000
Training Epoch: 4 [24832/47500]	Loss: 2.0541	LR: 0.100000
Training Epoch: 4 [25088/47500]	Loss: 2.0983	LR: 0.100000
Training Epoch: 4 [25344/47500]	Loss: 2.0667	LR: 0.100000
Training Epoch: 4 [25600/47500]	Loss: 2.0477	LR: 0.100000
Training Epoch: 4 [25856/47500]	Loss: 2.0852	LR: 0.100000
Training Epoch: 4 [26112/47500]	Loss: 2.1311	LR: 0.100000
Training Epoch: 4 [26368/47500]	Loss: 2.0480	LR: 0.100000
Training Epoch: 4 [26624/47500]	Loss: 2.0343	LR: 0.100000
Training Epoch: 4 [26880/47500]	Loss: 2.0481	LR: 0.100000
Training Epoch: 4 [27136/47500]	Loss: 2.0585	LR: 0.100000
Training Epoch: 4 [27392/47500]	Loss: 2.0687	LR: 0.100000
Training Epoch: 4 [27648/47500]	Loss: 2.0536	LR: 0.100000
Training Epoch: 4 [27904/47500]	Loss: 2.0272	LR: 0.100000
Training Epoch: 4 [28160/47500]	Loss: 2.0291	LR: 0.100000
Training Epoch: 4 [28416/47500]	Loss: 2.0221	LR: 0.100000
Training Epoch: 4 [28672/47500]	Loss: 2.0797	LR: 0.100000
Training Epoch: 4 [28928/47500]	Loss: 2.0055	LR: 0.100000
Training Epoch: 4 [29184/47500]	Loss: 2.0077	LR: 0.100000
Training Epoch: 4 [29440/47500]	Loss: 2.0186	LR: 0.100000
Training Epoch: 4 [29696/47500]	Loss: 2.0133	LR: 0.100000
Training Epoch: 4 [29952/47500]	Loss: 2.0058	LR: 0.100000
Training Epoch: 4 [30208/47500]	Loss: 2.1303	LR: 0.100000
Training Epoch: 4 [30464/47500]	Loss: 2.0650	LR: 0.100000
Training Epoch: 4 [30720/47500]	Loss: 2.0452	LR: 0.100000
Training Epoch: 4 [30976/47500]	Loss: 2.0239	LR: 0.100000
Training Epoch: 4 [31232/47500]	Loss: 2.0560	LR: 0.100000
Training Epoch: 4 [31488/47500]	Loss: 2.0063	LR: 0.100000
Training Epoch: 4 [31744/47500]	Loss: 2.1309	LR: 0.100000
Training Epoch: 4 [32000/47500]	Loss: 2.0845	LR: 0.100000
Training Epoch: 4 [32256/47500]	Loss: 2.0548	LR: 0.100000
Training Epoch: 4 [32512/47500]	Loss: 2.1101	LR: 0.100000
Training Epoch: 4 [32768/47500]	Loss: 2.0688	LR: 0.100000
Training Epoch: 4 [33024/47500]	Loss: 2.1377	LR: 0.100000
Training Epoch: 4 [33280/47500]	Loss: 2.0744	LR: 0.100000
Training Epoch: 4 [33536/47500]	Loss: 2.0481	LR: 0.100000
Training Epoch: 4 [33792/47500]	Loss: 2.0844	LR: 0.100000
Training Epoch: 4 [34048/47500]	Loss: 2.0209	LR: 0.100000
Training Epoch: 4 [34304/47500]	Loss: 2.0524	LR: 0.100000
Training Epoch: 4 [34560/47500]	Loss: 2.0317	LR: 0.100000
Training Epoch: 4 [34816/47500]	Loss: 2.0581	LR: 0.100000
Training Epoch: 4 [35072/47500]	Loss: 2.0383	LR: 0.100000
Training Epoch: 4 [35328/47500]	Loss: 2.0981	LR: 0.100000
Training Epoch: 4 [35584/47500]	Loss: 2.0197	LR: 0.100000
Training Epoch: 4 [35840/47500]	Loss: 2.1223	LR: 0.100000
Training Epoch: 4 [36096/47500]	Loss: 2.0505	LR: 0.100000
Training Epoch: 4 [36352/47500]	Loss: 2.0815	LR: 0.100000
Training Epoch: 4 [36608/47500]	Loss: 2.0539	LR: 0.100000
Training Epoch: 4 [36864/47500]	Loss: 2.0696	LR: 0.100000
Training Epoch: 4 [37120/47500]	Loss: 2.0612	LR: 0.100000
Training Epoch: 4 [37376/47500]	Loss: 2.0523	LR: 0.100000
Training Epoch: 4 [37632/47500]	Loss: 1.9706	LR: 0.100000
Training Epoch: 4 [37888/47500]	Loss: 2.0391	LR: 0.100000
Training Epoch: 4 [38144/47500]	Loss: 2.0740	LR: 0.100000
Training Epoch: 4 [38400/47500]	Loss: 2.0686	LR: 0.100000
Training Epoch: 4 [38656/47500]	Loss: 2.0030	LR: 0.100000
Training Epoch: 4 [38912/47500]	Loss: 2.0070	LR: 0.100000
Training Epoch: 4 [39168/47500]	Loss: 2.1158	LR: 0.100000
Training Epoch: 4 [39424/47500]	Loss: 2.1535	LR: 0.100000
Training Epoch: 4 [39680/47500]	Loss: 2.0188	LR: 0.100000
Training Epoch: 4 [39936/47500]	Loss: 2.0221	LR: 0.100000
Training Epoch: 4 [40192/47500]	Loss: 2.1010	LR: 0.100000
Training Epoch: 4 [40448/47500]	Loss: 2.0469	LR: 0.100000
Training Epoch: 4 [40704/47500]	Loss: 2.0568	LR: 0.100000
Training Epoch: 4 [40960/47500]	Loss: 2.0965	LR: 0.100000
Training Epoch: 4 [41216/47500]	Loss: 2.1011	LR: 0.100000
Training Epoch: 4 [41472/47500]	Loss: 2.0228	LR: 0.100000
Training Epoch: 4 [41728/47500]	Loss: 2.0010	LR: 0.100000
Training Epoch: 4 [41984/47500]	Loss: 2.0606	LR: 0.100000
Training Epoch: 4 [42240/47500]	Loss: 2.0297	LR: 0.100000
Training Epoch: 4 [42496/47500]	Loss: 2.0632	LR: 0.100000
Training Epoch: 4 [42752/47500]	Loss: 2.0356	LR: 0.100000
Training Epoch: 4 [43008/47500]	Loss: 2.0676	LR: 0.100000
Training Epoch: 4 [43264/47500]	Loss: 2.0168	LR: 0.100000
Training Epoch: 4 [43520/47500]	Loss: 2.0345	LR: 0.100000
Training Epoch: 4 [43776/47500]	Loss: 2.0186	LR: 0.100000
Training Epoch: 4 [44032/47500]	Loss: 2.0408	LR: 0.100000
Training Epoch: 4 [44288/47500]	Loss: 2.0040	LR: 0.100000
Training Epoch: 4 [44544/47500]	Loss: 2.0369	LR: 0.100000
Training Epoch: 4 [44800/47500]	Loss: 2.0545	LR: 0.100000
Training Epoch: 4 [45056/47500]	Loss: 1.9950	LR: 0.100000
Training Epoch: 4 [45312/47500]	Loss: 2.0510	LR: 0.100000
Training Epoch: 4 [45568/47500]	Loss: 1.9452	LR: 0.100000
Training Epoch: 4 [45824/47500]	Loss: 1.9902	LR: 0.100000
Training Epoch: 4 [46080/47500]	Loss: 1.9781	LR: 0.100000
Training Epoch: 4 [46336/47500]	Loss: 2.0665	LR: 0.100000
Training Epoch: 4 [46592/47500]	Loss: 2.0402	LR: 0.100000
Training Epoch: 4 [46848/47500]	Loss: 2.0557	LR: 0.100000
Training Epoch: 4 [47104/47500]	Loss: 2.0413	LR: 0.100000
Training Epoch: 4 [47360/47500]	Loss: 1.9542	LR: 0.100000
Training Epoch: 4 [47500/47500]	Loss: 2.0316	LR: 0.100000
Epoch 4 - Average Train Loss: 2.0601, Train Accuracy: 0.2292
Epoch 4 training time consumed: 343.59s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0081, Accuracy: 0.2365, Time consumed:23.51s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-4-best.pth
Training Epoch: 5 [256/47500]	Loss: 2.0257	LR: 0.100000
Training Epoch: 5 [512/47500]	Loss: 1.9738	LR: 0.100000
Training Epoch: 5 [768/47500]	Loss: 2.0473	LR: 0.100000
Training Epoch: 5 [1024/47500]	Loss: 2.1115	LR: 0.100000
Training Epoch: 5 [1280/47500]	Loss: 2.0126	LR: 0.100000
Training Epoch: 5 [1536/47500]	Loss: 2.0824	LR: 0.100000
Training Epoch: 5 [1792/47500]	Loss: 2.0357	LR: 0.100000
Training Epoch: 5 [2048/47500]	Loss: 2.0788	LR: 0.100000
Training Epoch: 5 [2304/47500]	Loss: 2.0407	LR: 0.100000
Training Epoch: 5 [2560/47500]	Loss: 2.0645	LR: 0.100000
Training Epoch: 5 [2816/47500]	Loss: 2.0189	LR: 0.100000
Training Epoch: 5 [3072/47500]	Loss: 1.9954	LR: 0.100000
Training Epoch: 5 [3328/47500]	Loss: 2.0929	LR: 0.100000
Training Epoch: 5 [3584/47500]	Loss: 2.1162	LR: 0.100000
Training Epoch: 5 [3840/47500]	Loss: 2.0486	LR: 0.100000
Training Epoch: 5 [4096/47500]	Loss: 2.0586	LR: 0.100000
Training Epoch: 5 [4352/47500]	Loss: 2.0577	LR: 0.100000
Training Epoch: 5 [4608/47500]	Loss: 1.9487	LR: 0.100000
Training Epoch: 5 [4864/47500]	Loss: 2.0794	LR: 0.100000
Training Epoch: 5 [5120/47500]	Loss: 2.0311	LR: 0.100000
Training Epoch: 5 [5376/47500]	Loss: 2.0282	LR: 0.100000
Training Epoch: 5 [5632/47500]	Loss: 2.0771	LR: 0.100000
Training Epoch: 5 [5888/47500]	Loss: 1.9989	LR: 0.100000
Training Epoch: 5 [6144/47500]	Loss: 1.9969	LR: 0.100000
Training Epoch: 5 [6400/47500]	Loss: 1.9852	LR: 0.100000
Training Epoch: 5 [6656/47500]	Loss: 2.0212	LR: 0.100000
Training Epoch: 5 [6912/47500]	Loss: 1.9948	LR: 0.100000
Training Epoch: 5 [7168/47500]	Loss: 1.9954	LR: 0.100000
Training Epoch: 5 [7424/47500]	Loss: 2.0721	LR: 0.100000
Training Epoch: 5 [7680/47500]	Loss: 2.0849	LR: 0.100000
Training Epoch: 5 [7936/47500]	Loss: 2.0215	LR: 0.100000
Training Epoch: 5 [8192/47500]	Loss: 2.1164	LR: 0.100000
Training Epoch: 5 [8448/47500]	Loss: 2.0311	LR: 0.100000
Training Epoch: 5 [8704/47500]	Loss: 1.9981	LR: 0.100000
Training Epoch: 5 [8960/47500]	Loss: 2.0696	LR: 0.100000
Training Epoch: 5 [9216/47500]	Loss: 2.0507	LR: 0.100000
Training Epoch: 5 [9472/47500]	Loss: 2.0672	LR: 0.100000
Training Epoch: 5 [9728/47500]	Loss: 2.0414	LR: 0.100000
Training Epoch: 5 [9984/47500]	Loss: 2.0791	LR: 0.100000
Training Epoch: 5 [10240/47500]	Loss: 2.0431	LR: 0.100000
Training Epoch: 5 [10496/47500]	Loss: 2.1257	LR: 0.100000
Training Epoch: 5 [10752/47500]	Loss: 2.0749	LR: 0.100000
Training Epoch: 5 [11008/47500]	Loss: 2.0676	LR: 0.100000
Training Epoch: 5 [11264/47500]	Loss: 2.1380	LR: 0.100000
Training Epoch: 5 [11520/47500]	Loss: 1.9942	LR: 0.100000
Training Epoch: 5 [11776/47500]	Loss: 2.0562	LR: 0.100000
Training Epoch: 5 [12032/47500]	Loss: 2.0418	LR: 0.100000
Training Epoch: 5 [12288/47500]	Loss: 2.0401	LR: 0.100000
Training Epoch: 5 [12544/47500]	Loss: 2.0455	LR: 0.100000
Training Epoch: 5 [12800/47500]	Loss: 2.0072	LR: 0.100000
Training Epoch: 5 [13056/47500]	Loss: 1.9252	LR: 0.100000
Training Epoch: 5 [13312/47500]	Loss: 2.0676	LR: 0.100000
Training Epoch: 5 [13568/47500]	Loss: 2.0428	LR: 0.100000
Training Epoch: 5 [13824/47500]	Loss: 2.0516	LR: 0.100000
Training Epoch: 5 [14080/47500]	Loss: 1.9694	LR: 0.100000
Training Epoch: 5 [14336/47500]	Loss: 2.0021	LR: 0.100000
Training Epoch: 5 [14592/47500]	Loss: 2.0250	LR: 0.100000
Training Epoch: 5 [14848/47500]	Loss: 2.0370	LR: 0.100000
Training Epoch: 5 [15104/47500]	Loss: 2.0228	LR: 0.100000
Training Epoch: 5 [15360/47500]	Loss: 1.9477	LR: 0.100000
Training Epoch: 5 [15616/47500]	Loss: 1.9387	LR: 0.100000
Training Epoch: 5 [15872/47500]	Loss: 2.0919	LR: 0.100000
Training Epoch: 5 [16128/47500]	Loss: 1.8744	LR: 0.100000
Training Epoch: 5 [16384/47500]	Loss: 2.0600	LR: 0.100000
Training Epoch: 5 [16640/47500]	Loss: 2.0142	LR: 0.100000
Training Epoch: 5 [16896/47500]	Loss: 2.0575	LR: 0.100000
Training Epoch: 5 [17152/47500]	Loss: 2.0632	LR: 0.100000
Training Epoch: 5 [17408/47500]	Loss: 1.9194	LR: 0.100000
Training Epoch: 5 [17664/47500]	Loss: 2.0136	LR: 0.100000
Training Epoch: 5 [17920/47500]	Loss: 2.1226	LR: 0.100000
Training Epoch: 5 [18176/47500]	Loss: 1.9461	LR: 0.100000
Training Epoch: 5 [18432/47500]	Loss: 1.9848	LR: 0.100000
Training Epoch: 5 [18688/47500]	Loss: 2.0378	LR: 0.100000
Training Epoch: 5 [18944/47500]	Loss: 2.0831	LR: 0.100000
Training Epoch: 5 [19200/47500]	Loss: 1.9975	LR: 0.100000
Training Epoch: 5 [19456/47500]	Loss: 1.9857	LR: 0.100000
Training Epoch: 5 [19712/47500]	Loss: 1.9899	LR: 0.100000
Training Epoch: 5 [19968/47500]	Loss: 1.9528	LR: 0.100000
Training Epoch: 5 [20224/47500]	Loss: 1.9253	LR: 0.100000
Training Epoch: 5 [20480/47500]	Loss: 2.0193	LR: 0.100000
Training Epoch: 5 [20736/47500]	Loss: 2.0158	LR: 0.100000
Training Epoch: 5 [20992/47500]	Loss: 2.0269	LR: 0.100000
Training Epoch: 5 [21248/47500]	Loss: 2.0219	LR: 0.100000
Training Epoch: 5 [21504/47500]	Loss: 2.0488	LR: 0.100000
Training Epoch: 5 [21760/47500]	Loss: 1.9788	LR: 0.100000
Training Epoch: 5 [22016/47500]	Loss: 2.0971	LR: 0.100000
Training Epoch: 5 [22272/47500]	Loss: 2.0834	LR: 0.100000
Training Epoch: 5 [22528/47500]	Loss: 2.0437	LR: 0.100000
Training Epoch: 5 [22784/47500]	Loss: 2.0186	LR: 0.100000
Training Epoch: 5 [23040/47500]	Loss: 2.0201	LR: 0.100000
Training Epoch: 5 [23296/47500]	Loss: 2.0781	LR: 0.100000
Training Epoch: 5 [23552/47500]	Loss: 2.0573	LR: 0.100000
Training Epoch: 5 [23808/47500]	Loss: 2.0545	LR: 0.100000
Training Epoch: 5 [24064/47500]	Loss: 2.0534	LR: 0.100000
Training Epoch: 5 [24320/47500]	Loss: 2.1198	LR: 0.100000
Training Epoch: 5 [24576/47500]	Loss: 2.0145	LR: 0.100000
Training Epoch: 5 [24832/47500]	Loss: 1.9010	LR: 0.100000
Training Epoch: 5 [25088/47500]	Loss: 1.9260	LR: 0.100000
Training Epoch: 5 [25344/47500]	Loss: 1.9835	LR: 0.100000
Training Epoch: 5 [25600/47500]	Loss: 2.0225	LR: 0.100000
Training Epoch: 5 [25856/47500]	Loss: 2.0381	LR: 0.100000
Training Epoch: 5 [26112/47500]	Loss: 2.0154	LR: 0.100000
Training Epoch: 5 [26368/47500]	Loss: 2.0933	LR: 0.100000
Training Epoch: 5 [26624/47500]	Loss: 2.0294	LR: 0.100000
Training Epoch: 5 [26880/47500]	Loss: 1.9947	LR: 0.100000
Training Epoch: 5 [27136/47500]	Loss: 2.0266	LR: 0.100000
Training Epoch: 5 [27392/47500]	Loss: 2.0005	LR: 0.100000
Training Epoch: 5 [27648/47500]	Loss: 2.0252	LR: 0.100000
Training Epoch: 5 [27904/47500]	Loss: 2.1430	LR: 0.100000
Training Epoch: 5 [28160/47500]	Loss: 2.0086	LR: 0.100000
Training Epoch: 5 [28416/47500]	Loss: 1.9954	LR: 0.100000
Training Epoch: 5 [28672/47500]	Loss: 2.0091	LR: 0.100000
Training Epoch: 5 [28928/47500]	Loss: 2.0162	LR: 0.100000
Training Epoch: 5 [29184/47500]	Loss: 1.9690	LR: 0.100000
Training Epoch: 5 [29440/47500]	Loss: 2.0668	LR: 0.100000
Training Epoch: 5 [29696/47500]	Loss: 1.9804	LR: 0.100000
Training Epoch: 5 [29952/47500]	Loss: 2.0658	LR: 0.100000
Training Epoch: 5 [30208/47500]	Loss: 2.0224	LR: 0.100000
Training Epoch: 5 [30464/47500]	Loss: 2.0565	LR: 0.100000
Training Epoch: 5 [30720/47500]	Loss: 1.9771	LR: 0.100000
Training Epoch: 5 [30976/47500]	Loss: 1.9577	LR: 0.100000
Training Epoch: 5 [31232/47500]	Loss: 2.0072	LR: 0.100000
Training Epoch: 5 [31488/47500]	Loss: 1.9457	LR: 0.100000
Training Epoch: 5 [31744/47500]	Loss: 2.0487	LR: 0.100000
Training Epoch: 5 [32000/47500]	Loss: 2.0326	LR: 0.100000
Training Epoch: 5 [32256/47500]	Loss: 1.9704	LR: 0.100000
Training Epoch: 5 [32512/47500]	Loss: 1.9918	LR: 0.100000
Training Epoch: 5 [32768/47500]	Loss: 2.0416	LR: 0.100000
Training Epoch: 5 [33024/47500]	Loss: 2.1258	LR: 0.100000
Training Epoch: 5 [33280/47500]	Loss: 1.9862	LR: 0.100000
Training Epoch: 5 [33536/47500]	Loss: 2.0395	LR: 0.100000
Training Epoch: 5 [33792/47500]	Loss: 2.0368	LR: 0.100000
Training Epoch: 5 [34048/47500]	Loss: 2.0335	LR: 0.100000
Training Epoch: 5 [34304/47500]	Loss: 2.0338	LR: 0.100000
Training Epoch: 5 [34560/47500]	Loss: 1.9855	LR: 0.100000
Training Epoch: 5 [34816/47500]	Loss: 2.0006	LR: 0.100000
Training Epoch: 5 [35072/47500]	Loss: 2.0252	LR: 0.100000
Training Epoch: 5 [35328/47500]	Loss: 1.9890	LR: 0.100000
Training Epoch: 5 [35584/47500]	Loss: 2.0469	LR: 0.100000
Training Epoch: 5 [35840/47500]	Loss: 1.9687	LR: 0.100000
Training Epoch: 5 [36096/47500]	Loss: 1.9507	LR: 0.100000
Training Epoch: 5 [36352/47500]	Loss: 2.0333	LR: 0.100000
Training Epoch: 5 [36608/47500]	Loss: 1.9274	LR: 0.100000
Training Epoch: 5 [36864/47500]	Loss: 1.9812	LR: 0.100000
Training Epoch: 5 [37120/47500]	Loss: 2.0390	LR: 0.100000
Training Epoch: 5 [37376/47500]	Loss: 2.0540	LR: 0.100000
Training Epoch: 5 [37632/47500]	Loss: 1.9416	LR: 0.100000
Training Epoch: 5 [37888/47500]	Loss: 2.0289	LR: 0.100000
Training Epoch: 5 [38144/47500]	Loss: 1.9916	LR: 0.100000
Training Epoch: 5 [38400/47500]	Loss: 1.9466	LR: 0.100000
Training Epoch: 5 [38656/47500]	Loss: 1.9812	LR: 0.100000
Training Epoch: 5 [38912/47500]	Loss: 2.0074	LR: 0.100000
Training Epoch: 5 [39168/47500]	Loss: 2.0134	LR: 0.100000
Training Epoch: 5 [39424/47500]	Loss: 1.9861	LR: 0.100000
Training Epoch: 5 [39680/47500]	Loss: 1.9579	LR: 0.100000
Training Epoch: 5 [39936/47500]	Loss: 1.9245	LR: 0.100000
Training Epoch: 5 [40192/47500]	Loss: 2.0003	LR: 0.100000
Training Epoch: 5 [40448/47500]	Loss: 2.0102	LR: 0.100000
Training Epoch: 5 [40704/47500]	Loss: 2.0090	LR: 0.100000
Training Epoch: 5 [40960/47500]	Loss: 2.0127	LR: 0.100000
Training Epoch: 5 [41216/47500]	Loss: 2.0140	LR: 0.100000
Training Epoch: 5 [41472/47500]	Loss: 2.0556	LR: 0.100000
Training Epoch: 5 [41728/47500]	Loss: 2.0778	LR: 0.100000
Training Epoch: 5 [41984/47500]	Loss: 2.0384	LR: 0.100000
Training Epoch: 5 [42240/47500]	Loss: 1.9564	LR: 0.100000
Training Epoch: 5 [42496/47500]	Loss: 1.9997	LR: 0.100000
Training Epoch: 5 [42752/47500]	Loss: 1.9784	LR: 0.100000
Training Epoch: 5 [43008/47500]	Loss: 1.9890	LR: 0.100000
Training Epoch: 5 [43264/47500]	Loss: 1.9925	LR: 0.100000
Training Epoch: 5 [43520/47500]	Loss: 1.9453	LR: 0.100000
Training Epoch: 5 [43776/47500]	Loss: 1.9775	LR: 0.100000
Training Epoch: 5 [44032/47500]	Loss: 2.0069	LR: 0.100000
Training Epoch: 5 [44288/47500]	Loss: 1.9375	LR: 0.100000
Training Epoch: 5 [44544/47500]	Loss: 2.1416	LR: 0.100000
Training Epoch: 5 [44800/47500]	Loss: 2.0126	LR: 0.100000
Training Epoch: 5 [45056/47500]	Loss: 2.0112	LR: 0.100000
Training Epoch: 5 [45312/47500]	Loss: 1.9917	LR: 0.100000
Training Epoch: 5 [45568/47500]	Loss: 2.0044	LR: 0.100000
Training Epoch: 5 [45824/47500]	Loss: 1.9186	LR: 0.100000
Training Epoch: 5 [46080/47500]	Loss: 1.9853	LR: 0.100000
Training Epoch: 5 [46336/47500]	Loss: 1.9841	LR: 0.100000
Training Epoch: 5 [46592/47500]	Loss: 2.0612	LR: 0.100000
Training Epoch: 5 [46848/47500]	Loss: 2.0305	LR: 0.100000
Training Epoch: 5 [47104/47500]	Loss: 2.0562	LR: 0.100000
Training Epoch: 5 [47360/47500]	Loss: 2.1033	LR: 0.100000
Training Epoch: 5 [47500/47500]	Loss: 1.9238	LR: 0.100000
Epoch 5 - Average Train Loss: 2.0207, Train Accuracy: 0.2431
Epoch 5 training time consumed: 343.34s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0078, Accuracy: 0.2624, Time consumed:23.49s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-5-best.pth
Training Epoch: 6 [256/47500]	Loss: 1.9805	LR: 0.100000
Training Epoch: 6 [512/47500]	Loss: 1.9369	LR: 0.100000
Training Epoch: 6 [768/47500]	Loss: 2.0392	LR: 0.100000
Training Epoch: 6 [1024/47500]	Loss: 2.1145	LR: 0.100000
Training Epoch: 6 [1280/47500]	Loss: 2.1239	LR: 0.100000
Training Epoch: 6 [1536/47500]	Loss: 1.9737	LR: 0.100000
Training Epoch: 6 [1792/47500]	Loss: 2.0331	LR: 0.100000
Training Epoch: 6 [2048/47500]	Loss: 2.0133	LR: 0.100000
Training Epoch: 6 [2304/47500]	Loss: 1.9428	LR: 0.100000
Training Epoch: 6 [2560/47500]	Loss: 1.9108	LR: 0.100000
Training Epoch: 6 [2816/47500]	Loss: 1.9880	LR: 0.100000
Training Epoch: 6 [3072/47500]	Loss: 2.0330	LR: 0.100000
Training Epoch: 6 [3328/47500]	Loss: 2.0622	LR: 0.100000
Training Epoch: 6 [3584/47500]	Loss: 2.0054	LR: 0.100000
Training Epoch: 6 [3840/47500]	Loss: 1.9306	LR: 0.100000
Training Epoch: 6 [4096/47500]	Loss: 1.9763	LR: 0.100000
Training Epoch: 6 [4352/47500]	Loss: 2.0081	LR: 0.100000
Training Epoch: 6 [4608/47500]	Loss: 1.9696	LR: 0.100000
Training Epoch: 6 [4864/47500]	Loss: 1.9951	LR: 0.100000
Training Epoch: 6 [5120/47500]	Loss: 2.0051	LR: 0.100000
Training Epoch: 6 [5376/47500]	Loss: 1.9686	LR: 0.100000
Training Epoch: 6 [5632/47500]	Loss: 2.1130	LR: 0.100000
Training Epoch: 6 [5888/47500]	Loss: 1.9156	LR: 0.100000
Training Epoch: 6 [6144/47500]	Loss: 1.9561	LR: 0.100000
Training Epoch: 6 [6400/47500]	Loss: 1.9713	LR: 0.100000
Training Epoch: 6 [6656/47500]	Loss: 2.0888	LR: 0.100000
Training Epoch: 6 [6912/47500]	Loss: 1.9769	LR: 0.100000
Training Epoch: 6 [7168/47500]	Loss: 2.0142	LR: 0.100000
Training Epoch: 6 [7424/47500]	Loss: 2.0059	LR: 0.100000
Training Epoch: 6 [7680/47500]	Loss: 2.0405	LR: 0.100000
Training Epoch: 6 [7936/47500]	Loss: 1.9254	LR: 0.100000
Training Epoch: 6 [8192/47500]	Loss: 2.0047	LR: 0.100000
Training Epoch: 6 [8448/47500]	Loss: 1.9595	LR: 0.100000
Training Epoch: 6 [8704/47500]	Loss: 1.9846	LR: 0.100000
Training Epoch: 6 [8960/47500]	Loss: 1.9535	LR: 0.100000
Training Epoch: 6 [9216/47500]	Loss: 1.9600	LR: 0.100000
Training Epoch: 6 [9472/47500]	Loss: 1.9857	LR: 0.100000
Training Epoch: 6 [9728/47500]	Loss: 1.9858	LR: 0.100000
Training Epoch: 6 [9984/47500]	Loss: 2.0138	LR: 0.100000
Training Epoch: 6 [10240/47500]	Loss: 1.9548	LR: 0.100000
Training Epoch: 6 [10496/47500]	Loss: 1.9978	LR: 0.100000
Training Epoch: 6 [10752/47500]	Loss: 1.9920	LR: 0.100000
Training Epoch: 6 [11008/47500]	Loss: 1.9924	LR: 0.100000
Training Epoch: 6 [11264/47500]	Loss: 2.0029	LR: 0.100000
Training Epoch: 6 [11520/47500]	Loss: 1.9788	LR: 0.100000
Training Epoch: 6 [11776/47500]	Loss: 1.9095	LR: 0.100000
Training Epoch: 6 [12032/47500]	Loss: 1.8663	LR: 0.100000
Training Epoch: 6 [12288/47500]	Loss: 1.8731	LR: 0.100000
Training Epoch: 6 [12544/47500]	Loss: 1.9810	LR: 0.100000
Training Epoch: 6 [12800/47500]	Loss: 1.9644	LR: 0.100000
Training Epoch: 6 [13056/47500]	Loss: 1.9983	LR: 0.100000
Training Epoch: 6 [13312/47500]	Loss: 1.9144	LR: 0.100000
Training Epoch: 6 [13568/47500]	Loss: 2.0273	LR: 0.100000
Training Epoch: 6 [13824/47500]	Loss: 1.9258	LR: 0.100000
Training Epoch: 6 [14080/47500]	Loss: 2.0140	LR: 0.100000
Training Epoch: 6 [14336/47500]	Loss: 2.0184	LR: 0.100000
Training Epoch: 6 [14592/47500]	Loss: 2.0278	LR: 0.100000
Training Epoch: 6 [14848/47500]	Loss: 1.9730	LR: 0.100000
Training Epoch: 6 [15104/47500]	Loss: 1.9878	LR: 0.100000
Training Epoch: 6 [15360/47500]	Loss: 2.0128	LR: 0.100000
Training Epoch: 6 [15616/47500]	Loss: 1.9808	LR: 0.100000
Training Epoch: 6 [15872/47500]	Loss: 1.9237	LR: 0.100000
Training Epoch: 6 [16128/47500]	Loss: 2.0306	LR: 0.100000
Training Epoch: 6 [16384/47500]	Loss: 1.9572	LR: 0.100000
Training Epoch: 6 [16640/47500]	Loss: 1.9158	LR: 0.100000
Training Epoch: 6 [16896/47500]	Loss: 1.9738	LR: 0.100000
Training Epoch: 6 [17152/47500]	Loss: 2.0356	LR: 0.100000
Training Epoch: 6 [17408/47500]	Loss: 1.9839	LR: 0.100000
Training Epoch: 6 [17664/47500]	Loss: 2.0084	LR: 0.100000
Training Epoch: 6 [17920/47500]	Loss: 1.8633	LR: 0.100000
Training Epoch: 6 [18176/47500]	Loss: 1.9752	LR: 0.100000
Training Epoch: 6 [18432/47500]	Loss: 2.0527	LR: 0.100000
Training Epoch: 6 [18688/47500]	Loss: 1.9210	LR: 0.100000
Training Epoch: 6 [18944/47500]	Loss: 1.9865	LR: 0.100000
Training Epoch: 6 [19200/47500]	Loss: 1.9542	LR: 0.100000
Training Epoch: 6 [19456/47500]	Loss: 1.9404	LR: 0.100000
Training Epoch: 6 [19712/47500]	Loss: 1.9348	LR: 0.100000
Training Epoch: 6 [19968/47500]	Loss: 2.0024	LR: 0.100000
Training Epoch: 6 [20224/47500]	Loss: 1.9580	LR: 0.100000
Training Epoch: 6 [20480/47500]	Loss: 2.0438	LR: 0.100000
Training Epoch: 6 [20736/47500]	Loss: 1.9622	LR: 0.100000
Training Epoch: 6 [20992/47500]	Loss: 1.9597	LR: 0.100000
Training Epoch: 6 [21248/47500]	Loss: 2.0144	LR: 0.100000
Training Epoch: 6 [21504/47500]	Loss: 2.0335	LR: 0.100000
Training Epoch: 6 [21760/47500]	Loss: 1.9515	LR: 0.100000
Training Epoch: 6 [22016/47500]	Loss: 1.8951	LR: 0.100000
Training Epoch: 6 [22272/47500]	Loss: 1.9547	LR: 0.100000
Training Epoch: 6 [22528/47500]	Loss: 2.0420	LR: 0.100000
Training Epoch: 6 [22784/47500]	Loss: 2.0036	LR: 0.100000
Training Epoch: 6 [23040/47500]	Loss: 1.9624	LR: 0.100000
Training Epoch: 6 [23296/47500]	Loss: 2.0518	LR: 0.100000
Training Epoch: 6 [23552/47500]	Loss: 2.1057	LR: 0.100000
Training Epoch: 6 [23808/47500]	Loss: 1.9986	LR: 0.100000
Training Epoch: 6 [24064/47500]	Loss: 1.8881	LR: 0.100000
Training Epoch: 6 [24320/47500]	Loss: 2.0469	LR: 0.100000
Training Epoch: 6 [24576/47500]	Loss: 1.9594	LR: 0.100000
Training Epoch: 6 [24832/47500]	Loss: 1.9268	LR: 0.100000
Training Epoch: 6 [25088/47500]	Loss: 1.8919	LR: 0.100000
Training Epoch: 6 [25344/47500]	Loss: 1.9627	LR: 0.100000
Training Epoch: 6 [25600/47500]	Loss: 1.9314	LR: 0.100000
Training Epoch: 6 [25856/47500]	Loss: 1.9883	LR: 0.100000
Training Epoch: 6 [26112/47500]	Loss: 1.9684	LR: 0.100000
Training Epoch: 6 [26368/47500]	Loss: 1.9147	LR: 0.100000
Training Epoch: 6 [26624/47500]	Loss: 1.9875	LR: 0.100000
Training Epoch: 6 [26880/47500]	Loss: 2.0313	LR: 0.100000
Training Epoch: 6 [27136/47500]	Loss: 2.0043	LR: 0.100000
Training Epoch: 6 [27392/47500]	Loss: 1.9705	LR: 0.100000
Training Epoch: 6 [27648/47500]	Loss: 2.0199	LR: 0.100000
Training Epoch: 6 [27904/47500]	Loss: 1.9908	LR: 0.100000
Training Epoch: 6 [28160/47500]	Loss: 2.0088	LR: 0.100000
Training Epoch: 6 [28416/47500]	Loss: 1.9886	LR: 0.100000
Training Epoch: 6 [28672/47500]	Loss: 1.9912	LR: 0.100000
Training Epoch: 6 [28928/47500]	Loss: 1.9680	LR: 0.100000
Training Epoch: 6 [29184/47500]	Loss: 1.9511	LR: 0.100000
Training Epoch: 6 [29440/47500]	Loss: 1.9632	LR: 0.100000
Training Epoch: 6 [29696/47500]	Loss: 1.8872	LR: 0.100000
Training Epoch: 6 [29952/47500]	Loss: 1.9279	LR: 0.100000
Training Epoch: 6 [30208/47500]	Loss: 1.9653	LR: 0.100000
Training Epoch: 6 [30464/47500]	Loss: 1.9489	LR: 0.100000
Training Epoch: 6 [30720/47500]	Loss: 1.9474	LR: 0.100000
Training Epoch: 6 [30976/47500]	Loss: 2.0368	LR: 0.100000
Training Epoch: 6 [31232/47500]	Loss: 1.9987	LR: 0.100000
Training Epoch: 6 [31488/47500]	Loss: 1.9840	LR: 0.100000
Training Epoch: 6 [31744/47500]	Loss: 1.9547	LR: 0.100000
Training Epoch: 6 [32000/47500]	Loss: 2.0464	LR: 0.100000
Training Epoch: 6 [32256/47500]	Loss: 2.0068	LR: 0.100000
Training Epoch: 6 [32512/47500]	Loss: 1.9408	LR: 0.100000
Training Epoch: 6 [32768/47500]	Loss: 1.9180	LR: 0.100000
Training Epoch: 6 [33024/47500]	Loss: 1.9338	LR: 0.100000
Training Epoch: 6 [33280/47500]	Loss: 1.9413	LR: 0.100000
Training Epoch: 6 [33536/47500]	Loss: 1.9856	LR: 0.100000
Training Epoch: 6 [33792/47500]	Loss: 2.0160	LR: 0.100000
Training Epoch: 6 [34048/47500]	Loss: 1.9516	LR: 0.100000
Training Epoch: 6 [34304/47500]	Loss: 2.0162	LR: 0.100000
Training Epoch: 6 [34560/47500]	Loss: 1.9286	LR: 0.100000
Training Epoch: 6 [34816/47500]	Loss: 2.0059	LR: 0.100000
Training Epoch: 6 [35072/47500]	Loss: 1.9108	LR: 0.100000
Training Epoch: 6 [35328/47500]	Loss: 2.0528	LR: 0.100000
Training Epoch: 6 [35584/47500]	Loss: 2.0517	LR: 0.100000
Training Epoch: 6 [35840/47500]	Loss: 1.8280	LR: 0.100000
Training Epoch: 6 [36096/47500]	Loss: 1.9795	LR: 0.100000
Training Epoch: 6 [36352/47500]	Loss: 2.0560	LR: 0.100000
Training Epoch: 6 [36608/47500]	Loss: 2.0159	LR: 0.100000
Training Epoch: 6 [36864/47500]	Loss: 1.9152	LR: 0.100000
Training Epoch: 6 [37120/47500]	Loss: 1.9272	LR: 0.100000
Training Epoch: 6 [37376/47500]	Loss: 1.9721	LR: 0.100000
Training Epoch: 6 [37632/47500]	Loss: 1.9630	LR: 0.100000
Training Epoch: 6 [37888/47500]	Loss: 1.8952	LR: 0.100000
Training Epoch: 6 [38144/47500]	Loss: 1.9400	LR: 0.100000
Training Epoch: 6 [38400/47500]	Loss: 1.9789	LR: 0.100000
Training Epoch: 6 [38656/47500]	Loss: 2.0032	LR: 0.100000
Training Epoch: 6 [38912/47500]	Loss: 1.8789	LR: 0.100000
Training Epoch: 6 [39168/47500]	Loss: 1.9200	LR: 0.100000
Training Epoch: 6 [39424/47500]	Loss: 1.9569	LR: 0.100000
Training Epoch: 6 [39680/47500]	Loss: 1.9671	LR: 0.100000
Training Epoch: 6 [39936/47500]	Loss: 1.9668	LR: 0.100000
Training Epoch: 6 [40192/47500]	Loss: 1.9799	LR: 0.100000
Training Epoch: 6 [40448/47500]	Loss: 1.8954	LR: 0.100000
Training Epoch: 6 [40704/47500]	Loss: 1.9272	LR: 0.100000
Training Epoch: 6 [40960/47500]	Loss: 1.8735	LR: 0.100000
Training Epoch: 6 [41216/47500]	Loss: 1.8970	LR: 0.100000
Training Epoch: 6 [41472/47500]	Loss: 1.9811	LR: 0.100000
Training Epoch: 6 [41728/47500]	Loss: 1.9336	LR: 0.100000
Training Epoch: 6 [41984/47500]	Loss: 1.9113	LR: 0.100000
Training Epoch: 6 [42240/47500]	Loss: 1.9820	LR: 0.100000
Training Epoch: 6 [42496/47500]	Loss: 1.8685	LR: 0.100000
Training Epoch: 6 [42752/47500]	Loss: 1.8775	LR: 0.100000
Training Epoch: 6 [43008/47500]	Loss: 1.8873	LR: 0.100000
Training Epoch: 6 [43264/47500]	Loss: 2.0307	LR: 0.100000
Training Epoch: 6 [43520/47500]	Loss: 1.9757	LR: 0.100000
Training Epoch: 6 [43776/47500]	Loss: 1.9495	LR: 0.100000
Training Epoch: 6 [44032/47500]	Loss: 1.9958	LR: 0.100000
Training Epoch: 6 [44288/47500]	Loss: 2.0120	LR: 0.100000
Training Epoch: 6 [44544/47500]	Loss: 1.9497	LR: 0.100000
Training Epoch: 6 [44800/47500]	Loss: 1.9758	LR: 0.100000
Training Epoch: 6 [45056/47500]	Loss: 1.9263	LR: 0.100000
Training Epoch: 6 [45312/47500]	Loss: 1.9248	LR: 0.100000
Training Epoch: 6 [45568/47500]	Loss: 1.9938	LR: 0.100000
Training Epoch: 6 [45824/47500]	Loss: 1.9611	LR: 0.100000
Training Epoch: 6 [46080/47500]	Loss: 2.0857	LR: 0.100000
Training Epoch: 6 [46336/47500]	Loss: 1.9723	LR: 0.100000
Training Epoch: 6 [46592/47500]	Loss: 1.9230	LR: 0.100000
Training Epoch: 6 [46848/47500]	Loss: 1.9197	LR: 0.100000
Training Epoch: 6 [47104/47500]	Loss: 1.9458	LR: 0.100000
Training Epoch: 6 [47360/47500]	Loss: 2.0002	LR: 0.100000
Training Epoch: 6 [47500/47500]	Loss: 1.8970	LR: 0.100000
Epoch 6 - Average Train Loss: 1.9732, Train Accuracy: 0.2640
Epoch 6 training time consumed: 343.36s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0077, Accuracy: 0.2742, Time consumed:23.49s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-6-best.pth
Training Epoch: 7 [256/47500]	Loss: 1.9461	LR: 0.020000
Training Epoch: 7 [512/47500]	Loss: 2.0415	LR: 0.020000
Training Epoch: 7 [768/47500]	Loss: 1.9392	LR: 0.020000
Training Epoch: 7 [1024/47500]	Loss: 1.9336	LR: 0.020000
Training Epoch: 7 [1280/47500]	Loss: 1.9008	LR: 0.020000
Training Epoch: 7 [1536/47500]	Loss: 1.9705	LR: 0.020000
Training Epoch: 7 [1792/47500]	Loss: 2.0072	LR: 0.020000
Training Epoch: 7 [2048/47500]	Loss: 1.8759	LR: 0.020000
Training Epoch: 7 [2304/47500]	Loss: 1.9186	LR: 0.020000
Training Epoch: 7 [2560/47500]	Loss: 1.8362	LR: 0.020000
Training Epoch: 7 [2816/47500]	Loss: 1.9176	LR: 0.020000
Training Epoch: 7 [3072/47500]	Loss: 1.8443	LR: 0.020000
Training Epoch: 7 [3328/47500]	Loss: 1.8875	LR: 0.020000
Training Epoch: 7 [3584/47500]	Loss: 1.9081	LR: 0.020000
Training Epoch: 7 [3840/47500]	Loss: 1.8973	LR: 0.020000
Training Epoch: 7 [4096/47500]	Loss: 1.8164	LR: 0.020000
Training Epoch: 7 [4352/47500]	Loss: 1.8965	LR: 0.020000
Training Epoch: 7 [4608/47500]	Loss: 1.9712	LR: 0.020000
Training Epoch: 7 [4864/47500]	Loss: 1.8767	LR: 0.020000
Training Epoch: 7 [5120/47500]	Loss: 1.9820	LR: 0.020000
Training Epoch: 7 [5376/47500]	Loss: 1.9030	LR: 0.020000
Training Epoch: 7 [5632/47500]	Loss: 1.8769	LR: 0.020000
Training Epoch: 7 [5888/47500]	Loss: 1.8713	LR: 0.020000
Training Epoch: 7 [6144/47500]	Loss: 1.9293	LR: 0.020000
Training Epoch: 7 [6400/47500]	Loss: 1.8929	LR: 0.020000
Training Epoch: 7 [6656/47500]	Loss: 1.9443	LR: 0.020000
Training Epoch: 7 [6912/47500]	Loss: 1.9691	LR: 0.020000
Training Epoch: 7 [7168/47500]	Loss: 1.9522	LR: 0.020000
Training Epoch: 7 [7424/47500]	Loss: 1.9367	LR: 0.020000
Training Epoch: 7 [7680/47500]	Loss: 1.8713	LR: 0.020000
Training Epoch: 7 [7936/47500]	Loss: 1.8471	LR: 0.020000
Training Epoch: 7 [8192/47500]	Loss: 1.8423	LR: 0.020000
Training Epoch: 7 [8448/47500]	Loss: 1.9433	LR: 0.020000
Training Epoch: 7 [8704/47500]	Loss: 1.8856	LR: 0.020000
Training Epoch: 7 [8960/47500]	Loss: 1.8411	LR: 0.020000
Training Epoch: 7 [9216/47500]	Loss: 1.8881	LR: 0.020000
Training Epoch: 7 [9472/47500]	Loss: 1.8796	LR: 0.020000
Training Epoch: 7 [9728/47500]	Loss: 1.8664	LR: 0.020000
Training Epoch: 7 [9984/47500]	Loss: 1.8541	LR: 0.020000
Training Epoch: 7 [10240/47500]	Loss: 1.9388	LR: 0.020000
Training Epoch: 7 [10496/47500]	Loss: 1.9442	LR: 0.020000
Training Epoch: 7 [10752/47500]	Loss: 1.9531	LR: 0.020000
Training Epoch: 7 [11008/47500]	Loss: 1.9007	LR: 0.020000
Training Epoch: 7 [11264/47500]	Loss: 1.8279	LR: 0.020000
Training Epoch: 7 [11520/47500]	Loss: 1.9927	LR: 0.020000
Training Epoch: 7 [11776/47500]	Loss: 1.9302	LR: 0.020000
Training Epoch: 7 [12032/47500]	Loss: 1.8219	LR: 0.020000
Training Epoch: 7 [12288/47500]	Loss: 1.9152	LR: 0.020000
Training Epoch: 7 [12544/47500]	Loss: 1.9248	LR: 0.020000
Training Epoch: 7 [12800/47500]	Loss: 1.8917	LR: 0.020000
Training Epoch: 7 [13056/47500]	Loss: 1.8694	LR: 0.020000
Training Epoch: 7 [13312/47500]	Loss: 1.9349	LR: 0.020000
Training Epoch: 7 [13568/47500]	Loss: 1.8255	LR: 0.020000
Training Epoch: 7 [13824/47500]	Loss: 1.8714	LR: 0.020000
Training Epoch: 7 [14080/47500]	Loss: 1.9034	LR: 0.020000
Training Epoch: 7 [14336/47500]	Loss: 1.9194	LR: 0.020000
Training Epoch: 7 [14592/47500]	Loss: 1.9402	LR: 0.020000
Training Epoch: 7 [14848/47500]	Loss: 1.8912	LR: 0.020000
Training Epoch: 7 [15104/47500]	Loss: 1.9558	LR: 0.020000
Training Epoch: 7 [15360/47500]	Loss: 1.9355	LR: 0.020000
Training Epoch: 7 [15616/47500]	Loss: 2.0067	LR: 0.020000
Training Epoch: 7 [15872/47500]	Loss: 1.9035	LR: 0.020000
Training Epoch: 7 [16128/47500]	Loss: 1.9159	LR: 0.020000
Training Epoch: 7 [16384/47500]	Loss: 1.8950	LR: 0.020000
Training Epoch: 7 [16640/47500]	Loss: 1.8837	LR: 0.020000
Training Epoch: 7 [16896/47500]	Loss: 1.8822	LR: 0.020000
Training Epoch: 7 [17152/47500]	Loss: 1.8378	LR: 0.020000
Training Epoch: 7 [17408/47500]	Loss: 1.8927	LR: 0.020000
Training Epoch: 7 [17664/47500]	Loss: 1.8742	LR: 0.020000
Training Epoch: 7 [17920/47500]	Loss: 1.8336	LR: 0.020000
Training Epoch: 7 [18176/47500]	Loss: 1.8651	LR: 0.020000
Training Epoch: 7 [18432/47500]	Loss: 1.8534	LR: 0.020000
Training Epoch: 7 [18688/47500]	Loss: 1.9618	LR: 0.020000
Training Epoch: 7 [18944/47500]	Loss: 1.9351	LR: 0.020000
Training Epoch: 7 [19200/47500]	Loss: 1.9159	LR: 0.020000
Training Epoch: 7 [19456/47500]	Loss: 1.9311	LR: 0.020000
Training Epoch: 7 [19712/47500]	Loss: 1.8733	LR: 0.020000
Training Epoch: 7 [19968/47500]	Loss: 1.8221	LR: 0.020000
Training Epoch: 7 [20224/47500]	Loss: 1.9619	LR: 0.020000
Training Epoch: 7 [20480/47500]	Loss: 1.9282	LR: 0.020000
Training Epoch: 7 [20736/47500]	Loss: 1.8871	LR: 0.020000
Training Epoch: 7 [20992/47500]	Loss: 1.8806	LR: 0.020000
Training Epoch: 7 [21248/47500]	Loss: 1.9021	LR: 0.020000
Training Epoch: 7 [21504/47500]	Loss: 1.9288	LR: 0.020000
Training Epoch: 7 [21760/47500]	Loss: 1.9324	LR: 0.020000
Training Epoch: 7 [22016/47500]	Loss: 1.8303	LR: 0.020000
Training Epoch: 7 [22272/47500]	Loss: 1.8628	LR: 0.020000
Training Epoch: 7 [22528/47500]	Loss: 1.9337	LR: 0.020000
Training Epoch: 7 [22784/47500]	Loss: 1.9073	LR: 0.020000
Training Epoch: 7 [23040/47500]	Loss: 1.9478	LR: 0.020000
Training Epoch: 7 [23296/47500]	Loss: 1.8579	LR: 0.020000
Training Epoch: 7 [23552/47500]	Loss: 1.8618	LR: 0.020000
Training Epoch: 7 [23808/47500]	Loss: 1.8360	LR: 0.020000
Training Epoch: 7 [24064/47500]	Loss: 1.9171	LR: 0.020000
Training Epoch: 7 [24320/47500]	Loss: 1.8785	LR: 0.020000
Training Epoch: 7 [24576/47500]	Loss: 1.9336	LR: 0.020000
Training Epoch: 7 [24832/47500]	Loss: 1.8659	LR: 0.020000
Training Epoch: 7 [25088/47500]	Loss: 1.9523	LR: 0.020000
Training Epoch: 7 [25344/47500]	Loss: 1.8443	LR: 0.020000
Training Epoch: 7 [25600/47500]	Loss: 1.8454	LR: 0.020000
Training Epoch: 7 [25856/47500]	Loss: 1.8443	LR: 0.020000
Training Epoch: 7 [26112/47500]	Loss: 1.9252	LR: 0.020000
Training Epoch: 7 [26368/47500]	Loss: 1.8493	LR: 0.020000
Training Epoch: 7 [26624/47500]	Loss: 1.8249	LR: 0.020000
Training Epoch: 7 [26880/47500]	Loss: 1.8256	LR: 0.020000
Training Epoch: 7 [27136/47500]	Loss: 1.9121	LR: 0.020000
Training Epoch: 7 [27392/47500]	Loss: 1.9075	LR: 0.020000
Training Epoch: 7 [27648/47500]	Loss: 1.9471	LR: 0.020000
Training Epoch: 7 [27904/47500]	Loss: 1.9056	LR: 0.020000
Training Epoch: 7 [28160/47500]	Loss: 1.9132	LR: 0.020000
Training Epoch: 7 [28416/47500]	Loss: 1.8917	LR: 0.020000
Training Epoch: 7 [28672/47500]	Loss: 1.8440	LR: 0.020000
Training Epoch: 7 [28928/47500]	Loss: 1.8322	LR: 0.020000
Training Epoch: 7 [29184/47500]	Loss: 1.9091	LR: 0.020000
Training Epoch: 7 [29440/47500]	Loss: 1.9620	LR: 0.020000
Training Epoch: 7 [29696/47500]	Loss: 1.9331	LR: 0.020000
Training Epoch: 7 [29952/47500]	Loss: 1.9147	LR: 0.020000
Training Epoch: 7 [30208/47500]	Loss: 1.9201	LR: 0.020000
Training Epoch: 7 [30464/47500]	Loss: 1.8861	LR: 0.020000
Training Epoch: 7 [30720/47500]	Loss: 1.9572	LR: 0.020000
Training Epoch: 7 [30976/47500]	Loss: 1.8679	LR: 0.020000
Training Epoch: 7 [31232/47500]	Loss: 1.8169	LR: 0.020000
Training Epoch: 7 [31488/47500]	Loss: 1.8935	LR: 0.020000
Training Epoch: 7 [31744/47500]	Loss: 1.9537	LR: 0.020000
Training Epoch: 7 [32000/47500]	Loss: 1.9675	LR: 0.020000
Training Epoch: 7 [32256/47500]	Loss: 1.8609	LR: 0.020000
Training Epoch: 7 [32512/47500]	Loss: 1.9144	LR: 0.020000
Training Epoch: 7 [32768/47500]	Loss: 1.8969	LR: 0.020000
Training Epoch: 7 [33024/47500]	Loss: 1.8268	LR: 0.020000
Training Epoch: 7 [33280/47500]	Loss: 1.8554	LR: 0.020000
Training Epoch: 7 [33536/47500]	Loss: 1.9032	LR: 0.020000
Training Epoch: 7 [33792/47500]	Loss: 1.8568	LR: 0.020000
Training Epoch: 7 [34048/47500]	Loss: 1.8062	LR: 0.020000
Training Epoch: 7 [34304/47500]	Loss: 1.8498	LR: 0.020000
Training Epoch: 7 [34560/47500]	Loss: 1.8891	LR: 0.020000
Training Epoch: 7 [34816/47500]	Loss: 1.9474	LR: 0.020000
Training Epoch: 7 [35072/47500]	Loss: 1.8815	LR: 0.020000
Training Epoch: 7 [35328/47500]	Loss: 1.9362	LR: 0.020000
Training Epoch: 7 [35584/47500]	Loss: 1.8034	LR: 0.020000
Training Epoch: 7 [35840/47500]	Loss: 1.8662	LR: 0.020000
Training Epoch: 7 [36096/47500]	Loss: 1.8365	LR: 0.020000
Training Epoch: 7 [36352/47500]	Loss: 1.8928	LR: 0.020000
Training Epoch: 7 [36608/47500]	Loss: 1.9673	LR: 0.020000
Training Epoch: 7 [36864/47500]	Loss: 1.8842	LR: 0.020000
Training Epoch: 7 [37120/47500]	Loss: 1.9519	LR: 0.020000
Training Epoch: 7 [37376/47500]	Loss: 1.8120	LR: 0.020000
Training Epoch: 7 [37632/47500]	Loss: 1.8962	LR: 0.020000
Training Epoch: 7 [37888/47500]	Loss: 1.9557	LR: 0.020000
Training Epoch: 7 [38144/47500]	Loss: 1.8634	LR: 0.020000
Training Epoch: 7 [38400/47500]	Loss: 1.9531	LR: 0.020000
Training Epoch: 7 [38656/47500]	Loss: 1.8955	LR: 0.020000
Training Epoch: 7 [38912/47500]	Loss: 1.9174	LR: 0.020000
Training Epoch: 7 [39168/47500]	Loss: 1.8596	LR: 0.020000
Training Epoch: 7 [39424/47500]	Loss: 1.8800	LR: 0.020000
Training Epoch: 7 [39680/47500]	Loss: 1.7605	LR: 0.020000
Training Epoch: 7 [39936/47500]	Loss: 1.8545	LR: 0.020000
Training Epoch: 7 [40192/47500]	Loss: 1.8659	LR: 0.020000
Training Epoch: 7 [40448/47500]	Loss: 1.9106	LR: 0.020000
Training Epoch: 7 [40704/47500]	Loss: 1.8960	LR: 0.020000
Training Epoch: 7 [40960/47500]	Loss: 1.8886	LR: 0.020000
Training Epoch: 7 [41216/47500]	Loss: 1.8212	LR: 0.020000
Training Epoch: 7 [41472/47500]	Loss: 1.7988	LR: 0.020000
Training Epoch: 7 [41728/47500]	Loss: 1.9260	LR: 0.020000
Training Epoch: 7 [41984/47500]	Loss: 1.9804	LR: 0.020000
Training Epoch: 7 [42240/47500]	Loss: 1.9230	LR: 0.020000
Training Epoch: 7 [42496/47500]	Loss: 1.8167	LR: 0.020000
Training Epoch: 7 [42752/47500]	Loss: 1.8941	LR: 0.020000
Training Epoch: 7 [43008/47500]	Loss: 1.9033	LR: 0.020000
Training Epoch: 7 [43264/47500]	Loss: 1.9015	LR: 0.020000
Training Epoch: 7 [43520/47500]	Loss: 1.9598	LR: 0.020000
Training Epoch: 7 [43776/47500]	Loss: 1.8886	LR: 0.020000
Training Epoch: 7 [44032/47500]	Loss: 1.9412	LR: 0.020000
Training Epoch: 7 [44288/47500]	Loss: 1.8853	LR: 0.020000
Training Epoch: 7 [44544/47500]	Loss: 1.8204	LR: 0.020000
Training Epoch: 7 [44800/47500]	Loss: 1.9634	LR: 0.020000
Training Epoch: 7 [45056/47500]	Loss: 1.9139	LR: 0.020000
Training Epoch: 7 [45312/47500]	Loss: 1.9315	LR: 0.020000
Training Epoch: 7 [45568/47500]	Loss: 1.8822	LR: 0.020000
Training Epoch: 7 [45824/47500]	Loss: 1.9361	LR: 0.020000
Training Epoch: 7 [46080/47500]	Loss: 1.9508	LR: 0.020000
Training Epoch: 7 [46336/47500]	Loss: 1.9454	LR: 0.020000
Training Epoch: 7 [46592/47500]	Loss: 1.9075	LR: 0.020000
Training Epoch: 7 [46848/47500]	Loss: 1.8837	LR: 0.020000
Training Epoch: 7 [47104/47500]	Loss: 1.8940	LR: 0.020000
Training Epoch: 7 [47360/47500]	Loss: 1.8214	LR: 0.020000
Training Epoch: 7 [47500/47500]	Loss: 1.7909	LR: 0.020000
Epoch 7 - Average Train Loss: 1.8968, Train Accuracy: 0.2973
Epoch 7 training time consumed: 343.26s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0076, Accuracy: 0.3007, Time consumed:23.52s
Saving weights file to checkpoint/retrain/ViT/Friday_18_July_2025_20h_12m_52s/ViT-Cifar10-seed4-ret50-7-best.pth
Training Epoch: 8 [256/47500]	Loss: 1.9688	LR: 0.020000
Training Epoch: 8 [512/47500]	Loss: 1.8926	LR: 0.020000
Training Epoch: 8 [768/47500]	Loss: 1.8510	LR: 0.020000
Training Epoch: 8 [1024/47500]	Loss: 1.9900	LR: 0.020000
Training Epoch: 8 [1280/47500]	Loss: 1.8407	LR: 0.020000
Training Epoch: 8 [1536/47500]	Loss: 1.8536	LR: 0.020000
Training Epoch: 8 [1792/47500]	Loss: 1.9134	LR: 0.020000
Training Epoch: 8 [2048/47500]	Loss: 1.8395	LR: 0.020000
Training Epoch: 8 [2304/47500]	Loss: 1.8010	LR: 0.020000
Training Epoch: 8 [2560/47500]	Loss: 1.7851	LR: 0.020000
Training Epoch: 8 [2816/47500]	Loss: 1.8996	LR: 0.020000
Training Epoch: 8 [3072/47500]	Loss: 1.7681	LR: 0.020000
Training Epoch: 8 [3328/47500]	Loss: 1.9315	LR: 0.020000
Training Epoch: 8 [3584/47500]	Loss: 1.8677	LR: 0.020000
Training Epoch: 8 [3840/47500]	Loss: 1.8555	LR: 0.020000
Training Epoch: 8 [4096/47500]	Loss: 1.7892	LR: 0.020000
Training Epoch: 8 [4352/47500]	Loss: 1.8151	LR: 0.020000
Training Epoch: 8 [4608/47500]	Loss: 1.9256	LR: 0.020000
Training Epoch: 8 [4864/47500]	Loss: 1.9401	LR: 0.020000
Training Epoch: 8 [5120/47500]	Loss: 1.9304	LR: 0.020000
Training Epoch: 8 [5376/47500]	Loss: 2.0140	LR: 0.020000
Training Epoch: 8 [5632/47500]	Loss: 1.8234	LR: 0.020000
Training Epoch: 8 [5888/47500]	Loss: 1.9385	LR: 0.020000
Training Epoch: 8 [6144/47500]	Loss: 1.8993	LR: 0.020000
Training Epoch: 8 [6400/47500]	Loss: 1.8857	LR: 0.020000
Training Epoch: 8 [6656/47500]	Loss: 1.8976	LR: 0.020000
Training Epoch: 8 [6912/47500]	Loss: 1.9278	LR: 0.020000
Training Epoch: 8 [7168/47500]	Loss: 1.8831	LR: 0.020000
Training Epoch: 8 [7424/47500]	Loss: 1.9668	LR: 0.020000
Training Epoch: 8 [7680/47500]	Loss: 1.8926	LR: 0.020000
Training Epoch: 8 [7936/47500]	Loss: 1.8842	LR: 0.020000
Training Epoch: 8 [8192/47500]	Loss: 1.9540	LR: 0.020000
Training Epoch: 8 [8448/47500]	Loss: 1.8982	LR: 0.020000
Training Epoch: 8 [8704/47500]	Loss: 1.8504	LR: 0.020000
Training Epoch: 8 [8960/47500]	Loss: 1.8730	LR: 0.020000
Training Epoch: 8 [9216/47500]	Loss: 1.9654	LR: 0.020000
Training Epoch: 8 [9472/47500]	Loss: 1.9433	LR: 0.020000
Training Epoch: 8 [9728/47500]	Loss: 1.8981	LR: 0.020000
Training Epoch: 8 [9984/47500]	Loss: 1.8801	LR: 0.020000
Training Epoch: 8 [10240/47500]	Loss: 1.8846	LR: 0.020000
Training Epoch: 8 [10496/47500]	Loss: 1.8470	LR: 0.020000
Training Epoch: 8 [10752/47500]	Loss: 1.8680	LR: 0.020000
Training Epoch: 8 [11008/47500]	Loss: 1.8983	LR: 0.020000
Training Epoch: 8 [11264/47500]	Loss: 1.9138	LR: 0.020000
Training Epoch: 8 [11520/47500]	Loss: 1.8536	LR: 0.020000
Training Epoch: 8 [11776/47500]	Loss: 1.8839	LR: 0.020000
Training Epoch: 8 [12032/47500]	Loss: 1.8691	LR: 0.020000
Training Epoch: 8 [12288/47500]	Loss: 1.9236	LR: 0.020000
Training Epoch: 8 [12544/47500]	Loss: 1.8126	LR: 0.020000
Training Epoch: 8 [12800/47500]	Loss: 1.8708	LR: 0.020000
Training Epoch: 8 [13056/47500]	Loss: 1.8513	LR: 0.020000
Training Epoch: 8 [13312/47500]	Loss: 1.8107	LR: 0.020000
Training Epoch: 8 [13568/47500]	Loss: 1.8863	LR: 0.020000
Training Epoch: 8 [13824/47500]	Loss: 1.8275	LR: 0.020000
Training Epoch: 8 [14080/47500]	Loss: 1.7849	LR: 0.020000
Training Epoch: 8 [14336/47500]	Loss: 1.8505	LR: 0.020000
Training Epoch: 8 [14592/47500]	Loss: 1.8552	LR: 0.020000
Training Epoch: 8 [14848/47500]	Loss: 1.9036	LR: 0.020000
Training Epoch: 8 [15104/47500]	Loss: 1.7101	LR: 0.020000
Training Epoch: 8 [15360/47500]	Loss: 1.8975	LR: 0.020000
Training Epoch: 8 [15616/47500]	Loss: 2.0066	LR: 0.020000
Training Epoch: 8 [15872/47500]	Loss: 1.8715	LR: 0.020000
Training Epoch: 8 [16128/47500]	Loss: 1.8869	LR: 0.020000
Training Epoch: 8 [16384/47500]	Loss: 1.7745	LR: 0.020000
Training Epoch: 8 [16640/47500]	Loss: 1.8246	LR: 0.020000
Training Epoch: 8 [16896/47500]	Loss: 1.8401	LR: 0.020000
Training Epoch: 8 [17152/47500]	Loss: 1.8602	LR: 0.020000
Training Epoch: 8 [17408/47500]	Loss: 1.8359	LR: 0.020000
Training Epoch: 8 [17664/47500]	Loss: 1.8625	LR: 0.020000
Training Epoch: 8 [17920/47500]	Loss: 1.8984	LR: 0.020000
Training Epoch: 8 [18176/47500]	Loss: 1.8617	LR: 0.020000
Training Epoch: 8 [18432/47500]	Loss: 1.9085	LR: 0.020000
Training Epoch: 8 [18688/47500]	Loss: 1.8022	LR: 0.020000
Training Epoch: 8 [18944/47500]	Loss: 1.9869	LR: 0.020000
Training Epoch: 8 [19200/47500]	Loss: 1.8851	LR: 0.020000
Training Epoch: 8 [19456/47500]	Loss: 1.8086	LR: 0.020000
Training Epoch: 8 [19712/47500]	Loss: 1.8532	LR: 0.020000
Training Epoch: 8 [19968/47500]	Loss: 1.9235	LR: 0.020000
Training Epoch: 8 [20224/47500]	Loss: 1.8047	LR: 0.020000
Training Epoch: 8 [20480/47500]	Loss: 1.7861	LR: 0.020000
Training Epoch: 8 [20736/47500]	Loss: 1.8762	LR: 0.020000
Training Epoch: 8 [20992/47500]	Loss: 1.9214	LR: 0.020000
Training Epoch: 8 [21248/47500]	Loss: 1.8433	LR: 0.020000
Training Epoch: 8 [21504/47500]	Loss: 1.8049	LR: 0.020000
Training Epoch: 8 [21760/47500]	Loss: 1.8745	LR: 0.020000
Training Epoch: 8 [22016/47500]	Loss: 1.8203	LR: 0.020000
Training Epoch: 8 [22272/47500]	Loss: 1.7819	LR: 0.020000
Training Epoch: 8 [22528/47500]	Loss: 1.9338	LR: 0.020000
Training Epoch: 8 [22784/47500]	Loss: 1.9217	LR: 0.020000
Training Epoch: 8 [23040/47500]	Loss: 1.8230	LR: 0.020000
Training Epoch: 8 [23296/47500]	Loss: 1.9164	LR: 0.020000
Training Epoch: 8 [23552/47500]	Loss: 1.8271	LR: 0.020000
Training Epoch: 8 [23808/47500]	Loss: 1.8736	LR: 0.020000
Training Epoch: 8 [24064/47500]	Loss: 1.8079	LR: 0.020000
Training Epoch: 8 [24320/47500]	Loss: 1.8402	LR: 0.020000
Training Epoch: 8 [24576/47500]	Loss: 1.7644	LR: 0.020000
Training Epoch: 8 [24832/47500]	Loss: 1.9051	LR: 0.020000
Training Epoch: 8 [25088/47500]	Loss: 1.9381	LR: 0.020000
Training Epoch: 8 [25344/47500]	Loss: 1.8047	LR: 0.020000
Training Epoch: 8 [25600/47500]	Loss: 1.8952	LR: 0.020000
Training Epoch: 8 [25856/47500]	Loss: 1.8949	LR: 0.020000
Training Epoch: 8 [26112/47500]	Loss: 1.8223	LR: 0.020000
Training Epoch: 8 [26368/47500]	Loss: 1.9286	LR: 0.020000
Training Epoch: 8 [26624/47500]	Loss: 1.8108	LR: 0.020000
Training Epoch: 8 [26880/47500]	Loss: 1.7496	LR: 0.020000
Training Epoch: 8 [27136/47500]	Loss: 1.8322	LR: 0.020000
Training Epoch: 8 [27392/47500]	Loss: 1.8800	LR: 0.020000
Training Epoch: 8 [27648/47500]	Loss: 1.8733	LR: 0.020000
Training Epoch: 8 [27904/47500]	Loss: 1.9120	LR: 0.020000
Training Epoch: 8 [28160/47500]	Loss: 1.9249	LR: 0.020000
Training Epoch: 8 [28416/47500]	Loss: 1.8618	LR: 0.020000
Training Epoch: 8 [28672/47500]	Loss: 1.8645	LR: 0.020000
Training Epoch: 8 [28928/47500]	Loss: 1.9168	LR: 0.020000
Training Epoch: 8 [29184/47500]	Loss: 1.9347	LR: 0.020000
Training Epoch: 8 [29440/47500]	Loss: 1.8661	LR: 0.020000
Training Epoch: 8 [29696/47500]	Loss: 1.8265	LR: 0.020000
Training Epoch: 8 [29952/47500]	Loss: 1.8830	LR: 0.020000
Training Epoch: 8 [30208/47500]	Loss: 1.8990	LR: 0.020000
Training Epoch: 8 [30464/47500]	Loss: 1.9188	LR: 0.020000
Training Epoch: 8 [30720/47500]	Loss: 1.8529	LR: 0.020000
Training Epoch: 8 [30976/47500]	Loss: 1.8231	LR: 0.020000
Training Epoch: 8 [31232/47500]	Loss: 1.8055	LR: 0.020000
Training Epoch: 8 [31488/47500]	Loss: 1.8967	LR: 0.020000
Training Epoch: 8 [31744/47500]	Loss: 1.8215	LR: 0.020000
Training Epoch: 8 [32000/47500]	Loss: 1.8815	LR: 0.020000
Training Epoch: 8 [32256/47500]	Loss: 1.8886	LR: 0.020000
Training Epoch: 8 [32512/47500]	Loss: 1.8391	LR: 0.020000
Training Epoch: 8 [32768/47500]	Loss: 1.9236	LR: 0.020000
Training Epoch: 8 [33024/47500]	Loss: 1.8506	LR: 0.020000
Training Epoch: 8 [33280/47500]	Loss: 1.8237	LR: 0.020000
Training Epoch: 8 [33536/47500]	Loss: 1.9669	LR: 0.020000
Training Epoch: 8 [33792/47500]	Loss: 1.8216	LR: 0.020000
Training Epoch: 8 [34048/47500]	Loss: 1.8596	LR: 0.020000
Training Epoch: 8 [34304/47500]	Loss: 1.8820	LR: 0.020000
Training Epoch: 8 [34560/47500]	Loss: 1.9158	LR: 0.020000
Training Epoch: 8 [34816/47500]	Loss: 1.8031	LR: 0.020000
Training Epoch: 8 [35072/47500]	Loss: 1.8809	LR: 0.020000
Training Epoch: 8 [35328/47500]	Loss: 1.7829	LR: 0.020000
Training Epoch: 8 [35584/47500]	Loss: 1.8856	LR: 0.020000
Training Epoch: 8 [35840/47500]	Loss: 1.7953	LR: 0.020000
Training Epoch: 8 [36096/47500]	Loss: 1.9428	LR: 0.020000
Training Epoch: 8 [36352/47500]	Loss: 1.8812	LR: 0.020000
Training Epoch: 8 [36608/47500]	Loss: 1.8045	LR: 0.020000
Training Epoch: 8 [36864/47500]	Loss: 1.9332	LR: 0.020000
Training Epoch: 8 [37120/47500]	Loss: 1.9430	LR: 0.020000
Training Epoch: 8 [37376/47500]	Loss: 1.8436	LR: 0.020000
Training Epoch: 8 [37632/47500]	Loss: 1.8589	LR: 0.020000
Training Epoch: 8 [37888/47500]	Loss: 1.8822	LR: 0.020000
Training Epoch: 8 [38144/47500]	Loss: 1.8605	LR: 0.020000
Training Epoch: 8 [38400/47500]	Loss: 1.8008	LR: 0.020000
Training Epoch: 8 [38656/47500]	Loss: 1.8555	LR: 0.020000
Training Epoch: 8 [38912/47500]	Loss: 1.9322	LR: 0.020000
Training Epoch: 8 [39168/47500]	Loss: 1.8609	LR: 0.020000
Training Epoch: 8 [39424/47500]	Loss: 1.9229	LR: 0.020000
Training Epoch: 8 [39680/47500]	Loss: 1.9232	LR: 0.020000
Training Epoch: 8 [39936/47500]	Loss: 1.8793	LR: 0.020000
Training Epoch: 8 [40192/47500]	Loss: 1.8915	LR: 0.020000
Training Epoch: 8 [40448/47500]	Loss: 1.8551	LR: 0.020000
Training Epoch: 8 [40704/47500]	Loss: 1.8485	LR: 0.020000
Training Epoch: 8 [40960/47500]	Loss: 1.8758	LR: 0.020000
Training Epoch: 8 [41216/47500]	Loss: 1.8742	LR: 0.020000
Training Epoch: 8 [41472/47500]	Loss: 1.9564	LR: 0.020000
Training Epoch: 8 [41728/47500]	Loss: 1.8654	LR: 0.020000
Training Epoch: 8 [41984/47500]	Loss: 1.8438	LR: 0.020000
Training Epoch: 8 [42240/47500]	Loss: 1.9387	LR: 0.020000
Training Epoch: 8 [42496/47500]	Loss: 1.9345	LR: 0.020000
Training Epoch: 8 [42752/47500]	Loss: 1.8879	LR: 0.020000
Training Epoch: 8 [43008/47500]	Loss: 1.9008	LR: 0.020000
Training Epoch: 8 [43264/47500]	Loss: 1.9538	LR: 0.020000
Training Epoch: 8 [43520/47500]	Loss: 1.8688	LR: 0.020000
Training Epoch: 8 [43776/47500]	Loss: 1.8661	LR: 0.020000
Training Epoch: 8 [44032/47500]	Loss: 1.8606	LR: 0.020000
Training Epoch: 8 [44288/47500]	Loss: 1.8654	LR: 0.020000
Training Epoch: 8 [44544/47500]	Loss: 1.8638	LR: 0.020000
Training Epoch: 8 [44800/47500]	Loss: 1.9114	LR: 0.020000
Training Epoch: 8 [45056/47500]	Loss: 1.9047	LR: 0.020000
Training Epoch: 8 [45312/47500]	Loss: 1.7525	LR: 0.020000
Training Epoch: 8 [45568/47500]	Loss: 1.9044	LR: 0.020000
Training Epoch: 8 [45824/47500]	Loss: 1.8071	LR: 0.020000
Training Epoch: 8 [46080/47500]	Loss: 1.8457	LR: 0.020000
Training Epoch: 8 [46336/47500]	Loss: 1.8660	LR: 0.020000
Training Epoch: 8 [46592/47500]	Loss: 1.8341	LR: 0.020000
Training Epoch: 8 [46848/47500]	Loss: 1.8861	LR: 0.020000
Training Epoch: 8 [47104/47500]	Loss: 1.8166	LR: 0.020000
Training Epoch: 8 [47360/47500]	Loss: 1.9019	LR: 0.020000
Training Epoch: 8 [47500/47500]	Loss: 1.8292	LR: 0.020000
Epoch 8 - Average Train Loss: 1.8718, Train Accuracy: 0.3073
Epoch 8 training time consumed: 343.03s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0077, Accuracy: 0.3007, Time consumed:23.51s
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: 30.09765625
Retain Accuracy: 31.368928909301758
Zero-Retain Forget (ZRF): 0.9784944653511047
Membership Inference Attack (MIA): 0.6924
Forget vs Retain Membership Inference Attack (MIA): 0.622
Forget vs Test Membership Inference Attack (MIA): 0.562
Test vs Retain Membership Inference Attack (MIA): 0.50325
Train vs Test Membership Inference Attack (MIA): 0.495
Forget Set Accuracy (Df): 31.890941619873047
Method Execution Time: 5350.11 seconds
