【Ubuntu 24.04.3】Quotient Network: experiments_on_cifar10 — q44

MSI Cyborg-15-A12VE

Acknowledgments and References

(quotient) wish@wish-Cyborg-15-A12VE:~/Quotient-Networks/experiments_on_cifar10$ python ./src/train.py --model q44
Training Progress:   0%|                                | 0/182 [00:00<?, ?it/s]Training: Epoch[001/182] Iteration[050/352] Loss: 2.0619 Acc:22.59%
Training: Epoch[001/182] Iteration[100/352] Loss: 1.9566 Acc:26.30%
Training: Epoch[001/182] Iteration[150/352] Loss: 1.8690 Acc:29.72%
Training: Epoch[001/182] Iteration[200/352] Loss: 1.7976 Acc:32.24%
Training: Epoch[001/182] Iteration[250/352] Loss: 1.7280 Acc:35.02%
Training: Epoch[001/182] Iteration[300/352] Loss: 1.6702 Acc:37.34%
Training: Epoch[001/182] Iteration[350/352] Loss: 1.6166 Acc:39.49%
Training Progress:   0%| | 0/182 [00:19<?, ?it/s, Train Acc=39.54%, Valid Acc=50Epoch[001/182] Train Acc: 39.54% Valid Acc:50.04% Train loss:1.6157 Valid loss:1.4855 LR:0.1
Training Progress:   1%| | 1/182 [00:19<59:35, 19.75s/it, Train Acc=39.54%, ValiTraining: Epoch[002/182] Iteration[050/352] Loss: 1.2390 Acc:55.31%
Training: Epoch[002/182] Iteration[100/352] Loss: 1.2042 Acc:56.82%
Training: Epoch[002/182] Iteration[150/352] Loss: 1.1675 Acc:57.99%
Training: Epoch[002/182] Iteration[200/352] Loss: 1.1392 Acc:59.11%
Training: Epoch[002/182] Iteration[250/352] Loss: 1.1213 Acc:59.84%
Training: Epoch[002/182] Iteration[300/352] Loss: 1.0972 Acc:60.74%
Training: Epoch[002/182] Iteration[350/352] Loss: 1.0780 Acc:61.39%
Training Progress:   1%| | 1/182 [00:39<59:35, 19.75s/it, Train Acc=61.44%, ValiEpoch[002/182] Train Acc: 61.44% Valid Acc:66.16% Train loss:1.0763 Valid loss:0.9998 LR:0.1
Training Progress:   1%| | 2/182 [00:39<58:39, 19.55s/it, Train Acc=61.44%, ValiTraining: Epoch[003/182] Iteration[050/352] Loss: 0.8946 Acc:68.66%
Training: Epoch[003/182] Iteration[100/352] Loss: 0.8892 Acc:68.62%
Training: Epoch[003/182] Iteration[150/352] Loss: 0.8747 Acc:69.33%
Training: Epoch[003/182] Iteration[200/352] Loss: 0.8515 Acc:70.15%
Training: Epoch[003/182] Iteration[250/352] Loss: 0.8410 Acc:70.48%
Training: Epoch[003/182] Iteration[300/352] Loss: 0.8353 Acc:70.69%
Training: Epoch[003/182] Iteration[350/352] Loss: 0.8222 Acc:71.24%
Training Progress:   1%| | 2/182 [00:58<58:39, 19.55s/it, Train Acc=71.25%, ValiEpoch[003/182] Train Acc: 71.25% Valid Acc:72.24% Train loss:0.8215 Valid loss:0.8109 LR:0.1
Training Progress:   2%| | 3/182 [00:58<58:18, 19.55s/it, Train Acc=71.25%, ValiTraining: Epoch[004/182] Iteration[050/352] Loss: 0.7410 Acc:74.73%
Training: Epoch[004/182] Iteration[100/352] Loss: 0.7313 Acc:74.70%
Training: Epoch[004/182] Iteration[150/352] Loss: 0.7239 Acc:74.99%
Training: Epoch[004/182] Iteration[200/352] Loss: 0.7260 Acc:74.84%
Training: Epoch[004/182] Iteration[250/352] Loss: 0.7173 Acc:75.07%
Training: Epoch[004/182] Iteration[300/352] Loss: 0.7110 Acc:75.29%
Training: Epoch[004/182] Iteration[350/352] Loss: 0.7056 Acc:75.43%
Training Progress:   2%| | 3/182 [01:18<58:18, 19.55s/it, Train Acc=75.42%, ValiEpoch[004/182] Train Acc: 75.42% Valid Acc:74.90% Train loss:0.7056 Valid loss:0.7469 LR:0.1
Training Progress:   2%| | 4/182 [01:18<58:11, 19.61s/it, Train Acc=75.42%, ValiTraining: Epoch[005/182] Iteration[050/352] Loss: 0.6248 Acc:78.45%
Training: Epoch[005/182] Iteration[100/352] Loss: 0.6289 Acc:78.11%
Training: Epoch[005/182] Iteration[150/352] Loss: 0.6356 Acc:77.97%
Training: Epoch[005/182] Iteration[200/352] Loss: 0.6344 Acc:77.98%
Training: Epoch[005/182] Iteration[250/352] Loss: 0.6279 Acc:78.20%
Training: Epoch[005/182] Iteration[300/352] Loss: 0.6220 Acc:78.47%
Training: Epoch[005/182] Iteration[350/352] Loss: 0.6170 Acc:78.66%
Training Progress:   2%| | 4/182 [01:38<58:11, 19.61s/it, Train Acc=78.67%, ValiEpoch[005/182] Train Acc: 78.67% Valid Acc:74.74% Train loss:0.6167 Valid loss:0.7534 LR:0.1
Training Progress:   3%| | 5/182 [01:38<57:56, 19.64s/it, Train Acc=78.67%, ValiTraining: Epoch[006/182] Iteration[050/352] Loss: 0.5494 Acc:81.00%
Training: Epoch[006/182] Iteration[100/352] Loss: 0.5541 Acc:81.01%
Training: Epoch[006/182] Iteration[150/352] Loss: 0.5536 Acc:81.06%
Training: Epoch[006/182] Iteration[200/352] Loss: 0.5539 Acc:81.04%
Training: Epoch[006/182] Iteration[250/352] Loss: 0.5499 Acc:81.09%
Training: Epoch[006/182] Iteration[300/352] Loss: 0.5557 Acc:80.90%
Training: Epoch[006/182] Iteration[350/352] Loss: 0.5506 Acc:81.04%
Training Progress:   3%| | 5/182 [01:57<57:56, 19.64s/it, Train Acc=81.04%, ValiEpoch[006/182] Train Acc: 81.04% Valid Acc:73.18% Train loss:0.5506 Valid loss:0.7857 LR:0.1
Training Progress:   3%| | 6/182 [01:57<57:43, 19.68s/it, Train Acc=81.04%, ValiTraining: Epoch[007/182] Iteration[050/352] Loss: 0.5021 Acc:82.75%
Training: Epoch[007/182] Iteration[100/352] Loss: 0.5069 Acc:82.67%
Training: Epoch[007/182] Iteration[150/352] Loss: 0.5042 Acc:82.65%
Training: Epoch[007/182] Iteration[200/352] Loss: 0.5059 Acc:82.55%
Training: Epoch[007/182] Iteration[250/352] Loss: 0.5047 Acc:82.60%
Training: Epoch[007/182] Iteration[300/352] Loss: 0.5040 Acc:82.65%
Training: Epoch[007/182] Iteration[350/352] Loss: 0.5021 Acc:82.70%
Training Progress:   3%| | 6/182 [02:17<57:43, 19.68s/it, Train Acc=82.69%, ValiEpoch[007/182] Train Acc: 82.69% Valid Acc:80.82% Train loss:0.5024 Valid loss:0.5703 LR:0.1
Training Progress:   4%| | 7/182 [02:17<57:30, 19.72s/it, Train Acc=82.69%, ValiTraining: Epoch[008/182] Iteration[050/352] Loss: 0.4654 Acc:84.02%
Training: Epoch[008/182] Iteration[100/352] Loss: 0.4680 Acc:83.75%
Training: Epoch[008/182] Iteration[150/352] Loss: 0.4754 Acc:83.44%
Training: Epoch[008/182] Iteration[200/352] Loss: 0.4689 Acc:83.71%
Training: Epoch[008/182] Iteration[250/352] Loss: 0.4726 Acc:83.54%
Training: Epoch[008/182] Iteration[300/352] Loss: 0.4734 Acc:83.56%
Training: Epoch[008/182] Iteration[350/352] Loss: 0.4722 Acc:83.63%
Training Progress:   4%| | 7/182 [02:37<57:30, 19.72s/it, Train Acc=83.65%, ValiEpoch[008/182] Train Acc: 83.65% Valid Acc:81.64% Train loss:0.4717 Valid loss:0.5743 LR:0.1
Training Progress:   4%| | 8/182 [02:37<57:25, 19.80s/it, Train Acc=83.65%, ValiTraining: Epoch[009/182] Iteration[050/352] Loss: 0.4261 Acc:85.11%
Training: Epoch[009/182] Iteration[100/352] Loss: 0.4317 Acc:85.30%
Training: Epoch[009/182] Iteration[150/352] Loss: 0.4398 Acc:84.85%
Training: Epoch[009/182] Iteration[200/352] Loss: 0.4444 Acc:84.66%
Training: Epoch[009/182] Iteration[250/352] Loss: 0.4430 Acc:84.65%
Training: Epoch[009/182] Iteration[300/352] Loss: 0.4415 Acc:84.69%
Training: Epoch[009/182] Iteration[350/352] Loss: 0.4393 Acc:84.75%
Training Progress:   4%| | 8/182 [02:57<57:25, 19.80s/it, Train Acc=84.72%, ValiEpoch[009/182] Train Acc: 84.72% Valid Acc:82.14% Train loss:0.4402 Valid loss:0.5249 LR:0.1
Training Progress:   5%| | 9/182 [02:57<57:15, 19.86s/it, Train Acc=84.72%, ValiTraining: Epoch[010/182] Iteration[050/352] Loss: 0.4339 Acc:85.02%
Training: Epoch[010/182] Iteration[100/352] Loss: 0.4197 Acc:85.40%
Training: Epoch[010/182] Iteration[150/352] Loss: 0.4222 Acc:85.41%
Training: Epoch[010/182] Iteration[200/352] Loss: 0.4202 Acc:85.40%
Training: Epoch[010/182] Iteration[250/352] Loss: 0.4162 Acc:85.55%
Training: Epoch[010/182] Iteration[300/352] Loss: 0.4157 Acc:85.53%
Training: Epoch[010/182] Iteration[350/352] Loss: 0.4145 Acc:85.62%
Training Progress:   5%| | 9/182 [03:17<57:15, 19.86s/it, Train Acc=85.61%, ValiEpoch[010/182] Train Acc: 85.61% Valid Acc:80.98% Train loss:0.4149 Valid loss:0.5816 LR:0.1
Training Progress:   5%| | 10/182 [03:17<57:01, 19.89s/it, Train Acc=85.61%, ValTraining: Epoch[011/182] Iteration[050/352] Loss: 0.3796 Acc:86.64%
Training: Epoch[011/182] Iteration[100/352] Loss: 0.3765 Acc:86.69%
Training: Epoch[011/182] Iteration[150/352] Loss: 0.3848 Acc:86.39%
Training: Epoch[011/182] Iteration[200/352] Loss: 0.3838 Acc:86.53%
Training: Epoch[011/182] Iteration[250/352] Loss: 0.3902 Acc:86.37%
Training: Epoch[011/182] Iteration[300/352] Loss: 0.3872 Acc:86.47%
Training: Epoch[011/182] Iteration[350/352] Loss: 0.3916 Acc:86.42%
Training Progress:   5%| | 10/182 [03:37<57:01, 19.89s/it, Train Acc=86.42%, ValEpoch[011/182] Train Acc: 86.42% Valid Acc:83.72% Train loss:0.3918 Valid loss:0.4872 LR:0.1
Training Progress:   6%| | 11/182 [03:37<56:52, 19.95s/it, Train Acc=86.42%, ValTraining: Epoch[012/182] Iteration[050/352] Loss: 0.3535 Acc:87.73%
Training: Epoch[012/182] Iteration[100/352] Loss: 0.3575 Acc:87.52%
Training: Epoch[012/182] Iteration[150/352] Loss: 0.3604 Acc:87.33%
Training: Epoch[012/182] Iteration[200/352] Loss: 0.3628 Acc:87.23%
Training: Epoch[012/182] Iteration[250/352] Loss: 0.3622 Acc:87.22%
Training: Epoch[012/182] Iteration[300/352] Loss: 0.3653 Acc:87.26%
Training: Epoch[012/182] Iteration[350/352] Loss: 0.3686 Acc:87.18%
Training Progress:   6%| | 11/182 [03:57<56:52, 19.95s/it, Train Acc=87.19%, ValEpoch[012/182] Train Acc: 87.19% Valid Acc:82.98% Train loss:0.3687 Valid loss:0.5367 LR:0.1
Training Progress:   7%| | 12/182 [03:57<56:40, 20.00s/it, Train Acc=87.19%, ValTraining: Epoch[013/182] Iteration[050/352] Loss: 0.3595 Acc:87.42%
Training: Epoch[013/182] Iteration[100/352] Loss: 0.3430 Acc:87.98%
Training: Epoch[013/182] Iteration[150/352] Loss: 0.3459 Acc:87.98%
Training: Epoch[013/182] Iteration[200/352] Loss: 0.3499 Acc:87.77%
Training: Epoch[013/182] Iteration[250/352] Loss: 0.3537 Acc:87.62%
Training: Epoch[013/182] Iteration[300/352] Loss: 0.3544 Acc:87.63%
Training: Epoch[013/182] Iteration[350/352] Loss: 0.3552 Acc:87.63%
Training Progress:   7%| | 12/182 [04:17<56:40, 20.00s/it, Train Acc=87.64%, ValEpoch[013/182] Train Acc: 87.64% Valid Acc:86.02% Train loss:0.3552 Valid loss:0.4213 LR:0.1
Training Progress:   7%| | 13/182 [04:17<56:26, 20.04s/it, Train Acc=87.64%, ValTraining: Epoch[014/182] Iteration[050/352] Loss: 0.3115 Acc:89.39%
Training: Epoch[014/182] Iteration[100/352] Loss: 0.3311 Acc:88.48%
Training: Epoch[014/182] Iteration[150/352] Loss: 0.3306 Acc:88.54%
Training: Epoch[014/182] Iteration[200/352] Loss: 0.3310 Acc:88.59%
Training: Epoch[014/182] Iteration[250/352] Loss: 0.3380 Acc:88.24%
Training: Epoch[014/182] Iteration[300/352] Loss: 0.3372 Acc:88.32%
Training: Epoch[014/182] Iteration[350/352] Loss: 0.3391 Acc:88.25%
Training Progress:   7%| | 13/182 [04:38<56:26, 20.04s/it, Train Acc=88.24%, ValEpoch[014/182] Train Acc: 88.24% Valid Acc:82.86% Train loss:0.3394 Valid loss:0.5597 LR:0.1
Training Progress:   8%| | 14/182 [04:38<56:29, 20.18s/it, Train Acc=88.24%, ValTraining: Epoch[015/182] Iteration[050/352] Loss: 0.3243 Acc:88.48%
Training: Epoch[015/182] Iteration[100/352] Loss: 0.3286 Acc:88.38%
Training: Epoch[015/182] Iteration[150/352] Loss: 0.3279 Acc:88.36%
Training: Epoch[015/182] Iteration[200/352] Loss: 0.3298 Acc:88.45%
Training: Epoch[015/182] Iteration[250/352] Loss: 0.3310 Acc:88.36%
Training: Epoch[015/182] Iteration[300/352] Loss: 0.3311 Acc:88.41%
Training: Epoch[015/182] Iteration[350/352] Loss: 0.3283 Acc:88.54%
Training Progress:   8%| | 14/182 [04:58<56:29, 20.18s/it, Train Acc=88.54%, ValEpoch[015/182] Train Acc: 88.54% Valid Acc:82.94% Train loss:0.3281 Valid loss:0.5383 LR:0.1
Training Progress:   8%| | 15/182 [04:58<56:27, 20.29s/it, Train Acc=88.54%, ValTraining: Epoch[016/182] Iteration[050/352] Loss: 0.2762 Acc:90.34%
Training: Epoch[016/182] Iteration[100/352] Loss: 0.2890 Acc:89.93%
Training: Epoch[016/182] Iteration[150/352] Loss: 0.3036 Acc:89.41%
Training: Epoch[016/182] Iteration[200/352] Loss: 0.3051 Acc:89.38%
Training: Epoch[016/182] Iteration[250/352] Loss: 0.3069 Acc:89.34%
Training: Epoch[016/182] Iteration[300/352] Loss: 0.3102 Acc:89.19%
Training: Epoch[016/182] Iteration[350/352] Loss: 0.3135 Acc:89.09%
Training Progress:   8%| | 15/182 [05:19<56:27, 20.29s/it, Train Acc=89.10%, ValEpoch[016/182] Train Acc: 89.10% Valid Acc:85.70% Train loss:0.3134 Valid loss:0.4357 LR:0.1
Training Progress:   9%| | 16/182 [05:19<56:01, 20.25s/it, Train Acc=89.10%, ValTraining: Epoch[017/182] Iteration[050/352] Loss: 0.2818 Acc:90.38%
Training: Epoch[017/182] Iteration[100/352] Loss: 0.2864 Acc:90.16%
Training: Epoch[017/182] Iteration[150/352] Loss: 0.2864 Acc:90.17%
Training: Epoch[017/182] Iteration[200/352] Loss: 0.2883 Acc:90.11%
Training: Epoch[017/182] Iteration[250/352] Loss: 0.2908 Acc:89.95%
Training: Epoch[017/182] Iteration[300/352] Loss: 0.2944 Acc:89.76%
Training: Epoch[017/182] Iteration[350/352] Loss: 0.2988 Acc:89.60%
Training Progress:   9%| | 16/182 [05:39<56:01, 20.25s/it, Train Acc=89.61%, ValEpoch[017/182] Train Acc: 89.61% Valid Acc:86.60% Train loss:0.2988 Valid loss:0.4112 LR:0.1
Training Progress:   9%| | 17/182 [05:39<55:39, 20.24s/it, Train Acc=89.61%, ValTraining: Epoch[018/182] Iteration[050/352] Loss: 0.2792 Acc:90.47%
Training: Epoch[018/182] Iteration[100/352] Loss: 0.2795 Acc:90.10%
Training: Epoch[018/182] Iteration[150/352] Loss: 0.2823 Acc:90.03%
Training: Epoch[018/182] Iteration[200/352] Loss: 0.2864 Acc:89.86%
Training: Epoch[018/182] Iteration[250/352] Loss: 0.2893 Acc:89.82%
Training: Epoch[018/182] Iteration[300/352] Loss: 0.2890 Acc:89.88%
Training: Epoch[018/182] Iteration[350/352] Loss: 0.2883 Acc:89.90%
Training Progress:   9%| | 17/182 [05:59<55:39, 20.24s/it, Train Acc=89.90%, ValEpoch[018/182] Train Acc: 89.90% Valid Acc:85.08% Train loss:0.2883 Valid loss:0.4461 LR:0.1
Training Progress:  10%| | 18/182 [05:59<55:17, 20.23s/it, Train Acc=89.90%, ValTraining: Epoch[019/182] Iteration[050/352] Loss: 0.2676 Acc:90.44%
Training: Epoch[019/182] Iteration[100/352] Loss: 0.2680 Acc:90.29%
Training: Epoch[019/182] Iteration[150/352] Loss: 0.2708 Acc:90.38%
Training: Epoch[019/182] Iteration[200/352] Loss: 0.2749 Acc:90.18%
Training: Epoch[019/182] Iteration[250/352] Loss: 0.2823 Acc:90.01%
Training: Epoch[019/182] Iteration[300/352] Loss: 0.2810 Acc:90.08%
Training: Epoch[019/182] Iteration[350/352] Loss: 0.2828 Acc:90.04%
Training Progress:  10%| | 18/182 [06:19<55:17, 20.23s/it, Train Acc=90.05%, ValEpoch[019/182] Train Acc: 90.05% Valid Acc:86.96% Train loss:0.2824 Valid loss:0.4176 LR:0.1
Training Progress:  10%| | 19/182 [06:19<54:56, 20.23s/it, Train Acc=90.05%, ValTraining: Epoch[020/182] Iteration[050/352] Loss: 0.2426 Acc:91.19%
Training: Epoch[020/182] Iteration[100/352] Loss: 0.2571 Acc:90.99%
Training: Epoch[020/182] Iteration[150/352] Loss: 0.2582 Acc:90.98%
Training: Epoch[020/182] Iteration[200/352] Loss: 0.2624 Acc:90.88%
Training: Epoch[020/182] Iteration[250/352] Loss: 0.2683 Acc:90.71%
Training: Epoch[020/182] Iteration[300/352] Loss: 0.2698 Acc:90.70%
Training: Epoch[020/182] Iteration[350/352] Loss: 0.2691 Acc:90.72%
Training Progress:  10%| | 19/182 [06:39<54:56, 20.23s/it, Train Acc=90.72%, ValEpoch[020/182] Train Acc: 90.72% Valid Acc:86.48% Train loss:0.2692 Valid loss:0.4438 LR:0.1
Training Progress:  11%| | 20/182 [06:39<54:34, 20.21s/it, Train Acc=90.72%, ValTraining: Epoch[021/182] Iteration[050/352] Loss: 0.2460 Acc:91.55%
Training: Epoch[021/182] Iteration[100/352] Loss: 0.2397 Acc:91.76%
Training: Epoch[021/182] Iteration[150/352] Loss: 0.2476 Acc:91.53%
Training: Epoch[021/182] Iteration[200/352] Loss: 0.2565 Acc:91.21%
Training: Epoch[021/182] Iteration[250/352] Loss: 0.2623 Acc:91.00%
Training: Epoch[021/182] Iteration[300/352] Loss: 0.2628 Acc:90.91%
Training: Epoch[021/182] Iteration[350/352] Loss: 0.2651 Acc:90.82%
Training Progress:  11%| | 20/182 [07:00<54:34, 20.21s/it, Train Acc=90.83%, ValEpoch[021/182] Train Acc: 90.83% Valid Acc:85.28% Train loss:0.2650 Valid loss:0.4729 LR:0.1
Training Progress:  12%| | 21/182 [07:00<54:14, 20.21s/it, Train Acc=90.83%, ValTraining: Epoch[022/182] Iteration[050/352] Loss: 0.2299 Acc:92.52%
Training: Epoch[022/182] Iteration[100/352] Loss: 0.2465 Acc:91.72%
Training: Epoch[022/182] Iteration[150/352] Loss: 0.2457 Acc:91.75%
Training: Epoch[022/182] Iteration[200/352] Loss: 0.2494 Acc:91.41%
Training: Epoch[022/182] Iteration[250/352] Loss: 0.2536 Acc:91.29%
Training: Epoch[022/182] Iteration[300/352] Loss: 0.2520 Acc:91.34%
Training: Epoch[022/182] Iteration[350/352] Loss: 0.2531 Acc:91.31%
Training Progress:  12%| | 21/182 [07:20<54:14, 20.21s/it, Train Acc=91.31%, ValEpoch[022/182] Train Acc: 91.31% Valid Acc:81.06% Train loss:0.2531 Valid loss:0.6273 LR:0.1
Training Progress:  12%| | 22/182 [07:20<54:12, 20.33s/it, Train Acc=91.31%, ValTraining: Epoch[023/182] Iteration[050/352] Loss: 0.2465 Acc:91.17%
Training: Epoch[023/182] Iteration[100/352] Loss: 0.2519 Acc:91.16%
Training: Epoch[023/182] Iteration[150/352] Loss: 0.2484 Acc:91.32%
Training: Epoch[023/182] Iteration[200/352] Loss: 0.2447 Acc:91.45%
Training: Epoch[023/182] Iteration[250/352] Loss: 0.2470 Acc:91.39%
Training: Epoch[023/182] Iteration[300/352] Loss: 0.2479 Acc:91.40%
Training: Epoch[023/182] Iteration[350/352] Loss: 0.2491 Acc:91.35%
Training Progress:  12%| | 22/182 [07:40<54:12, 20.33s/it, Train Acc=91.36%, ValEpoch[023/182] Train Acc: 91.36% Valid Acc:83.68% Train loss:0.2489 Valid loss:0.5406 LR:0.1
Training Progress:  13%|▏| 23/182 [07:40<53:47, 20.30s/it, Train Acc=91.36%, ValTraining: Epoch[024/182] Iteration[050/352] Loss: 0.2290 Acc:91.66%
Training: Epoch[024/182] Iteration[100/352] Loss: 0.2292 Acc:91.93%
Training: Epoch[024/182] Iteration[150/352] Loss: 0.2343 Acc:91.77%
Training: Epoch[024/182] Iteration[200/352] Loss: 0.2347 Acc:91.77%
Training: Epoch[024/182] Iteration[250/352] Loss: 0.2412 Acc:91.52%
Training: Epoch[024/182] Iteration[300/352] Loss: 0.2434 Acc:91.45%
Training: Epoch[024/182] Iteration[350/352] Loss: 0.2448 Acc:91.36%
Training Progress:  13%|▏| 23/182 [08:01<53:47, 20.30s/it, Train Acc=91.34%, ValEpoch[024/182] Train Acc: 91.34% Valid Acc:84.74% Train loss:0.2456 Valid loss:0.5209 LR:0.1
Training Progress:  13%|▏| 24/182 [08:01<53:33, 20.34s/it, Train Acc=91.34%, ValTraining: Epoch[025/182] Iteration[050/352] Loss: 0.2369 Acc:91.83%
Training: Epoch[025/182] Iteration[100/352] Loss: 0.2282 Acc:92.11%
Training: Epoch[025/182] Iteration[150/352] Loss: 0.2290 Acc:92.12%
Training: Epoch[025/182] Iteration[200/352] Loss: 0.2338 Acc:91.85%
Training: Epoch[025/182] Iteration[250/352] Loss: 0.2354 Acc:91.87%
Training: Epoch[025/182] Iteration[300/352] Loss: 0.2360 Acc:91.81%
Training: Epoch[025/182] Iteration[350/352] Loss: 0.2366 Acc:91.81%
Training Progress:  13%|▏| 24/182 [08:21<53:33, 20.34s/it, Train Acc=91.81%, ValEpoch[025/182] Train Acc: 91.81% Valid Acc:85.54% Train loss:0.2368 Valid loss:0.4760 LR:0.1
Training Progress:  14%|▏| 25/182 [08:21<53:08, 20.31s/it, Train Acc=91.81%, ValTraining: Epoch[026/182] Iteration[050/352] Loss: 0.2279 Acc:91.89%
Training: Epoch[026/182] Iteration[100/352] Loss: 0.2330 Acc:91.73%
Training: Epoch[026/182] Iteration[150/352] Loss: 0.2338 Acc:91.86%
Training: Epoch[026/182] Iteration[200/352] Loss: 0.2288 Acc:92.03%
Training: Epoch[026/182] Iteration[250/352] Loss: 0.2286 Acc:92.04%
Training: Epoch[026/182] Iteration[300/352] Loss: 0.2308 Acc:91.98%
Training: Epoch[026/182] Iteration[350/352] Loss: 0.2305 Acc:91.98%
Training Progress:  14%|▏| 25/182 [08:41<53:08, 20.31s/it, Train Acc=91.99%, ValEpoch[026/182] Train Acc: 91.99% Valid Acc:85.32% Train loss:0.2302 Valid loss:0.5284 LR:0.1
Training Progress:  14%|▏| 26/182 [08:41<52:43, 20.28s/it, Train Acc=91.99%, ValTraining: Epoch[027/182] Iteration[050/352] Loss: 0.2087 Acc:92.91%
Training: Epoch[027/182] Iteration[100/352] Loss: 0.2089 Acc:92.65%
Training: Epoch[027/182] Iteration[150/352] Loss: 0.2155 Acc:92.47%
Training: Epoch[027/182] Iteration[200/352] Loss: 0.2232 Acc:92.20%
Training: Epoch[027/182] Iteration[250/352] Loss: 0.2244 Acc:92.15%
Training: Epoch[027/182] Iteration[300/352] Loss: 0.2262 Acc:92.11%
Training: Epoch[027/182] Iteration[350/352] Loss: 0.2274 Acc:92.09%
Training Progress:  14%|▏| 26/182 [09:02<52:43, 20.28s/it, Train Acc=92.10%, ValEpoch[027/182] Train Acc: 92.10% Valid Acc:85.90% Train loss:0.2276 Valid loss:0.4682 LR:0.1
Training Progress:  15%|▏| 27/182 [09:02<52:23, 20.28s/it, Train Acc=92.10%, ValTraining: Epoch[028/182] Iteration[050/352] Loss: 0.2205 Acc:92.36%
Training: Epoch[028/182] Iteration[100/352] Loss: 0.2183 Acc:92.52%
Training: Epoch[028/182] Iteration[150/352] Loss: 0.2201 Acc:92.54%
Training: Epoch[028/182] Iteration[200/352] Loss: 0.2205 Acc:92.48%
Training: Epoch[028/182] Iteration[250/352] Loss: 0.2195 Acc:92.46%
Training: Epoch[028/182] Iteration[300/352] Loss: 0.2181 Acc:92.47%
Training: Epoch[028/182] Iteration[350/352] Loss: 0.2192 Acc:92.42%
Training Progress:  15%|▏| 27/182 [09:22<52:23, 20.28s/it, Train Acc=92.43%, ValEpoch[028/182] Train Acc: 92.43% Valid Acc:85.68% Train loss:0.2189 Valid loss:0.4656 LR:0.1
Training Progress:  15%|▏| 28/182 [09:22<52:02, 20.28s/it, Train Acc=92.43%, ValTraining: Epoch[029/182] Iteration[050/352] Loss: 0.2015 Acc:92.89%
Training: Epoch[029/182] Iteration[100/352] Loss: 0.2139 Acc:92.59%
Training: Epoch[029/182] Iteration[150/352] Loss: 0.2098 Acc:92.67%
Training: Epoch[029/182] Iteration[200/352] Loss: 0.2120 Acc:92.56%
Training: Epoch[029/182] Iteration[250/352] Loss: 0.2152 Acc:92.41%
Training: Epoch[029/182] Iteration[300/352] Loss: 0.2171 Acc:92.34%
Training: Epoch[029/182] Iteration[350/352] Loss: 0.2158 Acc:92.40%
Training Progress:  15%|▏| 28/182 [09:42<52:02, 20.28s/it, Train Acc=92.38%, ValEpoch[029/182] Train Acc: 92.38% Valid Acc:86.78% Train loss:0.2163 Valid loss:0.4449 LR:0.1
Training Progress:  16%|▏| 29/182 [09:42<51:44, 20.29s/it, Train Acc=92.38%, ValTraining: Epoch[030/182] Iteration[050/352] Loss: 0.2318 Acc:91.72%
Training: Epoch[030/182] Iteration[100/352] Loss: 0.2232 Acc:91.90%
Training: Epoch[030/182] Iteration[150/352] Loss: 0.2155 Acc:92.23%
Training: Epoch[030/182] Iteration[200/352] Loss: 0.2155 Acc:92.37%
Training: Epoch[030/182] Iteration[250/352] Loss: 0.2164 Acc:92.33%
Training: Epoch[030/182] Iteration[300/352] Loss: 0.2155 Acc:92.38%
Training: Epoch[030/182] Iteration[350/352] Loss: 0.2175 Acc:92.27%
Training Progress:  16%|▏| 29/182 [10:03<51:44, 20.29s/it, Train Acc=92.27%, ValEpoch[030/182] Train Acc: 92.27% Valid Acc:87.48% Train loss:0.2177 Valid loss:0.3903 LR:0.1
Training Progress:  16%|▏| 30/182 [10:03<51:28, 20.32s/it, Train Acc=92.27%, ValTraining: Epoch[031/182] Iteration[050/352] Loss: 0.2155 Acc:92.14%
Training: Epoch[031/182] Iteration[100/352] Loss: 0.1999 Acc:92.79%
Training: Epoch[031/182] Iteration[150/352] Loss: 0.2070 Acc:92.61%
Training: Epoch[031/182] Iteration[200/352] Loss: 0.2080 Acc:92.62%
Training: Epoch[031/182] Iteration[250/352] Loss: 0.2097 Acc:92.52%
Training: Epoch[031/182] Iteration[300/352] Loss: 0.2107 Acc:92.55%
Training: Epoch[031/182] Iteration[350/352] Loss: 0.2126 Acc:92.49%
Training Progress:  16%|▏| 30/182 [10:23<51:28, 20.32s/it, Train Acc=92.47%, ValEpoch[031/182] Train Acc: 92.47% Valid Acc:87.56% Train loss:0.2129 Valid loss:0.3948 LR:0.1
Training Progress:  17%|▏| 31/182 [10:23<51:13, 20.35s/it, Train Acc=92.47%, ValTraining: Epoch[032/182] Iteration[050/352] Loss: 0.1886 Acc:93.44%
Training: Epoch[032/182] Iteration[100/352] Loss: 0.1955 Acc:93.15%
Training: Epoch[032/182] Iteration[150/352] Loss: 0.1967 Acc:93.01%
Training: Epoch[032/182] Iteration[200/352] Loss: 0.1955 Acc:93.07%
Training: Epoch[032/182] Iteration[250/352] Loss: 0.2009 Acc:92.83%
Training: Epoch[032/182] Iteration[300/352] Loss: 0.2020 Acc:92.83%
Training: Epoch[032/182] Iteration[350/352] Loss: 0.2040 Acc:92.73%
Training Progress:  17%|▏| 31/182 [10:43<51:13, 20.35s/it, Train Acc=92.73%, ValEpoch[032/182] Train Acc: 92.73% Valid Acc:85.60% Train loss:0.2039 Valid loss:0.5197 LR:0.1
Training Progress:  18%|▏| 32/182 [10:43<50:50, 20.33s/it, Train Acc=92.73%, ValTraining: Epoch[033/182] Iteration[050/352] Loss: 0.1833 Acc:93.33%
Training: Epoch[033/182] Iteration[100/352] Loss: 0.1829 Acc:93.30%
Training: Epoch[033/182] Iteration[150/352] Loss: 0.1904 Acc:93.11%
Training: Epoch[033/182] Iteration[200/352] Loss: 0.1943 Acc:93.07%
Training: Epoch[033/182] Iteration[250/352] Loss: 0.1939 Acc:93.09%
Training: Epoch[033/182] Iteration[300/352] Loss: 0.1947 Acc:93.08%
Training: Epoch[033/182] Iteration[350/352] Loss: 0.1991 Acc:92.91%
Training Progress:  18%|▏| 32/182 [11:04<50:50, 20.33s/it, Train Acc=92.91%, ValEpoch[033/182] Train Acc: 92.91% Valid Acc:88.44% Train loss:0.1991 Valid loss:0.3688 LR:0.1
Training Progress:  18%|▏| 33/182 [11:04<50:26, 20.31s/it, Train Acc=92.91%, ValTraining: Epoch[034/182] Iteration[050/352] Loss: 0.1902 Acc:93.14%
Training: Epoch[034/182] Iteration[100/352] Loss: 0.1946 Acc:93.17%
Training: Epoch[034/182] Iteration[150/352] Loss: 0.1897 Acc:93.31%
Training: Epoch[034/182] Iteration[200/352] Loss: 0.1918 Acc:93.29%
Training: Epoch[034/182] Iteration[250/352] Loss: 0.1927 Acc:93.23%
Training: Epoch[034/182] Iteration[300/352] Loss: 0.1928 Acc:93.23%
Training: Epoch[034/182] Iteration[350/352] Loss: 0.1948 Acc:93.14%
Training Progress:  18%|▏| 33/182 [11:24<50:26, 20.31s/it, Train Acc=93.13%, ValEpoch[034/182] Train Acc: 93.13% Valid Acc:83.48% Train loss:0.1951 Valid loss:0.5642 LR:0.1
Training Progress:  19%|▏| 34/182 [11:24<50:06, 20.31s/it, Train Acc=93.13%, ValTraining: Epoch[035/182] Iteration[050/352] Loss: 0.1823 Acc:93.41%
Training: Epoch[035/182] Iteration[100/352] Loss: 0.1845 Acc:93.55%
Training: Epoch[035/182] Iteration[150/352] Loss: 0.1872 Acc:93.52%
Training: Epoch[035/182] Iteration[200/352] Loss: 0.1907 Acc:93.37%
Training: Epoch[035/182] Iteration[250/352] Loss: 0.1919 Acc:93.36%
Training: Epoch[035/182] Iteration[300/352] Loss: 0.1910 Acc:93.33%
Training: Epoch[035/182] Iteration[350/352] Loss: 0.1911 Acc:93.31%
Training Progress:  19%|▏| 34/182 [11:44<50:06, 20.31s/it, Train Acc=93.31%, ValEpoch[035/182] Train Acc: 93.31% Valid Acc:86.66% Train loss:0.1914 Valid loss:0.4765 LR:0.1
Training Progress:  19%|▏| 35/182 [11:44<49:49, 20.34s/it, Train Acc=93.31%, ValTraining: Epoch[036/182] Iteration[050/352] Loss: 0.1781 Acc:93.81%
Training: Epoch[036/182] Iteration[100/352] Loss: 0.1836 Acc:93.46%
Training: Epoch[036/182] Iteration[150/352] Loss: 0.1903 Acc:93.19%
Training: Epoch[036/182] Iteration[200/352] Loss: 0.1890 Acc:93.24%
Training: Epoch[036/182] Iteration[250/352] Loss: 0.1899 Acc:93.23%
Training: Epoch[036/182] Iteration[300/352] Loss: 0.1920 Acc:93.16%
Training: Epoch[036/182] Iteration[350/352] Loss: 0.1939 Acc:93.12%
Training Progress:  19%|▏| 35/182 [12:05<49:49, 20.34s/it, Train Acc=93.10%, ValEpoch[036/182] Train Acc: 93.10% Valid Acc:87.16% Train loss:0.1943 Valid loss:0.4145 LR:0.1
Training Progress:  20%|▏| 36/182 [12:05<49:28, 20.33s/it, Train Acc=93.10%, ValTraining: Epoch[037/182] Iteration[050/352] Loss: 0.1799 Acc:93.25%
Training: Epoch[037/182] Iteration[100/352] Loss: 0.1830 Acc:93.29%
Training: Epoch[037/182] Iteration[150/352] Loss: 0.1826 Acc:93.38%
Training: Epoch[037/182] Iteration[200/352] Loss: 0.1864 Acc:93.18%
Training: Epoch[037/182] Iteration[250/352] Loss: 0.1916 Acc:93.08%
Training: Epoch[037/182] Iteration[300/352] Loss: 0.1953 Acc:93.01%
Training: Epoch[037/182] Iteration[350/352] Loss: 0.1946 Acc:93.06%
Training Progress:  20%|▏| 36/182 [12:25<49:28, 20.33s/it, Train Acc=93.06%, ValEpoch[037/182] Train Acc: 93.06% Valid Acc:88.90% Train loss:0.1943 Valid loss:0.3737 LR:0.1
Training Progress:  20%|▏| 37/182 [12:25<49:11, 20.36s/it, Train Acc=93.06%, ValTraining: Epoch[038/182] Iteration[050/352] Loss: 0.1696 Acc:94.05%
Training: Epoch[038/182] Iteration[100/352] Loss: 0.1686 Acc:93.99%
Training: Epoch[038/182] Iteration[150/352] Loss: 0.1702 Acc:93.95%
Training: Epoch[038/182] Iteration[200/352] Loss: 0.1734 Acc:93.86%
Training: Epoch[038/182] Iteration[250/352] Loss: 0.1759 Acc:93.80%
Training: Epoch[038/182] Iteration[300/352] Loss: 0.1802 Acc:93.66%
Training: Epoch[038/182] Iteration[350/352] Loss: 0.1844 Acc:93.48%
Training Progress:  20%|▏| 37/182 [12:45<49:11, 20.36s/it, Train Acc=93.47%, ValEpoch[038/182] Train Acc: 93.47% Valid Acc:87.56% Train loss:0.1845 Valid loss:0.3995 LR:0.1
Training Progress:  21%|▏| 38/182 [12:45<48:53, 20.37s/it, Train Acc=93.47%, ValTraining: Epoch[039/182] Iteration[050/352] Loss: 0.1783 Acc:93.67%
Training: Epoch[039/182] Iteration[100/352] Loss: 0.1828 Acc:93.60%
Training: Epoch[039/182] Iteration[150/352] Loss: 0.1798 Acc:93.73%
Training: Epoch[039/182] Iteration[200/352] Loss: 0.1827 Acc:93.69%
Training: Epoch[039/182] Iteration[250/352] Loss: 0.1813 Acc:93.73%
Training: Epoch[039/182] Iteration[300/352] Loss: 0.1852 Acc:93.56%
Training: Epoch[039/182] Iteration[350/352] Loss: 0.1850 Acc:93.57%
Training Progress:  21%|▏| 38/182 [13:06<48:53, 20.37s/it, Train Acc=93.55%, ValEpoch[039/182] Train Acc: 93.55% Valid Acc:86.22% Train loss:0.1855 Valid loss:0.5033 LR:0.1
Training Progress:  21%|▏| 39/182 [13:06<48:27, 20.33s/it, Train Acc=93.55%, ValTraining: Epoch[040/182] Iteration[050/352] Loss: 0.1681 Acc:94.03%
Training: Epoch[040/182] Iteration[100/352] Loss: 0.1757 Acc:93.80%
Training: Epoch[040/182] Iteration[150/352] Loss: 0.1754 Acc:93.83%
Training: Epoch[040/182] Iteration[200/352] Loss: 0.1781 Acc:93.76%
Training: Epoch[040/182] Iteration[250/352] Loss: 0.1785 Acc:93.78%
Training: Epoch[040/182] Iteration[300/352] Loss: 0.1780 Acc:93.83%
Training: Epoch[040/182] Iteration[350/352] Loss: 0.1781 Acc:93.81%
Training Progress:  21%|▏| 39/182 [13:26<48:27, 20.33s/it, Train Acc=93.81%, ValEpoch[040/182] Train Acc: 93.81% Valid Acc:85.68% Train loss:0.1784 Valid loss:0.5185 LR:0.1
Training Progress:  22%|▏| 40/182 [13:26<48:09, 20.35s/it, Train Acc=93.81%, ValTraining: Epoch[041/182] Iteration[050/352] Loss: 0.1737 Acc:93.80%
Training: Epoch[041/182] Iteration[100/352] Loss: 0.1738 Acc:93.80%
Training: Epoch[041/182] Iteration[150/352] Loss: 0.1728 Acc:93.79%
Training: Epoch[041/182] Iteration[200/352] Loss: 0.1722 Acc:93.80%
Training: Epoch[041/182] Iteration[250/352] Loss: 0.1774 Acc:93.66%
Training: Epoch[041/182] Iteration[300/352] Loss: 0.1786 Acc:93.63%
Training: Epoch[041/182] Iteration[350/352] Loss: 0.1791 Acc:93.62%
Training Progress:  22%|▏| 40/182 [13:46<48:09, 20.35s/it, Train Acc=93.62%, ValEpoch[041/182] Train Acc: 93.62% Valid Acc:87.48% Train loss:0.1794 Valid loss:0.4206 LR:0.1
Training Progress:  23%|▏| 41/182 [13:46<47:48, 20.34s/it, Train Acc=93.62%, ValTraining: Epoch[042/182] Iteration[050/352] Loss: 0.1698 Acc:94.03%
Training: Epoch[042/182] Iteration[100/352] Loss: 0.1655 Acc:94.09%
Training: Epoch[042/182] Iteration[150/352] Loss: 0.1724 Acc:93.85%
Training: Epoch[042/182] Iteration[200/352] Loss: 0.1722 Acc:93.87%
Training: Epoch[042/182] Iteration[250/352] Loss: 0.1731 Acc:93.93%
Training: Epoch[042/182] Iteration[300/352] Loss: 0.1756 Acc:93.83%
Training: Epoch[042/182] Iteration[350/352] Loss: 0.1764 Acc:93.78%
Training Progress:  23%|▏| 41/182 [14:07<47:48, 20.34s/it, Train Acc=93.79%, ValEpoch[042/182] Train Acc: 93.79% Valid Acc:88.14% Train loss:0.1761 Valid loss:0.3870 LR:0.1
Training Progress:  23%|▏| 42/182 [14:07<47:27, 20.34s/it, Train Acc=93.79%, ValTraining: Epoch[043/182] Iteration[050/352] Loss: 0.1650 Acc:94.38%
Training: Epoch[043/182] Iteration[100/352] Loss: 0.1713 Acc:94.09%
Training: Epoch[043/182] Iteration[150/352] Loss: 0.1744 Acc:93.99%
Training: Epoch[043/182] Iteration[200/352] Loss: 0.1739 Acc:93.98%
Training: Epoch[043/182] Iteration[250/352] Loss: 0.1750 Acc:93.90%
Training: Epoch[043/182] Iteration[300/352] Loss: 0.1800 Acc:93.71%
Training: Epoch[043/182] Iteration[350/352] Loss: 0.1819 Acc:93.65%
Training Progress:  23%|▏| 42/182 [14:27<47:27, 20.34s/it, Train Acc=93.66%, ValEpoch[043/182] Train Acc: 93.66% Valid Acc:88.16% Train loss:0.1819 Valid loss:0.3986 LR:0.1
Training Progress:  24%|▏| 43/182 [14:27<47:07, 20.34s/it, Train Acc=93.66%, ValTraining: Epoch[044/182] Iteration[050/352] Loss: 0.1437 Acc:94.92%
Training: Epoch[044/182] Iteration[100/352] Loss: 0.1502 Acc:94.73%
Training: Epoch[044/182] Iteration[150/352] Loss: 0.1574 Acc:94.51%
Training: Epoch[044/182] Iteration[200/352] Loss: 0.1659 Acc:94.16%
Training: Epoch[044/182] Iteration[250/352] Loss: 0.1706 Acc:93.96%
Training: Epoch[044/182] Iteration[300/352] Loss: 0.1758 Acc:93.78%
Training: Epoch[044/182] Iteration[350/352] Loss: 0.1784 Acc:93.74%
Training Progress:  24%|▏| 43/182 [14:47<47:07, 20.34s/it, Train Acc=93.74%, ValEpoch[044/182] Train Acc: 93.74% Valid Acc:86.04% Train loss:0.1783 Valid loss:0.4847 LR:0.1
Training Progress:  24%|▏| 44/182 [14:47<46:46, 20.33s/it, Train Acc=93.74%, ValTraining: Epoch[045/182] Iteration[050/352] Loss: 0.1585 Acc:94.47%
Training: Epoch[045/182] Iteration[100/352] Loss: 0.1613 Acc:94.22%
Training: Epoch[045/182] Iteration[150/352] Loss: 0.1633 Acc:94.09%
Training: Epoch[045/182] Iteration[200/352] Loss: 0.1685 Acc:93.92%
Training: Epoch[045/182] Iteration[250/352] Loss: 0.1715 Acc:93.86%
Training: Epoch[045/182] Iteration[300/352] Loss: 0.1740 Acc:93.77%
Training: Epoch[045/182] Iteration[350/352] Loss: 0.1725 Acc:93.82%
Training Progress:  24%|▏| 44/182 [15:08<46:46, 20.33s/it, Train Acc=93.81%, ValEpoch[045/182] Train Acc: 93.81% Valid Acc:86.36% Train loss:0.1725 Valid loss:0.5119 LR:0.1
Training Progress:  25%|▏| 45/182 [15:08<46:27, 20.35s/it, Train Acc=93.81%, ValTraining: Epoch[046/182] Iteration[050/352] Loss: 0.1492 Acc:94.78%
Training: Epoch[046/182] Iteration[100/352] Loss: 0.1590 Acc:94.27%
Training: Epoch[046/182] Iteration[150/352] Loss: 0.1637 Acc:94.07%
Training: Epoch[046/182] Iteration[200/352] Loss: 0.1623 Acc:94.23%
Training: Epoch[046/182] Iteration[250/352] Loss: 0.1648 Acc:94.12%
Training: Epoch[046/182] Iteration[300/352] Loss: 0.1675 Acc:94.05%
Training: Epoch[046/182] Iteration[350/352] Loss: 0.1712 Acc:93.92%
Training Progress:  25%|▏| 45/182 [15:28<46:27, 20.35s/it, Train Acc=93.93%, ValEpoch[046/182] Train Acc: 93.93% Valid Acc:86.84% Train loss:0.1710 Valid loss:0.4704 LR:0.1
Training Progress:  25%|▎| 46/182 [15:28<46:04, 20.33s/it, Train Acc=93.93%, ValTraining: Epoch[047/182] Iteration[050/352] Loss: 0.1405 Acc:94.94%
Training: Epoch[047/182] Iteration[100/352] Loss: 0.1497 Acc:94.73%
Training: Epoch[047/182] Iteration[150/352] Loss: 0.1529 Acc:94.64%
Training: Epoch[047/182] Iteration[200/352] Loss: 0.1542 Acc:94.58%
Training: Epoch[047/182] Iteration[250/352] Loss: 0.1566 Acc:94.43%
Training: Epoch[047/182] Iteration[300/352] Loss: 0.1586 Acc:94.40%
Training: Epoch[047/182] Iteration[350/352] Loss: 0.1645 Acc:94.22%
Training Progress:  25%|▎| 46/182 [15:48<46:04, 20.33s/it, Train Acc=94.21%, ValEpoch[047/182] Train Acc: 94.21% Valid Acc:86.52% Train loss:0.1650 Valid loss:0.4666 LR:0.1
Training Progress:  26%|▎| 47/182 [15:48<45:43, 20.32s/it, Train Acc=94.21%, ValTraining: Epoch[048/182] Iteration[050/352] Loss: 0.1608 Acc:94.28%
Training: Epoch[048/182] Iteration[100/352] Loss: 0.1569 Acc:94.51%
Training: Epoch[048/182] Iteration[150/352] Loss: 0.1586 Acc:94.51%
Training: Epoch[048/182] Iteration[200/352] Loss: 0.1614 Acc:94.39%
Training: Epoch[048/182] Iteration[250/352] Loss: 0.1616 Acc:94.33%
Training: Epoch[048/182] Iteration[300/352] Loss: 0.1677 Acc:94.18%
Training: Epoch[048/182] Iteration[350/352] Loss: 0.1691 Acc:94.10%
Training Progress:  26%|▎| 47/182 [16:09<45:43, 20.32s/it, Train Acc=94.08%, ValEpoch[048/182] Train Acc: 94.08% Valid Acc:89.12% Train loss:0.1695 Valid loss:0.3661 LR:0.1
Training Progress:  26%|▎| 48/182 [16:09<45:28, 20.36s/it, Train Acc=94.08%, ValTraining: Epoch[049/182] Iteration[050/352] Loss: 0.1456 Acc:94.81%
Training: Epoch[049/182] Iteration[100/352] Loss: 0.1526 Acc:94.62%
Training: Epoch[049/182] Iteration[150/352] Loss: 0.1571 Acc:94.53%
Training: Epoch[049/182] Iteration[200/352] Loss: 0.1626 Acc:94.34%
Training: Epoch[049/182] Iteration[250/352] Loss: 0.1636 Acc:94.22%
Training: Epoch[049/182] Iteration[300/352] Loss: 0.1672 Acc:94.10%
Training: Epoch[049/182] Iteration[350/352] Loss: 0.1672 Acc:94.08%
Training Progress:  26%|▎| 48/182 [16:29<45:28, 20.36s/it, Train Acc=94.08%, ValEpoch[049/182] Train Acc: 94.08% Valid Acc:87.90% Train loss:0.1671 Valid loss:0.4143 LR:0.1
Training Progress:  27%|▎| 49/182 [16:29<45:06, 20.35s/it, Train Acc=94.08%, ValTraining: Epoch[050/182] Iteration[050/352] Loss: 0.1462 Acc:94.72%
Training: Epoch[050/182] Iteration[100/352] Loss: 0.1439 Acc:94.80%
Training: Epoch[050/182] Iteration[150/352] Loss: 0.1495 Acc:94.65%
Training: Epoch[050/182] Iteration[200/352] Loss: 0.1581 Acc:94.42%
Training: Epoch[050/182] Iteration[250/352] Loss: 0.1631 Acc:94.22%
Training: Epoch[050/182] Iteration[300/352] Loss: 0.1657 Acc:94.13%
Training: Epoch[050/182] Iteration[350/352] Loss: 0.1660 Acc:94.12%
Training Progress:  27%|▎| 49/182 [16:49<45:06, 20.35s/it, Train Acc=94.12%, ValEpoch[050/182] Train Acc: 94.12% Valid Acc:87.02% Train loss:0.1658 Valid loss:0.4735 LR:0.1
Training Progress:  27%|▎| 50/182 [16:49<44:46, 20.35s/it, Train Acc=94.12%, ValTraining: Epoch[051/182] Iteration[050/352] Loss: 0.1435 Acc:95.09%
Training: Epoch[051/182] Iteration[100/352] Loss: 0.1471 Acc:94.97%
Training: Epoch[051/182] Iteration[150/352] Loss: 0.1449 Acc:94.95%
Training: Epoch[051/182] Iteration[200/352] Loss: 0.1485 Acc:94.82%
Training: Epoch[051/182] Iteration[250/352] Loss: 0.1502 Acc:94.74%
Training: Epoch[051/182] Iteration[300/352] Loss: 0.1533 Acc:94.62%
Training: Epoch[051/182] Iteration[350/352] Loss: 0.1562 Acc:94.48%
Training Progress:  27%|▎| 50/182 [17:10<44:46, 20.35s/it, Train Acc=94.48%, ValEpoch[051/182] Train Acc: 94.48% Valid Acc:88.60% Train loss:0.1559 Valid loss:0.4045 LR:0.1
Training Progress:  28%|▎| 51/182 [17:10<44:23, 20.33s/it, Train Acc=94.48%, ValTraining: Epoch[052/182] Iteration[050/352] Loss: 0.1443 Acc:95.09%
Training: Epoch[052/182] Iteration[100/352] Loss: 0.1515 Acc:94.66%
Training: Epoch[052/182] Iteration[150/352] Loss: 0.1617 Acc:94.34%
Training: Epoch[052/182] Iteration[200/352] Loss: 0.1609 Acc:94.37%
Training: Epoch[052/182] Iteration[250/352] Loss: 0.1557 Acc:94.60%
Training: Epoch[052/182] Iteration[300/352] Loss: 0.1574 Acc:94.54%
Training: Epoch[052/182] Iteration[350/352] Loss: 0.1596 Acc:94.47%
Training Progress:  28%|▎| 51/182 [17:30<44:23, 20.33s/it, Train Acc=94.47%, ValEpoch[052/182] Train Acc: 94.47% Valid Acc:88.32% Train loss:0.1594 Valid loss:0.4044 LR:0.1
Training Progress:  29%|▎| 52/182 [17:30<44:06, 20.36s/it, Train Acc=94.47%, ValTraining: Epoch[053/182] Iteration[050/352] Loss: 0.1307 Acc:95.23%
Training: Epoch[053/182] Iteration[100/352] Loss: 0.1354 Acc:95.10%
Training: Epoch[053/182] Iteration[150/352] Loss: 0.1413 Acc:95.03%
Training: Epoch[053/182] Iteration[200/352] Loss: 0.1418 Acc:94.98%
Training: Epoch[053/182] Iteration[250/352] Loss: 0.1444 Acc:94.91%
Training: Epoch[053/182] Iteration[300/352] Loss: 0.1527 Acc:94.60%
Training: Epoch[053/182] Iteration[350/352] Loss: 0.1558 Acc:94.50%
Training Progress:  29%|▎| 52/182 [17:51<44:06, 20.36s/it, Train Acc=94.50%, ValEpoch[053/182] Train Acc: 94.50% Valid Acc:86.44% Train loss:0.1559 Valid loss:0.4614 LR:0.1
Training Progress:  29%|▎| 53/182 [17:51<43:49, 20.38s/it, Train Acc=94.50%, ValTraining: Epoch[054/182] Iteration[050/352] Loss: 0.1456 Acc:94.95%
Training: Epoch[054/182] Iteration[100/352] Loss: 0.1535 Acc:94.62%
Training: Epoch[054/182] Iteration[150/352] Loss: 0.1559 Acc:94.48%
Training: Epoch[054/182] Iteration[200/352] Loss: 0.1608 Acc:94.28%
Training: Epoch[054/182] Iteration[250/352] Loss: 0.1597 Acc:94.38%
Training: Epoch[054/182] Iteration[300/352] Loss: 0.1602 Acc:94.36%
Training: Epoch[054/182] Iteration[350/352] Loss: 0.1612 Acc:94.28%
Training Progress:  29%|▎| 53/182 [18:11<43:49, 20.38s/it, Train Acc=94.29%, ValEpoch[054/182] Train Acc: 94.29% Valid Acc:88.88% Train loss:0.1608 Valid loss:0.3945 LR:0.1
Training Progress:  30%|▎| 54/182 [18:11<43:29, 20.39s/it, Train Acc=94.29%, ValTraining: Epoch[055/182] Iteration[050/352] Loss: 0.1323 Acc:95.27%
Training: Epoch[055/182] Iteration[100/352] Loss: 0.1391 Acc:95.11%
Training: Epoch[055/182] Iteration[150/352] Loss: 0.1449 Acc:94.86%
Training: Epoch[055/182] Iteration[200/352] Loss: 0.1544 Acc:94.59%
Training: Epoch[055/182] Iteration[250/352] Loss: 0.1538 Acc:94.62%
Training: Epoch[055/182] Iteration[300/352] Loss: 0.1551 Acc:94.58%
Training: Epoch[055/182] Iteration[350/352] Loss: 0.1589 Acc:94.40%
Training Progress:  30%|▎| 54/182 [18:32<43:29, 20.39s/it, Train Acc=94.39%, ValEpoch[055/182] Train Acc: 94.39% Valid Acc:87.30% Train loss:0.1591 Valid loss:0.4736 LR:0.1
Training Progress:  30%|▎| 55/182 [18:32<43:17, 20.45s/it, Train Acc=94.39%, ValTraining: Epoch[056/182] Iteration[050/352] Loss: 0.1365 Acc:95.05%
Training: Epoch[056/182] Iteration[100/352] Loss: 0.1354 Acc:95.08%
Training: Epoch[056/182] Iteration[150/352] Loss: 0.1418 Acc:94.95%
Training: Epoch[056/182] Iteration[200/352] Loss: 0.1443 Acc:94.82%
Training: Epoch[056/182] Iteration[250/352] Loss: 0.1475 Acc:94.73%
Training: Epoch[056/182] Iteration[300/352] Loss: 0.1523 Acc:94.56%
Training: Epoch[056/182] Iteration[350/352] Loss: 0.1557 Acc:94.43%
Training Progress:  30%|▎| 55/182 [18:52<43:17, 20.45s/it, Train Acc=94.42%, ValEpoch[056/182] Train Acc: 94.42% Valid Acc:88.44% Train loss:0.1561 Valid loss:0.3778 LR:0.1
Training Progress:  31%|▎| 56/182 [18:52<42:53, 20.43s/it, Train Acc=94.42%, ValTraining: Epoch[057/182] Iteration[050/352] Loss: 0.1513 Acc:94.55%
Training: Epoch[057/182] Iteration[100/352] Loss: 0.1494 Acc:94.60%
Training: Epoch[057/182] Iteration[150/352] Loss: 0.1459 Acc:94.79%
Training: Epoch[057/182] Iteration[200/352] Loss: 0.1505 Acc:94.57%
Training: Epoch[057/182] Iteration[250/352] Loss: 0.1520 Acc:94.52%
Training: Epoch[057/182] Iteration[300/352] Loss: 0.1543 Acc:94.48%
Training: Epoch[057/182] Iteration[350/352] Loss: 0.1536 Acc:94.53%
Training Progress:  31%|▎| 56/182 [19:13<42:53, 20.43s/it, Train Acc=94.53%, ValEpoch[057/182] Train Acc: 94.53% Valid Acc:88.62% Train loss:0.1535 Valid loss:0.4042 LR:0.1
Training Progress:  31%|▎| 57/182 [19:13<42:48, 20.55s/it, Train Acc=94.53%, ValTraining: Epoch[058/182] Iteration[050/352] Loss: 0.1382 Acc:95.28%
Training: Epoch[058/182] Iteration[100/352] Loss: 0.1369 Acc:95.22%
Training: Epoch[058/182] Iteration[150/352] Loss: 0.1436 Acc:94.98%
Training: Epoch[058/182] Iteration[200/352] Loss: 0.1452 Acc:94.89%
Training: Epoch[058/182] Iteration[250/352] Loss: 0.1495 Acc:94.75%
Training: Epoch[058/182] Iteration[300/352] Loss: 0.1526 Acc:94.62%
Training: Epoch[058/182] Iteration[350/352] Loss: 0.1553 Acc:94.55%
Training Progress:  31%|▎| 57/182 [19:33<42:48, 20.55s/it, Train Acc=94.55%, ValEpoch[058/182] Train Acc: 94.55% Valid Acc:87.70% Train loss:0.1550 Valid loss:0.4454 LR:0.1
Training Progress:  32%|▎| 58/182 [19:33<42:19, 20.48s/it, Train Acc=94.55%, ValTraining: Epoch[059/182] Iteration[050/352] Loss: 0.1346 Acc:95.27%
Training: Epoch[059/182] Iteration[100/352] Loss: 0.1387 Acc:95.21%
Training: Epoch[059/182] Iteration[150/352] Loss: 0.1420 Acc:95.06%
Training: Epoch[059/182] Iteration[200/352] Loss: 0.1405 Acc:95.14%
Training: Epoch[059/182] Iteration[250/352] Loss: 0.1453 Acc:95.01%
Training: Epoch[059/182] Iteration[300/352] Loss: 0.1491 Acc:94.85%
Training: Epoch[059/182] Iteration[350/352] Loss: 0.1536 Acc:94.67%
Training Progress:  32%|▎| 58/182 [19:53<42:19, 20.48s/it, Train Acc=94.67%, ValEpoch[059/182] Train Acc: 94.67% Valid Acc:88.10% Train loss:0.1538 Valid loss:0.4323 LR:0.1
Training Progress:  32%|▎| 59/182 [19:53<41:49, 20.40s/it, Train Acc=94.67%, ValTraining: Epoch[060/182] Iteration[050/352] Loss: 0.1363 Acc:95.27%
Training: Epoch[060/182] Iteration[100/352] Loss: 0.1374 Acc:95.14%
Training: Epoch[060/182] Iteration[150/352] Loss: 0.1401 Acc:95.02%
Training: Epoch[060/182] Iteration[200/352] Loss: 0.1417 Acc:94.98%
Training: Epoch[060/182] Iteration[250/352] Loss: 0.1448 Acc:94.88%
Training: Epoch[060/182] Iteration[300/352] Loss: 0.1440 Acc:94.89%
Training: Epoch[060/182] Iteration[350/352] Loss: 0.1447 Acc:94.88%
Training Progress:  32%|▎| 59/182 [20:14<41:49, 20.40s/it, Train Acc=94.88%, ValEpoch[060/182] Train Acc: 94.88% Valid Acc:88.38% Train loss:0.1449 Valid loss:0.4273 LR:0.1
Training Progress:  33%|▎| 60/182 [20:14<41:30, 20.41s/it, Train Acc=94.88%, ValTraining: Epoch[061/182] Iteration[050/352] Loss: 0.1435 Acc:94.80%
Training: Epoch[061/182] Iteration[100/352] Loss: 0.1393 Acc:95.01%
Training: Epoch[061/182] Iteration[150/352] Loss: 0.1402 Acc:94.96%
Training: Epoch[061/182] Iteration[200/352] Loss: 0.1413 Acc:94.94%
Training: Epoch[061/182] Iteration[250/352] Loss: 0.1451 Acc:94.88%
Training: Epoch[061/182] Iteration[300/352] Loss: 0.1472 Acc:94.79%
Training: Epoch[061/182] Iteration[350/352] Loss: 0.1489 Acc:94.69%
Training Progress:  33%|▎| 60/182 [20:34<41:30, 20.41s/it, Train Acc=94.69%, ValEpoch[061/182] Train Acc: 94.69% Valid Acc:85.42% Train loss:0.1491 Valid loss:0.5563 LR:0.1
Training Progress:  34%|▎| 61/182 [20:34<41:09, 20.41s/it, Train Acc=94.69%, ValTraining: Epoch[062/182] Iteration[050/352] Loss: 0.1476 Acc:94.95%
Training: Epoch[062/182] Iteration[100/352] Loss: 0.1420 Acc:95.09%
Training: Epoch[062/182] Iteration[150/352] Loss: 0.1390 Acc:95.09%
Training: Epoch[062/182] Iteration[200/352] Loss: 0.1420 Acc:94.98%
Training: Epoch[062/182] Iteration[250/352] Loss: 0.1460 Acc:94.85%
Training: Epoch[062/182] Iteration[300/352] Loss: 0.1500 Acc:94.70%
Training: Epoch[062/182] Iteration[350/352] Loss: 0.1521 Acc:94.62%
Training Progress:  34%|▎| 61/182 [20:55<41:09, 20.41s/it, Train Acc=94.62%, ValEpoch[062/182] Train Acc: 94.62% Valid Acc:87.82% Train loss:0.1521 Valid loss:0.4036 LR:0.1
Training Progress:  34%|▎| 62/182 [20:55<40:50, 20.42s/it, Train Acc=94.62%, ValTraining: Epoch[063/182] Iteration[050/352] Loss: 0.1392 Acc:95.09%
Training: Epoch[063/182] Iteration[100/352] Loss: 0.1415 Acc:95.04%
Training: Epoch[063/182] Iteration[150/352] Loss: 0.1409 Acc:95.06%
Training: Epoch[063/182] Iteration[200/352] Loss: 0.1468 Acc:94.88%
Training: Epoch[063/182] Iteration[250/352] Loss: 0.1484 Acc:94.83%
Training: Epoch[063/182] Iteration[300/352] Loss: 0.1493 Acc:94.76%
Training: Epoch[063/182] Iteration[350/352] Loss: 0.1513 Acc:94.70%
Training Progress:  34%|▎| 62/182 [21:15<40:50, 20.42s/it, Train Acc=94.70%, ValEpoch[063/182] Train Acc: 94.70% Valid Acc:88.52% Train loss:0.1514 Valid loss:0.3929 LR:0.1
Training Progress:  35%|▎| 63/182 [21:15<40:26, 20.39s/it, Train Acc=94.70%, ValTraining: Epoch[064/182] Iteration[050/352] Loss: 0.1296 Acc:95.17%
Training: Epoch[064/182] Iteration[100/352] Loss: 0.1335 Acc:95.16%
Training: Epoch[064/182] Iteration[150/352] Loss: 0.1395 Acc:95.07%
Training: Epoch[064/182] Iteration[200/352] Loss: 0.1429 Acc:94.96%
Training: Epoch[064/182] Iteration[250/352] Loss: 0.1465 Acc:94.81%
Training: Epoch[064/182] Iteration[300/352] Loss: 0.1476 Acc:94.84%
Training: Epoch[064/182] Iteration[350/352] Loss: 0.1517 Acc:94.71%
Training Progress:  35%|▎| 63/182 [21:35<40:26, 20.39s/it, Train Acc=94.70%, ValEpoch[064/182] Train Acc: 94.70% Valid Acc:88.84% Train loss:0.1519 Valid loss:0.3679 LR:0.1
Training Progress:  35%|▎| 64/182 [21:35<40:09, 20.42s/it, Train Acc=94.70%, ValTraining: Epoch[065/182] Iteration[050/352] Loss: 0.1387 Acc:94.98%
Training: Epoch[065/182] Iteration[100/352] Loss: 0.1328 Acc:95.36%
Training: Epoch[065/182] Iteration[150/352] Loss: 0.1394 Acc:95.09%
Training: Epoch[065/182] Iteration[200/352] Loss: 0.1425 Acc:94.94%
Training: Epoch[065/182] Iteration[250/352] Loss: 0.1394 Acc:95.00%
Training: Epoch[065/182] Iteration[300/352] Loss: 0.1439 Acc:94.84%
Training: Epoch[065/182] Iteration[350/352] Loss: 0.1450 Acc:94.77%
Training Progress:  35%|▎| 64/182 [21:56<40:09, 20.42s/it, Train Acc=94.78%, ValEpoch[065/182] Train Acc: 94.78% Valid Acc:87.54% Train loss:0.1450 Valid loss:0.4569 LR:0.1
Training Progress:  36%|▎| 65/182 [21:56<39:47, 20.40s/it, Train Acc=94.78%, ValTraining: Epoch[066/182] Iteration[050/352] Loss: 0.1344 Acc:95.36%
Training: Epoch[066/182] Iteration[100/352] Loss: 0.1263 Acc:95.68%
Training: Epoch[066/182] Iteration[150/352] Loss: 0.1387 Acc:95.11%
Training: Epoch[066/182] Iteration[200/352] Loss: 0.1427 Acc:95.00%
Training: Epoch[066/182] Iteration[250/352] Loss: 0.1446 Acc:95.03%
Training: Epoch[066/182] Iteration[300/352] Loss: 0.1475 Acc:94.91%
Training: Epoch[066/182] Iteration[350/352] Loss: 0.1484 Acc:94.84%
Training Progress:  36%|▎| 65/182 [22:16<39:47, 20.40s/it, Train Acc=94.84%, ValEpoch[066/182] Train Acc: 94.84% Valid Acc:86.60% Train loss:0.1484 Valid loss:0.4708 LR:0.1
Training Progress:  36%|▎| 66/182 [22:16<39:22, 20.36s/it, Train Acc=94.84%, ValTraining: Epoch[067/182] Iteration[050/352] Loss: 0.1293 Acc:95.27%
Training: Epoch[067/182] Iteration[100/352] Loss: 0.1345 Acc:95.10%
Training: Epoch[067/182] Iteration[150/352] Loss: 0.1321 Acc:95.29%
Training: Epoch[067/182] Iteration[200/352] Loss: 0.1335 Acc:95.25%
Training: Epoch[067/182] Iteration[250/352] Loss: 0.1384 Acc:95.10%
Training: Epoch[067/182] Iteration[300/352] Loss: 0.1419 Acc:95.01%
Training: Epoch[067/182] Iteration[350/352] Loss: 0.1413 Acc:95.05%
Training Progress:  36%|▎| 66/182 [22:36<39:22, 20.36s/it, Train Acc=95.05%, ValEpoch[067/182] Train Acc: 95.05% Valid Acc:88.42% Train loss:0.1412 Valid loss:0.4302 LR:0.1
Training Progress:  37%|▎| 67/182 [22:36<38:59, 20.35s/it, Train Acc=95.05%, ValTraining: Epoch[068/182] Iteration[050/352] Loss: 0.1120 Acc:96.06%
Training: Epoch[068/182] Iteration[100/352] Loss: 0.1221 Acc:95.73%
Training: Epoch[068/182] Iteration[150/352] Loss: 0.1288 Acc:95.49%
Training: Epoch[068/182] Iteration[200/352] Loss: 0.1341 Acc:95.28%
Training: Epoch[068/182] Iteration[250/352] Loss: 0.1405 Acc:95.12%
Training: Epoch[068/182] Iteration[300/352] Loss: 0.1430 Acc:95.02%
Training: Epoch[068/182] Iteration[350/352] Loss: 0.1470 Acc:94.88%
Training Progress:  37%|▎| 67/182 [22:57<38:59, 20.35s/it, Train Acc=94.87%, ValEpoch[068/182] Train Acc: 94.87% Valid Acc:87.08% Train loss:0.1471 Valid loss:0.4689 LR:0.1
Training Progress:  37%|▎| 68/182 [22:57<38:42, 20.38s/it, Train Acc=94.87%, ValTraining: Epoch[069/182] Iteration[050/352] Loss: 0.1232 Acc:95.42%
Training: Epoch[069/182] Iteration[100/352] Loss: 0.1246 Acc:95.55%
Training: Epoch[069/182] Iteration[150/352] Loss: 0.1232 Acc:95.67%
Training: Epoch[069/182] Iteration[200/352] Loss: 0.1300 Acc:95.43%
Training: Epoch[069/182] Iteration[250/352] Loss: 0.1369 Acc:95.22%
Training: Epoch[069/182] Iteration[300/352] Loss: 0.1386 Acc:95.09%
Training: Epoch[069/182] Iteration[350/352] Loss: 0.1393 Acc:95.07%
Training Progress:  37%|▎| 68/182 [23:17<38:42, 20.38s/it, Train Acc=95.07%, ValEpoch[069/182] Train Acc: 95.07% Valid Acc:87.90% Train loss:0.1391 Valid loss:0.4167 LR:0.1
Training Progress:  38%|▍| 69/182 [23:17<38:20, 20.36s/it, Train Acc=95.07%, ValTraining: Epoch[070/182] Iteration[050/352] Loss: 0.1304 Acc:95.38%
Training: Epoch[070/182] Iteration[100/352] Loss: 0.1314 Acc:95.12%
Training: Epoch[070/182] Iteration[150/352] Loss: 0.1311 Acc:95.16%
Training: Epoch[070/182] Iteration[200/352] Loss: 0.1381 Acc:95.02%
Training: Epoch[070/182] Iteration[250/352] Loss: 0.1404 Acc:94.99%
Training: Epoch[070/182] Iteration[300/352] Loss: 0.1421 Acc:94.96%
Training: Epoch[070/182] Iteration[350/352] Loss: 0.1439 Acc:94.92%
Training Progress:  38%|▍| 69/182 [23:38<38:20, 20.36s/it, Train Acc=94.92%, ValEpoch[070/182] Train Acc: 94.92% Valid Acc:88.04% Train loss:0.1438 Valid loss:0.4421 LR:0.1
Training Progress:  38%|▍| 70/182 [23:38<38:00, 20.36s/it, Train Acc=94.92%, ValTraining: Epoch[071/182] Iteration[050/352] Loss: 0.1350 Acc:95.17%
Training: Epoch[071/182] Iteration[100/352] Loss: 0.1312 Acc:95.20%
Training: Epoch[071/182] Iteration[150/352] Loss: 0.1330 Acc:95.17%
Training: Epoch[071/182] Iteration[200/352] Loss: 0.1378 Acc:95.12%
Training: Epoch[071/182] Iteration[250/352] Loss: 0.1396 Acc:95.08%
Training: Epoch[071/182] Iteration[300/352] Loss: 0.1396 Acc:95.09%
Training: Epoch[071/182] Iteration[350/352] Loss: 0.1405 Acc:95.06%
Training Progress:  38%|▍| 70/182 [23:58<38:00, 20.36s/it, Train Acc=95.06%, ValEpoch[071/182] Train Acc: 95.06% Valid Acc:86.36% Train loss:0.1403 Valid loss:0.5352 LR:0.1
Training Progress:  39%|▍| 71/182 [23:58<37:35, 20.32s/it, Train Acc=95.06%, ValTraining: Epoch[072/182] Iteration[050/352] Loss: 0.1260 Acc:95.55%
Training: Epoch[072/182] Iteration[100/352] Loss: 0.1298 Acc:95.34%
Training: Epoch[072/182] Iteration[150/352] Loss: 0.1314 Acc:95.30%
Training: Epoch[072/182] Iteration[200/352] Loss: 0.1332 Acc:95.23%
Training: Epoch[072/182] Iteration[250/352] Loss: 0.1351 Acc:95.14%
Training: Epoch[072/182] Iteration[300/352] Loss: 0.1359 Acc:95.15%
Training: Epoch[072/182] Iteration[350/352] Loss: 0.1364 Acc:95.12%
Training Progress:  39%|▍| 71/182 [24:18<37:35, 20.32s/it, Train Acc=95.11%, ValEpoch[072/182] Train Acc: 95.11% Valid Acc:83.78% Train loss:0.1365 Valid loss:0.6625 LR:0.1
Training Progress:  40%|▍| 72/182 [24:18<37:15, 20.32s/it, Train Acc=95.11%, ValTraining: Epoch[073/182] Iteration[050/352] Loss: 0.1327 Acc:95.41%
Training: Epoch[073/182] Iteration[100/352] Loss: 0.1348 Acc:95.23%
Training: Epoch[073/182] Iteration[150/352] Loss: 0.1436 Acc:95.00%
Training: Epoch[073/182] Iteration[200/352] Loss: 0.1470 Acc:94.83%
Training: Epoch[073/182] Iteration[250/352] Loss: 0.1474 Acc:94.78%
Training: Epoch[073/182] Iteration[300/352] Loss: 0.1456 Acc:94.85%
Training: Epoch[073/182] Iteration[350/352] Loss: 0.1469 Acc:94.83%
Training Progress:  40%|▍| 72/182 [24:39<37:15, 20.32s/it, Train Acc=94.84%, ValEpoch[073/182] Train Acc: 94.84% Valid Acc:87.26% Train loss:0.1464 Valid loss:0.4535 LR:0.1
Training Progress:  40%|▍| 73/182 [24:39<36:59, 20.36s/it, Train Acc=94.84%, ValTraining: Epoch[074/182] Iteration[050/352] Loss: 0.1137 Acc:95.88%
Training: Epoch[074/182] Iteration[100/352] Loss: 0.1177 Acc:95.77%
Training: Epoch[074/182] Iteration[150/352] Loss: 0.1243 Acc:95.57%
Training: Epoch[074/182] Iteration[200/352] Loss: 0.1298 Acc:95.40%
Training: Epoch[074/182] Iteration[250/352] Loss: 0.1323 Acc:95.29%
Training: Epoch[074/182] Iteration[300/352] Loss: 0.1378 Acc:95.08%
Training: Epoch[074/182] Iteration[350/352] Loss: 0.1377 Acc:95.09%
Training Progress:  40%|▍| 73/182 [24:59<36:59, 20.36s/it, Train Acc=95.09%, ValEpoch[074/182] Train Acc: 95.09% Valid Acc:86.48% Train loss:0.1378 Valid loss:0.4915 LR:0.1
Training Progress:  41%|▍| 74/182 [24:59<36:46, 20.43s/it, Train Acc=95.09%, ValTraining: Epoch[075/182] Iteration[050/352] Loss: 0.1173 Acc:96.05%
Training: Epoch[075/182] Iteration[100/352] Loss: 0.1206 Acc:95.88%
Training: Epoch[075/182] Iteration[150/352] Loss: 0.1258 Acc:95.66%
Training: Epoch[075/182] Iteration[200/352] Loss: 0.1306 Acc:95.47%
Training: Epoch[075/182] Iteration[250/352] Loss: 0.1348 Acc:95.32%
Training: Epoch[075/182] Iteration[300/352] Loss: 0.1366 Acc:95.22%
Training: Epoch[075/182] Iteration[350/352] Loss: 0.1367 Acc:95.20%
Training Progress:  41%|▍| 74/182 [25:19<36:46, 20.43s/it, Train Acc=95.19%, ValEpoch[075/182] Train Acc: 95.19% Valid Acc:87.32% Train loss:0.1371 Valid loss:0.4819 LR:0.1
Training Progress:  41%|▍| 75/182 [25:19<36:21, 20.39s/it, Train Acc=95.19%, ValTraining: Epoch[076/182] Iteration[050/352] Loss: 0.1319 Acc:95.42%
Training: Epoch[076/182] Iteration[100/352] Loss: 0.1317 Acc:95.46%
Training: Epoch[076/182] Iteration[150/352] Loss: 0.1247 Acc:95.65%
Training: Epoch[076/182] Iteration[200/352] Loss: 0.1333 Acc:95.30%
Training: Epoch[076/182] Iteration[250/352] Loss: 0.1360 Acc:95.24%
Training: Epoch[076/182] Iteration[300/352] Loss: 0.1381 Acc:95.14%
Training: Epoch[076/182] Iteration[350/352] Loss: 0.1394 Acc:95.06%
Training Progress:  41%|▍| 75/182 [25:40<36:21, 20.39s/it, Train Acc=95.06%, ValEpoch[076/182] Train Acc: 95.06% Valid Acc:88.52% Train loss:0.1394 Valid loss:0.4204 LR:0.1
Training Progress:  42%|▍| 76/182 [25:40<36:02, 20.40s/it, Train Acc=95.06%, ValTraining: Epoch[077/182] Iteration[050/352] Loss: 0.1181 Acc:95.67%
Training: Epoch[077/182] Iteration[100/352] Loss: 0.1265 Acc:95.41%
Training: Epoch[077/182] Iteration[150/352] Loss: 0.1335 Acc:95.18%
Training: Epoch[077/182] Iteration[200/352] Loss: 0.1344 Acc:95.22%
Training: Epoch[077/182] Iteration[250/352] Loss: 0.1336 Acc:95.25%
Training: Epoch[077/182] Iteration[300/352] Loss: 0.1361 Acc:95.15%
Training: Epoch[077/182] Iteration[350/352] Loss: 0.1356 Acc:95.21%
Training Progress:  42%|▍| 76/182 [26:00<36:02, 20.40s/it, Train Acc=95.22%, ValEpoch[077/182] Train Acc: 95.22% Valid Acc:88.00% Train loss:0.1357 Valid loss:0.3918 LR:0.1
Training Progress:  42%|▍| 77/182 [26:00<35:41, 20.39s/it, Train Acc=95.22%, ValTraining: Epoch[078/182] Iteration[050/352] Loss: 0.1287 Acc:95.67%
Training: Epoch[078/182] Iteration[100/352] Loss: 0.1241 Acc:95.66%
Training: Epoch[078/182] Iteration[150/352] Loss: 0.1282 Acc:95.47%
Training: Epoch[078/182] Iteration[200/352] Loss: 0.1293 Acc:95.38%
Training: Epoch[078/182] Iteration[250/352] Loss: 0.1290 Acc:95.38%
Training: Epoch[078/182] Iteration[300/352] Loss: 0.1285 Acc:95.40%
Training: Epoch[078/182] Iteration[350/352] Loss: 0.1320 Acc:95.24%
Training Progress:  42%|▍| 77/182 [26:21<35:41, 20.39s/it, Train Acc=95.23%, ValEpoch[078/182] Train Acc: 95.23% Valid Acc:86.38% Train loss:0.1322 Valid loss:0.5086 LR:0.1
Training Progress:  43%|▍| 78/182 [26:21<35:25, 20.43s/it, Train Acc=95.23%, ValTraining: Epoch[079/182] Iteration[050/352] Loss: 0.1419 Acc:95.03%
Training: Epoch[079/182] Iteration[100/352] Loss: 0.1402 Acc:95.20%
Training: Epoch[079/182] Iteration[150/352] Loss: 0.1390 Acc:95.18%
Training: Epoch[079/182] Iteration[200/352] Loss: 0.1321 Acc:95.45%
Training: Epoch[079/182] Iteration[250/352] Loss: 0.1350 Acc:95.30%
Training: Epoch[079/182] Iteration[300/352] Loss: 0.1381 Acc:95.20%
Training: Epoch[079/182] Iteration[350/352] Loss: 0.1408 Acc:95.08%
Training Progress:  43%|▍| 78/182 [26:41<35:25, 20.43s/it, Train Acc=95.07%, ValEpoch[079/182] Train Acc: 95.07% Valid Acc:88.12% Train loss:0.1409 Valid loss:0.4449 LR:0.1
Training Progress:  43%|▍| 79/182 [26:41<35:02, 20.41s/it, Train Acc=95.07%, ValTraining: Epoch[080/182] Iteration[050/352] Loss: 0.1245 Acc:95.42%
Training: Epoch[080/182] Iteration[100/352] Loss: 0.1234 Acc:95.67%
Training: Epoch[080/182] Iteration[150/352] Loss: 0.1322 Acc:95.35%
Training: Epoch[080/182] Iteration[200/352] Loss: 0.1356 Acc:95.20%
Training: Epoch[080/182] Iteration[250/352] Loss: 0.1371 Acc:95.15%
Training: Epoch[080/182] Iteration[300/352] Loss: 0.1353 Acc:95.24%
Training: Epoch[080/182] Iteration[350/352] Loss: 0.1357 Acc:95.21%
Training Progress:  43%|▍| 79/182 [27:02<35:02, 20.41s/it, Train Acc=95.21%, ValEpoch[080/182] Train Acc: 95.21% Valid Acc:89.30% Train loss:0.1355 Valid loss:0.3811 LR:0.1
Training Progress:  44%|▍| 80/182 [27:02<34:42, 20.42s/it, Train Acc=95.21%, ValTraining: Epoch[081/182] Iteration[050/352] Loss: 0.1171 Acc:95.95%
Training: Epoch[081/182] Iteration[100/352] Loss: 0.1231 Acc:95.80%
Training: Epoch[081/182] Iteration[150/352] Loss: 0.1242 Acc:95.62%
Training: Epoch[081/182] Iteration[200/352] Loss: 0.1268 Acc:95.54%
Training: Epoch[081/182] Iteration[250/352] Loss: 0.1272 Acc:95.49%
Training: Epoch[081/182] Iteration[300/352] Loss: 0.1326 Acc:95.26%
Training: Epoch[081/182] Iteration[350/352] Loss: 0.1318 Acc:95.28%
Training Progress:  44%|▍| 80/182 [27:22<34:42, 20.42s/it, Train Acc=95.27%, ValEpoch[081/182] Train Acc: 95.27% Valid Acc:88.92% Train loss:0.1320 Valid loss:0.4093 LR:0.1
Training Progress:  45%|▍| 81/182 [27:22<34:22, 20.42s/it, Train Acc=95.27%, ValTraining: Epoch[082/182] Iteration[050/352] Loss: 0.1133 Acc:96.20%
Training: Epoch[082/182] Iteration[100/352] Loss: 0.1199 Acc:95.88%
Training: Epoch[082/182] Iteration[150/352] Loss: 0.1309 Acc:95.52%
Training: Epoch[082/182] Iteration[200/352] Loss: 0.1372 Acc:95.30%
Training: Epoch[082/182] Iteration[250/352] Loss: 0.1397 Acc:95.23%
Training: Epoch[082/182] Iteration[300/352] Loss: 0.1400 Acc:95.20%
Training: Epoch[082/182] Iteration[350/352] Loss: 0.1384 Acc:95.22%
Training Progress:  45%|▍| 81/182 [27:42<34:22, 20.42s/it, Train Acc=95.21%, ValEpoch[082/182] Train Acc: 95.21% Valid Acc:86.82% Train loss:0.1387 Valid loss:0.4794 LR:0.1
Training Progress:  45%|▍| 82/182 [27:42<33:59, 20.39s/it, Train Acc=95.21%, ValTraining: Epoch[083/182] Iteration[050/352] Loss: 0.1138 Acc:96.16%
Training: Epoch[083/182] Iteration[100/352] Loss: 0.1097 Acc:96.09%
Training: Epoch[083/182] Iteration[150/352] Loss: 0.1138 Acc:95.96%
Training: Epoch[083/182] Iteration[200/352] Loss: 0.1210 Acc:95.64%
Training: Epoch[083/182] Iteration[250/352] Loss: 0.1268 Acc:95.42%
Training: Epoch[083/182] Iteration[300/352] Loss: 0.1279 Acc:95.42%
Training: Epoch[083/182] Iteration[350/352] Loss: 0.1305 Acc:95.34%
Training Progress:  45%|▍| 82/182 [28:03<33:59, 20.39s/it, Train Acc=95.33%, ValEpoch[083/182] Train Acc: 95.33% Valid Acc:86.30% Train loss:0.1306 Valid loss:0.5405 LR:0.1
Training Progress:  46%|▍| 83/182 [28:03<33:49, 20.50s/it, Train Acc=95.33%, ValTraining: Epoch[084/182] Iteration[050/352] Loss: 0.1215 Acc:95.78%
Training: Epoch[084/182] Iteration[100/352] Loss: 0.1270 Acc:95.59%
Training: Epoch[084/182] Iteration[150/352] Loss: 0.1298 Acc:95.43%
Training: Epoch[084/182] Iteration[200/352] Loss: 0.1312 Acc:95.43%
Training: Epoch[084/182] Iteration[250/352] Loss: 0.1353 Acc:95.30%
Training: Epoch[084/182] Iteration[300/352] Loss: 0.1377 Acc:95.17%
Training: Epoch[084/182] Iteration[350/352] Loss: 0.1383 Acc:95.14%
Training Progress:  46%|▍| 83/182 [28:23<33:49, 20.50s/it, Train Acc=95.14%, ValEpoch[084/182] Train Acc: 95.14% Valid Acc:89.40% Train loss:0.1382 Valid loss:0.3964 LR:0.1
Training Progress:  46%|▍| 84/182 [28:23<33:25, 20.47s/it, Train Acc=95.14%, ValTraining: Epoch[085/182] Iteration[050/352] Loss: 0.1137 Acc:95.94%
Training: Epoch[085/182] Iteration[100/352] Loss: 0.1132 Acc:95.90%
Training: Epoch[085/182] Iteration[150/352] Loss: 0.1186 Acc:95.73%
Training: Epoch[085/182] Iteration[200/352] Loss: 0.1224 Acc:95.65%
Training: Epoch[085/182] Iteration[250/352] Loss: 0.1248 Acc:95.53%
Training: Epoch[085/182] Iteration[300/352] Loss: 0.1309 Acc:95.28%
Training: Epoch[085/182] Iteration[350/352] Loss: 0.1328 Acc:95.23%
Training Progress:  46%|▍| 84/182 [28:44<33:25, 20.47s/it, Train Acc=95.23%, ValEpoch[085/182] Train Acc: 95.23% Valid Acc:89.02% Train loss:0.1329 Valid loss:0.3890 LR:0.1
Training Progress:  47%|▍| 85/182 [28:44<33:03, 20.45s/it, Train Acc=95.23%, ValTraining: Epoch[086/182] Iteration[050/352] Loss: 0.1147 Acc:95.80%
Training: Epoch[086/182] Iteration[100/352] Loss: 0.1153 Acc:95.92%
Training: Epoch[086/182] Iteration[150/352] Loss: 0.1181 Acc:95.81%
Training: Epoch[086/182] Iteration[200/352] Loss: 0.1271 Acc:95.55%
Training: Epoch[086/182] Iteration[250/352] Loss: 0.1298 Acc:95.47%
Training: Epoch[086/182] Iteration[300/352] Loss: 0.1346 Acc:95.28%
Training: Epoch[086/182] Iteration[350/352] Loss: 0.1366 Acc:95.21%
Training Progress:  47%|▍| 85/182 [29:04<33:03, 20.45s/it, Train Acc=95.21%, ValEpoch[086/182] Train Acc: 95.21% Valid Acc:88.00% Train loss:0.1366 Valid loss:0.4476 LR:0.1
Training Progress:  47%|▍| 86/182 [29:04<32:41, 20.43s/it, Train Acc=95.21%, ValTraining: Epoch[087/182] Iteration[050/352] Loss: 0.1221 Acc:95.83%
Training: Epoch[087/182] Iteration[100/352] Loss: 0.1177 Acc:95.80%
Training: Epoch[087/182] Iteration[150/352] Loss: 0.1196 Acc:95.77%
Training: Epoch[087/182] Iteration[200/352] Loss: 0.1265 Acc:95.52%
Training: Epoch[087/182] Iteration[250/352] Loss: 0.1302 Acc:95.37%
Training: Epoch[087/182] Iteration[300/352] Loss: 0.1318 Acc:95.30%
Training: Epoch[087/182] Iteration[350/352] Loss: 0.1346 Acc:95.22%
Training Progress:  47%|▍| 86/182 [29:25<32:41, 20.43s/it, Train Acc=95.22%, ValEpoch[087/182] Train Acc: 95.22% Valid Acc:88.66% Train loss:0.1347 Valid loss:0.3893 LR:0.1
Training Progress:  48%|▍| 87/182 [29:25<32:18, 20.41s/it, Train Acc=95.22%, ValTraining: Epoch[088/182] Iteration[050/352] Loss: 0.1223 Acc:95.62%
Training: Epoch[088/182] Iteration[100/352] Loss: 0.1194 Acc:95.63%
Training: Epoch[088/182] Iteration[150/352] Loss: 0.1175 Acc:95.83%
Training: Epoch[088/182] Iteration[200/352] Loss: 0.1238 Acc:95.62%
Training: Epoch[088/182] Iteration[250/352] Loss: 0.1240 Acc:95.59%
Training: Epoch[088/182] Iteration[300/352] Loss: 0.1242 Acc:95.59%
Training: Epoch[088/182] Iteration[350/352] Loss: 0.1251 Acc:95.56%
Training Progress:  48%|▍| 87/182 [29:45<32:18, 20.41s/it, Train Acc=95.56%, ValEpoch[088/182] Train Acc: 95.56% Valid Acc:89.16% Train loss:0.1252 Valid loss:0.3903 LR:0.1
Training Progress:  48%|▍| 88/182 [29:45<32:01, 20.44s/it, Train Acc=95.56%, ValTraining: Epoch[089/182] Iteration[050/352] Loss: 0.1150 Acc:96.05%
Training: Epoch[089/182] Iteration[100/352] Loss: 0.1162 Acc:96.12%
Training: Epoch[089/182] Iteration[150/352] Loss: 0.1169 Acc:96.04%
Training: Epoch[089/182] Iteration[200/352] Loss: 0.1203 Acc:95.90%
Training: Epoch[089/182] Iteration[250/352] Loss: 0.1242 Acc:95.71%
Training: Epoch[089/182] Iteration[300/352] Loss: 0.1262 Acc:95.61%
Training: Epoch[089/182] Iteration[350/352] Loss: 0.1262 Acc:95.61%
Training Progress:  48%|▍| 88/182 [30:06<32:01, 20.44s/it, Train Acc=95.60%, ValEpoch[089/182] Train Acc: 95.60% Valid Acc:88.96% Train loss:0.1264 Valid loss:0.4188 LR:0.1
Training Progress:  49%|▍| 89/182 [30:06<31:42, 20.46s/it, Train Acc=95.60%, ValTraining: Epoch[090/182] Iteration[050/352] Loss: 0.1168 Acc:96.31%
Training: Epoch[090/182] Iteration[100/352] Loss: 0.1177 Acc:95.99%
Training: Epoch[090/182] Iteration[150/352] Loss: 0.1248 Acc:95.63%
Training: Epoch[090/182] Iteration[200/352] Loss: 0.1299 Acc:95.47%
Training: Epoch[090/182] Iteration[250/352] Loss: 0.1306 Acc:95.43%
Training: Epoch[090/182] Iteration[300/352] Loss: 0.1333 Acc:95.33%
Training: Epoch[090/182] Iteration[350/352] Loss: 0.1351 Acc:95.25%
Training Progress:  49%|▍| 89/182 [30:26<31:42, 20.46s/it, Train Acc=95.24%, ValEpoch[090/182] Train Acc: 95.24% Valid Acc:87.02% Train loss:0.1354 Valid loss:0.4665 LR:0.1
Training Progress:  49%|▍| 90/182 [30:26<31:23, 20.47s/it, Train Acc=95.24%, ValTraining: Epoch[091/182] Iteration[050/352] Loss: 0.1257 Acc:95.44%
Training: Epoch[091/182] Iteration[100/352] Loss: 0.1275 Acc:95.38%
Training: Epoch[091/182] Iteration[150/352] Loss: 0.1285 Acc:95.39%
Training: Epoch[091/182] Iteration[200/352] Loss: 0.1382 Acc:95.09%
Training: Epoch[091/182] Iteration[250/352] Loss: 0.1375 Acc:95.12%
Training: Epoch[091/182] Iteration[300/352] Loss: 0.1357 Acc:95.21%
Training: Epoch[091/182] Iteration[350/352] Loss: 0.1368 Acc:95.20%
Training Progress:  49%|▍| 90/182 [30:46<31:23, 20.47s/it, Train Acc=95.20%, ValEpoch[091/182] Train Acc: 95.20% Valid Acc:87.96% Train loss:0.1368 Valid loss:0.4657 LR:0.1
Training Progress:  50%|▌| 91/182 [30:46<30:59, 20.44s/it, Train Acc=95.20%, ValTraining: Epoch[092/182] Iteration[050/352] Loss: 0.1085 Acc:96.20%
Training: Epoch[092/182] Iteration[100/352] Loss: 0.1077 Acc:96.21%
Training: Epoch[092/182] Iteration[150/352] Loss: 0.1196 Acc:95.77%
Training: Epoch[092/182] Iteration[200/352] Loss: 0.1231 Acc:95.62%
Training: Epoch[092/182] Iteration[250/352] Loss: 0.1261 Acc:95.44%
Training: Epoch[092/182] Iteration[300/352] Loss: 0.1280 Acc:95.38%
Training: Epoch[092/182] Iteration[350/352] Loss: 0.1288 Acc:95.39%
Training Progress:  50%|▌| 91/182 [31:07<30:59, 20.44s/it, Train Acc=95.39%, ValEpoch[092/182] Train Acc: 95.39% Valid Acc:88.26% Train loss:0.1288 Valid loss:0.4243 LR:0.1
Training Progress:  51%|▌| 92/182 [31:07<30:36, 20.41s/it, Train Acc=95.39%, ValTraining: Epoch[093/182] Iteration[050/352] Loss: 0.0890 Acc:97.05%
Training: Epoch[093/182] Iteration[100/352] Loss: 0.0795 Acc:97.34%
Training: Epoch[093/182] Iteration[150/352] Loss: 0.0738 Acc:97.55%
Training: Epoch[093/182] Iteration[200/352] Loss: 0.0688 Acc:97.77%
Training: Epoch[093/182] Iteration[250/352] Loss: 0.0648 Acc:97.90%
Training: Epoch[093/182] Iteration[300/352] Loss: 0.0614 Acc:98.04%
Training: Epoch[093/182] Iteration[350/352] Loss: 0.0602 Acc:98.09%
Training Progress:  51%|▌| 92/182 [31:27<30:36, 20.41s/it, Train Acc=98.10%, ValEpoch[093/182] Train Acc: 98.10% Valid Acc:92.76% Train loss:0.0599 Valid loss:0.2672 LR:0.010000000000000002
Training Progress:  51%|▌| 93/182 [31:27<30:19, 20.44s/it, Train Acc=98.10%, ValTraining: Epoch[094/182] Iteration[050/352] Loss: 0.0448 Acc:98.59%
Training: Epoch[094/182] Iteration[100/352] Loss: 0.0417 Acc:98.68%
Training: Epoch[094/182] Iteration[150/352] Loss: 0.0412 Acc:98.73%
Training: Epoch[094/182] Iteration[200/352] Loss: 0.0406 Acc:98.72%
Training: Epoch[094/182] Iteration[250/352] Loss: 0.0404 Acc:98.72%
Training: Epoch[094/182] Iteration[300/352] Loss: 0.0399 Acc:98.74%
Training: Epoch[094/182] Iteration[350/352] Loss: 0.0395 Acc:98.74%
Training Progress:  51%|▌| 93/182 [31:48<30:19, 20.44s/it, Train Acc=98.74%, ValEpoch[094/182] Train Acc: 98.74% Valid Acc:93.16% Train loss:0.0394 Valid loss:0.2624 LR:0.010000000000000002
Training Progress:  52%|▌| 94/182 [31:48<29:56, 20.41s/it, Train Acc=98.74%, ValTraining: Epoch[095/182] Iteration[050/352] Loss: 0.0315 Acc:99.14%
Training: Epoch[095/182] Iteration[100/352] Loss: 0.0324 Acc:99.07%
Training: Epoch[095/182] Iteration[150/352] Loss: 0.0320 Acc:99.03%
Training: Epoch[095/182] Iteration[200/352] Loss: 0.0316 Acc:99.03%
Training: Epoch[095/182] Iteration[250/352] Loss: 0.0306 Acc:99.07%
Training: Epoch[095/182] Iteration[300/352] Loss: 0.0305 Acc:99.08%
Training: Epoch[095/182] Iteration[350/352] Loss: 0.0308 Acc:99.08%
Training Progress:  52%|▌| 94/182 [32:08<29:56, 20.41s/it, Train Acc=99.08%, ValEpoch[095/182] Train Acc: 99.08% Valid Acc:92.98% Train loss:0.0307 Valid loss:0.2665 LR:0.010000000000000002
Training Progress:  52%|▌| 95/182 [32:08<29:45, 20.53s/it, Train Acc=99.08%, ValTraining: Epoch[096/182] Iteration[050/352] Loss: 0.0263 Acc:99.36%
Training: Epoch[096/182] Iteration[100/352] Loss: 0.0274 Acc:99.28%
Training: Epoch[096/182] Iteration[150/352] Loss: 0.0270 Acc:99.30%
Training: Epoch[096/182] Iteration[200/352] Loss: 0.0266 Acc:99.31%
Training: Epoch[096/182] Iteration[250/352] Loss: 0.0262 Acc:99.31%
Training: Epoch[096/182] Iteration[300/352] Loss: 0.0264 Acc:99.28%
Training: Epoch[096/182] Iteration[350/352] Loss: 0.0261 Acc:99.30%
Training Progress:  52%|▌| 95/182 [32:29<29:45, 20.53s/it, Train Acc=99.30%, ValEpoch[096/182] Train Acc: 99.30% Valid Acc:93.14% Train loss:0.0261 Valid loss:0.2724 LR:0.010000000000000002
Training Progress:  53%|▌| 96/182 [32:29<29:21, 20.48s/it, Train Acc=99.30%, ValTraining: Epoch[097/182] Iteration[050/352] Loss: 0.0218 Acc:99.47%
Training: Epoch[097/182] Iteration[100/352] Loss: 0.0217 Acc:99.43%
Training: Epoch[097/182] Iteration[150/352] Loss: 0.0225 Acc:99.37%
Training: Epoch[097/182] Iteration[200/352] Loss: 0.0230 Acc:99.36%
Training: Epoch[097/182] Iteration[250/352] Loss: 0.0226 Acc:99.38%
Training: Epoch[097/182] Iteration[300/352] Loss: 0.0223 Acc:99.41%
Training: Epoch[097/182] Iteration[350/352] Loss: 0.0225 Acc:99.42%
Training Progress:  53%|▌| 96/182 [32:49<29:21, 20.48s/it, Train Acc=99.42%, ValEpoch[097/182] Train Acc: 99.42% Valid Acc:93.28% Train loss:0.0226 Valid loss:0.2778 LR:0.010000000000000002
Training Progress:  53%|▌| 97/182 [32:49<28:57, 20.44s/it, Train Acc=99.42%, ValTraining: Epoch[098/182] Iteration[050/352] Loss: 0.0212 Acc:99.48%
Training: Epoch[098/182] Iteration[100/352] Loss: 0.0224 Acc:99.37%
Training: Epoch[098/182] Iteration[150/352] Loss: 0.0223 Acc:99.38%
Training: Epoch[098/182] Iteration[200/352] Loss: 0.0212 Acc:99.43%
Training: Epoch[098/182] Iteration[250/352] Loss: 0.0210 Acc:99.41%
Training: Epoch[098/182] Iteration[300/352] Loss: 0.0212 Acc:99.38%
Training: Epoch[098/182] Iteration[350/352] Loss: 0.0204 Acc:99.42%
Training Progress:  53%|▌| 97/182 [33:10<28:57, 20.44s/it, Train Acc=99.42%, ValEpoch[098/182] Train Acc: 99.42% Valid Acc:93.28% Train loss:0.0204 Valid loss:0.2789 LR:0.010000000000000002
Training Progress:  54%|▌| 98/182 [33:10<28:40, 20.48s/it, Train Acc=99.42%, ValTraining: Epoch[099/182] Iteration[050/352] Loss: 0.0185 Acc:99.47%
Training: Epoch[099/182] Iteration[100/352] Loss: 0.0195 Acc:99.47%
Training: Epoch[099/182] Iteration[150/352] Loss: 0.0186 Acc:99.53%
Training: Epoch[099/182] Iteration[200/352] Loss: 0.0191 Acc:99.50%
Training: Epoch[099/182] Iteration[250/352] Loss: 0.0187 Acc:99.50%
Training: Epoch[099/182] Iteration[300/352] Loss: 0.0189 Acc:99.49%
Training: Epoch[099/182] Iteration[350/352] Loss: 0.0194 Acc:99.47%
Training Progress:  54%|▌| 98/182 [33:34<28:40, 20.48s/it, Train Acc=99.47%, ValEpoch[099/182] Train Acc: 99.47% Valid Acc:93.08% Train loss:0.0194 Valid loss:0.2824 LR:0.010000000000000002
Training Progress:  54%|▌| 99/182 [33:34<29:42, 21.47s/it, Train Acc=99.47%, ValTraining: Epoch[100/182] Iteration[050/352] Loss: 0.0156 Acc:99.56%
Training: Epoch[100/182] Iteration[100/352] Loss: 0.0153 Acc:99.64%
Training: Epoch[100/182] Iteration[150/352] Loss: 0.0169 Acc:99.60%
Training: Epoch[100/182] Iteration[200/352] Loss: 0.0169 Acc:99.56%
Training: Epoch[100/182] Iteration[250/352] Loss: 0.0179 Acc:99.52%
Training: Epoch[100/182] Iteration[300/352] Loss: 0.0180 Acc:99.51%
Training: Epoch[100/182] Iteration[350/352] Loss: 0.0180 Acc:99.50%
Training Progress:  54%|▌| 99/182 [33:54<29:42, 21.47s/it, Train Acc=99.50%, ValEpoch[100/182] Train Acc: 99.50% Valid Acc:93.44% Train loss:0.0180 Valid loss:0.2826 LR:0.010000000000000002
Training Progress:  55%|▌| 100/182 [33:54<28:53, 21.14s/it, Train Acc=99.50%, VaTraining: Epoch[101/182] Iteration[050/352] Loss: 0.0155 Acc:99.58%
Training: Epoch[101/182] Iteration[100/352] Loss: 0.0166 Acc:99.58%
Training: Epoch[101/182] Iteration[150/352] Loss: 0.0165 Acc:99.56%
Training: Epoch[101/182] Iteration[200/352] Loss: 0.0161 Acc:99.57%
Training: Epoch[101/182] Iteration[250/352] Loss: 0.0160 Acc:99.59%
Training: Epoch[101/182] Iteration[300/352] Loss: 0.0160 Acc:99.58%
Training: Epoch[101/182] Iteration[350/352] Loss: 0.0158 Acc:99.58%
Training Progress:  55%|▌| 100/182 [34:14<28:53, 21.14s/it, Train Acc=99.58%, VaEpoch[101/182] Train Acc: 99.58% Valid Acc:93.46% Train loss:0.0159 Valid loss:0.2829 LR:0.010000000000000002
Training Progress:  55%|▌| 101/182 [34:14<28:15, 20.94s/it, Train Acc=99.58%, VaTraining: Epoch[102/182] Iteration[050/352] Loss: 0.0148 Acc:99.67%
Training: Epoch[102/182] Iteration[100/352] Loss: 0.0149 Acc:99.63%
Training: Epoch[102/182] Iteration[150/352] Loss: 0.0152 Acc:99.59%
Training: Epoch[102/182] Iteration[200/352] Loss: 0.0155 Acc:99.59%
Training: Epoch[102/182] Iteration[250/352] Loss: 0.0152 Acc:99.59%
Training: Epoch[102/182] Iteration[300/352] Loss: 0.0150 Acc:99.59%
Training: Epoch[102/182] Iteration[350/352] Loss: 0.0151 Acc:99.58%
Training Progress:  55%|▌| 101/182 [34:35<28:15, 20.94s/it, Train Acc=99.58%, VaEpoch[102/182] Train Acc: 99.58% Valid Acc:93.44% Train loss:0.0151 Valid loss:0.2905 LR:0.010000000000000002
Training Progress:  56%|▌| 102/182 [34:35<27:40, 20.75s/it, Train Acc=99.58%, VaTraining: Epoch[103/182] Iteration[050/352] Loss: 0.0137 Acc:99.59%
Training: Epoch[103/182] Iteration[100/352] Loss: 0.0130 Acc:99.65%
Training: Epoch[103/182] Iteration[150/352] Loss: 0.0124 Acc:99.68%
Training: Epoch[103/182] Iteration[200/352] Loss: 0.0129 Acc:99.65%
Training: Epoch[103/182] Iteration[250/352] Loss: 0.0128 Acc:99.67%
Training: Epoch[103/182] Iteration[300/352] Loss: 0.0134 Acc:99.65%
Training: Epoch[103/182] Iteration[350/352] Loss: 0.0134 Acc:99.66%
Training Progress:  56%|▌| 102/182 [34:55<27:40, 20.75s/it, Train Acc=99.66%, VaEpoch[103/182] Train Acc: 99.66% Valid Acc:93.46% Train loss:0.0133 Valid loss:0.2926 LR:0.010000000000000002
Training Progress:  57%|▌| 103/182 [34:55<27:16, 20.71s/it, Train Acc=99.66%, VaTraining: Epoch[104/182] Iteration[050/352] Loss: 0.0131 Acc:99.69%
Training: Epoch[104/182] Iteration[100/352] Loss: 0.0124 Acc:99.72%
Training: Epoch[104/182] Iteration[150/352] Loss: 0.0122 Acc:99.70%
Training: Epoch[104/182] Iteration[200/352] Loss: 0.0123 Acc:99.71%
Training: Epoch[104/182] Iteration[250/352] Loss: 0.0124 Acc:99.70%
Training: Epoch[104/182] Iteration[300/352] Loss: 0.0125 Acc:99.68%
Training: Epoch[104/182] Iteration[350/352] Loss: 0.0128 Acc:99.68%
Training Progress:  57%|▌| 103/182 [35:16<27:16, 20.71s/it, Train Acc=99.68%, VaEpoch[104/182] Train Acc: 99.68% Valid Acc:93.58% Train loss:0.0127 Valid loss:0.2959 LR:0.010000000000000002
Training Progress:  57%|▌| 104/182 [35:16<26:47, 20.61s/it, Train Acc=99.68%, VaTraining: Epoch[105/182] Iteration[050/352] Loss: 0.0129 Acc:99.64%
Training: Epoch[105/182] Iteration[100/352] Loss: 0.0128 Acc:99.66%
Training: Epoch[105/182] Iteration[150/352] Loss: 0.0128 Acc:99.67%
Training: Epoch[105/182] Iteration[200/352] Loss: 0.0126 Acc:99.68%
Training: Epoch[105/182] Iteration[250/352] Loss: 0.0122 Acc:99.69%
Training: Epoch[105/182] Iteration[300/352] Loss: 0.0118 Acc:99.70%
Training: Epoch[105/182] Iteration[350/352] Loss: 0.0119 Acc:99.70%
Training Progress:  57%|▌| 104/182 [35:36<26:47, 20.61s/it, Train Acc=99.70%, VaEpoch[105/182] Train Acc: 99.70% Valid Acc:93.46% Train loss:0.0120 Valid loss:0.3008 LR:0.010000000000000002
Training Progress:  58%|▌| 105/182 [35:36<26:21, 20.54s/it, Train Acc=99.70%, VaTraining: Epoch[106/182] Iteration[050/352] Loss: 0.0097 Acc:99.72%
Training: Epoch[106/182] Iteration[100/352] Loss: 0.0106 Acc:99.73%
Training: Epoch[106/182] Iteration[150/352] Loss: 0.0108 Acc:99.73%
Training: Epoch[106/182] Iteration[200/352] Loss: 0.0107 Acc:99.74%
Training: Epoch[106/182] Iteration[250/352] Loss: 0.0107 Acc:99.74%
Training: Epoch[106/182] Iteration[300/352] Loss: 0.0107 Acc:99.74%
Training: Epoch[106/182] Iteration[350/352] Loss: 0.0106 Acc:99.75%
Training Progress:  58%|▌| 105/182 [35:56<26:21, 20.54s/it, Train Acc=99.75%, VaEpoch[106/182] Train Acc: 99.75% Valid Acc:93.62% Train loss:0.0106 Valid loss:0.3036 LR:0.010000000000000002
Training Progress:  58%|▌| 106/182 [35:57<25:58, 20.51s/it, Train Acc=99.75%, VaTraining: Epoch[107/182] Iteration[050/352] Loss: 0.0097 Acc:99.77%
Training: Epoch[107/182] Iteration[100/352] Loss: 0.0096 Acc:99.75%
Training: Epoch[107/182] Iteration[150/352] Loss: 0.0100 Acc:99.74%
Training: Epoch[107/182] Iteration[200/352] Loss: 0.0101 Acc:99.73%
Training: Epoch[107/182] Iteration[250/352] Loss: 0.0101 Acc:99.73%
Training: Epoch[107/182] Iteration[300/352] Loss: 0.0100 Acc:99.74%
Training: Epoch[107/182] Iteration[350/352] Loss: 0.0100 Acc:99.73%
Training Progress:  58%|▌| 106/182 [36:17<25:58, 20.51s/it, Train Acc=99.74%, VaEpoch[107/182] Train Acc: 99.74% Valid Acc:93.48% Train loss:0.0100 Valid loss:0.2996 LR:0.010000000000000002
Training Progress:  59%|▌| 107/182 [36:17<25:34, 20.47s/it, Train Acc=99.74%, VaTraining: Epoch[108/182] Iteration[050/352] Loss: 0.0099 Acc:99.75%
Training: Epoch[108/182] Iteration[100/352] Loss: 0.0104 Acc:99.74%
Training: Epoch[108/182] Iteration[150/352] Loss: 0.0102 Acc:99.74%
Training: Epoch[108/182] Iteration[200/352] Loss: 0.0105 Acc:99.71%
Training: Epoch[108/182] Iteration[250/352] Loss: 0.0103 Acc:99.74%
Training: Epoch[108/182] Iteration[300/352] Loss: 0.0106 Acc:99.73%
Training: Epoch[108/182] Iteration[350/352] Loss: 0.0107 Acc:99.73%
Training Progress:  59%|▌| 107/182 [36:37<25:34, 20.47s/it, Train Acc=99.74%, VaEpoch[108/182] Train Acc: 99.74% Valid Acc:93.56% Train loss:0.0106 Valid loss:0.3012 LR:0.010000000000000002
Training Progress:  59%|▌| 108/182 [36:37<25:15, 20.47s/it, Train Acc=99.74%, VaTraining: Epoch[109/182] Iteration[050/352] Loss: 0.0078 Acc:99.86%
Training: Epoch[109/182] Iteration[100/352] Loss: 0.0087 Acc:99.81%
Training: Epoch[109/182] Iteration[150/352] Loss: 0.0093 Acc:99.77%
Training: Epoch[109/182] Iteration[200/352] Loss: 0.0096 Acc:99.74%
Training: Epoch[109/182] Iteration[250/352] Loss: 0.0099 Acc:99.75%
Training: Epoch[109/182] Iteration[300/352] Loss: 0.0098 Acc:99.76%
Training: Epoch[109/182] Iteration[350/352] Loss: 0.0097 Acc:99.76%
Training Progress:  59%|▌| 108/182 [36:58<25:15, 20.47s/it, Train Acc=99.76%, VaEpoch[109/182] Train Acc: 99.76% Valid Acc:93.56% Train loss:0.0097 Valid loss:0.2991 LR:0.010000000000000002
Training Progress:  60%|▌| 109/182 [36:58<24:51, 20.43s/it, Train Acc=99.76%, VaTraining: Epoch[110/182] Iteration[050/352] Loss: 0.0098 Acc:99.77%
Training: Epoch[110/182] Iteration[100/352] Loss: 0.0092 Acc:99.80%
Training: Epoch[110/182] Iteration[150/352] Loss: 0.0091 Acc:99.79%
Training: Epoch[110/182] Iteration[200/352] Loss: 0.0093 Acc:99.79%
Training: Epoch[110/182] Iteration[250/352] Loss: 0.0095 Acc:99.78%
Training: Epoch[110/182] Iteration[300/352] Loss: 0.0092 Acc:99.78%
Training: Epoch[110/182] Iteration[350/352] Loss: 0.0092 Acc:99.78%
Training Progress:  60%|▌| 109/182 [37:18<24:51, 20.43s/it, Train Acc=99.78%, VaEpoch[110/182] Train Acc: 99.78% Valid Acc:93.62% Train loss:0.0092 Valid loss:0.3089 LR:0.010000000000000002
Training Progress:  60%|▌| 110/182 [37:18<24:29, 20.40s/it, Train Acc=99.78%, VaTraining: Epoch[111/182] Iteration[050/352] Loss: 0.0095 Acc:99.77%
Training: Epoch[111/182] Iteration[100/352] Loss: 0.0080 Acc:99.83%
Training: Epoch[111/182] Iteration[150/352] Loss: 0.0078 Acc:99.83%
Training: Epoch[111/182] Iteration[200/352] Loss: 0.0077 Acc:99.84%
Training: Epoch[111/182] Iteration[250/352] Loss: 0.0081 Acc:99.82%
Training: Epoch[111/182] Iteration[300/352] Loss: 0.0080 Acc:99.82%
Training: Epoch[111/182] Iteration[350/352] Loss: 0.0082 Acc:99.82%
Training Progress:  60%|▌| 110/182 [37:38<24:29, 20.40s/it, Train Acc=99.82%, VaEpoch[111/182] Train Acc: 99.82% Valid Acc:93.66% Train loss:0.0083 Valid loss:0.3110 LR:0.010000000000000002
Training Progress:  61%|▌| 111/182 [37:38<24:08, 20.40s/it, Train Acc=99.82%, VaTraining: Epoch[112/182] Iteration[050/352] Loss: 0.0089 Acc:99.81%
Training: Epoch[112/182] Iteration[100/352] Loss: 0.0081 Acc:99.84%
Training: Epoch[112/182] Iteration[150/352] Loss: 0.0083 Acc:99.82%
Training: Epoch[112/182] Iteration[200/352] Loss: 0.0083 Acc:99.80%
Training: Epoch[112/182] Iteration[250/352] Loss: 0.0082 Acc:99.80%
Training: Epoch[112/182] Iteration[300/352] Loss: 0.0083 Acc:99.78%
Training: Epoch[112/182] Iteration[350/352] Loss: 0.0086 Acc:99.77%
Training Progress:  61%|▌| 111/182 [37:59<24:08, 20.40s/it, Train Acc=99.77%, VaEpoch[112/182] Train Acc: 99.77% Valid Acc:93.36% Train loss:0.0086 Valid loss:0.3239 LR:0.010000000000000002
Training Progress:  62%|▌| 112/182 [37:59<23:49, 20.42s/it, Train Acc=99.77%, VaTraining: Epoch[113/182] Iteration[050/352] Loss: 0.0065 Acc:99.92%
Training: Epoch[113/182] Iteration[100/352] Loss: 0.0068 Acc:99.89%
Training: Epoch[113/182] Iteration[150/352] Loss: 0.0069 Acc:99.86%
Training: Epoch[113/182] Iteration[200/352] Loss: 0.0073 Acc:99.84%
Training: Epoch[113/182] Iteration[250/352] Loss: 0.0074 Acc:99.84%
Training: Epoch[113/182] Iteration[300/352] Loss: 0.0077 Acc:99.83%
Training: Epoch[113/182] Iteration[350/352] Loss: 0.0077 Acc:99.82%
Training Progress:  62%|▌| 112/182 [38:19<23:49, 20.42s/it, Train Acc=99.82%, VaEpoch[113/182] Train Acc: 99.82% Valid Acc:93.64% Train loss:0.0077 Valid loss:0.3151 LR:0.010000000000000002
Training Progress:  62%|▌| 113/182 [38:19<23:26, 20.39s/it, Train Acc=99.82%, VaTraining: Epoch[114/182] Iteration[050/352] Loss: 0.0067 Acc:99.84%
Training: Epoch[114/182] Iteration[100/352] Loss: 0.0065 Acc:99.87%
Training: Epoch[114/182] Iteration[150/352] Loss: 0.0064 Acc:99.88%
Training: Epoch[114/182] Iteration[200/352] Loss: 0.0069 Acc:99.84%
Training: Epoch[114/182] Iteration[250/352] Loss: 0.0072 Acc:99.82%
Training: Epoch[114/182] Iteration[300/352] Loss: 0.0073 Acc:99.81%
Training: Epoch[114/182] Iteration[350/352] Loss: 0.0075 Acc:99.81%
Training Progress:  62%|▌| 113/182 [38:40<23:26, 20.39s/it, Train Acc=99.81%, VaEpoch[114/182] Train Acc: 99.81% Valid Acc:93.64% Train loss:0.0074 Valid loss:0.3172 LR:0.010000000000000002
Training Progress:  63%|▋| 114/182 [38:40<23:06, 20.38s/it, Train Acc=99.81%, VaTraining: Epoch[115/182] Iteration[050/352] Loss: 0.0074 Acc:99.84%
Training: Epoch[115/182] Iteration[100/352] Loss: 0.0069 Acc:99.87%
Training: Epoch[115/182] Iteration[150/352] Loss: 0.0067 Acc:99.87%
Training: Epoch[115/182] Iteration[200/352] Loss: 0.0068 Acc:99.86%
Training: Epoch[115/182] Iteration[250/352] Loss: 0.0069 Acc:99.86%
Training: Epoch[115/182] Iteration[300/352] Loss: 0.0070 Acc:99.85%
Training: Epoch[115/182] Iteration[350/352] Loss: 0.0069 Acc:99.85%
Training Progress:  63%|▋| 114/182 [39:00<23:06, 20.38s/it, Train Acc=99.85%, VaEpoch[115/182] Train Acc: 99.85% Valid Acc:93.68% Train loss:0.0069 Valid loss:0.3173 LR:0.010000000000000002
Training Progress:  63%|▋| 115/182 [39:00<22:46, 20.39s/it, Train Acc=99.85%, VaTraining: Epoch[116/182] Iteration[050/352] Loss: 0.0057 Acc:99.94%
Training: Epoch[116/182] Iteration[100/352] Loss: 0.0058 Acc:99.92%
Training: Epoch[116/182] Iteration[150/352] Loss: 0.0059 Acc:99.91%
Training: Epoch[116/182] Iteration[200/352] Loss: 0.0060 Acc:99.90%
Training: Epoch[116/182] Iteration[250/352] Loss: 0.0062 Acc:99.89%
Training: Epoch[116/182] Iteration[300/352] Loss: 0.0064 Acc:99.87%
Training: Epoch[116/182] Iteration[350/352] Loss: 0.0069 Acc:99.85%
Training Progress:  63%|▋| 115/182 [39:20<22:46, 20.39s/it, Train Acc=99.85%, VaEpoch[116/182] Train Acc: 99.85% Valid Acc:93.68% Train loss:0.0069 Valid loss:0.3269 LR:0.010000000000000002
Training Progress:  64%|▋| 116/182 [39:20<22:25, 20.38s/it, Train Acc=99.85%, VaTraining: Epoch[117/182] Iteration[050/352] Loss: 0.0074 Acc:99.81%
Training: Epoch[117/182] Iteration[100/352] Loss: 0.0074 Acc:99.80%
Training: Epoch[117/182] Iteration[150/352] Loss: 0.0070 Acc:99.84%
Training: Epoch[117/182] Iteration[200/352] Loss: 0.0066 Acc:99.85%
Training: Epoch[117/182] Iteration[250/352] Loss: 0.0067 Acc:99.84%
Training: Epoch[117/182] Iteration[300/352] Loss: 0.0065 Acc:99.86%
Training: Epoch[117/182] Iteration[350/352] Loss: 0.0066 Acc:99.86%
Training Progress:  64%|▋| 116/182 [39:41<22:25, 20.38s/it, Train Acc=99.85%, VaEpoch[117/182] Train Acc: 99.85% Valid Acc:93.40% Train loss:0.0067 Valid loss:0.3230 LR:0.010000000000000002
Training Progress:  64%|▋| 117/182 [39:41<22:04, 20.37s/it, Train Acc=99.85%, VaTraining: Epoch[118/182] Iteration[050/352] Loss: 0.0066 Acc:99.88%
Training: Epoch[118/182] Iteration[100/352] Loss: 0.0065 Acc:99.87%
Training: Epoch[118/182] Iteration[150/352] Loss: 0.0071 Acc:99.86%
Training: Epoch[118/182] Iteration[200/352] Loss: 0.0073 Acc:99.84%
Training: Epoch[118/182] Iteration[250/352] Loss: 0.0077 Acc:99.82%
Training: Epoch[118/182] Iteration[300/352] Loss: 0.0076 Acc:99.81%
Training: Epoch[118/182] Iteration[350/352] Loss: 0.0076 Acc:99.81%
Training Progress:  64%|▋| 117/182 [40:01<22:04, 20.37s/it, Train Acc=99.81%, VaEpoch[118/182] Train Acc: 99.81% Valid Acc:93.54% Train loss:0.0075 Valid loss:0.3205 LR:0.010000000000000002
Training Progress:  65%|▋| 118/182 [40:01<21:42, 20.35s/it, Train Acc=99.81%, VaTraining: Epoch[119/182] Iteration[050/352] Loss: 0.0068 Acc:99.84%
Training: Epoch[119/182] Iteration[100/352] Loss: 0.0067 Acc:99.84%
Training: Epoch[119/182] Iteration[150/352] Loss: 0.0067 Acc:99.85%
Training: Epoch[119/182] Iteration[200/352] Loss: 0.0066 Acc:99.85%
Training: Epoch[119/182] Iteration[250/352] Loss: 0.0065 Acc:99.84%
Training: Epoch[119/182] Iteration[300/352] Loss: 0.0067 Acc:99.84%
Training: Epoch[119/182] Iteration[350/352] Loss: 0.0066 Acc:99.85%
Training Progress:  65%|▋| 118/182 [40:21<21:42, 20.35s/it, Train Acc=99.85%, VaEpoch[119/182] Train Acc: 99.85% Valid Acc:93.38% Train loss:0.0066 Valid loss:0.3250 LR:0.010000000000000002
Training Progress:  65%|▋| 119/182 [40:21<21:21, 20.34s/it, Train Acc=99.85%, VaTraining: Epoch[120/182] Iteration[050/352] Loss: 0.0068 Acc:99.83%
Training: Epoch[120/182] Iteration[100/352] Loss: 0.0067 Acc:99.84%
Training: Epoch[120/182] Iteration[150/352] Loss: 0.0066 Acc:99.84%
Training: Epoch[120/182] Iteration[200/352] Loss: 0.0066 Acc:99.85%
Training: Epoch[120/182] Iteration[250/352] Loss: 0.0069 Acc:99.84%
Training: Epoch[120/182] Iteration[300/352] Loss: 0.0069 Acc:99.83%
Training: Epoch[120/182] Iteration[350/352] Loss: 0.0068 Acc:99.83%
Training Progress:  65%|▋| 119/182 [40:42<21:21, 20.34s/it, Train Acc=99.83%, VaEpoch[120/182] Train Acc: 99.83% Valid Acc:93.68% Train loss:0.0068 Valid loss:0.3206 LR:0.010000000000000002
Training Progress:  66%|▋| 120/182 [40:42<21:00, 20.34s/it, Train Acc=99.83%, VaTraining: Epoch[121/182] Iteration[050/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[121/182] Iteration[100/352] Loss: 0.0054 Acc:99.92%
Training: Epoch[121/182] Iteration[150/352] Loss: 0.0058 Acc:99.90%
Training: Epoch[121/182] Iteration[200/352] Loss: 0.0056 Acc:99.91%
Training: Epoch[121/182] Iteration[250/352] Loss: 0.0055 Acc:99.91%
Training: Epoch[121/182] Iteration[300/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[121/182] Iteration[350/352] Loss: 0.0061 Acc:99.88%
Training Progress:  66%|▋| 120/182 [41:02<21:00, 20.34s/it, Train Acc=99.88%, VaEpoch[121/182] Train Acc: 99.88% Valid Acc:93.72% Train loss:0.0061 Valid loss:0.3269 LR:0.010000000000000002
Training Progress:  66%|▋| 121/182 [41:02<20:43, 20.39s/it, Train Acc=99.88%, VaTraining: Epoch[122/182] Iteration[050/352] Loss: 0.0066 Acc:99.86%
Training: Epoch[122/182] Iteration[100/352] Loss: 0.0063 Acc:99.85%
Training: Epoch[122/182] Iteration[150/352] Loss: 0.0062 Acc:99.85%
Training: Epoch[122/182] Iteration[200/352] Loss: 0.0058 Acc:99.88%
Training: Epoch[122/182] Iteration[250/352] Loss: 0.0059 Acc:99.87%
Training: Epoch[122/182] Iteration[300/352] Loss: 0.0061 Acc:99.86%
Training: Epoch[122/182] Iteration[350/352] Loss: 0.0061 Acc:99.87%
Training Progress:  66%|▋| 121/182 [41:23<20:43, 20.39s/it, Train Acc=99.87%, VaEpoch[122/182] Train Acc: 99.87% Valid Acc:93.62% Train loss:0.0060 Valid loss:0.3253 LR:0.010000000000000002
Training Progress:  67%|▋| 122/182 [41:23<20:22, 20.38s/it, Train Acc=99.87%, VaTraining: Epoch[123/182] Iteration[050/352] Loss: 0.0048 Acc:99.95%
Training: Epoch[123/182] Iteration[100/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[123/182] Iteration[150/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[123/182] Iteration[200/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[123/182] Iteration[250/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[123/182] Iteration[300/352] Loss: 0.0055 Acc:99.88%
Training: Epoch[123/182] Iteration[350/352] Loss: 0.0056 Acc:99.88%
Training Progress:  67%|▋| 122/182 [41:43<20:22, 20.38s/it, Train Acc=99.88%, VaEpoch[123/182] Train Acc: 99.88% Valid Acc:93.64% Train loss:0.0056 Valid loss:0.3223 LR:0.010000000000000002
Training Progress:  68%|▋| 123/182 [41:43<20:01, 20.37s/it, Train Acc=99.88%, VaTraining: Epoch[124/182] Iteration[050/352] Loss: 0.0053 Acc:99.88%
Training: Epoch[124/182] Iteration[100/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[124/182] Iteration[150/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[124/182] Iteration[200/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[124/182] Iteration[250/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[124/182] Iteration[300/352] Loss: 0.0051 Acc:99.90%
Training: Epoch[124/182] Iteration[350/352] Loss: 0.0053 Acc:99.88%
Training Progress:  68%|▋| 123/182 [42:03<20:01, 20.37s/it, Train Acc=99.88%, VaEpoch[124/182] Train Acc: 99.88% Valid Acc:93.76% Train loss:0.0053 Valid loss:0.3325 LR:0.010000000000000002
Training Progress:  68%|▋| 124/182 [42:03<19:41, 20.37s/it, Train Acc=99.88%, VaTraining: Epoch[125/182] Iteration[050/352] Loss: 0.0040 Acc:99.97%
Training: Epoch[125/182] Iteration[100/352] Loss: 0.0042 Acc:99.97%
Training: Epoch[125/182] Iteration[150/352] Loss: 0.0047 Acc:99.94%
Training: Epoch[125/182] Iteration[200/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[125/182] Iteration[250/352] Loss: 0.0054 Acc:99.90%
Training: Epoch[125/182] Iteration[300/352] Loss: 0.0054 Acc:99.90%
Training: Epoch[125/182] Iteration[350/352] Loss: 0.0053 Acc:99.90%
Training Progress:  68%|▋| 124/182 [42:24<19:41, 20.37s/it, Train Acc=99.90%, VaEpoch[125/182] Train Acc: 99.90% Valid Acc:93.52% Train loss:0.0053 Valid loss:0.3296 LR:0.010000000000000002
Training Progress:  69%|▋| 125/182 [42:24<19:23, 20.41s/it, Train Acc=99.90%, VaTraining: Epoch[126/182] Iteration[050/352] Loss: 0.0055 Acc:99.89%
Training: Epoch[126/182] Iteration[100/352] Loss: 0.0052 Acc:99.88%
Training: Epoch[126/182] Iteration[150/352] Loss: 0.0055 Acc:99.86%
Training: Epoch[126/182] Iteration[200/352] Loss: 0.0054 Acc:99.86%
Training: Epoch[126/182] Iteration[250/352] Loss: 0.0053 Acc:99.88%
Training: Epoch[126/182] Iteration[300/352] Loss: 0.0054 Acc:99.88%
Training: Epoch[126/182] Iteration[350/352] Loss: 0.0055 Acc:99.87%
Training Progress:  69%|▋| 125/182 [42:44<19:23, 20.41s/it, Train Acc=99.87%, VaEpoch[126/182] Train Acc: 99.87% Valid Acc:93.64% Train loss:0.0055 Valid loss:0.3305 LR:0.010000000000000002
Training Progress:  69%|▋| 126/182 [42:44<19:03, 20.43s/it, Train Acc=99.87%, VaTraining: Epoch[127/182] Iteration[050/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[127/182] Iteration[100/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[127/182] Iteration[150/352] Loss: 0.0052 Acc:99.89%
Training: Epoch[127/182] Iteration[200/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[127/182] Iteration[250/352] Loss: 0.0055 Acc:99.88%
Training: Epoch[127/182] Iteration[300/352] Loss: 0.0056 Acc:99.88%
Training: Epoch[127/182] Iteration[350/352] Loss: 0.0054 Acc:99.88%
Training Progress:  69%|▋| 126/182 [43:05<19:03, 20.43s/it, Train Acc=99.88%, VaEpoch[127/182] Train Acc: 99.88% Valid Acc:93.62% Train loss:0.0054 Valid loss:0.3283 LR:0.010000000000000002
Training Progress:  70%|▋| 127/182 [43:05<18:42, 20.40s/it, Train Acc=99.88%, VaTraining: Epoch[128/182] Iteration[050/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[128/182] Iteration[100/352] Loss: 0.0040 Acc:99.95%
Training: Epoch[128/182] Iteration[150/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[128/182] Iteration[200/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[128/182] Iteration[250/352] Loss: 0.0046 Acc:99.92%
Training: Epoch[128/182] Iteration[300/352] Loss: 0.0045 Acc:99.93%
Training: Epoch[128/182] Iteration[350/352] Loss: 0.0045 Acc:99.93%
Training Progress:  70%|▋| 127/182 [43:25<18:42, 20.40s/it, Train Acc=99.93%, VaEpoch[128/182] Train Acc: 99.93% Valid Acc:93.54% Train loss:0.0045 Valid loss:0.3326 LR:0.010000000000000002
Training Progress:  70%|▋| 128/182 [43:25<18:24, 20.45s/it, Train Acc=99.93%, VaTraining: Epoch[129/182] Iteration[050/352] Loss: 0.0065 Acc:99.84%
Training: Epoch[129/182] Iteration[100/352] Loss: 0.0059 Acc:99.87%
Training: Epoch[129/182] Iteration[150/352] Loss: 0.0056 Acc:99.88%
Training: Epoch[129/182] Iteration[200/352] Loss: 0.0053 Acc:99.88%
Training: Epoch[129/182] Iteration[250/352] Loss: 0.0054 Acc:99.87%
Training: Epoch[129/182] Iteration[300/352] Loss: 0.0053 Acc:99.88%
Training: Epoch[129/182] Iteration[350/352] Loss: 0.0054 Acc:99.88%
Training Progress:  70%|▋| 128/182 [43:45<18:24, 20.45s/it, Train Acc=99.88%, VaEpoch[129/182] Train Acc: 99.88% Valid Acc:93.50% Train loss:0.0054 Valid loss:0.3353 LR:0.010000000000000002
Training Progress:  71%|▋| 129/182 [43:45<18:01, 20.40s/it, Train Acc=99.88%, VaTraining: Epoch[130/182] Iteration[050/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[130/182] Iteration[100/352] Loss: 0.0051 Acc:99.90%
Training: Epoch[130/182] Iteration[150/352] Loss: 0.0054 Acc:99.88%
Training: Epoch[130/182] Iteration[200/352] Loss: 0.0053 Acc:99.88%
Training: Epoch[130/182] Iteration[250/352] Loss: 0.0051 Acc:99.88%
Training: Epoch[130/182] Iteration[300/352] Loss: 0.0052 Acc:99.88%
Training: Epoch[130/182] Iteration[350/352] Loss: 0.0052 Acc:99.88%
Training Progress:  71%|▋| 129/182 [44:06<18:01, 20.40s/it, Train Acc=99.88%, VaEpoch[130/182] Train Acc: 99.88% Valid Acc:93.48% Train loss:0.0052 Valid loss:0.3370 LR:0.010000000000000002
Training Progress:  71%|▋| 130/182 [44:06<17:40, 20.40s/it, Train Acc=99.88%, VaTraining: Epoch[131/182] Iteration[050/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[131/182] Iteration[100/352] Loss: 0.0041 Acc:99.92%
Training: Epoch[131/182] Iteration[150/352] Loss: 0.0041 Acc:99.92%
Training: Epoch[131/182] Iteration[200/352] Loss: 0.0041 Acc:99.93%
Training: Epoch[131/182] Iteration[250/352] Loss: 0.0041 Acc:99.93%
Training: Epoch[131/182] Iteration[300/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[131/182] Iteration[350/352] Loss: 0.0043 Acc:99.92%
Training Progress:  71%|▋| 130/182 [44:26<17:40, 20.40s/it, Train Acc=99.92%, VaEpoch[131/182] Train Acc: 99.92% Valid Acc:93.64% Train loss:0.0043 Valid loss:0.3349 LR:0.010000000000000002
Training Progress:  72%|▋| 131/182 [44:26<17:21, 20.41s/it, Train Acc=99.92%, VaTraining: Epoch[132/182] Iteration[050/352] Loss: 0.0049 Acc:99.88%
Training: Epoch[132/182] Iteration[100/352] Loss: 0.0047 Acc:99.90%
Training: Epoch[132/182] Iteration[150/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[132/182] Iteration[200/352] Loss: 0.0049 Acc:99.89%
Training: Epoch[132/182] Iteration[250/352] Loss: 0.0050 Acc:99.90%
Training: Epoch[132/182] Iteration[300/352] Loss: 0.0051 Acc:99.89%
Training: Epoch[132/182] Iteration[350/352] Loss: 0.0053 Acc:99.87%
Training Progress:  72%|▋| 131/182 [44:47<17:21, 20.41s/it, Train Acc=99.87%, VaEpoch[132/182] Train Acc: 99.87% Valid Acc:93.70% Train loss:0.0053 Valid loss:0.3422 LR:0.010000000000000002
Training Progress:  73%|▋| 132/182 [44:47<16:59, 20.39s/it, Train Acc=99.87%, VaTraining: Epoch[133/182] Iteration[050/352] Loss: 0.0050 Acc:99.89%
Training: Epoch[133/182] Iteration[100/352] Loss: 0.0051 Acc:99.88%
Training: Epoch[133/182] Iteration[150/352] Loss: 0.0049 Acc:99.90%
Training: Epoch[133/182] Iteration[200/352] Loss: 0.0049 Acc:99.89%
Training: Epoch[133/182] Iteration[250/352] Loss: 0.0049 Acc:99.90%
Training: Epoch[133/182] Iteration[300/352] Loss: 0.0048 Acc:99.90%
Training: Epoch[133/182] Iteration[350/352] Loss: 0.0049 Acc:99.90%
Training Progress:  73%|▋| 132/182 [45:07<16:59, 20.39s/it, Train Acc=99.90%, VaEpoch[133/182] Train Acc: 99.90% Valid Acc:93.78% Train loss:0.0049 Valid loss:0.3354 LR:0.010000000000000002
Training Progress:  73%|▋| 133/182 [45:07<16:40, 20.41s/it, Train Acc=99.90%, VaTraining: Epoch[134/182] Iteration[050/352] Loss: 0.0046 Acc:99.92%
Training: Epoch[134/182] Iteration[100/352] Loss: 0.0044 Acc:99.95%
Training: Epoch[134/182] Iteration[150/352] Loss: 0.0041 Acc:99.95%
Training: Epoch[134/182] Iteration[200/352] Loss: 0.0039 Acc:99.96%
Training: Epoch[134/182] Iteration[250/352] Loss: 0.0042 Acc:99.94%
Training: Epoch[134/182] Iteration[300/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[134/182] Iteration[350/352] Loss: 0.0044 Acc:99.93%
Training Progress:  73%|▋| 133/182 [45:28<16:40, 20.41s/it, Train Acc=99.93%, VaEpoch[134/182] Train Acc: 99.93% Valid Acc:93.40% Train loss:0.0044 Valid loss:0.3448 LR:0.010000000000000002
Training Progress:  74%|▋| 134/182 [45:28<16:21, 20.45s/it, Train Acc=99.93%, VaTraining: Epoch[135/182] Iteration[050/352] Loss: 0.0046 Acc:99.91%
Training: Epoch[135/182] Iteration[100/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[135/182] Iteration[150/352] Loss: 0.0042 Acc:99.91%
Training: Epoch[135/182] Iteration[200/352] Loss: 0.0042 Acc:99.92%
Training: Epoch[135/182] Iteration[250/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[135/182] Iteration[300/352] Loss: 0.0042 Acc:99.92%
Training: Epoch[135/182] Iteration[350/352] Loss: 0.0041 Acc:99.92%
Training Progress:  74%|▋| 134/182 [45:48<16:21, 20.45s/it, Train Acc=99.92%, VaEpoch[135/182] Train Acc: 99.92% Valid Acc:93.58% Train loss:0.0041 Valid loss:0.3362 LR:0.010000000000000002
Training Progress:  74%|▋| 135/182 [45:48<16:01, 20.45s/it, Train Acc=99.92%, VaTraining: Epoch[136/182] Iteration[050/352] Loss: 0.0042 Acc:99.92%
Training: Epoch[136/182] Iteration[100/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[136/182] Iteration[150/352] Loss: 0.0041 Acc:99.91%
Training: Epoch[136/182] Iteration[200/352] Loss: 0.0043 Acc:99.90%
Training: Epoch[136/182] Iteration[250/352] Loss: 0.0043 Acc:99.90%
Training: Epoch[136/182] Iteration[300/352] Loss: 0.0042 Acc:99.90%
Training: Epoch[136/182] Iteration[350/352] Loss: 0.0042 Acc:99.91%
Training Progress:  74%|▋| 135/182 [46:08<16:01, 20.45s/it, Train Acc=99.91%, VaEpoch[136/182] Train Acc: 99.91% Valid Acc:93.62% Train loss:0.0042 Valid loss:0.3276 LR:0.010000000000000002
Training Progress:  75%|▋| 136/182 [46:08<15:40, 20.44s/it, Train Acc=99.91%, VaTraining: Epoch[137/182] Iteration[050/352] Loss: 0.0035 Acc:99.94%
Training: Epoch[137/182] Iteration[100/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[137/182] Iteration[150/352] Loss: 0.0041 Acc:99.91%
Training: Epoch[137/182] Iteration[200/352] Loss: 0.0041 Acc:99.93%
Training: Epoch[137/182] Iteration[250/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[137/182] Iteration[300/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[137/182] Iteration[350/352] Loss: 0.0039 Acc:99.93%
Training Progress:  75%|▋| 136/182 [46:29<15:40, 20.44s/it, Train Acc=99.93%, VaEpoch[137/182] Train Acc: 99.93% Valid Acc:93.58% Train loss:0.0039 Valid loss:0.3289 LR:0.0010000000000000002
Training Progress:  75%|▊| 137/182 [46:29<15:18, 20.42s/it, Train Acc=99.93%, VaTraining: Epoch[138/182] Iteration[050/352] Loss: 0.0031 Acc:99.98%
Training: Epoch[138/182] Iteration[100/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[138/182] Iteration[150/352] Loss: 0.0037 Acc:99.92%
Training: Epoch[138/182] Iteration[200/352] Loss: 0.0036 Acc:99.93%
Training: Epoch[138/182] Iteration[250/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[138/182] Iteration[300/352] Loss: 0.0038 Acc:99.92%
Training: Epoch[138/182] Iteration[350/352] Loss: 0.0037 Acc:99.93%
Training Progress:  75%|▊| 137/182 [46:49<15:18, 20.42s/it, Train Acc=99.93%, VaEpoch[138/182] Train Acc: 99.93% Valid Acc:93.50% Train loss:0.0037 Valid loss:0.3285 LR:0.0010000000000000002
Training Progress:  76%|▊| 138/182 [46:49<14:58, 20.41s/it, Train Acc=99.93%, VaTraining: Epoch[139/182] Iteration[050/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[139/182] Iteration[100/352] Loss: 0.0039 Acc:99.95%
Training: Epoch[139/182] Iteration[150/352] Loss: 0.0037 Acc:99.96%
Training: Epoch[139/182] Iteration[200/352] Loss: 0.0038 Acc:99.95%
Training: Epoch[139/182] Iteration[250/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[139/182] Iteration[300/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[139/182] Iteration[350/352] Loss: 0.0038 Acc:99.94%
Training Progress:  76%|▊| 138/182 [47:10<14:58, 20.41s/it, Train Acc=99.94%, VaEpoch[139/182] Train Acc: 99.94% Valid Acc:93.50% Train loss:0.0038 Valid loss:0.3283 LR:0.0010000000000000002
Training Progress:  76%|▊| 139/182 [47:10<14:36, 20.39s/it, Train Acc=99.94%, VaTraining: Epoch[140/182] Iteration[050/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[140/182] Iteration[100/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[140/182] Iteration[150/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[140/182] Iteration[200/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[140/182] Iteration[250/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[140/182] Iteration[300/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[140/182] Iteration[350/352] Loss: 0.0034 Acc:99.96%
Training Progress:  76%|▊| 139/182 [47:30<14:36, 20.39s/it, Train Acc=99.96%, VaEpoch[140/182] Train Acc: 99.96% Valid Acc:93.52% Train loss:0.0034 Valid loss:0.3305 LR:0.0010000000000000002
Training Progress:  77%|▊| 140/182 [47:30<14:19, 20.47s/it, Train Acc=99.96%, VaTraining: Epoch[141/182] Iteration[050/352] Loss: 0.0042 Acc:99.94%
Training: Epoch[141/182] Iteration[100/352] Loss: 0.0044 Acc:99.91%
Training: Epoch[141/182] Iteration[150/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[141/182] Iteration[200/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[141/182] Iteration[250/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[141/182] Iteration[300/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[141/182] Iteration[350/352] Loss: 0.0038 Acc:99.93%
Training Progress:  77%|▊| 140/182 [47:51<14:19, 20.47s/it, Train Acc=99.93%, VaEpoch[141/182] Train Acc: 99.93% Valid Acc:93.46% Train loss:0.0038 Valid loss:0.3299 LR:0.0010000000000000002
Training Progress:  77%|▊| 141/182 [47:51<13:59, 20.47s/it, Train Acc=99.93%, VaTraining: Epoch[142/182] Iteration[050/352] Loss: 0.0033 Acc:99.97%
Training: Epoch[142/182] Iteration[100/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[142/182] Iteration[150/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[142/182] Iteration[200/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[142/182] Iteration[250/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[142/182] Iteration[300/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[142/182] Iteration[350/352] Loss: 0.0035 Acc:99.94%
Training Progress:  77%|▊| 141/182 [48:11<13:59, 20.47s/it, Train Acc=99.94%, VaEpoch[142/182] Train Acc: 99.94% Valid Acc:93.54% Train loss:0.0035 Valid loss:0.3285 LR:0.0010000000000000002
Training Progress:  78%|▊| 142/182 [48:11<13:38, 20.47s/it, Train Acc=99.94%, VaTraining: Epoch[143/182] Iteration[050/352] Loss: 0.0041 Acc:99.95%
Training: Epoch[143/182] Iteration[100/352] Loss: 0.0035 Acc:99.96%
Training: Epoch[143/182] Iteration[150/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[143/182] Iteration[200/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[143/182] Iteration[250/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[143/182] Iteration[300/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[143/182] Iteration[350/352] Loss: 0.0038 Acc:99.94%
Training Progress:  78%|▊| 142/182 [48:31<13:38, 20.47s/it, Train Acc=99.94%, VaEpoch[143/182] Train Acc: 99.94% Valid Acc:93.48% Train loss:0.0038 Valid loss:0.3298 LR:0.0010000000000000002
Training Progress:  79%|▊| 143/182 [48:31<13:16, 20.43s/it, Train Acc=99.94%, VaTraining: Epoch[144/182] Iteration[050/352] Loss: 0.0039 Acc:99.92%
Training: Epoch[144/182] Iteration[100/352] Loss: 0.0037 Acc:99.93%
Training: Epoch[144/182] Iteration[150/352] Loss: 0.0041 Acc:99.91%
Training: Epoch[144/182] Iteration[200/352] Loss: 0.0038 Acc:99.92%
Training: Epoch[144/182] Iteration[250/352] Loss: 0.0039 Acc:99.92%
Training: Epoch[144/182] Iteration[300/352] Loss: 0.0037 Acc:99.92%
Training: Epoch[144/182] Iteration[350/352] Loss: 0.0038 Acc:99.92%
Training Progress:  79%|▊| 143/182 [48:52<13:16, 20.43s/it, Train Acc=99.92%, VaEpoch[144/182] Train Acc: 99.92% Valid Acc:93.56% Train loss:0.0037 Valid loss:0.3285 LR:0.0010000000000000002
Training Progress:  79%|▊| 144/182 [48:52<12:56, 20.42s/it, Train Acc=99.92%, VaTraining: Epoch[145/182] Iteration[050/352] Loss: 0.0033 Acc:99.98%
Training: Epoch[145/182] Iteration[100/352] Loss: 0.0033 Acc:99.97%
Training: Epoch[145/182] Iteration[150/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[145/182] Iteration[200/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[145/182] Iteration[250/352] Loss: 0.0037 Acc:99.93%
Training: Epoch[145/182] Iteration[300/352] Loss: 0.0035 Acc:99.93%
Training: Epoch[145/182] Iteration[350/352] Loss: 0.0035 Acc:99.94%
Training Progress:  79%|▊| 144/182 [49:12<12:56, 20.42s/it, Train Acc=99.94%, VaEpoch[145/182] Train Acc: 99.94% Valid Acc:93.60% Train loss:0.0035 Valid loss:0.3292 LR:0.0010000000000000002
Training Progress:  80%|▊| 145/182 [49:12<12:35, 20.41s/it, Train Acc=99.94%, VaTraining: Epoch[146/182] Iteration[050/352] Loss: 0.0040 Acc:99.89%
Training: Epoch[146/182] Iteration[100/352] Loss: 0.0038 Acc:99.91%
Training: Epoch[146/182] Iteration[150/352] Loss: 0.0037 Acc:99.91%
Training: Epoch[146/182] Iteration[200/352] Loss: 0.0036 Acc:99.91%
Training: Epoch[146/182] Iteration[250/352] Loss: 0.0035 Acc:99.93%
Training: Epoch[146/182] Iteration[300/352] Loss: 0.0036 Acc:99.92%
Training: Epoch[146/182] Iteration[350/352] Loss: 0.0036 Acc:99.92%
Training Progress:  80%|▊| 145/182 [49:33<12:35, 20.41s/it, Train Acc=99.92%, VaEpoch[146/182] Train Acc: 99.92% Valid Acc:93.58% Train loss:0.0036 Valid loss:0.3300 LR:0.0010000000000000002
Training Progress:  80%|▊| 146/182 [49:33<12:15, 20.43s/it, Train Acc=99.92%, VaTraining: Epoch[147/182] Iteration[050/352] Loss: 0.0024 Acc:100.00%
Training: Epoch[147/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[147/182] Iteration[150/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[147/182] Iteration[200/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[147/182] Iteration[250/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[147/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[147/182] Iteration[350/352] Loss: 0.0033 Acc:99.95%
Training Progress:  80%|▊| 146/182 [49:53<12:15, 20.43s/it, Train Acc=99.95%, VaEpoch[147/182] Train Acc: 99.95% Valid Acc:93.38% Train loss:0.0033 Valid loss:0.3313 LR:0.0010000000000000002
Training Progress:  81%|▊| 147/182 [49:53<11:54, 20.43s/it, Train Acc=99.95%, VaTraining: Epoch[148/182] Iteration[050/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[148/182] Iteration[100/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[148/182] Iteration[150/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[148/182] Iteration[200/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[148/182] Iteration[250/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[148/182] Iteration[300/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[148/182] Iteration[350/352] Loss: 0.0033 Acc:99.95%
Training Progress:  81%|▊| 147/182 [50:13<11:54, 20.43s/it, Train Acc=99.95%, VaEpoch[148/182] Train Acc: 99.95% Valid Acc:93.42% Train loss:0.0034 Valid loss:0.3297 LR:0.0010000000000000002
Training Progress:  81%|▊| 148/182 [50:13<11:33, 20.39s/it, Train Acc=99.95%, VaTraining: Epoch[149/182] Iteration[050/352] Loss: 0.0021 Acc:100.00%
Training: Epoch[149/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[149/182] Iteration[150/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[149/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[149/182] Iteration[250/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[149/182] Iteration[300/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[149/182] Iteration[350/352] Loss: 0.0035 Acc:99.94%
Training Progress:  81%|▊| 148/182 [50:34<11:33, 20.39s/it, Train Acc=99.94%, VaEpoch[149/182] Train Acc: 99.94% Valid Acc:93.56% Train loss:0.0035 Valid loss:0.3299 LR:0.0010000000000000002
Training Progress:  82%|▊| 149/182 [50:34<11:12, 20.39s/it, Train Acc=99.94%, VaTraining: Epoch[150/182] Iteration[050/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[150/182] Iteration[100/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[150/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[150/182] Iteration[200/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[150/182] Iteration[250/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[150/182] Iteration[300/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[150/182] Iteration[350/352] Loss: 0.0032 Acc:99.95%
Training Progress:  82%|▊| 149/182 [50:54<11:12, 20.39s/it, Train Acc=99.95%, VaEpoch[150/182] Train Acc: 99.95% Valid Acc:93.54% Train loss:0.0032 Valid loss:0.3304 LR:0.0010000000000000002
Training Progress:  82%|▊| 150/182 [50:54<10:52, 20.38s/it, Train Acc=99.95%, VaTraining: Epoch[151/182] Iteration[050/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[151/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[151/182] Iteration[150/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[151/182] Iteration[200/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[151/182] Iteration[250/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[151/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[151/182] Iteration[350/352] Loss: 0.0033 Acc:99.96%
Training Progress:  82%|▊| 150/182 [51:15<10:52, 20.38s/it, Train Acc=99.96%, VaEpoch[151/182] Train Acc: 99.96% Valid Acc:93.48% Train loss:0.0032 Valid loss:0.3288 LR:0.0010000000000000002
Training Progress:  83%|▊| 151/182 [51:15<10:31, 20.37s/it, Train Acc=99.96%, VaTraining: Epoch[152/182] Iteration[050/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[152/182] Iteration[100/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[152/182] Iteration[150/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[152/182] Iteration[200/352] Loss: 0.0035 Acc:99.96%
Training: Epoch[152/182] Iteration[250/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[152/182] Iteration[300/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[152/182] Iteration[350/352] Loss: 0.0033 Acc:99.96%
Training Progress:  83%|▊| 151/182 [51:35<10:31, 20.37s/it, Train Acc=99.96%, VaEpoch[152/182] Train Acc: 99.96% Valid Acc:93.60% Train loss:0.0033 Valid loss:0.3290 LR:0.0010000000000000002
Training Progress:  84%|▊| 152/182 [51:35<10:12, 20.40s/it, Train Acc=99.96%, VaTraining: Epoch[153/182] Iteration[050/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[153/182] Iteration[100/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[153/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[153/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[153/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[153/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[153/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  84%|▊| 152/182 [51:55<10:12, 20.40s/it, Train Acc=99.96%, VaEpoch[153/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0030 Valid loss:0.3337 LR:0.0010000000000000002
Training Progress:  84%|▊| 153/182 [51:55<09:51, 20.40s/it, Train Acc=99.96%, VaTraining: Epoch[154/182] Iteration[050/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[154/182] Iteration[100/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[154/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[154/182] Iteration[200/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[154/182] Iteration[250/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[154/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[154/182] Iteration[350/352] Loss: 0.0032 Acc:99.94%
Training Progress:  84%|▊| 153/182 [52:16<09:51, 20.40s/it, Train Acc=99.94%, VaEpoch[154/182] Train Acc: 99.94% Valid Acc:93.58% Train loss:0.0031 Valid loss:0.3289 LR:0.0010000000000000002
Training Progress:  85%|▊| 154/182 [52:16<09:31, 20.40s/it, Train Acc=99.94%, VaTraining: Epoch[155/182] Iteration[050/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[155/182] Iteration[100/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[155/182] Iteration[150/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[155/182] Iteration[200/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[155/182] Iteration[250/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[155/182] Iteration[300/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[155/182] Iteration[350/352] Loss: 0.0035 Acc:99.95%
Training Progress:  85%|▊| 154/182 [52:36<09:31, 20.40s/it, Train Acc=99.95%, VaEpoch[155/182] Train Acc: 99.95% Valid Acc:93.56% Train loss:0.0035 Valid loss:0.3328 LR:0.0010000000000000002
Training Progress:  85%|▊| 155/182 [52:36<09:11, 20.43s/it, Train Acc=99.95%, VaTraining: Epoch[156/182] Iteration[050/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[156/182] Iteration[100/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[156/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[156/182] Iteration[200/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[156/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[156/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[156/182] Iteration[350/352] Loss: 0.0030 Acc:99.97%
Training Progress:  85%|▊| 155/182 [52:57<09:11, 20.43s/it, Train Acc=99.97%, VaEpoch[156/182] Train Acc: 99.97% Valid Acc:93.52% Train loss:0.0030 Valid loss:0.3315 LR:0.0010000000000000002
Training Progress:  86%|▊| 156/182 [52:57<08:52, 20.46s/it, Train Acc=99.97%, VaTraining: Epoch[157/182] Iteration[050/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[157/182] Iteration[100/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[157/182] Iteration[150/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[157/182] Iteration[200/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[157/182] Iteration[250/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[157/182] Iteration[300/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[157/182] Iteration[350/352] Loss: 0.0032 Acc:99.96%
Training Progress:  86%|▊| 156/182 [53:17<08:52, 20.46s/it, Train Acc=99.96%, VaEpoch[157/182] Train Acc: 99.96% Valid Acc:93.46% Train loss:0.0032 Valid loss:0.3315 LR:0.0010000000000000002
Training Progress:  86%|▊| 157/182 [53:17<08:31, 20.47s/it, Train Acc=99.96%, VaTraining: Epoch[158/182] Iteration[050/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[158/182] Iteration[100/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[158/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[158/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[158/182] Iteration[250/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[158/182] Iteration[300/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[158/182] Iteration[350/352] Loss: 0.0032 Acc:99.95%
Training Progress:  86%|▊| 157/182 [53:38<08:31, 20.47s/it, Train Acc=99.95%, VaEpoch[158/182] Train Acc: 99.95% Valid Acc:93.56% Train loss:0.0032 Valid loss:0.3325 LR:0.0010000000000000002
Training Progress:  87%|▊| 158/182 [53:38<08:11, 20.47s/it, Train Acc=99.95%, VaTraining: Epoch[159/182] Iteration[050/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[159/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[159/182] Iteration[150/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[159/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[159/182] Iteration[250/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[159/182] Iteration[300/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[159/182] Iteration[350/352] Loss: 0.0030 Acc:99.97%
Training Progress:  87%|▊| 158/182 [53:59<08:11, 20.47s/it, Train Acc=99.96%, VaEpoch[159/182] Train Acc: 99.96% Valid Acc:93.56% Train loss:0.0030 Valid loss:0.3318 LR:0.0010000000000000002
Training Progress:  87%|▊| 159/182 [53:59<07:52, 20.55s/it, Train Acc=99.96%, VaTraining: Epoch[160/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[160/182] Iteration[100/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[160/182] Iteration[150/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[160/182] Iteration[200/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[160/182] Iteration[250/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[160/182] Iteration[300/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[160/182] Iteration[350/352] Loss: 0.0031 Acc:99.95%
Training Progress:  87%|▊| 159/182 [54:19<07:52, 20.55s/it, Train Acc=99.95%, VaEpoch[160/182] Train Acc: 99.95% Valid Acc:93.58% Train loss:0.0031 Valid loss:0.3297 LR:0.0010000000000000002
Training Progress:  88%|▉| 160/182 [54:19<07:31, 20.51s/it, Train Acc=99.95%, VaTraining: Epoch[161/182] Iteration[050/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[161/182] Iteration[100/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[161/182] Iteration[150/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[161/182] Iteration[200/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[161/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[161/182] Iteration[300/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[161/182] Iteration[350/352] Loss: 0.0032 Acc:99.96%
Training Progress:  88%|▉| 160/182 [54:39<07:31, 20.51s/it, Train Acc=99.96%, VaEpoch[161/182] Train Acc: 99.96% Valid Acc:93.64% Train loss:0.0032 Valid loss:0.3287 LR:0.0010000000000000002
Training Progress:  88%|▉| 161/182 [54:39<07:09, 20.46s/it, Train Acc=99.96%, VaTraining: Epoch[162/182] Iteration[050/352] Loss: 0.0035 Acc:99.91%
Training: Epoch[162/182] Iteration[100/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[162/182] Iteration[150/352] Loss: 0.0032 Acc:99.93%
Training: Epoch[162/182] Iteration[200/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[162/182] Iteration[250/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[162/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[162/182] Iteration[350/352] Loss: 0.0032 Acc:99.94%
Training Progress:  88%|▉| 161/182 [55:00<07:09, 20.46s/it, Train Acc=99.94%, VaEpoch[162/182] Train Acc: 99.94% Valid Acc:93.68% Train loss:0.0032 Valid loss:0.3301 LR:0.0010000000000000002
Training Progress:  89%|▉| 162/182 [55:00<06:48, 20.44s/it, Train Acc=99.94%, VaTraining: Epoch[163/182] Iteration[050/352] Loss: 0.0040 Acc:99.91%
Training: Epoch[163/182] Iteration[100/352] Loss: 0.0036 Acc:99.93%
Training: Epoch[163/182] Iteration[150/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[163/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[163/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[163/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[163/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  89%|▉| 162/182 [55:20<06:48, 20.44s/it, Train Acc=99.97%, VaEpoch[163/182] Train Acc: 99.97% Valid Acc:93.80% Train loss:0.0029 Valid loss:0.3307 LR:0.0010000000000000002
Training Progress:  90%|▉| 163/182 [55:20<06:28, 20.47s/it, Train Acc=99.97%, VaTraining: Epoch[164/182] Iteration[050/352] Loss: 0.0026 Acc:100.00%
Training: Epoch[164/182] Iteration[100/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[164/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[164/182] Iteration[200/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[164/182] Iteration[250/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[164/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[164/182] Iteration[350/352] Loss: 0.0031 Acc:99.95%
Training Progress:  90%|▉| 163/182 [55:41<06:28, 20.47s/it, Train Acc=99.95%, VaEpoch[164/182] Train Acc: 99.95% Valid Acc:93.62% Train loss:0.0031 Valid loss:0.3297 LR:0.0010000000000000002
Training Progress:  90%|▉| 164/182 [55:41<06:08, 20.45s/it, Train Acc=99.95%, VaTraining: Epoch[165/182] Iteration[050/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[165/182] Iteration[100/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[165/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[165/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[165/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[165/182] Iteration[300/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[165/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  90%|▉| 164/182 [56:01<06:08, 20.45s/it, Train Acc=99.96%, VaEpoch[165/182] Train Acc: 99.96% Valid Acc:93.58% Train loss:0.0030 Valid loss:0.3320 LR:0.0010000000000000002
Training Progress:  91%|▉| 165/182 [56:01<05:47, 20.43s/it, Train Acc=99.96%, VaTraining: Epoch[166/182] Iteration[050/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[166/182] Iteration[100/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[166/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[166/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[166/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[166/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[166/182] Iteration[350/352] Loss: 0.0028 Acc:99.97%
Training Progress:  91%|▉| 165/182 [56:21<05:47, 20.43s/it, Train Acc=99.97%, VaEpoch[166/182] Train Acc: 99.97% Valid Acc:93.58% Train loss:0.0028 Valid loss:0.3291 LR:0.0010000000000000002
Training Progress:  91%|▉| 166/182 [56:21<05:26, 20.43s/it, Train Acc=99.97%, VaTraining: Epoch[167/182] Iteration[050/352] Loss: 0.0024 Acc:99.95%
Training: Epoch[167/182] Iteration[100/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[167/182] Iteration[150/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[167/182] Iteration[200/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[167/182] Iteration[250/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[167/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[167/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  91%|▉| 166/182 [56:42<05:26, 20.43s/it, Train Acc=99.96%, VaEpoch[167/182] Train Acc: 99.96% Valid Acc:93.66% Train loss:0.0029 Valid loss:0.3313 LR:0.0010000000000000002
Training Progress:  92%|▉| 167/182 [56:42<05:06, 20.43s/it, Train Acc=99.96%, VaTraining: Epoch[168/182] Iteration[050/352] Loss: 0.0041 Acc:99.91%
Training: Epoch[168/182] Iteration[100/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[168/182] Iteration[150/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[168/182] Iteration[200/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[168/182] Iteration[250/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[168/182] Iteration[300/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[168/182] Iteration[350/352] Loss: 0.0033 Acc:99.96%
Training Progress:  92%|▉| 167/182 [57:02<05:06, 20.43s/it, Train Acc=99.96%, VaEpoch[168/182] Train Acc: 99.96% Valid Acc:93.58% Train loss:0.0033 Valid loss:0.3305 LR:0.0010000000000000002
Training Progress:  92%|▉| 168/182 [57:02<04:45, 20.41s/it, Train Acc=99.96%, VaTraining: Epoch[169/182] Iteration[050/352] Loss: 0.0024 Acc:99.95%
Training: Epoch[169/182] Iteration[100/352] Loss: 0.0029 Acc:99.94%
Training: Epoch[169/182] Iteration[150/352] Loss: 0.0029 Acc:99.94%
Training: Epoch[169/182] Iteration[200/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[169/182] Iteration[250/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[169/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[169/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  92%|▉| 168/182 [57:23<04:45, 20.41s/it, Train Acc=99.96%, VaEpoch[169/182] Train Acc: 99.96% Valid Acc:93.52% Train loss:0.0028 Valid loss:0.3308 LR:0.0010000000000000002
Training Progress:  93%|▉| 169/182 [57:23<04:25, 20.39s/it, Train Acc=99.96%, VaTraining: Epoch[170/182] Iteration[050/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[170/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[170/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[170/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[170/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[170/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[170/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  93%|▉| 169/182 [57:43<04:25, 20.39s/it, Train Acc=99.96%, VaEpoch[170/182] Train Acc: 99.96% Valid Acc:93.66% Train loss:0.0029 Valid loss:0.3336 LR:0.0010000000000000002
Training Progress:  93%|▉| 170/182 [57:43<04:04, 20.37s/it, Train Acc=99.96%, VaTraining: Epoch[171/182] Iteration[050/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[171/182] Iteration[100/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[171/182] Iteration[150/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[171/182] Iteration[200/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[171/182] Iteration[250/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[171/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[171/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  93%|▉| 170/182 [58:03<04:04, 20.37s/it, Train Acc=99.96%, VaEpoch[171/182] Train Acc: 99.96% Valid Acc:93.66% Train loss:0.0029 Valid loss:0.3300 LR:0.0010000000000000002
Training Progress:  94%|▉| 171/182 [58:03<03:44, 20.43s/it, Train Acc=99.96%, VaTraining: Epoch[172/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[172/182] Iteration[100/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[172/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[172/182] Iteration[200/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[172/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[172/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[172/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  94%|▉| 171/182 [58:24<03:44, 20.43s/it, Train Acc=99.97%, VaEpoch[172/182] Train Acc: 99.97% Valid Acc:93.66% Train loss:0.0029 Valid loss:0.3321 LR:0.0010000000000000002
Training Progress:  95%|▉| 172/182 [58:24<03:24, 20.42s/it, Train Acc=99.97%, VaTraining: Epoch[173/182] Iteration[050/352] Loss: 0.0034 Acc:99.98%
Training: Epoch[173/182] Iteration[100/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[173/182] Iteration[150/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[173/182] Iteration[200/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[173/182] Iteration[250/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[173/182] Iteration[300/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[173/182] Iteration[350/352] Loss: 0.0031 Acc:99.97%
Training Progress:  95%|▉| 172/182 [58:44<03:24, 20.42s/it, Train Acc=99.97%, VaEpoch[173/182] Train Acc: 99.97% Valid Acc:93.68% Train loss:0.0030 Valid loss:0.3332 LR:0.0010000000000000002
Training Progress:  95%|▉| 173/182 [58:44<03:03, 20.39s/it, Train Acc=99.97%, VaTraining: Epoch[174/182] Iteration[050/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[174/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[174/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[174/182] Iteration[200/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[174/182] Iteration[250/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[174/182] Iteration[300/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[174/182] Iteration[350/352] Loss: 0.0028 Acc:99.98%
Training Progress:  95%|▉| 173/182 [59:05<03:03, 20.39s/it, Train Acc=99.98%, VaEpoch[174/182] Train Acc: 99.98% Valid Acc:93.60% Train loss:0.0028 Valid loss:0.3307 LR:0.0010000000000000002
Training Progress:  96%|▉| 174/182 [59:05<02:42, 20.37s/it, Train Acc=99.98%, VaTraining: Epoch[175/182] Iteration[050/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[175/182] Iteration[100/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[175/182] Iteration[150/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[175/182] Iteration[200/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[175/182] Iteration[250/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[175/182] Iteration[300/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[175/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  96%|▉| 174/182 [59:25<02:42, 20.37s/it, Train Acc=99.96%, VaEpoch[175/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0028 Valid loss:0.3363 LR:0.0010000000000000002
Training Progress:  96%|▉| 175/182 [59:25<02:23, 20.48s/it, Train Acc=99.96%, VaTraining: Epoch[176/182] Iteration[050/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[176/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[176/182] Iteration[150/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[176/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[176/182] Iteration[250/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[176/182] Iteration[300/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[176/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  96%|▉| 175/182 [59:46<02:23, 20.48s/it, Train Acc=99.97%, VaEpoch[176/182] Train Acc: 99.97% Valid Acc:93.66% Train loss:0.0029 Valid loss:0.3337 LR:0.0010000000000000002
Training Progress:  97%|▉| 176/182 [59:46<02:02, 20.44s/it, Train Acc=99.97%, VaTraining: Epoch[177/182] Iteration[050/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[177/182] Iteration[100/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[177/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[177/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[177/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[177/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[177/182] Iteration[350/352] Loss: 0.0030 Acc:99.97%
Training Progress:  97%|▉| 176/182 [1:00:06<02:02, 20.44s/it, Train Acc=99.97%, Epoch[177/182] Train Acc: 99.97% Valid Acc:93.52% Train loss:0.0030 Valid loss:0.3329 LR:0.0010000000000000002
Training Progress:  97%|▉| 177/182 [1:00:06<01:42, 20.44s/it, Train Acc=99.97%, Training: Epoch[178/182] Iteration[050/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[178/182] Iteration[100/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[178/182] Iteration[150/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[178/182] Iteration[200/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[178/182] Iteration[250/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[178/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[178/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  97%|▉| 177/182 [1:00:26<01:42, 20.44s/it, Train Acc=99.96%, Epoch[178/182] Train Acc: 99.96% Valid Acc:93.56% Train loss:0.0028 Valid loss:0.3341 LR:0.0010000000000000002
Training Progress:  98%|▉| 178/182 [1:00:26<01:21, 20.43s/it, Train Acc=99.96%, Training: Epoch[179/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[179/182] Iteration[100/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[179/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[179/182] Iteration[200/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[179/182] Iteration[250/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[179/182] Iteration[300/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[179/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  98%|▉| 178/182 [1:00:47<01:21, 20.43s/it, Train Acc=99.96%, Epoch[179/182] Train Acc: 99.96% Valid Acc:93.60% Train loss:0.0029 Valid loss:0.3336 LR:0.0010000000000000002
Training Progress:  98%|▉| 179/182 [1:00:47<01:01, 20.41s/it, Train Acc=99.96%, Training: Epoch[180/182] Iteration[050/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[180/182] Iteration[100/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[180/182] Iteration[150/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[180/182] Iteration[200/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[180/182] Iteration[250/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[180/182] Iteration[300/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[180/182] Iteration[350/352] Loss: 0.0030 Acc:99.95%
Training Progress:  98%|▉| 179/182 [1:01:07<01:01, 20.41s/it, Train Acc=99.95%, Epoch[180/182] Train Acc: 99.95% Valid Acc:93.64% Train loss:0.0030 Valid loss:0.3360 LR:0.0010000000000000002
Training Progress:  99%|▉| 180/182 [1:01:07<00:40, 20.42s/it, Train Acc=99.95%, Training: Epoch[181/182] Iteration[050/352] Loss: 0.0030 Acc:99.92%
Training: Epoch[181/182] Iteration[100/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[181/182] Iteration[150/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[181/182] Iteration[200/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[181/182] Iteration[250/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[181/182] Iteration[300/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[181/182] Iteration[350/352] Loss: 0.0027 Acc:99.96%
Training Progress:  99%|▉| 180/182 [1:01:28<00:40, 20.42s/it, Train Acc=99.96%, Epoch[181/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0027 Valid loss:0.3334 LR:0.0010000000000000002
Training Progress:  99%|▉| 181/182 [1:01:28<00:20, 20.40s/it, Train Acc=99.96%, Training: Epoch[182/182] Iteration[050/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[182/182] Iteration[100/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[182/182] Iteration[150/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[182/182] Iteration[200/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[182/182] Iteration[250/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[182/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[182/182] Iteration[350/352] Loss: 0.0031 Acc:99.95%
Training Progress:  99%|▉| 181/182 [1:01:48<00:20, 20.40s/it, Train Acc=99.95%, Epoch[182/182] Train Acc: 99.95% Valid Acc:93.64% Train loss:0.0032 Valid loss:0.3356 LR:0.0010000000000000002
class:plane     , total num:4508.0, correct num:4505.0  Recall: 99.93% Precision: 99.95%
class:car       , total num:4520.0, correct num:4514.0  Recall: 99.87% Precision: 100.00%
class:bird      , total num:4534.0, correct num:4533.0  Recall: 99.98% Precision: 99.93%
class:cat       , total num:4494.0, correct num:4493.0  Recall: 99.98% Precision: 99.82%
class:deer      , total num:4480.0, correct num:4477.0  Recall: 99.93% Precision: 100.00%
class:dog       , total num:4514.0, correct num:4509.0  Recall: 99.89% Precision: 99.91%
class:frog      , total num:4490.0, correct num:4490.0  Recall: 100.00% Precision: 99.98%
class:horse     , total num:4459.0, correct num:4454.0  Recall: 99.89% Precision: 100.00%
class:ship      , total num:4519.0, correct num:4519.0  Recall: 100.00% Precision: 99.95%
class:truck     , total num:4482.0, correct num:4482.0  Recall: 100.00% Precision: 99.91%
class:plane     , total num:492.0 , correct num:461.0  Recall: 93.68% Precision: 94.84%
class:car       , total num:480.0 , correct num:468.0  Recall: 97.48% Precision: 97.48%
class:bird      , total num:466.0 , correct num:428.0  Recall: 91.83% Precision: 90.09%
class:cat       , total num:506.0 , correct num:430.0  Recall: 84.96% Precision: 85.47%
class:deer      , total num:520.0 , correct num:485.0  Recall: 93.25% Precision: 94.89%
class:dog       , total num:486.0 , correct num:436.0  Recall: 89.69% Precision: 87.18%
class:frog      , total num:510.0 , correct num:493.0  Recall: 96.65% Precision: 96.65%
class:horse     , total num:541.0 , correct num:515.0  Recall: 95.18% Precision: 96.97%
class:ship      , total num:481.0 , correct num:466.0  Recall: 96.86% Precision: 95.67%
class:truck     , total num:518.0 , correct num:500.0  Recall: 96.51% Precision: 96.69%
Training Progress: 100%|█| 182/182 [1:01:49<00:00, 20.38s/it, Train Acc=99.95%, 

================ Training Finished ================
Finished Time      : 05-18_15-54
Best Validation Acc: 0.938
Best Epoch         : 162
Best Test Acc      : 0.93
Total Training Time: 3709.27 sec (61.82 min)
===================================================

Acknowledgments and References

• Quotient Network-A Network Similar to ResNet but Learning Quotients (GitHub)

↪Back to the content⤴