【Ubuntu 24.04.3】Quotient Network: experiments_on_cifar100 — q110

MSI Cyborg-15-A12VE

Acknowledgments and References

(quotient) wish@wish-Cyborg-15-A12VE:~/Quotient-Networks/experiments_on_cifar100$ python ./src/train.py --model q110
Training Progress:   0%|                                | 0/182 [00:00<?, ?it/s]Training: Epoch[001/182] Iteration[050/352] Loss: 4.7081 Acc:1.34%
Training: Epoch[001/182] Iteration[100/352] Loss: 4.6140 Acc:1.73%
Training: Epoch[001/182] Iteration[150/352] Loss: 4.5464 Acc:2.13%
Training: Epoch[001/182] Iteration[200/352] Loss: 4.4912 Acc:2.55%
Training: Epoch[001/182] Iteration[250/352] Loss: 4.4431 Acc:3.02%
Training: Epoch[001/182] Iteration[300/352] Loss: 4.3988 Acc:3.43%
Training: Epoch[001/182] Iteration[350/352] Loss: 4.3539 Acc:3.92%
Training Progress:   0%| | 0/182 [01:46<?, ?it/s, Train Acc=3.93%, Valid Acc=7.1Epoch[001/182] Train Acc: 3.93% Valid Acc:7.14% Train loss:4.3521 Valid loss:4.0724 LR:0.1
Training Progress:   1%| | 1/182 [01:46<5:20:04, 106.10s/it, Train Acc=3.93%, VaTraining: Epoch[002/182] Iteration[050/352] Loss: 3.9897 Acc:8.03%
Training: Epoch[002/182] Iteration[100/352] Loss: 3.9814 Acc:8.20%
Training: Epoch[002/182] Iteration[150/352] Loss: 3.9595 Acc:8.56%
Training: Epoch[002/182] Iteration[200/352] Loss: 3.9274 Acc:8.98%
Training: Epoch[002/182] Iteration[250/352] Loss: 3.8906 Acc:9.57%
Training: Epoch[002/182] Iteration[300/352] Loss: 3.8585 Acc:9.98%
Training: Epoch[002/182] Iteration[350/352] Loss: 3.8358 Acc:10.36%
Training Progress:   1%| | 1/182 [03:32<5:20:04, 106.10s/it, Train Acc=10.37%, VEpoch[002/182] Train Acc: 10.37% Valid Acc:14.44% Train loss:3.8352 Valid loss:3.6215 LR:0.1
Training Progress:   1%| | 2/182 [03:32<5:19:07, 106.38s/it, Train Acc=10.37%, VTraining: Epoch[003/182] Iteration[050/352] Loss: 3.5682 Acc:14.77%
Training: Epoch[003/182] Iteration[100/352] Loss: 3.5609 Acc:14.80%
Training: Epoch[003/182] Iteration[150/352] Loss: 3.5330 Acc:15.14%
Training: Epoch[003/182] Iteration[200/352] Loss: 3.5116 Acc:15.41%
Training: Epoch[003/182] Iteration[250/352] Loss: 3.4903 Acc:15.94%
Training: Epoch[003/182] Iteration[300/352] Loss: 3.4676 Acc:16.43%
Training: Epoch[003/182] Iteration[350/352] Loss: 3.4432 Acc:16.87%
Training Progress:   1%| | 2/182 [05:20<5:19:07, 106.38s/it, Train Acc=16.88%, VEpoch[003/182] Train Acc: 16.88% Valid Acc:19.82% Train loss:3.4424 Valid loss:3.2887 LR:0.1
Training Progress:   2%| | 3/182 [05:20<5:19:21, 107.05s/it, Train Acc=16.88%, VTraining: Epoch[004/182] Iteration[050/352] Loss: 3.2158 Acc:20.88%
Training: Epoch[004/182] Iteration[100/352] Loss: 3.1974 Acc:21.11%
Training: Epoch[004/182] Iteration[150/352] Loss: 3.1827 Acc:21.41%
Training: Epoch[004/182] Iteration[200/352] Loss: 3.1631 Acc:21.78%
Training: Epoch[004/182] Iteration[250/352] Loss: 3.1364 Acc:22.27%
Training: Epoch[004/182] Iteration[300/352] Loss: 3.1146 Acc:22.61%
Training: Epoch[004/182] Iteration[350/352] Loss: 3.0975 Acc:23.05%
Training Progress:   2%| | 3/182 [07:08<5:19:21, 107.05s/it, Train Acc=23.06%, VEpoch[004/182] Train Acc: 23.06% Valid Acc:26.56% Train loss:3.0963 Valid loss:2.9276 LR:0.1
Training Progress:   2%| | 4/182 [07:08<5:18:57, 107.51s/it, Train Acc=23.06%, VTraining: Epoch[005/182] Iteration[050/352] Loss: 2.8331 Acc:28.08%
Training: Epoch[005/182] Iteration[100/352] Loss: 2.8407 Acc:27.84%
Training: Epoch[005/182] Iteration[150/352] Loss: 2.8143 Acc:28.32%
Training: Epoch[005/182] Iteration[200/352] Loss: 2.7885 Acc:28.91%
Training: Epoch[005/182] Iteration[250/352] Loss: 2.7692 Acc:29.23%
Training: Epoch[005/182] Iteration[300/352] Loss: 2.7546 Acc:29.65%
Training: Epoch[005/182] Iteration[350/352] Loss: 2.7342 Acc:30.04%
Training Progress:   2%| | 4/182 [08:57<5:18:57, 107.51s/it, Train Acc=30.08%, VEpoch[005/182] Train Acc: 30.08% Valid Acc:31.84% Train loss:2.7324 Valid loss:2.6689 LR:0.1
Training Progress:   3%| | 5/182 [08:57<5:18:44, 108.05s/it, Train Acc=30.08%, VTraining: Epoch[006/182] Iteration[050/352] Loss: 2.5239 Acc:33.97%
Training: Epoch[006/182] Iteration[100/352] Loss: 2.5141 Acc:34.40%
Training: Epoch[006/182] Iteration[150/352] Loss: 2.4881 Acc:34.99%
Training: Epoch[006/182] Iteration[200/352] Loss: 2.4750 Acc:35.38%
Training: Epoch[006/182] Iteration[250/352] Loss: 2.4503 Acc:36.05%
Training: Epoch[006/182] Iteration[300/352] Loss: 2.4285 Acc:36.62%
Training: Epoch[006/182] Iteration[350/352] Loss: 2.4060 Acc:37.07%
Training Progress:   3%| | 5/182 [10:47<5:18:44, 108.05s/it, Train Acc=37.10%, VEpoch[006/182] Train Acc: 37.10% Valid Acc:37.28% Train loss:2.4056 Valid loss:2.4236 LR:0.1
Training Progress:   3%| | 6/182 [10:47<5:18:23, 108.54s/it, Train Acc=37.10%, VTraining: Epoch[007/182] Iteration[050/352] Loss: 2.2165 Acc:41.09%
Training: Epoch[007/182] Iteration[100/352] Loss: 2.1919 Acc:41.53%
Training: Epoch[007/182] Iteration[150/352] Loss: 2.1905 Acc:41.35%
Training: Epoch[007/182] Iteration[200/352] Loss: 2.1688 Acc:41.88%
Training: Epoch[007/182] Iteration[250/352] Loss: 2.1621 Acc:42.04%
Training: Epoch[007/182] Iteration[300/352] Loss: 2.1433 Acc:42.51%
Training: Epoch[007/182] Iteration[350/352] Loss: 2.1320 Acc:42.77%
Training Progress:   3%| | 6/182 [12:37<5:18:23, 108.54s/it, Train Acc=42.78%, VEpoch[007/182] Train Acc: 42.78% Valid Acc:41.30% Train loss:2.1317 Valid loss:2.2445 LR:0.1
Training Progress:   4%| | 7/182 [12:37<5:17:50, 108.97s/it, Train Acc=42.78%, VTraining: Epoch[008/182] Iteration[050/352] Loss: 1.9658 Acc:46.27%
Training: Epoch[008/182] Iteration[100/352] Loss: 1.9423 Acc:46.95%
Training: Epoch[008/182] Iteration[150/352] Loss: 1.9393 Acc:47.08%
Training: Epoch[008/182] Iteration[200/352] Loss: 1.9221 Acc:47.55%
Training: Epoch[008/182] Iteration[250/352] Loss: 1.9184 Acc:47.68%
Training: Epoch[008/182] Iteration[300/352] Loss: 1.9128 Acc:47.79%
Training: Epoch[008/182] Iteration[350/352] Loss: 1.9021 Acc:48.09%
Training Progress:   4%| | 7/182 [14:27<5:17:50, 108.97s/it, Train Acc=48.09%, VEpoch[008/182] Train Acc: 48.09% Valid Acc:46.66% Train loss:1.9021 Valid loss:2.0467 LR:0.1
Training Progress:   4%| | 8/182 [14:27<5:16:54, 109.28s/it, Train Acc=48.09%, VTraining: Epoch[009/182] Iteration[050/352] Loss: 1.7413 Acc:51.00%
Training: Epoch[009/182] Iteration[100/352] Loss: 1.7375 Acc:51.44%
Training: Epoch[009/182] Iteration[150/352] Loss: 1.7325 Acc:51.78%
Training: Epoch[009/182] Iteration[200/352] Loss: 1.7383 Acc:51.79%
Training: Epoch[009/182] Iteration[250/352] Loss: 1.7365 Acc:51.87%
Training: Epoch[009/182] Iteration[300/352] Loss: 1.7387 Acc:51.85%
Training: Epoch[009/182] Iteration[350/352] Loss: 1.7348 Acc:51.92%
Training Progress:   4%| | 8/182 [16:17<5:16:54, 109.28s/it, Train Acc=51.91%, VEpoch[009/182] Train Acc: 51.91% Valid Acc:50.40% Train loss:1.7347 Valid loss:1.8397 LR:0.1
Training Progress:   5%| | 9/182 [16:17<5:16:06, 109.63s/it, Train Acc=51.91%, VTraining: Epoch[010/182] Iteration[050/352] Loss: 1.5986 Acc:54.73%
Training: Epoch[010/182] Iteration[100/352] Loss: 1.5946 Acc:54.91%
Training: Epoch[010/182] Iteration[150/352] Loss: 1.5979 Acc:55.01%
Training: Epoch[010/182] Iteration[200/352] Loss: 1.5833 Acc:55.28%
Training: Epoch[010/182] Iteration[250/352] Loss: 1.5834 Acc:55.28%
Training: Epoch[010/182] Iteration[300/352] Loss: 1.5852 Acc:55.27%
Training: Epoch[010/182] Iteration[350/352] Loss: 1.5834 Acc:55.26%
Training Progress:   5%| | 9/182 [18:07<5:16:06, 109.63s/it, Train Acc=55.30%, VEpoch[010/182] Train Acc: 55.30% Valid Acc:49.68% Train loss:1.5828 Valid loss:1.9345 LR:0.1
Training Progress:   5%| | 10/182 [18:07<5:15:02, 109.90s/it, Train Acc=55.30%, Training: Epoch[011/182] Iteration[050/352] Loss: 1.4617 Acc:58.42%
Training: Epoch[011/182] Iteration[100/352] Loss: 1.4785 Acc:58.51%
Training: Epoch[011/182] Iteration[150/352] Loss: 1.4697 Acc:58.41%
Training: Epoch[011/182] Iteration[200/352] Loss: 1.4731 Acc:58.34%
Training: Epoch[011/182] Iteration[250/352] Loss: 1.4728 Acc:58.30%
Training: Epoch[011/182] Iteration[300/352] Loss: 1.4737 Acc:58.28%
Training: Epoch[011/182] Iteration[350/352] Loss: 1.4725 Acc:58.43%
Training Progress:   5%| | 10/182 [19:58<5:15:02, 109.90s/it, Train Acc=58.45%, Epoch[011/182] Train Acc: 58.45% Valid Acc:54.22% Train loss:1.4717 Valid loss:1.7306 LR:0.1
Training Progress:   6%| | 11/182 [19:58<5:13:57, 110.16s/it, Train Acc=58.45%, Training: Epoch[012/182] Iteration[050/352] Loss: 1.3360 Acc:61.86%
Training: Epoch[012/182] Iteration[100/352] Loss: 1.3591 Acc:61.27%
Training: Epoch[012/182] Iteration[150/352] Loss: 1.3715 Acc:60.90%
Training: Epoch[012/182] Iteration[200/352] Loss: 1.3754 Acc:60.74%
Training: Epoch[012/182] Iteration[250/352] Loss: 1.3759 Acc:60.82%
Training: Epoch[012/182] Iteration[300/352] Loss: 1.3742 Acc:60.84%
Training: Epoch[012/182] Iteration[350/352] Loss: 1.3706 Acc:60.80%
Training Progress:   6%| | 11/182 [21:49<5:13:57, 110.16s/it, Train Acc=60.84%, Epoch[012/182] Train Acc: 60.84% Valid Acc:53.44% Train loss:1.3702 Valid loss:1.7410 LR:0.1
Training Progress:   7%| | 12/182 [21:49<5:12:51, 110.42s/it, Train Acc=60.84%, Training: Epoch[013/182] Iteration[050/352] Loss: 1.2568 Acc:63.89%
Training: Epoch[013/182] Iteration[100/352] Loss: 1.2587 Acc:63.69%
Training: Epoch[013/182] Iteration[150/352] Loss: 1.2798 Acc:63.05%
Training: Epoch[013/182] Iteration[200/352] Loss: 1.2840 Acc:62.82%
Training: Epoch[013/182] Iteration[250/352] Loss: 1.2848 Acc:62.80%
Training: Epoch[013/182] Iteration[300/352] Loss: 1.2899 Acc:62.65%
Training: Epoch[013/182] Iteration[350/352] Loss: 1.2910 Acc:62.69%
Training Progress:   7%| | 12/182 [23:40<5:12:51, 110.42s/it, Train Acc=62.72%, Epoch[013/182] Train Acc: 62.72% Valid Acc:57.02% Train loss:1.2904 Valid loss:1.6098 LR:0.1
Training Progress:   7%| | 13/182 [23:40<5:11:21, 110.54s/it, Train Acc=62.72%, Training: Epoch[014/182] Iteration[050/352] Loss: 1.1495 Acc:66.84%
Training: Epoch[014/182] Iteration[100/352] Loss: 1.1630 Acc:66.17%
Training: Epoch[014/182] Iteration[150/352] Loss: 1.1698 Acc:65.86%
Training: Epoch[014/182] Iteration[200/352] Loss: 1.1857 Acc:65.54%
Training: Epoch[014/182] Iteration[250/352] Loss: 1.1891 Acc:65.32%
Training: Epoch[014/182] Iteration[300/352] Loss: 1.1988 Acc:64.98%
Training: Epoch[014/182] Iteration[350/352] Loss: 1.2041 Acc:64.85%
Training Progress:   7%| | 13/182 [25:31<5:11:21, 110.54s/it, Train Acc=64.84%, Epoch[014/182] Train Acc: 64.84% Valid Acc:55.76% Train loss:1.2045 Valid loss:1.7066 LR:0.1
Training Progress:   8%| | 14/182 [25:31<5:09:53, 110.67s/it, Train Acc=64.84%, Training: Epoch[015/182] Iteration[050/352] Loss: 1.0583 Acc:68.97%
Training: Epoch[015/182] Iteration[100/352] Loss: 1.0818 Acc:68.34%
Training: Epoch[015/182] Iteration[150/352] Loss: 1.1034 Acc:67.91%
Training: Epoch[015/182] Iteration[200/352] Loss: 1.1115 Acc:67.59%
Training: Epoch[015/182] Iteration[250/352] Loss: 1.1261 Acc:67.24%
Training: Epoch[015/182] Iteration[300/352] Loss: 1.1389 Acc:66.75%
Training: Epoch[015/182] Iteration[350/352] Loss: 1.1397 Acc:66.72%
Training Progress:   8%| | 14/182 [27:22<5:09:53, 110.67s/it, Train Acc=66.74%, Epoch[015/182] Train Acc: 66.74% Valid Acc:57.76% Train loss:1.1390 Valid loss:1.6194 LR:0.1
Training Progress:   8%| | 15/182 [27:22<5:08:25, 110.81s/it, Train Acc=66.74%, Training: Epoch[016/182] Iteration[050/352] Loss: 1.0194 Acc:69.34%
Training: Epoch[016/182] Iteration[100/352] Loss: 1.0394 Acc:68.73%
Training: Epoch[016/182] Iteration[150/352] Loss: 1.0601 Acc:68.21%
Training: Epoch[016/182] Iteration[200/352] Loss: 1.0698 Acc:68.07%
Training: Epoch[016/182] Iteration[250/352] Loss: 1.0704 Acc:68.23%
Training: Epoch[016/182] Iteration[300/352] Loss: 1.0708 Acc:68.35%
Training: Epoch[016/182] Iteration[350/352] Loss: 1.0768 Acc:68.27%
Training Progress:   8%| | 15/182 [29:13<5:08:25, 110.81s/it, Train Acc=68.25%, Epoch[016/182] Train Acc: 68.25% Valid Acc:59.98% Train loss:1.0765 Valid loss:1.5559 LR:0.1
Training Progress:   9%| | 16/182 [29:13<5:06:50, 110.91s/it, Train Acc=68.25%, Training: Epoch[017/182] Iteration[050/352] Loss: 0.9375 Acc:71.56%
Training: Epoch[017/182] Iteration[100/352] Loss: 0.9754 Acc:70.71%
Training: Epoch[017/182] Iteration[150/352] Loss: 0.9863 Acc:70.28%
Training: Epoch[017/182] Iteration[200/352] Loss: 1.0007 Acc:69.96%
Training: Epoch[017/182] Iteration[250/352] Loss: 1.0088 Acc:69.80%
Training: Epoch[017/182] Iteration[300/352] Loss: 1.0172 Acc:69.69%
Training: Epoch[017/182] Iteration[350/352] Loss: 1.0232 Acc:69.55%
Training Progress:   9%| | 16/182 [31:05<5:06:50, 110.91s/it, Train Acc=69.53%, Epoch[017/182] Train Acc: 69.53% Valid Acc:60.34% Train loss:1.0234 Valid loss:1.5283 LR:0.1
Training Progress:   9%| | 17/182 [31:05<5:05:18, 111.02s/it, Train Acc=69.53%, Training: Epoch[018/182] Iteration[050/352] Loss: 0.9122 Acc:72.62%
Training: Epoch[018/182] Iteration[100/352] Loss: 0.9256 Acc:72.08%
Training: Epoch[018/182] Iteration[150/352] Loss: 0.9363 Acc:71.80%
Training: Epoch[018/182] Iteration[200/352] Loss: 0.9424 Acc:71.69%
Training: Epoch[018/182] Iteration[250/352] Loss: 0.9503 Acc:71.62%
Training: Epoch[018/182] Iteration[300/352] Loss: 0.9617 Acc:71.34%
Training: Epoch[018/182] Iteration[350/352] Loss: 0.9665 Acc:71.21%
Training Progress:   9%| | 17/182 [32:56<5:05:18, 111.02s/it, Train Acc=71.22%, Epoch[018/182] Train Acc: 71.22% Valid Acc:58.20% Train loss:0.9660 Valid loss:1.6815 LR:0.1
Training Progress:  10%| | 18/182 [32:56<5:03:43, 111.12s/it, Train Acc=71.22%, Training: Epoch[019/182] Iteration[050/352] Loss: 0.8661 Acc:73.89%
Training: Epoch[019/182] Iteration[100/352] Loss: 0.8634 Acc:74.07%
Training: Epoch[019/182] Iteration[150/352] Loss: 0.8738 Acc:73.62%
Training: Epoch[019/182] Iteration[200/352] Loss: 0.8950 Acc:73.19%
Training: Epoch[019/182] Iteration[250/352] Loss: 0.8971 Acc:73.15%
Training: Epoch[019/182] Iteration[300/352] Loss: 0.9094 Acc:72.79%
Training: Epoch[019/182] Iteration[350/352] Loss: 0.9158 Acc:72.56%
Training Progress:  10%| | 18/182 [34:47<5:03:43, 111.12s/it, Train Acc=72.55%, Epoch[019/182] Train Acc: 72.55% Valid Acc:59.02% Train loss:0.9157 Valid loss:1.6302 LR:0.1
Training Progress:  10%| | 19/182 [34:47<5:02:04, 111.20s/it, Train Acc=72.55%, Training: Epoch[020/182] Iteration[050/352] Loss: 0.8017 Acc:75.80%
Training: Epoch[020/182] Iteration[100/352] Loss: 0.8123 Acc:75.46%
Training: Epoch[020/182] Iteration[150/352] Loss: 0.8297 Acc:74.85%
Training: Epoch[020/182] Iteration[200/352] Loss: 0.8490 Acc:74.42%
Training: Epoch[020/182] Iteration[250/352] Loss: 0.8571 Acc:74.32%
Training: Epoch[020/182] Iteration[300/352] Loss: 0.8590 Acc:74.27%
Training: Epoch[020/182] Iteration[350/352] Loss: 0.8652 Acc:74.02%
Training Progress:  10%| | 19/182 [36:39<5:02:04, 111.20s/it, Train Acc=74.01%, Epoch[020/182] Train Acc: 74.01% Valid Acc:60.88% Train loss:0.8652 Valid loss:1.5321 LR:0.1
Training Progress:  11%| | 20/182 [36:39<5:00:24, 111.26s/it, Train Acc=74.01%, Training: Epoch[021/182] Iteration[050/352] Loss: 0.7695 Acc:76.39%
Training: Epoch[021/182] Iteration[100/352] Loss: 0.7948 Acc:75.62%
Training: Epoch[021/182] Iteration[150/352] Loss: 0.8075 Acc:75.37%
Training: Epoch[021/182] Iteration[200/352] Loss: 0.8167 Acc:75.19%
Training: Epoch[021/182] Iteration[250/352] Loss: 0.8259 Acc:75.02%
Training: Epoch[021/182] Iteration[300/352] Loss: 0.8300 Acc:74.95%
Training: Epoch[021/182] Iteration[350/352] Loss: 0.8262 Acc:74.94%
Training Progress:  11%| | 20/182 [38:30<5:00:24, 111.26s/it, Train Acc=74.93%, Epoch[021/182] Train Acc: 74.93% Valid Acc:58.92% Train loss:0.8269 Valid loss:1.6768 LR:0.1
Training Progress:  12%| | 21/182 [38:30<4:58:48, 111.36s/it, Train Acc=74.93%, Training: Epoch[022/182] Iteration[050/352] Loss: 0.6952 Acc:79.53%
Training: Epoch[022/182] Iteration[100/352] Loss: 0.7083 Acc:78.44%
Training: Epoch[022/182] Iteration[150/352] Loss: 0.7408 Acc:77.10%
Training: Epoch[022/182] Iteration[200/352] Loss: 0.7581 Acc:76.53%
Training: Epoch[022/182] Iteration[250/352] Loss: 0.7680 Acc:76.43%
Training: Epoch[022/182] Iteration[300/352] Loss: 0.7774 Acc:76.08%
Training: Epoch[022/182] Iteration[350/352] Loss: 0.7848 Acc:75.95%
Training Progress:  12%| | 21/182 [40:22<4:58:48, 111.36s/it, Train Acc=75.91%, Epoch[022/182] Train Acc: 75.91% Valid Acc:60.66% Train loss:0.7856 Valid loss:1.5862 LR:0.1
Training Progress:  12%| | 22/182 [40:22<4:57:07, 111.42s/it, Train Acc=75.91%, Training: Epoch[023/182] Iteration[050/352] Loss: 0.7075 Acc:78.12%
Training: Epoch[023/182] Iteration[100/352] Loss: 0.7097 Acc:77.98%
Training: Epoch[023/182] Iteration[150/352] Loss: 0.7139 Acc:77.70%
Training: Epoch[023/182] Iteration[200/352] Loss: 0.7328 Acc:77.29%
Training: Epoch[023/182] Iteration[250/352] Loss: 0.7407 Acc:77.09%
Training: Epoch[023/182] Iteration[300/352] Loss: 0.7466 Acc:77.02%
Training: Epoch[023/182] Iteration[350/352] Loss: 0.7483 Acc:76.95%
Training Progress:  12%| | 22/182 [42:13<4:57:07, 111.42s/it, Train Acc=76.94%, Epoch[023/182] Train Acc: 76.94% Valid Acc:60.08% Train loss:0.7486 Valid loss:1.5958 LR:0.1
Training Progress:  13%|▏| 23/182 [42:13<4:55:26, 111.49s/it, Train Acc=76.94%, Training: Epoch[024/182] Iteration[050/352] Loss: 0.6477 Acc:80.66%
Training: Epoch[024/182] Iteration[100/352] Loss: 0.6759 Acc:79.65%
Training: Epoch[024/182] Iteration[150/352] Loss: 0.6882 Acc:79.20%
Training: Epoch[024/182] Iteration[200/352] Loss: 0.6944 Acc:78.84%
Training: Epoch[024/182] Iteration[250/352] Loss: 0.7005 Acc:78.56%
Training: Epoch[024/182] Iteration[300/352] Loss: 0.7188 Acc:77.98%
Training: Epoch[024/182] Iteration[350/352] Loss: 0.7234 Acc:77.82%
Training Progress:  13%|▏| 23/182 [44:05<4:55:26, 111.49s/it, Train Acc=77.81%, Epoch[024/182] Train Acc: 77.81% Valid Acc:59.34% Train loss:0.7239 Valid loss:1.6957 LR:0.1
Training Progress:  13%|▏| 24/182 [44:05<4:53:39, 111.51s/it, Train Acc=77.81%, Training: Epoch[025/182] Iteration[050/352] Loss: 0.6004 Acc:81.09%
Training: Epoch[025/182] Iteration[100/352] Loss: 0.6270 Acc:80.55%
Training: Epoch[025/182] Iteration[150/352] Loss: 0.6478 Acc:80.02%
Training: Epoch[025/182] Iteration[200/352] Loss: 0.6639 Acc:79.54%
Training: Epoch[025/182] Iteration[250/352] Loss: 0.6777 Acc:79.24%
Training: Epoch[025/182] Iteration[300/352] Loss: 0.6876 Acc:78.89%
Training: Epoch[025/182] Iteration[350/352] Loss: 0.6939 Acc:78.69%
Training Progress:  13%|▏| 24/182 [45:57<4:53:39, 111.51s/it, Train Acc=78.70%, Epoch[025/182] Train Acc: 78.70% Valid Acc:60.50% Train loss:0.6937 Valid loss:1.6569 LR:0.1
Training Progress:  14%|▏| 25/182 [45:57<4:51:48, 111.52s/it, Train Acc=78.70%, Training: Epoch[026/182] Iteration[050/352] Loss: 0.5686 Acc:82.33%
Training: Epoch[026/182] Iteration[100/352] Loss: 0.5863 Acc:81.81%
Training: Epoch[026/182] Iteration[150/352] Loss: 0.6138 Acc:80.91%
Training: Epoch[026/182] Iteration[200/352] Loss: 0.6302 Acc:80.45%
Training: Epoch[026/182] Iteration[250/352] Loss: 0.6414 Acc:80.12%
Training: Epoch[026/182] Iteration[300/352] Loss: 0.6446 Acc:79.98%
Training: Epoch[026/182] Iteration[350/352] Loss: 0.6526 Acc:79.74%
Training Progress:  14%|▏| 25/182 [47:48<4:51:48, 111.52s/it, Train Acc=79.74%, Epoch[026/182] Train Acc: 79.74% Valid Acc:62.02% Train loss:0.6529 Valid loss:1.6061 LR:0.1
Training Progress:  14%|▏| 26/182 [47:48<4:49:58, 111.53s/it, Train Acc=79.74%, Training: Epoch[027/182] Iteration[050/352] Loss: 0.5829 Acc:81.42%
Training: Epoch[027/182] Iteration[100/352] Loss: 0.5771 Acc:81.84%
Training: Epoch[027/182] Iteration[150/352] Loss: 0.5933 Acc:81.51%
Training: Epoch[027/182] Iteration[200/352] Loss: 0.6042 Acc:81.19%
Training: Epoch[027/182] Iteration[250/352] Loss: 0.6176 Acc:80.76%
Training: Epoch[027/182] Iteration[300/352] Loss: 0.6279 Acc:80.49%
Training: Epoch[027/182] Iteration[350/352] Loss: 0.6336 Acc:80.34%
Training Progress:  14%|▏| 26/182 [49:40<4:49:58, 111.53s/it, Train Acc=80.33%, Epoch[027/182] Train Acc: 80.33% Valid Acc:60.44% Train loss:0.6337 Valid loss:1.7456 LR:0.1
Training Progress:  15%|▏| 27/182 [49:40<4:48:07, 111.54s/it, Train Acc=80.33%, Training: Epoch[028/182] Iteration[050/352] Loss: 0.5283 Acc:83.33%
Training: Epoch[028/182] Iteration[100/352] Loss: 0.5258 Acc:83.49%
Training: Epoch[028/182] Iteration[150/352] Loss: 0.5543 Acc:82.53%
Training: Epoch[028/182] Iteration[200/352] Loss: 0.5791 Acc:81.79%
Training: Epoch[028/182] Iteration[250/352] Loss: 0.5885 Acc:81.37%
Training: Epoch[028/182] Iteration[300/352] Loss: 0.6027 Acc:80.93%
Training: Epoch[028/182] Iteration[350/352] Loss: 0.6115 Acc:80.72%
Training Progress:  15%|▏| 27/182 [51:31<4:48:07, 111.54s/it, Train Acc=80.74%, Epoch[028/182] Train Acc: 80.74% Valid Acc:62.82% Train loss:0.6112 Valid loss:1.5676 LR:0.1
Training Progress:  15%|▏| 28/182 [51:31<4:46:24, 111.59s/it, Train Acc=80.74%, Training: Epoch[029/182] Iteration[050/352] Loss: 0.5152 Acc:83.47%
Training: Epoch[029/182] Iteration[100/352] Loss: 0.5301 Acc:83.01%
Training: Epoch[029/182] Iteration[150/352] Loss: 0.5417 Acc:82.62%
Training: Epoch[029/182] Iteration[200/352] Loss: 0.5691 Acc:81.82%
Training: Epoch[029/182] Iteration[250/352] Loss: 0.5762 Acc:81.67%
Training: Epoch[029/182] Iteration[300/352] Loss: 0.5863 Acc:81.47%
Training: Epoch[029/182] Iteration[350/352] Loss: 0.5925 Acc:81.26%
Training Progress:  15%|▏| 28/182 [53:23<4:46:24, 111.59s/it, Train Acc=81.26%, Epoch[029/182] Train Acc: 81.26% Valid Acc:60.98% Train loss:0.5924 Valid loss:1.6979 LR:0.1
Training Progress:  16%|▏| 29/182 [53:23<4:44:34, 111.60s/it, Train Acc=81.26%, Training: Epoch[030/182] Iteration[050/352] Loss: 0.5043 Acc:83.70%
Training: Epoch[030/182] Iteration[100/352] Loss: 0.5053 Acc:83.71%
Training: Epoch[030/182] Iteration[150/352] Loss: 0.5243 Acc:83.27%
Training: Epoch[030/182] Iteration[200/352] Loss: 0.5391 Acc:82.91%
Training: Epoch[030/182] Iteration[250/352] Loss: 0.5543 Acc:82.47%
Training: Epoch[030/182] Iteration[300/352] Loss: 0.5587 Acc:82.42%
Training: Epoch[030/182] Iteration[350/352] Loss: 0.5586 Acc:82.45%
Training Progress:  16%|▏| 29/182 [55:15<4:44:34, 111.60s/it, Train Acc=82.46%, Epoch[030/182] Train Acc: 82.46% Valid Acc:61.58% Train loss:0.5583 Valid loss:1.7596 LR:0.1
Training Progress:  16%|▏| 30/182 [55:15<4:42:45, 111.61s/it, Train Acc=82.46%, Training: Epoch[031/182] Iteration[050/352] Loss: 0.4783 Acc:84.64%
Training: Epoch[031/182] Iteration[100/352] Loss: 0.4810 Acc:84.71%
Training: Epoch[031/182] Iteration[150/352] Loss: 0.5005 Acc:83.96%
Training: Epoch[031/182] Iteration[200/352] Loss: 0.5224 Acc:83.38%
Training: Epoch[031/182] Iteration[250/352] Loss: 0.5375 Acc:83.01%
Training: Epoch[031/182] Iteration[300/352] Loss: 0.5450 Acc:82.79%
Training: Epoch[031/182] Iteration[350/352] Loss: 0.5522 Acc:82.62%
Training Progress:  16%|▏| 30/182 [57:06<4:42:45, 111.61s/it, Train Acc=82.61%, Epoch[031/182] Train Acc: 82.61% Valid Acc:62.94% Train loss:0.5531 Valid loss:1.6305 LR:0.1
Training Progress:  17%|▏| 31/182 [57:06<4:40:53, 111.62s/it, Train Acc=82.61%, Training: Epoch[032/182] Iteration[050/352] Loss: 0.4664 Acc:85.06%
Training: Epoch[032/182] Iteration[100/352] Loss: 0.4773 Acc:84.70%
Training: Epoch[032/182] Iteration[150/352] Loss: 0.4994 Acc:84.08%
Training: Epoch[032/182] Iteration[200/352] Loss: 0.5092 Acc:83.85%
Training: Epoch[032/182] Iteration[250/352] Loss: 0.5109 Acc:83.83%
Training: Epoch[032/182] Iteration[300/352] Loss: 0.5185 Acc:83.56%
Training: Epoch[032/182] Iteration[350/352] Loss: 0.5244 Acc:83.38%
Training Progress:  17%|▏| 31/182 [58:58<4:40:53, 111.62s/it, Train Acc=83.39%, Epoch[032/182] Train Acc: 83.39% Valid Acc:59.78% Train loss:0.5247 Valid loss:1.9230 LR:0.1
Training Progress:  18%|▏| 32/182 [58:58<4:39:05, 111.64s/it, Train Acc=83.39%, Training: Epoch[033/182] Iteration[050/352] Loss: 0.4747 Acc:84.92%
Training: Epoch[033/182] Iteration[100/352] Loss: 0.4782 Acc:84.72%
Training: Epoch[033/182] Iteration[150/352] Loss: 0.4855 Acc:84.47%
Training: Epoch[033/182] Iteration[200/352] Loss: 0.4997 Acc:84.21%
Training: Epoch[033/182] Iteration[250/352] Loss: 0.5063 Acc:83.93%
Training: Epoch[033/182] Iteration[300/352] Loss: 0.5129 Acc:83.73%
Training: Epoch[033/182] Iteration[350/352] Loss: 0.5208 Acc:83.46%
Training Progress:  18%|▏| 32/182 [1:00:50<4:39:05, 111.64s/it, Train Acc=83.45%Epoch[033/182] Train Acc: 83.45% Valid Acc:62.00% Train loss:0.5211 Valid loss:1.7122 LR:0.1
Training Progress:  18%|▏| 33/182 [1:00:50<4:37:15, 111.65s/it, Train Acc=83.45%Training: Epoch[034/182] Iteration[050/352] Loss: 0.4423 Acc:85.38%
Training: Epoch[034/182] Iteration[100/352] Loss: 0.4568 Acc:85.09%
Training: Epoch[034/182] Iteration[150/352] Loss: 0.4691 Acc:84.78%
Training: Epoch[034/182] Iteration[200/352] Loss: 0.4836 Acc:84.37%
Training: Epoch[034/182] Iteration[250/352] Loss: 0.4955 Acc:84.09%
Training: Epoch[034/182] Iteration[300/352] Loss: 0.5031 Acc:83.89%
Training: Epoch[034/182] Iteration[350/352] Loss: 0.5078 Acc:83.70%
Training Progress:  18%|▏| 33/182 [1:02:41<4:37:15, 111.65s/it, Train Acc=83.70%Epoch[034/182] Train Acc: 83.70% Valid Acc:63.60% Train loss:0.5077 Valid loss:1.6505 LR:0.1
Training Progress:  19%|▏| 34/182 [1:02:41<4:35:21, 111.63s/it, Train Acc=83.70%Training: Epoch[035/182] Iteration[050/352] Loss: 0.3913 Acc:87.23%
Training: Epoch[035/182] Iteration[100/352] Loss: 0.4193 Acc:86.33%
Training: Epoch[035/182] Iteration[150/352] Loss: 0.4368 Acc:85.93%
Training: Epoch[035/182] Iteration[200/352] Loss: 0.4488 Acc:85.59%
Training: Epoch[035/182] Iteration[250/352] Loss: 0.4595 Acc:85.15%
Training: Epoch[035/182] Iteration[300/352] Loss: 0.4655 Acc:84.92%
Training: Epoch[035/182] Iteration[350/352] Loss: 0.4748 Acc:84.66%
Training Progress:  19%|▏| 34/182 [1:04:33<4:35:21, 111.63s/it, Train Acc=84.63%Epoch[035/182] Train Acc: 84.63% Valid Acc:62.22% Train loss:0.4755 Valid loss:1.7698 LR:0.1
Training Progress:  19%|▏| 35/182 [1:04:33<4:33:32, 111.65s/it, Train Acc=84.63%Training: Epoch[036/182] Iteration[050/352] Loss: 0.4328 Acc:86.25%
Training: Epoch[036/182] Iteration[100/352] Loss: 0.4412 Acc:85.94%
Training: Epoch[036/182] Iteration[150/352] Loss: 0.4452 Acc:85.83%
Training: Epoch[036/182] Iteration[200/352] Loss: 0.4509 Acc:85.59%
Training: Epoch[036/182] Iteration[250/352] Loss: 0.4592 Acc:85.31%
Training: Epoch[036/182] Iteration[300/352] Loss: 0.4630 Acc:85.18%
Training: Epoch[036/182] Iteration[350/352] Loss: 0.4688 Acc:85.01%
Training Progress:  19%|▏| 35/182 [1:06:25<4:33:32, 111.65s/it, Train Acc=85.01%Epoch[036/182] Train Acc: 85.01% Valid Acc:63.10% Train loss:0.4686 Valid loss:1.7217 LR:0.1
Training Progress:  20%|▏| 36/182 [1:06:25<4:31:42, 111.66s/it, Train Acc=85.01%Training: Epoch[037/182] Iteration[050/352] Loss: 0.4005 Acc:87.08%
Training: Epoch[037/182] Iteration[100/352] Loss: 0.4079 Acc:86.72%
Training: Epoch[037/182] Iteration[150/352] Loss: 0.4152 Acc:86.56%
Training: Epoch[037/182] Iteration[200/352] Loss: 0.4334 Acc:86.04%
Training: Epoch[037/182] Iteration[250/352] Loss: 0.4444 Acc:85.75%
Training: Epoch[037/182] Iteration[300/352] Loss: 0.4529 Acc:85.48%
Training: Epoch[037/182] Iteration[350/352] Loss: 0.4623 Acc:85.18%
Training Progress:  20%|▏| 36/182 [1:08:16<4:31:42, 111.66s/it, Train Acc=85.18%Epoch[037/182] Train Acc: 85.18% Valid Acc:62.26% Train loss:0.4622 Valid loss:1.7159 LR:0.1
Training Progress:  20%|▏| 37/182 [1:08:16<4:29:54, 111.68s/it, Train Acc=85.18%Training: Epoch[038/182] Iteration[050/352] Loss: 0.3747 Acc:87.84%
Training: Epoch[038/182] Iteration[100/352] Loss: 0.3884 Acc:87.56%
Training: Epoch[038/182] Iteration[150/352] Loss: 0.4165 Acc:86.70%
Training: Epoch[038/182] Iteration[200/352] Loss: 0.4288 Acc:86.39%
Training: Epoch[038/182] Iteration[250/352] Loss: 0.4324 Acc:86.24%
Training: Epoch[038/182] Iteration[300/352] Loss: 0.4392 Acc:85.98%
Training: Epoch[038/182] Iteration[350/352] Loss: 0.4453 Acc:85.73%
Training Progress:  20%|▏| 37/182 [1:10:08<4:29:54, 111.68s/it, Train Acc=85.72%Epoch[038/182] Train Acc: 85.72% Valid Acc:62.40% Train loss:0.4461 Valid loss:1.7358 LR:0.1
Training Progress:  21%|▏| 38/182 [1:10:08<4:28:12, 111.75s/it, Train Acc=85.72%Training: Epoch[039/182] Iteration[050/352] Loss: 0.3776 Acc:87.89%
Training: Epoch[039/182] Iteration[100/352] Loss: 0.3864 Acc:87.44%
Training: Epoch[039/182] Iteration[150/352] Loss: 0.3917 Acc:87.17%
Training: Epoch[039/182] Iteration[200/352] Loss: 0.3988 Acc:87.04%
Training: Epoch[039/182] Iteration[250/352] Loss: 0.4112 Acc:86.71%
Training: Epoch[039/182] Iteration[300/352] Loss: 0.4257 Acc:86.30%
Training: Epoch[039/182] Iteration[350/352] Loss: 0.4330 Acc:86.12%
Training Progress:  21%|▏| 38/182 [1:12:00<4:28:12, 111.75s/it, Train Acc=86.12%Epoch[039/182] Train Acc: 86.12% Valid Acc:63.68% Train loss:0.4328 Valid loss:1.7482 LR:0.1
Training Progress:  21%|▏| 39/182 [1:12:00<4:26:16, 111.73s/it, Train Acc=86.12%Training: Epoch[040/182] Iteration[050/352] Loss: 0.3883 Acc:87.28%
Training: Epoch[040/182] Iteration[100/352] Loss: 0.3967 Acc:87.02%
Training: Epoch[040/182] Iteration[150/352] Loss: 0.4089 Acc:86.62%
Training: Epoch[040/182] Iteration[200/352] Loss: 0.4146 Acc:86.50%
Training: Epoch[040/182] Iteration[250/352] Loss: 0.4215 Acc:86.31%
Training: Epoch[040/182] Iteration[300/352] Loss: 0.4304 Acc:86.04%
Training: Epoch[040/182] Iteration[350/352] Loss: 0.4342 Acc:85.96%
Training Progress:  21%|▏| 39/182 [1:13:52<4:26:16, 111.73s/it, Train Acc=85.96%Epoch[040/182] Train Acc: 85.96% Valid Acc:61.30% Train loss:0.4347 Valid loss:1.8224 LR:0.1
Training Progress:  22%|▏| 40/182 [1:13:52<4:24:23, 111.71s/it, Train Acc=85.96%Training: Epoch[041/182] Iteration[050/352] Loss: 0.3324 Acc:89.50%
Training: Epoch[041/182] Iteration[100/352] Loss: 0.3536 Acc:88.66%
Training: Epoch[041/182] Iteration[150/352] Loss: 0.3870 Acc:87.49%
Training: Epoch[041/182] Iteration[200/352] Loss: 0.3971 Acc:87.09%
Training: Epoch[041/182] Iteration[250/352] Loss: 0.4081 Acc:86.78%
Training: Epoch[041/182] Iteration[300/352] Loss: 0.4148 Acc:86.61%
Training: Epoch[041/182] Iteration[350/352] Loss: 0.4221 Acc:86.37%
Training Progress:  22%|▏| 40/182 [1:15:43<4:24:23, 111.71s/it, Train Acc=86.37%Epoch[041/182] Train Acc: 86.37% Valid Acc:63.08% Train loss:0.4220 Valid loss:1.7441 LR:0.1
Training Progress:  23%|▏| 41/182 [1:15:43<4:22:29, 111.70s/it, Train Acc=86.37%Training: Epoch[042/182] Iteration[050/352] Loss: 0.3246 Acc:89.41%
Training: Epoch[042/182] Iteration[100/352] Loss: 0.3346 Acc:89.23%
Training: Epoch[042/182] Iteration[150/352] Loss: 0.3549 Acc:88.47%
Training: Epoch[042/182] Iteration[200/352] Loss: 0.3679 Acc:88.07%
Training: Epoch[042/182] Iteration[250/352] Loss: 0.3869 Acc:87.57%
Training: Epoch[042/182] Iteration[300/352] Loss: 0.3922 Acc:87.37%
Training: Epoch[042/182] Iteration[350/352] Loss: 0.3974 Acc:87.23%
Training Progress:  23%|▏| 41/182 [1:17:35<4:22:29, 111.70s/it, Train Acc=87.23%Epoch[042/182] Train Acc: 87.23% Valid Acc:63.10% Train loss:0.3978 Valid loss:1.8070 LR:0.1
Training Progress:  23%|▏| 42/182 [1:17:35<4:20:41, 111.72s/it, Train Acc=87.23%Training: Epoch[043/182] Iteration[050/352] Loss: 0.3571 Acc:88.42%
Training: Epoch[043/182] Iteration[100/352] Loss: 0.3480 Acc:88.59%
Training: Epoch[043/182] Iteration[150/352] Loss: 0.3649 Acc:88.18%
Training: Epoch[043/182] Iteration[200/352] Loss: 0.3800 Acc:87.61%
Training: Epoch[043/182] Iteration[250/352] Loss: 0.3840 Acc:87.57%
Training: Epoch[043/182] Iteration[300/352] Loss: 0.3858 Acc:87.50%
Training: Epoch[043/182] Iteration[350/352] Loss: 0.3948 Acc:87.20%
Training Progress:  23%|▏| 42/182 [1:19:27<4:20:41, 111.72s/it, Train Acc=87.18%Epoch[043/182] Train Acc: 87.18% Valid Acc:62.02% Train loss:0.3958 Valid loss:1.9864 LR:0.1
Training Progress:  24%|▏| 43/182 [1:19:27<4:18:48, 111.71s/it, Train Acc=87.18%Training: Epoch[044/182] Iteration[050/352] Loss: 0.3829 Acc:88.06%
Training: Epoch[044/182] Iteration[100/352] Loss: 0.3745 Acc:88.05%
Training: Epoch[044/182] Iteration[150/352] Loss: 0.3744 Acc:87.93%
Training: Epoch[044/182] Iteration[200/352] Loss: 0.3780 Acc:87.85%
Training: Epoch[044/182] Iteration[250/352] Loss: 0.3805 Acc:87.74%
Training: Epoch[044/182] Iteration[300/352] Loss: 0.3905 Acc:87.38%
Training: Epoch[044/182] Iteration[350/352] Loss: 0.3948 Acc:87.18%
Training Progress:  24%|▏| 43/182 [1:21:18<4:18:48, 111.71s/it, Train Acc=87.16%Epoch[044/182] Train Acc: 87.16% Valid Acc:61.72% Train loss:0.3960 Valid loss:1.8532 LR:0.1
Training Progress:  24%|▏| 44/182 [1:21:18<4:16:56, 111.71s/it, Train Acc=87.16%Training: Epoch[045/182] Iteration[050/352] Loss: 0.3447 Acc:88.94%
Training: Epoch[045/182] Iteration[100/352] Loss: 0.3523 Acc:88.36%
Training: Epoch[045/182] Iteration[150/352] Loss: 0.3667 Acc:87.92%
Training: Epoch[045/182] Iteration[200/352] Loss: 0.3749 Acc:87.73%
Training: Epoch[045/182] Iteration[250/352] Loss: 0.3811 Acc:87.52%
Training: Epoch[045/182] Iteration[300/352] Loss: 0.3864 Acc:87.31%
Training: Epoch[045/182] Iteration[350/352] Loss: 0.3908 Acc:87.16%
Training Progress:  24%|▏| 44/182 [1:23:10<4:16:56, 111.71s/it, Train Acc=87.16%Epoch[045/182] Train Acc: 87.16% Valid Acc:60.58% Train loss:0.3915 Valid loss:1.9558 LR:0.1
Training Progress:  25%|▏| 45/182 [1:23:10<4:15:06, 111.72s/it, Train Acc=87.16%Training: Epoch[046/182] Iteration[050/352] Loss: 0.3374 Acc:89.05%
Training: Epoch[046/182] Iteration[100/352] Loss: 0.3361 Acc:88.98%
Training: Epoch[046/182] Iteration[150/352] Loss: 0.3425 Acc:88.80%
Training: Epoch[046/182] Iteration[200/352] Loss: 0.3539 Acc:88.54%
Training: Epoch[046/182] Iteration[250/352] Loss: 0.3684 Acc:88.02%
Training: Epoch[046/182] Iteration[300/352] Loss: 0.3814 Acc:87.63%
Training: Epoch[046/182] Iteration[350/352] Loss: 0.3858 Acc:87.49%
Training Progress:  25%|▏| 45/182 [1:25:02<4:15:06, 111.72s/it, Train Acc=87.48%Epoch[046/182] Train Acc: 87.48% Valid Acc:60.60% Train loss:0.3865 Valid loss:2.0722 LR:0.1
Training Progress:  25%|▎| 46/182 [1:25:02<4:13:10, 111.69s/it, Train Acc=87.48%Training: Epoch[047/182] Iteration[050/352] Loss: 0.3242 Acc:89.67%
Training: Epoch[047/182] Iteration[100/352] Loss: 0.3261 Acc:89.48%
Training: Epoch[047/182] Iteration[150/352] Loss: 0.3411 Acc:89.05%
Training: Epoch[047/182] Iteration[200/352] Loss: 0.3468 Acc:88.82%
Training: Epoch[047/182] Iteration[250/352] Loss: 0.3551 Acc:88.52%
Training: Epoch[047/182] Iteration[300/352] Loss: 0.3643 Acc:88.22%
Training: Epoch[047/182] Iteration[350/352] Loss: 0.3707 Acc:88.04%
Training Progress:  25%|▎| 46/182 [1:26:53<4:13:10, 111.69s/it, Train Acc=88.04%Epoch[047/182] Train Acc: 88.04% Valid Acc:63.52% Train loss:0.3705 Valid loss:1.7727 LR:0.1
Training Progress:  26%|▎| 47/182 [1:26:53<4:11:15, 111.67s/it, Train Acc=88.04%Training: Epoch[048/182] Iteration[050/352] Loss: 0.3248 Acc:89.53%
Training: Epoch[048/182] Iteration[100/352] Loss: 0.3248 Acc:89.40%
Training: Epoch[048/182] Iteration[150/352] Loss: 0.3438 Acc:88.86%
Training: Epoch[048/182] Iteration[200/352] Loss: 0.3482 Acc:88.72%
Training: Epoch[048/182] Iteration[250/352] Loss: 0.3570 Acc:88.53%
Training: Epoch[048/182] Iteration[300/352] Loss: 0.3597 Acc:88.41%
Training: Epoch[048/182] Iteration[350/352] Loss: 0.3680 Acc:88.19%
Training Progress:  26%|▎| 47/182 [1:28:45<4:11:15, 111.67s/it, Train Acc=88.18%Epoch[048/182] Train Acc: 88.18% Valid Acc:64.10% Train loss:0.3679 Valid loss:1.8550 LR:0.1
Training Progress:  26%|▎| 48/182 [1:28:45<4:09:16, 111.62s/it, Train Acc=88.18%Training: Epoch[049/182] Iteration[050/352] Loss: 0.3095 Acc:90.09%
Training: Epoch[049/182] Iteration[100/352] Loss: 0.3100 Acc:90.01%
Training: Epoch[049/182] Iteration[150/352] Loss: 0.3264 Acc:89.51%
Training: Epoch[049/182] Iteration[200/352] Loss: 0.3306 Acc:89.31%
Training: Epoch[049/182] Iteration[250/352] Loss: 0.3411 Acc:89.03%
Training: Epoch[049/182] Iteration[300/352] Loss: 0.3485 Acc:88.79%
Training: Epoch[049/182] Iteration[350/352] Loss: 0.3560 Acc:88.54%
Training Progress:  26%|▎| 48/182 [1:30:37<4:09:16, 111.62s/it, Train Acc=88.55%Epoch[049/182] Train Acc: 88.55% Valid Acc:63.14% Train loss:0.3559 Valid loss:1.8224 LR:0.1
Training Progress:  27%|▎| 49/182 [1:30:37<4:07:22, 111.60s/it, Train Acc=88.55%Training: Epoch[050/182] Iteration[050/352] Loss: 0.3209 Acc:89.28%
Training: Epoch[050/182] Iteration[100/352] Loss: 0.3241 Acc:89.12%
Training: Epoch[050/182] Iteration[150/352] Loss: 0.3398 Acc:88.78%
Training: Epoch[050/182] Iteration[200/352] Loss: 0.3421 Acc:88.70%
Training: Epoch[050/182] Iteration[250/352] Loss: 0.3419 Acc:88.71%
Training: Epoch[050/182] Iteration[300/352] Loss: 0.3522 Acc:88.43%
Training: Epoch[050/182] Iteration[350/352] Loss: 0.3566 Acc:88.30%
Training Progress:  27%|▎| 49/182 [1:32:28<4:07:22, 111.60s/it, Train Acc=88.30%Epoch[050/182] Train Acc: 88.30% Valid Acc:64.00% Train loss:0.3573 Valid loss:1.8463 LR:0.1
Training Progress:  27%|▎| 50/182 [1:32:28<4:05:31, 111.60s/it, Train Acc=88.30%Training: Epoch[051/182] Iteration[050/352] Loss: 0.3133 Acc:89.97%
Training: Epoch[051/182] Iteration[100/352] Loss: 0.3103 Acc:89.77%
Training: Epoch[051/182] Iteration[150/352] Loss: 0.3304 Acc:89.23%
Training: Epoch[051/182] Iteration[200/352] Loss: 0.3346 Acc:89.09%
Training: Epoch[051/182] Iteration[250/352] Loss: 0.3371 Acc:88.98%
Training: Epoch[051/182] Iteration[300/352] Loss: 0.3433 Acc:88.79%
Training: Epoch[051/182] Iteration[350/352] Loss: 0.3511 Acc:88.62%
Training Progress:  27%|▎| 50/182 [1:34:20<4:05:31, 111.60s/it, Train Acc=88.63%Epoch[051/182] Train Acc: 88.63% Valid Acc:62.26% Train loss:0.3507 Valid loss:1.9580 LR:0.1
Training Progress:  28%|▎| 51/182 [1:34:20<4:03:46, 111.65s/it, Train Acc=88.63%Training: Epoch[052/182] Iteration[050/352] Loss: 0.3095 Acc:90.30%
Training: Epoch[052/182] Iteration[100/352] Loss: 0.2981 Acc:90.56%
Training: Epoch[052/182] Iteration[150/352] Loss: 0.3054 Acc:90.21%
Training: Epoch[052/182] Iteration[200/352] Loss: 0.3224 Acc:89.64%
Training: Epoch[052/182] Iteration[250/352] Loss: 0.3304 Acc:89.36%
Training: Epoch[052/182] Iteration[300/352] Loss: 0.3362 Acc:89.15%
Training: Epoch[052/182] Iteration[350/352] Loss: 0.3388 Acc:89.08%
Training Progress:  28%|▎| 51/182 [1:36:12<4:03:46, 111.65s/it, Train Acc=89.07%Epoch[052/182] Train Acc: 89.07% Valid Acc:63.96% Train loss:0.3389 Valid loss:1.8645 LR:0.1
Training Progress:  29%|▎| 52/182 [1:36:12<4:01:54, 111.65s/it, Train Acc=89.07%Training: Epoch[053/182] Iteration[050/352] Loss: 0.2919 Acc:90.59%
Training: Epoch[053/182] Iteration[100/352] Loss: 0.2976 Acc:90.42%
Training: Epoch[053/182] Iteration[150/352] Loss: 0.3019 Acc:90.23%
Training: Epoch[053/182] Iteration[200/352] Loss: 0.3135 Acc:89.93%
Training: Epoch[053/182] Iteration[250/352] Loss: 0.3231 Acc:89.60%
Training: Epoch[053/182] Iteration[300/352] Loss: 0.3278 Acc:89.40%
Training: Epoch[053/182] Iteration[350/352] Loss: 0.3329 Acc:89.21%
Training Progress:  29%|▎| 52/182 [1:38:03<4:01:54, 111.65s/it, Train Acc=89.21%Epoch[053/182] Train Acc: 89.21% Valid Acc:64.44% Train loss:0.3331 Valid loss:1.9450 LR:0.1
Training Progress:  29%|▎| 53/182 [1:38:03<4:00:06, 111.68s/it, Train Acc=89.21%Training: Epoch[054/182] Iteration[050/352] Loss: 0.2647 Acc:91.44%
Training: Epoch[054/182] Iteration[100/352] Loss: 0.2755 Acc:90.92%
Training: Epoch[054/182] Iteration[150/352] Loss: 0.2874 Acc:90.62%
Training: Epoch[054/182] Iteration[200/352] Loss: 0.2979 Acc:90.22%
Training: Epoch[054/182] Iteration[250/352] Loss: 0.3118 Acc:89.89%
Training: Epoch[054/182] Iteration[300/352] Loss: 0.3214 Acc:89.64%
Training: Epoch[054/182] Iteration[350/352] Loss: 0.3295 Acc:89.39%
Training Progress:  29%|▎| 53/182 [1:39:55<4:00:06, 111.68s/it, Train Acc=89.38%Epoch[054/182] Train Acc: 89.38% Valid Acc:63.74% Train loss:0.3298 Valid loss:1.8822 LR:0.1
Training Progress:  30%|▎| 54/182 [1:39:55<3:58:16, 111.69s/it, Train Acc=89.38%Training: Epoch[055/182] Iteration[050/352] Loss: 0.3043 Acc:89.98%
Training: Epoch[055/182] Iteration[100/352] Loss: 0.2963 Acc:90.41%
Training: Epoch[055/182] Iteration[150/352] Loss: 0.2994 Acc:90.24%
Training: Epoch[055/182] Iteration[200/352] Loss: 0.3165 Acc:89.71%
Training: Epoch[055/182] Iteration[250/352] Loss: 0.3199 Acc:89.67%
Training: Epoch[055/182] Iteration[300/352] Loss: 0.3210 Acc:89.60%
Training: Epoch[055/182] Iteration[350/352] Loss: 0.3327 Acc:89.26%
Training Progress:  30%|▎| 54/182 [1:41:47<3:58:16, 111.69s/it, Train Acc=89.22%Epoch[055/182] Train Acc: 89.22% Valid Acc:62.78% Train loss:0.3336 Valid loss:1.8733 LR:0.1
Training Progress:  30%|▎| 55/182 [1:41:47<3:56:27, 111.71s/it, Train Acc=89.22%Training: Epoch[056/182] Iteration[050/352] Loss: 0.3043 Acc:89.91%
Training: Epoch[056/182] Iteration[100/352] Loss: 0.3006 Acc:90.09%
Training: Epoch[056/182] Iteration[150/352] Loss: 0.3110 Acc:89.76%
Training: Epoch[056/182] Iteration[200/352] Loss: 0.3225 Acc:89.45%
Training: Epoch[056/182] Iteration[250/352] Loss: 0.3313 Acc:89.27%
Training: Epoch[056/182] Iteration[300/352] Loss: 0.3327 Acc:89.15%
Training: Epoch[056/182] Iteration[350/352] Loss: 0.3371 Acc:89.07%
Training Progress:  30%|▎| 55/182 [1:43:39<3:56:27, 111.71s/it, Train Acc=89.06%Epoch[056/182] Train Acc: 89.06% Valid Acc:63.08% Train loss:0.3381 Valid loss:1.8546 LR:0.1
Training Progress:  31%|▎| 56/182 [1:43:39<3:54:37, 111.73s/it, Train Acc=89.06%Training: Epoch[057/182] Iteration[050/352] Loss: 0.2890 Acc:90.80%
Training: Epoch[057/182] Iteration[100/352] Loss: 0.2747 Acc:91.00%
Training: Epoch[057/182] Iteration[150/352] Loss: 0.2861 Acc:90.76%
Training: Epoch[057/182] Iteration[200/352] Loss: 0.2963 Acc:90.38%
Training: Epoch[057/182] Iteration[250/352] Loss: 0.3117 Acc:89.87%
Training: Epoch[057/182] Iteration[300/352] Loss: 0.3210 Acc:89.62%
Training: Epoch[057/182] Iteration[350/352] Loss: 0.3282 Acc:89.43%
Training Progress:  31%|▎| 56/182 [1:45:30<3:54:37, 111.73s/it, Train Acc=89.42%Epoch[057/182] Train Acc: 89.42% Valid Acc:62.42% Train loss:0.3288 Valid loss:2.0192 LR:0.1
Training Progress:  31%|▎| 57/182 [1:45:30<3:52:49, 111.75s/it, Train Acc=89.42%Training: Epoch[058/182] Iteration[050/352] Loss: 0.2891 Acc:90.61%
Training: Epoch[058/182] Iteration[100/352] Loss: 0.2836 Acc:90.91%
Training: Epoch[058/182] Iteration[150/352] Loss: 0.2887 Acc:90.67%
Training: Epoch[058/182] Iteration[200/352] Loss: 0.2986 Acc:90.34%
Training: Epoch[058/182] Iteration[250/352] Loss: 0.3022 Acc:90.19%
Training: Epoch[058/182] Iteration[300/352] Loss: 0.3098 Acc:89.91%
Training: Epoch[058/182] Iteration[350/352] Loss: 0.3139 Acc:89.71%
Training Progress:  31%|▎| 57/182 [1:47:22<3:52:49, 111.75s/it, Train Acc=89.71%Epoch[058/182] Train Acc: 89.71% Valid Acc:62.08% Train loss:0.3143 Valid loss:2.1300 LR:0.1
Training Progress:  32%|▎| 58/182 [1:47:22<3:51:00, 111.78s/it, Train Acc=89.71%Training: Epoch[059/182] Iteration[050/352] Loss: 0.2832 Acc:90.88%
Training: Epoch[059/182] Iteration[100/352] Loss: 0.2840 Acc:90.62%
Training: Epoch[059/182] Iteration[150/352] Loss: 0.2860 Acc:90.67%
Training: Epoch[059/182] Iteration[200/352] Loss: 0.2908 Acc:90.48%
Training: Epoch[059/182] Iteration[250/352] Loss: 0.2992 Acc:90.16%
Training: Epoch[059/182] Iteration[300/352] Loss: 0.3042 Acc:89.97%
Training: Epoch[059/182] Iteration[350/352] Loss: 0.3113 Acc:89.81%
Training Progress:  32%|▎| 58/182 [1:49:14<3:51:00, 111.78s/it, Train Acc=89.83%Epoch[059/182] Train Acc: 89.83% Valid Acc:64.48% Train loss:0.3108 Valid loss:1.8947 LR:0.1
Training Progress:  32%|▎| 59/182 [1:49:14<3:49:10, 111.80s/it, Train Acc=89.83%Training: Epoch[060/182] Iteration[050/352] Loss: 0.2651 Acc:91.62%
Training: Epoch[060/182] Iteration[100/352] Loss: 0.2839 Acc:90.98%
Training: Epoch[060/182] Iteration[150/352] Loss: 0.2828 Acc:90.92%
Training: Epoch[060/182] Iteration[200/352] Loss: 0.2947 Acc:90.45%
Training: Epoch[060/182] Iteration[250/352] Loss: 0.3050 Acc:90.17%
Training: Epoch[060/182] Iteration[300/352] Loss: 0.3149 Acc:89.87%
Training: Epoch[060/182] Iteration[350/352] Loss: 0.3209 Acc:89.69%
Training Progress:  32%|▎| 59/182 [1:51:06<3:49:10, 111.80s/it, Train Acc=89.68%Epoch[060/182] Train Acc: 89.68% Valid Acc:61.40% Train loss:0.3215 Valid loss:2.1086 LR:0.1
Training Progress:  33%|▎| 60/182 [1:51:06<3:47:20, 111.81s/it, Train Acc=89.68%Training: Epoch[061/182] Iteration[050/352] Loss: 0.2582 Acc:91.72%
Training: Epoch[061/182] Iteration[100/352] Loss: 0.2709 Acc:91.12%
Training: Epoch[061/182] Iteration[150/352] Loss: 0.2766 Acc:90.94%
Training: Epoch[061/182] Iteration[200/352] Loss: 0.2845 Acc:90.73%
Training: Epoch[061/182] Iteration[250/352] Loss: 0.2922 Acc:90.63%
Training: Epoch[061/182] Iteration[300/352] Loss: 0.2990 Acc:90.45%
Training: Epoch[061/182] Iteration[350/352] Loss: 0.3079 Acc:90.14%
Training Progress:  33%|▎| 60/182 [1:52:58<3:47:20, 111.81s/it, Train Acc=90.15%Epoch[061/182] Train Acc: 90.15% Valid Acc:62.98% Train loss:0.3078 Valid loss:1.9169 LR:0.1
Training Progress:  34%|▎| 61/182 [1:52:58<3:45:27, 111.80s/it, Train Acc=90.15%Training: Epoch[062/182] Iteration[050/352] Loss: 0.2740 Acc:91.14%
Training: Epoch[062/182] Iteration[100/352] Loss: 0.2829 Acc:90.90%
Training: Epoch[062/182] Iteration[150/352] Loss: 0.2843 Acc:90.78%
Training: Epoch[062/182] Iteration[200/352] Loss: 0.2933 Acc:90.49%
Training: Epoch[062/182] Iteration[250/352] Loss: 0.2975 Acc:90.39%
Training: Epoch[062/182] Iteration[300/352] Loss: 0.3041 Acc:90.21%
Training: Epoch[062/182] Iteration[350/352] Loss: 0.3109 Acc:89.95%
Training Progress:  34%|▎| 61/182 [1:54:49<3:45:27, 111.80s/it, Train Acc=89.95%Epoch[062/182] Train Acc: 89.95% Valid Acc:62.08% Train loss:0.3109 Valid loss:2.0404 LR:0.1
Training Progress:  34%|▎| 62/182 [1:54:49<3:43:36, 111.80s/it, Train Acc=89.95%Training: Epoch[063/182] Iteration[050/352] Loss: 0.2824 Acc:91.03%
Training: Epoch[063/182] Iteration[100/352] Loss: 0.2739 Acc:91.24%
Training: Epoch[063/182] Iteration[150/352] Loss: 0.2790 Acc:91.05%
Training: Epoch[063/182] Iteration[200/352] Loss: 0.2862 Acc:90.67%
Training: Epoch[063/182] Iteration[250/352] Loss: 0.2981 Acc:90.30%
Training: Epoch[063/182] Iteration[300/352] Loss: 0.3040 Acc:90.12%
Training: Epoch[063/182] Iteration[350/352] Loss: 0.3117 Acc:89.85%
Training Progress:  34%|▎| 62/182 [1:56:41<3:43:36, 111.80s/it, Train Acc=89.84%Epoch[063/182] Train Acc: 89.84% Valid Acc:62.70% Train loss:0.3120 Valid loss:1.9989 LR:0.1
Training Progress:  35%|▎| 63/182 [1:56:41<3:41:47, 111.83s/it, Train Acc=89.84%Training: Epoch[064/182] Iteration[050/352] Loss: 0.2829 Acc:90.67%
Training: Epoch[064/182] Iteration[100/352] Loss: 0.2726 Acc:91.10%
Training: Epoch[064/182] Iteration[150/352] Loss: 0.2759 Acc:91.07%
Training: Epoch[064/182] Iteration[200/352] Loss: 0.2798 Acc:90.97%
Training: Epoch[064/182] Iteration[250/352] Loss: 0.2855 Acc:90.86%
Training: Epoch[064/182] Iteration[300/352] Loss: 0.2921 Acc:90.60%
Training: Epoch[064/182] Iteration[350/352] Loss: 0.3003 Acc:90.37%
Training Progress:  35%|▎| 63/182 [1:58:33<3:41:47, 111.83s/it, Train Acc=90.34%Epoch[064/182] Train Acc: 90.34% Valid Acc:61.12% Train loss:0.3016 Valid loss:2.1611 LR:0.1
Training Progress:  35%|▎| 64/182 [1:58:33<3:39:58, 111.85s/it, Train Acc=90.34%Training: Epoch[065/182] Iteration[050/352] Loss: 0.2792 Acc:90.92%
Training: Epoch[065/182] Iteration[100/352] Loss: 0.2781 Acc:90.91%
Training: Epoch[065/182] Iteration[150/352] Loss: 0.2829 Acc:90.81%
Training: Epoch[065/182] Iteration[200/352] Loss: 0.2858 Acc:90.71%
Training: Epoch[065/182] Iteration[250/352] Loss: 0.2948 Acc:90.42%
Training: Epoch[065/182] Iteration[300/352] Loss: 0.3041 Acc:90.12%
Training: Epoch[065/182] Iteration[350/352] Loss: 0.3073 Acc:90.02%
Training Progress:  35%|▎| 64/182 [2:00:25<3:39:58, 111.85s/it, Train Acc=90.03%Epoch[065/182] Train Acc: 90.03% Valid Acc:63.18% Train loss:0.3076 Valid loss:1.8961 LR:0.1
Training Progress:  36%|▎| 65/182 [2:00:25<3:38:07, 111.85s/it, Train Acc=90.03%Training: Epoch[066/182] Iteration[050/352] Loss: 0.2510 Acc:91.72%
Training: Epoch[066/182] Iteration[100/352] Loss: 0.2479 Acc:92.05%
Training: Epoch[066/182] Iteration[150/352] Loss: 0.2578 Acc:91.75%
Training: Epoch[066/182] Iteration[200/352] Loss: 0.2735 Acc:91.25%
Training: Epoch[066/182] Iteration[250/352] Loss: 0.2841 Acc:90.91%
Training: Epoch[066/182] Iteration[300/352] Loss: 0.2888 Acc:90.71%
Training: Epoch[066/182] Iteration[350/352] Loss: 0.2942 Acc:90.49%
Training Progress:  36%|▎| 65/182 [2:02:17<3:38:07, 111.85s/it, Train Acc=90.49%Epoch[066/182] Train Acc: 90.49% Valid Acc:62.68% Train loss:0.2944 Valid loss:1.9704 LR:0.1
Training Progress:  36%|▎| 66/182 [2:02:17<3:36:11, 111.82s/it, Train Acc=90.49%Training: Epoch[067/182] Iteration[050/352] Loss: 0.2877 Acc:90.48%
Training: Epoch[067/182] Iteration[100/352] Loss: 0.2907 Acc:90.53%
Training: Epoch[067/182] Iteration[150/352] Loss: 0.2831 Acc:90.72%
Training: Epoch[067/182] Iteration[200/352] Loss: 0.2811 Acc:90.81%
Training: Epoch[067/182] Iteration[250/352] Loss: 0.2891 Acc:90.59%
Training: Epoch[067/182] Iteration[300/352] Loss: 0.2986 Acc:90.33%
Training: Epoch[067/182] Iteration[350/352] Loss: 0.3015 Acc:90.17%
Training Progress:  36%|▎| 66/182 [2:04:09<3:36:11, 111.82s/it, Train Acc=90.17%Epoch[067/182] Train Acc: 90.17% Valid Acc:63.92% Train loss:0.3019 Valid loss:1.9684 LR:0.1
Training Progress:  37%|▎| 67/182 [2:04:09<3:34:23, 111.85s/it, Train Acc=90.17%Training: Epoch[068/182] Iteration[050/352] Loss: 0.2511 Acc:91.80%
Training: Epoch[068/182] Iteration[100/352] Loss: 0.2549 Acc:91.70%
Training: Epoch[068/182] Iteration[150/352] Loss: 0.2664 Acc:91.37%
Training: Epoch[068/182] Iteration[200/352] Loss: 0.2705 Acc:91.28%
Training: Epoch[068/182] Iteration[250/352] Loss: 0.2746 Acc:91.10%
Training: Epoch[068/182] Iteration[300/352] Loss: 0.2818 Acc:90.87%
Training: Epoch[068/182] Iteration[350/352] Loss: 0.2877 Acc:90.70%
Training Progress:  37%|▎| 67/182 [2:06:01<3:34:23, 111.85s/it, Train Acc=90.68%Epoch[068/182] Train Acc: 90.68% Valid Acc:61.64% Train loss:0.2881 Valid loss:2.0678 LR:0.1
Training Progress:  37%|▎| 68/182 [2:06:01<3:32:32, 111.87s/it, Train Acc=90.68%Training: Epoch[069/182] Iteration[050/352] Loss: 0.2671 Acc:91.25%
Training: Epoch[069/182] Iteration[100/352] Loss: 0.2652 Acc:91.41%
Training: Epoch[069/182] Iteration[150/352] Loss: 0.2730 Acc:91.28%
Training: Epoch[069/182] Iteration[200/352] Loss: 0.2765 Acc:91.14%
Training: Epoch[069/182] Iteration[250/352] Loss: 0.2826 Acc:90.94%
Training: Epoch[069/182] Iteration[300/352] Loss: 0.2864 Acc:90.76%
Training: Epoch[069/182] Iteration[350/352] Loss: 0.2907 Acc:90.61%
Training Progress:  37%|▎| 68/182 [2:07:53<3:32:32, 111.87s/it, Train Acc=90.60%Epoch[069/182] Train Acc: 90.60% Valid Acc:63.26% Train loss:0.2911 Valid loss:2.0015 LR:0.1
Training Progress:  38%|▍| 69/182 [2:07:53<3:30:43, 111.89s/it, Train Acc=90.60%Training: Epoch[070/182] Iteration[050/352] Loss: 0.2792 Acc:91.03%
Training: Epoch[070/182] Iteration[100/352] Loss: 0.2575 Acc:91.68%
Training: Epoch[070/182] Iteration[150/352] Loss: 0.2635 Acc:91.41%
Training: Epoch[070/182] Iteration[200/352] Loss: 0.2632 Acc:91.40%
Training: Epoch[070/182] Iteration[250/352] Loss: 0.2727 Acc:91.08%
Training: Epoch[070/182] Iteration[300/352] Loss: 0.2867 Acc:90.62%
Training: Epoch[070/182] Iteration[350/352] Loss: 0.2991 Acc:90.22%
Training Progress:  38%|▍| 69/182 [2:09:44<3:30:43, 111.89s/it, Train Acc=90.21%Epoch[070/182] Train Acc: 90.21% Valid Acc:62.18% Train loss:0.2994 Valid loss:1.9246 LR:0.1
Training Progress:  38%|▍| 70/182 [2:09:44<3:28:51, 111.89s/it, Train Acc=90.21%Training: Epoch[071/182] Iteration[050/352] Loss: 0.2693 Acc:91.56%
Training: Epoch[071/182] Iteration[100/352] Loss: 0.2711 Acc:91.35%
Training: Epoch[071/182] Iteration[150/352] Loss: 0.2721 Acc:91.24%
Training: Epoch[071/182] Iteration[200/352] Loss: 0.2722 Acc:91.22%
Training: Epoch[071/182] Iteration[250/352] Loss: 0.2836 Acc:90.82%
Training: Epoch[071/182] Iteration[300/352] Loss: 0.2974 Acc:90.37%
Training: Epoch[071/182] Iteration[350/352] Loss: 0.2992 Acc:90.29%
Training Progress:  38%|▍| 70/182 [2:11:36<3:28:51, 111.89s/it, Train Acc=90.28%Epoch[071/182] Train Acc: 90.28% Valid Acc:63.10% Train loss:0.2994 Valid loss:1.9877 LR:0.1
Training Progress:  39%|▍| 71/182 [2:11:36<3:26:59, 111.89s/it, Train Acc=90.28%Training: Epoch[072/182] Iteration[050/352] Loss: 0.2610 Acc:91.61%
Training: Epoch[072/182] Iteration[100/352] Loss: 0.2533 Acc:91.89%
Training: Epoch[072/182] Iteration[150/352] Loss: 0.2514 Acc:91.90%
Training: Epoch[072/182] Iteration[200/352] Loss: 0.2543 Acc:91.77%
Training: Epoch[072/182] Iteration[250/352] Loss: 0.2601 Acc:91.57%
Training: Epoch[072/182] Iteration[300/352] Loss: 0.2713 Acc:91.28%
Training: Epoch[072/182] Iteration[350/352] Loss: 0.2769 Acc:91.08%
Training Progress:  39%|▍| 71/182 [2:13:28<3:26:59, 111.89s/it, Train Acc=91.09%Epoch[072/182] Train Acc: 91.09% Valid Acc:63.68% Train loss:0.2768 Valid loss:1.9259 LR:0.1
Training Progress:  40%|▍| 72/182 [2:13:28<3:25:10, 111.91s/it, Train Acc=91.09%Training: Epoch[073/182] Iteration[050/352] Loss: 0.2410 Acc:92.19%
Training: Epoch[073/182] Iteration[100/352] Loss: 0.2539 Acc:91.80%
Training: Epoch[073/182] Iteration[150/352] Loss: 0.2616 Acc:91.56%
Training: Epoch[073/182] Iteration[200/352] Loss: 0.2708 Acc:91.28%
Training: Epoch[073/182] Iteration[250/352] Loss: 0.2700 Acc:91.24%
Training: Epoch[073/182] Iteration[300/352] Loss: 0.2756 Acc:91.04%
Training: Epoch[073/182] Iteration[350/352] Loss: 0.2819 Acc:90.87%
Training Progress:  40%|▍| 72/182 [2:15:20<3:25:10, 111.91s/it, Train Acc=90.86%Epoch[073/182] Train Acc: 90.86% Valid Acc:61.44% Train loss:0.2818 Valid loss:2.0448 LR:0.1
Training Progress:  40%|▍| 73/182 [2:15:20<3:23:19, 111.92s/it, Train Acc=90.86%Training: Epoch[074/182] Iteration[050/352] Loss: 0.2647 Acc:91.19%
Training: Epoch[074/182] Iteration[100/352] Loss: 0.2599 Acc:91.38%
Training: Epoch[074/182] Iteration[150/352] Loss: 0.2656 Acc:91.28%
Training: Epoch[074/182] Iteration[200/352] Loss: 0.2789 Acc:90.99%
Training: Epoch[074/182] Iteration[250/352] Loss: 0.2809 Acc:90.86%
Training: Epoch[074/182] Iteration[300/352] Loss: 0.2828 Acc:90.76%
Training: Epoch[074/182] Iteration[350/352] Loss: 0.2812 Acc:90.82%
Training Progress:  40%|▍| 73/182 [2:17:12<3:23:19, 111.92s/it, Train Acc=90.84%Epoch[074/182] Train Acc: 90.84% Valid Acc:63.16% Train loss:0.2807 Valid loss:2.0323 LR:0.1
Training Progress:  41%|▍| 74/182 [2:17:12<3:21:31, 111.95s/it, Train Acc=90.84%Training: Epoch[075/182] Iteration[050/352] Loss: 0.2581 Acc:91.86%
Training: Epoch[075/182] Iteration[100/352] Loss: 0.2605 Acc:91.82%
Training: Epoch[075/182] Iteration[150/352] Loss: 0.2670 Acc:91.46%
Training: Epoch[075/182] Iteration[200/352] Loss: 0.2727 Acc:91.27%
Training: Epoch[075/182] Iteration[250/352] Loss: 0.2772 Acc:91.11%
Training: Epoch[075/182] Iteration[300/352] Loss: 0.2817 Acc:90.94%
Training: Epoch[075/182] Iteration[350/352] Loss: 0.2866 Acc:90.74%
Training Progress:  41%|▍| 74/182 [2:19:04<3:21:31, 111.95s/it, Train Acc=90.74%Epoch[075/182] Train Acc: 90.74% Valid Acc:60.10% Train loss:0.2863 Valid loss:2.2981 LR:0.1
Training Progress:  41%|▍| 75/182 [2:19:04<3:19:45, 112.01s/it, Train Acc=90.74%Training: Epoch[076/182] Iteration[050/352] Loss: 0.2508 Acc:92.12%
Training: Epoch[076/182] Iteration[100/352] Loss: 0.2357 Acc:92.41%
Training: Epoch[076/182] Iteration[150/352] Loss: 0.2414 Acc:92.11%
Training: Epoch[076/182] Iteration[200/352] Loss: 0.2547 Acc:91.61%
Training: Epoch[076/182] Iteration[250/352] Loss: 0.2641 Acc:91.27%
Training: Epoch[076/182] Iteration[300/352] Loss: 0.2769 Acc:90.85%
Training: Epoch[076/182] Iteration[350/352] Loss: 0.2836 Acc:90.65%
Training Progress:  41%|▍| 75/182 [2:20:57<3:19:45, 112.01s/it, Train Acc=90.65%Epoch[076/182] Train Acc: 90.65% Valid Acc:63.26% Train loss:0.2836 Valid loss:1.9420 LR:0.1
Training Progress:  42%|▍| 76/182 [2:20:57<3:17:55, 112.04s/it, Train Acc=90.65%Training: Epoch[077/182] Iteration[050/352] Loss: 0.2522 Acc:91.86%
Training: Epoch[077/182] Iteration[100/352] Loss: 0.2679 Acc:91.30%
Training: Epoch[077/182] Iteration[150/352] Loss: 0.2734 Acc:91.12%
Training: Epoch[077/182] Iteration[200/352] Loss: 0.2740 Acc:91.10%
Training: Epoch[077/182] Iteration[250/352] Loss: 0.2759 Acc:91.02%
Training: Epoch[077/182] Iteration[300/352] Loss: 0.2819 Acc:90.84%
Training: Epoch[077/182] Iteration[350/352] Loss: 0.2850 Acc:90.76%
Training Progress:  42%|▍| 76/182 [2:22:49<3:17:55, 112.04s/it, Train Acc=90.75%Epoch[077/182] Train Acc: 90.75% Valid Acc:63.98% Train loss:0.2852 Valid loss:2.0128 LR:0.1
Training Progress:  42%|▍| 77/182 [2:22:49<3:16:03, 112.03s/it, Train Acc=90.75%Training: Epoch[078/182] Iteration[050/352] Loss: 0.2411 Acc:92.19%
Training: Epoch[078/182] Iteration[100/352] Loss: 0.2561 Acc:91.70%
Training: Epoch[078/182] Iteration[150/352] Loss: 0.2622 Acc:91.54%
Training: Epoch[078/182] Iteration[200/352] Loss: 0.2699 Acc:91.29%
Training: Epoch[078/182] Iteration[250/352] Loss: 0.2744 Acc:91.10%
Training: Epoch[078/182] Iteration[300/352] Loss: 0.2800 Acc:90.92%
Training: Epoch[078/182] Iteration[350/352] Loss: 0.2850 Acc:90.75%
Training Progress:  42%|▍| 77/182 [2:24:41<3:16:03, 112.03s/it, Train Acc=90.73%Epoch[078/182] Train Acc: 90.73% Valid Acc:63.90% Train loss:0.2858 Valid loss:1.9624 LR:0.1
Training Progress:  43%|▍| 78/182 [2:24:41<3:14:12, 112.04s/it, Train Acc=90.73%Training: Epoch[079/182] Iteration[050/352] Loss: 0.2435 Acc:92.16%
Training: Epoch[079/182] Iteration[100/352] Loss: 0.2398 Acc:92.28%
Training: Epoch[079/182] Iteration[150/352] Loss: 0.2482 Acc:92.10%
Training: Epoch[079/182] Iteration[200/352] Loss: 0.2599 Acc:91.60%
Training: Epoch[079/182] Iteration[250/352] Loss: 0.2643 Acc:91.50%
Training: Epoch[079/182] Iteration[300/352] Loss: 0.2634 Acc:91.49%
Training: Epoch[079/182] Iteration[350/352] Loss: 0.2661 Acc:91.39%
Training Progress:  43%|▍| 78/182 [2:26:33<3:14:12, 112.04s/it, Train Acc=91.39%Epoch[079/182] Train Acc: 91.39% Valid Acc:63.88% Train loss:0.2660 Valid loss:1.9723 LR:0.1
Training Progress:  43%|▍| 79/182 [2:26:33<3:12:20, 112.04s/it, Train Acc=91.39%Training: Epoch[080/182] Iteration[050/352] Loss: 0.2300 Acc:92.36%
Training: Epoch[080/182] Iteration[100/352] Loss: 0.2390 Acc:91.84%
Training: Epoch[080/182] Iteration[150/352] Loss: 0.2459 Acc:91.82%
Training: Epoch[080/182] Iteration[200/352] Loss: 0.2638 Acc:91.24%
Training: Epoch[080/182] Iteration[250/352] Loss: 0.2717 Acc:91.02%
Training: Epoch[080/182] Iteration[300/352] Loss: 0.2765 Acc:90.88%
Training: Epoch[080/182] Iteration[350/352] Loss: 0.2791 Acc:90.82%
Training Progress:  43%|▍| 79/182 [2:28:25<3:12:20, 112.04s/it, Train Acc=90.82%Epoch[080/182] Train Acc: 90.82% Valid Acc:64.96% Train loss:0.2793 Valid loss:1.9118 LR:0.1
Training Progress:  44%|▍| 80/182 [2:28:25<3:10:33, 112.09s/it, Train Acc=90.82%Training: Epoch[081/182] Iteration[050/352] Loss: 0.2566 Acc:92.08%
Training: Epoch[081/182] Iteration[100/352] Loss: 0.2421 Acc:92.48%
Training: Epoch[081/182] Iteration[150/352] Loss: 0.2440 Acc:92.14%
Training: Epoch[081/182] Iteration[200/352] Loss: 0.2545 Acc:91.77%
Training: Epoch[081/182] Iteration[250/352] Loss: 0.2662 Acc:91.42%
Training: Epoch[081/182] Iteration[300/352] Loss: 0.2702 Acc:91.27%
Training: Epoch[081/182] Iteration[350/352] Loss: 0.2744 Acc:91.12%
Training Progress:  44%|▍| 80/182 [2:30:17<3:10:33, 112.09s/it, Train Acc=91.10%Epoch[081/182] Train Acc: 91.10% Valid Acc:62.80% Train loss:0.2753 Valid loss:2.0068 LR:0.1
Training Progress:  45%|▍| 81/182 [2:30:17<3:08:39, 112.07s/it, Train Acc=91.10%Training: Epoch[082/182] Iteration[050/352] Loss: 0.2201 Acc:92.66%
Training: Epoch[082/182] Iteration[100/352] Loss: 0.2200 Acc:92.80%
Training: Epoch[082/182] Iteration[150/352] Loss: 0.2319 Acc:92.48%
Training: Epoch[082/182] Iteration[200/352] Loss: 0.2439 Acc:92.13%
Training: Epoch[082/182] Iteration[250/352] Loss: 0.2563 Acc:91.76%
Training: Epoch[082/182] Iteration[300/352] Loss: 0.2635 Acc:91.50%
Training: Epoch[082/182] Iteration[350/352] Loss: 0.2717 Acc:91.22%
Training Progress:  45%|▍| 81/182 [2:32:09<3:08:39, 112.07s/it, Train Acc=91.21%Epoch[082/182] Train Acc: 91.21% Valid Acc:62.56% Train loss:0.2719 Valid loss:1.9198 LR:0.1
Training Progress:  45%|▍| 82/182 [2:32:09<3:06:44, 112.04s/it, Train Acc=91.21%Training: Epoch[083/182] Iteration[050/352] Loss: 0.2105 Acc:93.19%
Training: Epoch[083/182] Iteration[100/352] Loss: 0.2079 Acc:93.14%
Training: Epoch[083/182] Iteration[150/352] Loss: 0.2179 Acc:92.86%
Training: Epoch[083/182] Iteration[200/352] Loss: 0.2433 Acc:92.12%
Training: Epoch[083/182] Iteration[250/352] Loss: 0.2605 Acc:91.53%
Training: Epoch[083/182] Iteration[300/352] Loss: 0.2723 Acc:91.20%
Training: Epoch[083/182] Iteration[350/352] Loss: 0.2805 Acc:90.95%
Training Progress:  45%|▍| 82/182 [2:34:01<3:06:44, 112.04s/it, Train Acc=90.94%Epoch[083/182] Train Acc: 90.94% Valid Acc:63.32% Train loss:0.2806 Valid loss:1.9750 LR:0.1
Training Progress:  46%|▍| 83/182 [2:34:01<3:04:51, 112.04s/it, Train Acc=90.94%Training: Epoch[084/182] Iteration[050/352] Loss: 0.2457 Acc:92.20%
Training: Epoch[084/182] Iteration[100/352] Loss: 0.2450 Acc:92.13%
Training: Epoch[084/182] Iteration[150/352] Loss: 0.2313 Acc:92.58%
Training: Epoch[084/182] Iteration[200/352] Loss: 0.2318 Acc:92.54%
Training: Epoch[084/182] Iteration[250/352] Loss: 0.2426 Acc:92.14%
Training: Epoch[084/182] Iteration[300/352] Loss: 0.2516 Acc:91.86%
Training: Epoch[084/182] Iteration[350/352] Loss: 0.2596 Acc:91.63%
Training Progress:  46%|▍| 83/182 [2:35:53<3:04:51, 112.04s/it, Train Acc=91.62%Epoch[084/182] Train Acc: 91.62% Valid Acc:61.64% Train loss:0.2601 Valid loss:2.1659 LR:0.1
Training Progress:  46%|▍| 84/182 [2:35:53<3:02:58, 112.03s/it, Train Acc=91.62%Training: Epoch[085/182] Iteration[050/352] Loss: 0.2557 Acc:91.61%
Training: Epoch[085/182] Iteration[100/352] Loss: 0.2394 Acc:92.22%
Training: Epoch[085/182] Iteration[150/352] Loss: 0.2390 Acc:92.29%
Training: Epoch[085/182] Iteration[200/352] Loss: 0.2366 Acc:92.31%
Training: Epoch[085/182] Iteration[250/352] Loss: 0.2478 Acc:91.98%
Training: Epoch[085/182] Iteration[300/352] Loss: 0.2558 Acc:91.68%
Training: Epoch[085/182] Iteration[350/352] Loss: 0.2603 Acc:91.59%
Training Progress:  46%|▍| 84/182 [2:37:45<3:02:58, 112.03s/it, Train Acc=91.59%Epoch[085/182] Train Acc: 91.59% Valid Acc:65.40% Train loss:0.2604 Valid loss:1.8215 LR:0.1
Training Progress:  47%|▍| 85/182 [2:37:45<3:01:05, 112.02s/it, Train Acc=91.59%Training: Epoch[086/182] Iteration[050/352] Loss: 0.2135 Acc:93.31%
Training: Epoch[086/182] Iteration[100/352] Loss: 0.2229 Acc:92.83%
Training: Epoch[086/182] Iteration[150/352] Loss: 0.2362 Acc:92.33%
Training: Epoch[086/182] Iteration[200/352] Loss: 0.2454 Acc:92.07%
Training: Epoch[086/182] Iteration[250/352] Loss: 0.2564 Acc:91.69%
Training: Epoch[086/182] Iteration[300/352] Loss: 0.2684 Acc:91.32%
Training: Epoch[086/182] Iteration[350/352] Loss: 0.2727 Acc:91.13%
Training Progress:  47%|▍| 85/182 [2:39:37<3:01:05, 112.02s/it, Train Acc=91.12%Epoch[086/182] Train Acc: 91.12% Valid Acc:64.48% Train loss:0.2730 Valid loss:1.7791 LR:0.1
Training Progress:  47%|▍| 86/182 [2:39:37<2:59:15, 112.03s/it, Train Acc=91.12%Training: Epoch[087/182] Iteration[050/352] Loss: 0.2083 Acc:93.30%
Training: Epoch[087/182] Iteration[100/352] Loss: 0.2235 Acc:92.67%
Training: Epoch[087/182] Iteration[150/352] Loss: 0.2418 Acc:92.23%
Training: Epoch[087/182] Iteration[200/352] Loss: 0.2620 Acc:91.69%
Training: Epoch[087/182] Iteration[250/352] Loss: 0.2661 Acc:91.58%
Training: Epoch[087/182] Iteration[300/352] Loss: 0.2694 Acc:91.45%
Training: Epoch[087/182] Iteration[350/352] Loss: 0.2709 Acc:91.37%
Training Progress:  47%|▍| 86/182 [2:41:29<2:59:15, 112.03s/it, Train Acc=91.37%Epoch[087/182] Train Acc: 91.37% Valid Acc:63.36% Train loss:0.2710 Valid loss:2.0803 LR:0.1
Training Progress:  48%|▍| 87/182 [2:41:29<2:57:21, 112.01s/it, Train Acc=91.37%Training: Epoch[088/182] Iteration[050/352] Loss: 0.2082 Acc:93.73%
Training: Epoch[088/182] Iteration[100/352] Loss: 0.2105 Acc:93.55%
Training: Epoch[088/182] Iteration[150/352] Loss: 0.2231 Acc:92.98%
Training: Epoch[088/182] Iteration[200/352] Loss: 0.2381 Acc:92.43%
Training: Epoch[088/182] Iteration[250/352] Loss: 0.2487 Acc:92.07%
Training: Epoch[088/182] Iteration[300/352] Loss: 0.2586 Acc:91.75%
Training: Epoch[088/182] Iteration[350/352] Loss: 0.2693 Acc:91.39%
Training Progress:  48%|▍| 87/182 [2:43:21<2:57:21, 112.01s/it, Train Acc=91.38%Epoch[088/182] Train Acc: 91.38% Valid Acc:63.54% Train loss:0.2698 Valid loss:1.9503 LR:0.1
Training Progress:  48%|▍| 88/182 [2:43:21<2:55:28, 112.01s/it, Train Acc=91.38%Training: Epoch[089/182] Iteration[050/352] Loss: 0.2377 Acc:92.02%
Training: Epoch[089/182] Iteration[100/352] Loss: 0.2286 Acc:92.39%
Training: Epoch[089/182] Iteration[150/352] Loss: 0.2361 Acc:92.18%
Training: Epoch[089/182] Iteration[200/352] Loss: 0.2445 Acc:92.07%
Training: Epoch[089/182] Iteration[250/352] Loss: 0.2555 Acc:91.72%
Training: Epoch[089/182] Iteration[300/352] Loss: 0.2620 Acc:91.51%
Training: Epoch[089/182] Iteration[350/352] Loss: 0.2643 Acc:91.45%
Training Progress:  48%|▍| 88/182 [2:45:13<2:55:28, 112.01s/it, Train Acc=91.45%Epoch[089/182] Train Acc: 91.45% Valid Acc:64.82% Train loss:0.2639 Valid loss:1.8676 LR:0.1
Training Progress:  49%|▍| 89/182 [2:45:13<2:53:39, 112.04s/it, Train Acc=91.45%Training: Epoch[090/182] Iteration[050/352] Loss: 0.1843 Acc:94.03%
Training: Epoch[090/182] Iteration[100/352] Loss: 0.2137 Acc:93.04%
Training: Epoch[090/182] Iteration[150/352] Loss: 0.2242 Acc:92.67%
Training: Epoch[090/182] Iteration[200/352] Loss: 0.2333 Acc:92.42%
Training: Epoch[090/182] Iteration[250/352] Loss: 0.2438 Acc:92.12%
Training: Epoch[090/182] Iteration[300/352] Loss: 0.2537 Acc:91.81%
Training: Epoch[090/182] Iteration[350/352] Loss: 0.2648 Acc:91.48%
Training Progress:  49%|▍| 89/182 [2:47:05<2:53:39, 112.04s/it, Train Acc=91.48%Epoch[090/182] Train Acc: 91.48% Valid Acc:61.92% Train loss:0.2652 Valid loss:2.1328 LR:0.1
Training Progress:  49%|▍| 90/182 [2:47:05<2:51:48, 112.05s/it, Train Acc=91.48%Training: Epoch[091/182] Iteration[050/352] Loss: 0.2493 Acc:92.12%
Training: Epoch[091/182] Iteration[100/352] Loss: 0.2248 Acc:92.88%
Training: Epoch[091/182] Iteration[150/352] Loss: 0.2317 Acc:92.48%
Training: Epoch[091/182] Iteration[200/352] Loss: 0.2330 Acc:92.41%
Training: Epoch[091/182] Iteration[250/352] Loss: 0.2478 Acc:92.00%
Training: Epoch[091/182] Iteration[300/352] Loss: 0.2528 Acc:91.81%
Training: Epoch[091/182] Iteration[350/352] Loss: 0.2615 Acc:91.52%
Training Progress:  49%|▍| 90/182 [2:48:57<2:51:48, 112.05s/it, Train Acc=91.52%Epoch[091/182] Train Acc: 91.52% Valid Acc:62.62% Train loss:0.2613 Valid loss:2.1316 LR:0.1
Training Progress:  50%|▌| 91/182 [2:48:57<2:49:56, 112.05s/it, Train Acc=91.52%Training: Epoch[092/182] Iteration[050/352] Loss: 0.2213 Acc:93.09%
Training: Epoch[092/182] Iteration[100/352] Loss: 0.2051 Acc:93.48%
Training: Epoch[092/182] Iteration[150/352] Loss: 0.2072 Acc:93.38%
Training: Epoch[092/182] Iteration[200/352] Loss: 0.2129 Acc:93.24%
Training: Epoch[092/182] Iteration[250/352] Loss: 0.2256 Acc:92.82%
Training: Epoch[092/182] Iteration[300/352] Loss: 0.2393 Acc:92.45%
Training: Epoch[092/182] Iteration[350/352] Loss: 0.2468 Acc:92.17%
Training Progress:  50%|▌| 91/182 [2:50:49<2:49:56, 112.05s/it, Train Acc=92.18%Epoch[092/182] Train Acc: 92.18% Valid Acc:62.90% Train loss:0.2466 Valid loss:2.0777 LR:0.1
Training Progress:  51%|▌| 92/182 [2:50:49<2:48:05, 112.06s/it, Train Acc=92.18%Training: Epoch[093/182] Iteration[050/352] Loss: 0.1506 Acc:95.30%
Training: Epoch[093/182] Iteration[100/352] Loss: 0.1300 Acc:95.88%
Training: Epoch[093/182] Iteration[150/352] Loss: 0.1161 Acc:96.41%
Training: Epoch[093/182] Iteration[200/352] Loss: 0.1053 Acc:96.76%
Training: Epoch[093/182] Iteration[250/352] Loss: 0.0980 Acc:96.99%
Training: Epoch[093/182] Iteration[300/352] Loss: 0.0914 Acc:97.24%
Training: Epoch[093/182] Iteration[350/352] Loss: 0.0859 Acc:97.42%
Training Progress:  51%|▌| 92/182 [2:52:41<2:48:05, 112.06s/it, Train Acc=97.43%Epoch[093/182] Train Acc: 97.43% Valid Acc:71.54% Train loss:0.0857 Valid loss:1.5323 LR:0.010000000000000002
Training Progress:  51%|▌| 93/182 [2:52:41<2:46:17, 112.10s/it, Train Acc=97.43%Training: Epoch[094/182] Iteration[050/352] Loss: 0.0425 Acc:99.00%
Training: Epoch[094/182] Iteration[100/352] Loss: 0.0430 Acc:98.95%
Training: Epoch[094/182] Iteration[150/352] Loss: 0.0433 Acc:98.94%
Training: Epoch[094/182] Iteration[200/352] Loss: 0.0429 Acc:98.91%
Training: Epoch[094/182] Iteration[250/352] Loss: 0.0415 Acc:98.94%
Training: Epoch[094/182] Iteration[300/352] Loss: 0.0405 Acc:98.97%
Training: Epoch[094/182] Iteration[350/352] Loss: 0.0399 Acc:98.98%
Training Progress:  51%|▌| 93/182 [2:54:34<2:46:17, 112.10s/it, Train Acc=98.98%Epoch[094/182] Train Acc: 98.98% Valid Acc:72.14% Train loss:0.0400 Valid loss:1.5604 LR:0.010000000000000002
Training Progress:  52%|▌| 94/182 [2:54:34<2:44:26, 112.12s/it, Train Acc=98.98%Training: Epoch[095/182] Iteration[050/352] Loss: 0.0316 Acc:99.25%
Training: Epoch[095/182] Iteration[100/352] Loss: 0.0324 Acc:99.22%
Training: Epoch[095/182] Iteration[150/352] Loss: 0.0320 Acc:99.21%
Training: Epoch[095/182] Iteration[200/352] Loss: 0.0313 Acc:99.20%
Training: Epoch[095/182] Iteration[250/352] Loss: 0.0302 Acc:99.25%
Training: Epoch[095/182] Iteration[300/352] Loss: 0.0295 Acc:99.27%
Training: Epoch[095/182] Iteration[350/352] Loss: 0.0295 Acc:99.25%
Training Progress:  52%|▌| 94/182 [2:56:26<2:44:26, 112.12s/it, Train Acc=99.25%Epoch[095/182] Train Acc: 99.25% Valid Acc:72.68% Train loss:0.0295 Valid loss:1.5865 LR:0.010000000000000002
Training Progress:  52%|▌| 95/182 [2:56:26<2:42:36, 112.15s/it, Train Acc=99.25%Training: Epoch[096/182] Iteration[050/352] Loss: 0.0210 Acc:99.59%
Training: Epoch[096/182] Iteration[100/352] Loss: 0.0206 Acc:99.62%
Training: Epoch[096/182] Iteration[150/352] Loss: 0.0209 Acc:99.60%
Training: Epoch[096/182] Iteration[200/352] Loss: 0.0209 Acc:99.59%
Training: Epoch[096/182] Iteration[250/352] Loss: 0.0209 Acc:99.58%
Training: Epoch[096/182] Iteration[300/352] Loss: 0.0209 Acc:99.57%
Training: Epoch[096/182] Iteration[350/352] Loss: 0.0208 Acc:99.56%
Training Progress:  52%|▌| 95/182 [2:58:18<2:42:36, 112.15s/it, Train Acc=99.56%Epoch[096/182] Train Acc: 99.56% Valid Acc:72.66% Train loss:0.0207 Valid loss:1.6268 LR:0.010000000000000002
Training Progress:  53%|▌| 96/182 [2:58:18<2:40:43, 112.14s/it, Train Acc=99.56%Training: Epoch[097/182] Iteration[050/352] Loss: 0.0198 Acc:99.53%
Training: Epoch[097/182] Iteration[100/352] Loss: 0.0184 Acc:99.57%
Training: Epoch[097/182] Iteration[150/352] Loss: 0.0175 Acc:99.63%
Training: Epoch[097/182] Iteration[200/352] Loss: 0.0180 Acc:99.62%
Training: Epoch[097/182] Iteration[250/352] Loss: 0.0183 Acc:99.61%
Training: Epoch[097/182] Iteration[300/352] Loss: 0.0181 Acc:99.62%
Training: Epoch[097/182] Iteration[350/352] Loss: 0.0181 Acc:99.62%
Training Progress:  53%|▌| 96/182 [3:00:10<2:40:43, 112.14s/it, Train Acc=99.61%Epoch[097/182] Train Acc: 99.61% Valid Acc:72.72% Train loss:0.0182 Valid loss:1.6273 LR:0.010000000000000002
Training Progress:  53%|▌| 97/182 [3:00:10<2:38:54, 112.17s/it, Train Acc=99.61%Training: Epoch[098/182] Iteration[050/352] Loss: 0.0180 Acc:99.59%
Training: Epoch[098/182] Iteration[100/352] Loss: 0.0171 Acc:99.63%
Training: Epoch[098/182] Iteration[150/352] Loss: 0.0163 Acc:99.66%
Training: Epoch[098/182] Iteration[200/352] Loss: 0.0161 Acc:99.66%
Training: Epoch[098/182] Iteration[250/352] Loss: 0.0159 Acc:99.68%
Training: Epoch[098/182] Iteration[300/352] Loss: 0.0157 Acc:99.69%
Training: Epoch[098/182] Iteration[350/352] Loss: 0.0156 Acc:99.69%
Training Progress:  53%|▌| 97/182 [3:02:02<2:38:54, 112.17s/it, Train Acc=99.69%Epoch[098/182] Train Acc: 99.69% Valid Acc:72.72% Train loss:0.0155 Valid loss:1.6583 LR:0.010000000000000002
Training Progress:  54%|▌| 98/182 [3:02:02<2:37:00, 112.15s/it, Train Acc=99.69%Training: Epoch[099/182] Iteration[050/352] Loss: 0.0144 Acc:99.69%
Training: Epoch[099/182] Iteration[100/352] Loss: 0.0141 Acc:99.70%
Training: Epoch[099/182] Iteration[150/352] Loss: 0.0133 Acc:99.74%
Training: Epoch[099/182] Iteration[200/352] Loss: 0.0132 Acc:99.75%
Training: Epoch[099/182] Iteration[250/352] Loss: 0.0129 Acc:99.76%
Training: Epoch[099/182] Iteration[300/352] Loss: 0.0129 Acc:99.75%
Training: Epoch[099/182] Iteration[350/352] Loss: 0.0125 Acc:99.76%
Training Progress:  54%|▌| 98/182 [3:03:54<2:37:00, 112.15s/it, Train Acc=99.76%Epoch[099/182] Train Acc: 99.76% Valid Acc:72.50% Train loss:0.0125 Valid loss:1.6768 LR:0.010000000000000002
Training Progress:  54%|▌| 99/182 [3:03:54<2:35:06, 112.12s/it, Train Acc=99.76%Training: Epoch[100/182] Iteration[050/352] Loss: 0.0116 Acc:99.73%
Training: Epoch[100/182] Iteration[100/352] Loss: 0.0118 Acc:99.70%
Training: Epoch[100/182] Iteration[150/352] Loss: 0.0119 Acc:99.71%
Training: Epoch[100/182] Iteration[200/352] Loss: 0.0116 Acc:99.73%
Training: Epoch[100/182] Iteration[250/352] Loss: 0.0116 Acc:99.74%
Training: Epoch[100/182] Iteration[300/352] Loss: 0.0118 Acc:99.73%
Training: Epoch[100/182] Iteration[350/352] Loss: 0.0123 Acc:99.71%
Training Progress:  54%|▌| 99/182 [3:05:46<2:35:06, 112.12s/it, Train Acc=99.71%Epoch[100/182] Train Acc: 99.71% Valid Acc:72.88% Train loss:0.0123 Valid loss:1.6995 LR:0.010000000000000002
Training Progress:  55%|▌| 100/182 [3:05:47<2:33:17, 112.16s/it, Train Acc=99.71Training: Epoch[101/182] Iteration[050/352] Loss: 0.0121 Acc:99.69%
Training: Epoch[101/182] Iteration[100/352] Loss: 0.0119 Acc:99.72%
Training: Epoch[101/182] Iteration[150/352] Loss: 0.0118 Acc:99.72%
Training: Epoch[101/182] Iteration[200/352] Loss: 0.0113 Acc:99.75%
Training: Epoch[101/182] Iteration[250/352] Loss: 0.0113 Acc:99.76%
Training: Epoch[101/182] Iteration[300/352] Loss: 0.0112 Acc:99.76%
Training: Epoch[101/182] Iteration[350/352] Loss: 0.0111 Acc:99.76%
Training Progress:  55%|▌| 100/182 [3:07:39<2:33:17, 112.16s/it, Train Acc=99.76Epoch[101/182] Train Acc: 99.76% Valid Acc:73.16% Train loss:0.0111 Valid loss:1.7057 LR:0.010000000000000002
Training Progress:  55%|▌| 101/182 [3:07:39<2:31:30, 112.23s/it, Train Acc=99.76Training: Epoch[102/182] Iteration[050/352] Loss: 0.0093 Acc:99.84%
Training: Epoch[102/182] Iteration[100/352] Loss: 0.0093 Acc:99.84%
Training: Epoch[102/182] Iteration[150/352] Loss: 0.0097 Acc:99.83%
Training: Epoch[102/182] Iteration[200/352] Loss: 0.0102 Acc:99.80%
Training: Epoch[102/182] Iteration[250/352] Loss: 0.0098 Acc:99.81%
Training: Epoch[102/182] Iteration[300/352] Loss: 0.0101 Acc:99.79%
Training: Epoch[102/182] Iteration[350/352] Loss: 0.0100 Acc:99.80%
Training Progress:  55%|▌| 101/182 [3:09:31<2:31:30, 112.23s/it, Train Acc=99.80Epoch[102/182] Train Acc: 99.80% Valid Acc:72.92% Train loss:0.0100 Valid loss:1.7251 LR:0.010000000000000002
Training Progress:  56%|▌| 102/182 [3:09:31<2:29:35, 112.20s/it, Train Acc=99.80Training: Epoch[103/182] Iteration[050/352] Loss: 0.0091 Acc:99.78%
Training: Epoch[103/182] Iteration[100/352] Loss: 0.0088 Acc:99.82%
Training: Epoch[103/182] Iteration[150/352] Loss: 0.0092 Acc:99.79%
Training: Epoch[103/182] Iteration[200/352] Loss: 0.0090 Acc:99.79%
Training: Epoch[103/182] Iteration[250/352] Loss: 0.0090 Acc:99.80%
Training: Epoch[103/182] Iteration[300/352] Loss: 0.0090 Acc:99.80%
Training: Epoch[103/182] Iteration[350/352] Loss: 0.0089 Acc:99.81%
Training Progress:  56%|▌| 102/182 [3:11:23<2:29:35, 112.20s/it, Train Acc=99.81Epoch[103/182] Train Acc: 99.81% Valid Acc:72.94% Train loss:0.0089 Valid loss:1.7343 LR:0.010000000000000002
Training Progress:  57%|▌| 103/182 [3:11:23<2:27:41, 112.17s/it, Train Acc=99.81Training: Epoch[104/182] Iteration[050/352] Loss: 0.0081 Acc:99.88%
Training: Epoch[104/182] Iteration[100/352] Loss: 0.0074 Acc:99.89%
Training: Epoch[104/182] Iteration[150/352] Loss: 0.0078 Acc:99.86%
Training: Epoch[104/182] Iteration[200/352] Loss: 0.0076 Acc:99.87%
Training: Epoch[104/182] Iteration[250/352] Loss: 0.0080 Acc:99.87%
Training: Epoch[104/182] Iteration[300/352] Loss: 0.0079 Acc:99.87%
Training: Epoch[104/182] Iteration[350/352] Loss: 0.0079 Acc:99.87%
Training Progress:  57%|▌| 103/182 [3:13:15<2:27:41, 112.17s/it, Train Acc=99.87Epoch[104/182] Train Acc: 99.87% Valid Acc:73.10% Train loss:0.0080 Valid loss:1.7436 LR:0.010000000000000002
Training Progress:  57%|▌| 104/182 [3:13:15<2:25:49, 112.17s/it, Train Acc=99.87Training: Epoch[105/182] Iteration[050/352] Loss: 0.0070 Acc:99.91%
Training: Epoch[105/182] Iteration[100/352] Loss: 0.0077 Acc:99.88%
Training: Epoch[105/182] Iteration[150/352] Loss: 0.0074 Acc:99.90%
Training: Epoch[105/182] Iteration[200/352] Loss: 0.0072 Acc:99.90%
Training: Epoch[105/182] Iteration[250/352] Loss: 0.0076 Acc:99.89%
Training: Epoch[105/182] Iteration[300/352] Loss: 0.0078 Acc:99.88%
Training: Epoch[105/182] Iteration[350/352] Loss: 0.0077 Acc:99.88%
Training Progress:  57%|▌| 104/182 [3:15:08<2:25:49, 112.17s/it, Train Acc=99.88Epoch[105/182] Train Acc: 99.88% Valid Acc:73.24% Train loss:0.0076 Valid loss:1.7596 LR:0.010000000000000002
Training Progress:  58%|▌| 105/182 [3:15:08<2:23:58, 112.18s/it, Train Acc=99.88Training: Epoch[106/182] Iteration[050/352] Loss: 0.0066 Acc:99.88%
Training: Epoch[106/182] Iteration[100/352] Loss: 0.0066 Acc:99.89%
Training: Epoch[106/182] Iteration[150/352] Loss: 0.0071 Acc:99.88%
Training: Epoch[106/182] Iteration[200/352] Loss: 0.0070 Acc:99.88%
Training: Epoch[106/182] Iteration[250/352] Loss: 0.0071 Acc:99.88%
Training: Epoch[106/182] Iteration[300/352] Loss: 0.0070 Acc:99.88%
Training: Epoch[106/182] Iteration[350/352] Loss: 0.0071 Acc:99.87%
Training Progress:  58%|▌| 105/182 [3:17:00<2:23:58, 112.18s/it, Train Acc=99.87Epoch[106/182] Train Acc: 99.87% Valid Acc:73.18% Train loss:0.0071 Valid loss:1.7622 LR:0.010000000000000002
Training Progress:  58%|▌| 106/182 [3:17:00<2:22:04, 112.16s/it, Train Acc=99.87Training: Epoch[107/182] Iteration[050/352] Loss: 0.0076 Acc:99.88%
Training: Epoch[107/182] Iteration[100/352] Loss: 0.0067 Acc:99.90%
Training: Epoch[107/182] Iteration[150/352] Loss: 0.0064 Acc:99.91%
Training: Epoch[107/182] Iteration[200/352] Loss: 0.0065 Acc:99.91%
Training: Epoch[107/182] Iteration[250/352] Loss: 0.0064 Acc:99.92%
Training: Epoch[107/182] Iteration[300/352] Loss: 0.0067 Acc:99.90%
Training: Epoch[107/182] Iteration[350/352] Loss: 0.0067 Acc:99.89%
Training Progress:  58%|▌| 106/182 [3:18:52<2:22:04, 112.16s/it, Train Acc=99.89Epoch[107/182] Train Acc: 99.89% Valid Acc:73.16% Train loss:0.0067 Valid loss:1.7724 LR:0.010000000000000002
Training Progress:  59%|▌| 107/182 [3:18:52<2:20:14, 112.19s/it, Train Acc=99.89Training: Epoch[108/182] Iteration[050/352] Loss: 0.0059 Acc:99.89%
Training: Epoch[108/182] Iteration[100/352] Loss: 0.0062 Acc:99.90%
Training: Epoch[108/182] Iteration[150/352] Loss: 0.0062 Acc:99.90%
Training: Epoch[108/182] Iteration[200/352] Loss: 0.0063 Acc:99.90%
Training: Epoch[108/182] Iteration[250/352] Loss: 0.0065 Acc:99.90%
Training: Epoch[108/182] Iteration[300/352] Loss: 0.0066 Acc:99.89%
Training: Epoch[108/182] Iteration[350/352] Loss: 0.0068 Acc:99.89%
Training Progress:  59%|▌| 107/182 [3:20:44<2:20:14, 112.19s/it, Train Acc=99.89Epoch[108/182] Train Acc: 99.89% Valid Acc:73.44% Train loss:0.0068 Valid loss:1.7741 LR:0.010000000000000002
Training Progress:  59%|▌| 108/182 [3:20:44<2:18:24, 112.22s/it, Train Acc=99.89Training: Epoch[109/182] Iteration[050/352] Loss: 0.0061 Acc:99.84%
Training: Epoch[109/182] Iteration[100/352] Loss: 0.0065 Acc:99.86%
Training: Epoch[109/182] Iteration[150/352] Loss: 0.0062 Acc:99.88%
Training: Epoch[109/182] Iteration[200/352] Loss: 0.0065 Acc:99.88%
Training: Epoch[109/182] Iteration[250/352] Loss: 0.0067 Acc:99.87%
Training: Epoch[109/182] Iteration[300/352] Loss: 0.0065 Acc:99.88%
Training: Epoch[109/182] Iteration[350/352] Loss: 0.0066 Acc:99.88%
Training Progress:  59%|▌| 108/182 [3:22:36<2:18:24, 112.22s/it, Train Acc=99.88Epoch[109/182] Train Acc: 99.88% Valid Acc:73.58% Train loss:0.0066 Valid loss:1.7784 LR:0.010000000000000002
Training Progress:  60%|▌| 109/182 [3:22:37<2:16:33, 112.24s/it, Train Acc=99.88Training: Epoch[110/182] Iteration[050/352] Loss: 0.0050 Acc:99.95%
Training: Epoch[110/182] Iteration[100/352] Loss: 0.0053 Acc:99.93%
Training: Epoch[110/182] Iteration[150/352] Loss: 0.0053 Acc:99.94%
Training: Epoch[110/182] Iteration[200/352] Loss: 0.0052 Acc:99.94%
Training: Epoch[110/182] Iteration[250/352] Loss: 0.0055 Acc:99.92%
Training: Epoch[110/182] Iteration[300/352] Loss: 0.0054 Acc:99.93%
Training: Epoch[110/182] Iteration[350/352] Loss: 0.0057 Acc:99.91%
Training Progress:  60%|▌| 109/182 [3:24:29<2:16:33, 112.24s/it, Train Acc=99.91Epoch[110/182] Train Acc: 99.91% Valid Acc:73.54% Train loss:0.0057 Valid loss:1.7889 LR:0.010000000000000002
Training Progress:  60%|▌| 110/182 [3:24:29<2:14:40, 112.23s/it, Train Acc=99.91Training: Epoch[111/182] Iteration[050/352] Loss: 0.0053 Acc:99.95%
Training: Epoch[111/182] Iteration[100/352] Loss: 0.0052 Acc:99.95%
Training: Epoch[111/182] Iteration[150/352] Loss: 0.0060 Acc:99.91%
Training: Epoch[111/182] Iteration[200/352] Loss: 0.0061 Acc:99.91%
Training: Epoch[111/182] Iteration[250/352] Loss: 0.0059 Acc:99.92%
Training: Epoch[111/182] Iteration[300/352] Loss: 0.0058 Acc:99.92%
Training: Epoch[111/182] Iteration[350/352] Loss: 0.0058 Acc:99.92%
Training Progress:  60%|▌| 110/182 [3:26:21<2:14:40, 112.23s/it, Train Acc=99.92Epoch[111/182] Train Acc: 99.92% Valid Acc:73.40% Train loss:0.0058 Valid loss:1.7918 LR:0.010000000000000002
Training Progress:  61%|▌| 111/182 [3:26:21<2:12:47, 112.22s/it, Train Acc=99.92Training: Epoch[112/182] Iteration[050/352] Loss: 0.0069 Acc:99.88%
Training: Epoch[112/182] Iteration[100/352] Loss: 0.0058 Acc:99.91%
Training: Epoch[112/182] Iteration[150/352] Loss: 0.0058 Acc:99.89%
Training: Epoch[112/182] Iteration[200/352] Loss: 0.0059 Acc:99.89%
Training: Epoch[112/182] Iteration[250/352] Loss: 0.0062 Acc:99.89%
Training: Epoch[112/182] Iteration[300/352] Loss: 0.0061 Acc:99.90%
Training: Epoch[112/182] Iteration[350/352] Loss: 0.0061 Acc:99.89%
Training Progress:  61%|▌| 111/182 [3:28:13<2:12:47, 112.22s/it, Train Acc=99.89Epoch[112/182] Train Acc: 99.89% Valid Acc:73.30% Train loss:0.0061 Valid loss:1.8186 LR:0.010000000000000002
Training Progress:  62%|▌| 112/182 [3:28:13<2:10:54, 112.20s/it, Train Acc=99.89Training: Epoch[113/182] Iteration[050/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[113/182] Iteration[100/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[113/182] Iteration[150/352] Loss: 0.0053 Acc:99.93%
Training: Epoch[113/182] Iteration[200/352] Loss: 0.0051 Acc:99.93%
Training: Epoch[113/182] Iteration[250/352] Loss: 0.0050 Acc:99.94%
Training: Epoch[113/182] Iteration[300/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[113/182] Iteration[350/352] Loss: 0.0050 Acc:99.93%
Training Progress:  62%|▌| 112/182 [3:30:05<2:10:54, 112.20s/it, Train Acc=99.93Epoch[113/182] Train Acc: 99.93% Valid Acc:73.10% Train loss:0.0050 Valid loss:1.8102 LR:0.010000000000000002
Training Progress:  62%|▌| 113/182 [3:30:05<2:09:04, 112.24s/it, Train Acc=99.93Training: Epoch[114/182] Iteration[050/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[114/182] Iteration[100/352] Loss: 0.0047 Acc:99.92%
Training: Epoch[114/182] Iteration[150/352] Loss: 0.0045 Acc:99.92%
Training: Epoch[114/182] Iteration[200/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[114/182] Iteration[250/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[114/182] Iteration[300/352] Loss: 0.0047 Acc:99.92%
Training: Epoch[114/182] Iteration[350/352] Loss: 0.0047 Acc:99.93%
Training Progress:  62%|▌| 113/182 [3:31:58<2:09:04, 112.24s/it, Train Acc=99.93Epoch[114/182] Train Acc: 99.93% Valid Acc:73.28% Train loss:0.0047 Valid loss:1.8100 LR:0.010000000000000002
Training Progress:  63%|▋| 114/182 [3:31:58<2:07:14, 112.28s/it, Train Acc=99.93Training: Epoch[115/182] Iteration[050/352] Loss: 0.0049 Acc:99.94%
Training: Epoch[115/182] Iteration[100/352] Loss: 0.0047 Acc:99.95%
Training: Epoch[115/182] Iteration[150/352] Loss: 0.0045 Acc:99.95%
Training: Epoch[115/182] Iteration[200/352] Loss: 0.0047 Acc:99.94%
Training: Epoch[115/182] Iteration[250/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[115/182] Iteration[300/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[115/182] Iteration[350/352] Loss: 0.0050 Acc:99.91%
Training Progress:  63%|▋| 114/182 [3:33:50<2:07:14, 112.28s/it, Train Acc=99.91Epoch[115/182] Train Acc: 99.91% Valid Acc:73.44% Train loss:0.0050 Valid loss:1.8182 LR:0.010000000000000002
Training Progress:  63%|▋| 115/182 [3:33:50<2:05:21, 112.26s/it, Train Acc=99.91Training: Epoch[116/182] Iteration[050/352] Loss: 0.0039 Acc:99.95%
Training: Epoch[116/182] Iteration[100/352] Loss: 0.0051 Acc:99.89%
Training: Epoch[116/182] Iteration[150/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[116/182] Iteration[200/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[116/182] Iteration[250/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[116/182] Iteration[300/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[116/182] Iteration[350/352] Loss: 0.0047 Acc:99.92%
Training Progress:  63%|▋| 115/182 [3:35:42<2:05:21, 112.26s/it, Train Acc=99.92Epoch[116/182] Train Acc: 99.92% Valid Acc:73.36% Train loss:0.0048 Valid loss:1.8060 LR:0.010000000000000002
Training Progress:  64%|▋| 116/182 [3:35:42<2:03:27, 112.24s/it, Train Acc=99.92Training: Epoch[117/182] Iteration[050/352] Loss: 0.0047 Acc:99.95%
Training: Epoch[117/182] Iteration[100/352] Loss: 0.0050 Acc:99.94%
Training: Epoch[117/182] Iteration[150/352] Loss: 0.0048 Acc:99.94%
Training: Epoch[117/182] Iteration[200/352] Loss: 0.0049 Acc:99.93%
Training: Epoch[117/182] Iteration[250/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[117/182] Iteration[300/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[117/182] Iteration[350/352] Loss: 0.0050 Acc:99.92%
Training Progress:  64%|▋| 116/182 [3:37:34<2:03:27, 112.24s/it, Train Acc=99.92Epoch[117/182] Train Acc: 99.92% Valid Acc:73.68% Train loss:0.0050 Valid loss:1.8138 LR:0.010000000000000002
Training Progress:  64%|▋| 117/182 [3:37:35<2:01:36, 112.25s/it, Train Acc=99.92Training: Epoch[118/182] Iteration[050/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[118/182] Iteration[100/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[118/182] Iteration[150/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[118/182] Iteration[200/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[118/182] Iteration[250/352] Loss: 0.0050 Acc:99.91%
Training: Epoch[118/182] Iteration[300/352] Loss: 0.0049 Acc:99.92%
Training: Epoch[118/182] Iteration[350/352] Loss: 0.0047 Acc:99.92%
Training Progress:  64%|▋| 117/182 [3:39:27<2:01:36, 112.25s/it, Train Acc=99.92Epoch[118/182] Train Acc: 99.92% Valid Acc:73.68% Train loss:0.0048 Valid loss:1.8088 LR:0.010000000000000002
Training Progress:  65%|▋| 118/182 [3:39:27<1:59:42, 112.23s/it, Train Acc=99.92Training: Epoch[119/182] Iteration[050/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[119/182] Iteration[100/352] Loss: 0.0039 Acc:99.96%
Training: Epoch[119/182] Iteration[150/352] Loss: 0.0039 Acc:99.96%
Training: Epoch[119/182] Iteration[200/352] Loss: 0.0040 Acc:99.96%
Training: Epoch[119/182] Iteration[250/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[119/182] Iteration[300/352] Loss: 0.0044 Acc:99.94%
Training: Epoch[119/182] Iteration[350/352] Loss: 0.0045 Acc:99.94%
Training Progress:  65%|▋| 118/182 [3:41:19<1:59:42, 112.23s/it, Train Acc=99.94Epoch[119/182] Train Acc: 99.94% Valid Acc:73.78% Train loss:0.0045 Valid loss:1.8100 LR:0.010000000000000002
Training Progress:  65%|▋| 119/182 [3:41:19<1:57:53, 112.28s/it, Train Acc=99.94Training: Epoch[120/182] Iteration[050/352] Loss: 0.0056 Acc:99.92%
Training: Epoch[120/182] Iteration[100/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[120/182] Iteration[150/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[120/182] Iteration[200/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[120/182] Iteration[250/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[120/182] Iteration[300/352] Loss: 0.0045 Acc:99.93%
Training: Epoch[120/182] Iteration[350/352] Loss: 0.0044 Acc:99.94%
Training Progress:  65%|▋| 119/182 [3:43:11<1:57:53, 112.28s/it, Train Acc=99.94Epoch[120/182] Train Acc: 99.94% Valid Acc:73.58% Train loss:0.0044 Valid loss:1.8039 LR:0.010000000000000002
Training Progress:  66%|▋| 120/182 [3:43:11<1:56:02, 112.30s/it, Train Acc=99.94Training: Epoch[121/182] Iteration[050/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[121/182] Iteration[100/352] Loss: 0.0041 Acc:99.95%
Training: Epoch[121/182] Iteration[150/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[121/182] Iteration[200/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[121/182] Iteration[250/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[121/182] Iteration[300/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[121/182] Iteration[350/352] Loss: 0.0040 Acc:99.94%
Training Progress:  66%|▋| 120/182 [3:45:04<1:56:02, 112.30s/it, Train Acc=99.94Epoch[121/182] Train Acc: 99.94% Valid Acc:73.88% Train loss:0.0040 Valid loss:1.8110 LR:0.010000000000000002
Training Progress:  66%|▋| 121/182 [3:45:04<1:54:12, 112.34s/it, Train Acc=99.94Training: Epoch[122/182] Iteration[050/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[122/182] Iteration[100/352] Loss: 0.0036 Acc:99.96%
Training: Epoch[122/182] Iteration[150/352] Loss: 0.0035 Acc:99.97%
Training: Epoch[122/182] Iteration[200/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[122/182] Iteration[250/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[122/182] Iteration[300/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[122/182] Iteration[350/352] Loss: 0.0039 Acc:99.94%
Training Progress:  66%|▋| 121/182 [3:46:56<1:54:12, 112.34s/it, Train Acc=99.94Epoch[122/182] Train Acc: 99.94% Valid Acc:73.84% Train loss:0.0039 Valid loss:1.8064 LR:0.010000000000000002
Training Progress:  67%|▋| 122/182 [3:46:56<1:52:20, 112.35s/it, Train Acc=99.94Training: Epoch[123/182] Iteration[050/352] Loss: 0.0036 Acc:99.97%
Training: Epoch[123/182] Iteration[100/352] Loss: 0.0036 Acc:99.97%
Training: Epoch[123/182] Iteration[150/352] Loss: 0.0035 Acc:99.97%
Training: Epoch[123/182] Iteration[200/352] Loss: 0.0039 Acc:99.95%
Training: Epoch[123/182] Iteration[250/352] Loss: 0.0040 Acc:99.95%
Training: Epoch[123/182] Iteration[300/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[123/182] Iteration[350/352] Loss: 0.0041 Acc:99.94%
Training Progress:  67%|▋| 122/182 [3:48:48<1:52:20, 112.35s/it, Train Acc=99.94Epoch[123/182] Train Acc: 99.94% Valid Acc:73.68% Train loss:0.0041 Valid loss:1.8090 LR:0.010000000000000002
Training Progress:  68%|▋| 123/182 [3:48:48<1:50:25, 112.30s/it, Train Acc=99.94Training: Epoch[124/182] Iteration[050/352] Loss: 0.0042 Acc:99.94%
Training: Epoch[124/182] Iteration[100/352] Loss: 0.0042 Acc:99.93%
Training: Epoch[124/182] Iteration[150/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[124/182] Iteration[200/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[124/182] Iteration[250/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[124/182] Iteration[300/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[124/182] Iteration[350/352] Loss: 0.0040 Acc:99.94%
Training Progress:  68%|▋| 123/182 [3:50:41<1:50:25, 112.30s/it, Train Acc=99.94Epoch[124/182] Train Acc: 99.94% Valid Acc:73.72% Train loss:0.0040 Valid loss:1.8046 LR:0.010000000000000002
Training Progress:  68%|▋| 124/182 [3:50:41<1:48:31, 112.27s/it, Train Acc=99.94Training: Epoch[125/182] Iteration[050/352] Loss: 0.0031 Acc:99.98%
Training: Epoch[125/182] Iteration[100/352] Loss: 0.0032 Acc:99.99%
Training: Epoch[125/182] Iteration[150/352] Loss: 0.0034 Acc:99.98%
Training: Epoch[125/182] Iteration[200/352] Loss: 0.0037 Acc:99.97%
Training: Epoch[125/182] Iteration[250/352] Loss: 0.0036 Acc:99.97%
Training: Epoch[125/182] Iteration[300/352] Loss: 0.0038 Acc:99.97%
Training: Epoch[125/182] Iteration[350/352] Loss: 0.0040 Acc:99.95%
Training Progress:  68%|▋| 124/182 [3:52:33<1:48:31, 112.27s/it, Train Acc=99.95Epoch[125/182] Train Acc: 99.95% Valid Acc:73.60% Train loss:0.0040 Valid loss:1.8075 LR:0.010000000000000002
Training Progress:  69%|▋| 125/182 [3:52:33<1:46:37, 112.24s/it, Train Acc=99.95Training: Epoch[126/182] Iteration[050/352] Loss: 0.0043 Acc:99.94%
Training: Epoch[126/182] Iteration[100/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[126/182] Iteration[150/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[126/182] Iteration[200/352] Loss: 0.0038 Acc:99.95%
Training: Epoch[126/182] Iteration[250/352] Loss: 0.0037 Acc:99.96%
Training: Epoch[126/182] Iteration[300/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[126/182] Iteration[350/352] Loss: 0.0040 Acc:99.94%
Training Progress:  69%|▋| 125/182 [3:54:25<1:46:37, 112.24s/it, Train Acc=99.94Epoch[126/182] Train Acc: 99.94% Valid Acc:73.66% Train loss:0.0040 Valid loss:1.8053 LR:0.010000000000000002
Training Progress:  69%|▋| 126/182 [3:54:25<1:44:45, 112.24s/it, Train Acc=99.94Training: Epoch[127/182] Iteration[050/352] Loss: 0.0044 Acc:99.91%
Training: Epoch[127/182] Iteration[100/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[127/182] Iteration[150/352] Loss: 0.0042 Acc:99.93%
Training: Epoch[127/182] Iteration[200/352] Loss: 0.0043 Acc:99.93%
Training: Epoch[127/182] Iteration[250/352] Loss: 0.0042 Acc:99.92%
Training: Epoch[127/182] Iteration[300/352] Loss: 0.0043 Acc:99.93%
Training: Epoch[127/182] Iteration[350/352] Loss: 0.0043 Acc:99.93%
Training Progress:  69%|▋| 126/182 [3:56:17<1:44:45, 112.24s/it, Train Acc=99.93Epoch[127/182] Train Acc: 99.93% Valid Acc:73.72% Train loss:0.0043 Valid loss:1.7954 LR:0.010000000000000002
Training Progress:  70%|▋| 127/182 [3:56:17<1:42:53, 112.25s/it, Train Acc=99.93Training: Epoch[128/182] Iteration[050/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[128/182] Iteration[100/352] Loss: 0.0041 Acc:99.92%
Training: Epoch[128/182] Iteration[150/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[128/182] Iteration[200/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[128/182] Iteration[250/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[128/182] Iteration[300/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[128/182] Iteration[350/352] Loss: 0.0039 Acc:99.93%
Training Progress:  70%|▋| 127/182 [3:58:10<1:42:53, 112.25s/it, Train Acc=99.93Epoch[128/182] Train Acc: 99.93% Valid Acc:74.00% Train loss:0.0039 Valid loss:1.7942 LR:0.010000000000000002
Training Progress:  70%|▋| 128/182 [3:58:10<1:41:03, 112.29s/it, Train Acc=99.93Training: Epoch[129/182] Iteration[050/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[129/182] Iteration[100/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[129/182] Iteration[150/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[129/182] Iteration[200/352] Loss: 0.0038 Acc:99.95%
Training: Epoch[129/182] Iteration[250/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[129/182] Iteration[300/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[129/182] Iteration[350/352] Loss: 0.0038 Acc:99.95%
Training Progress:  70%|▋| 128/182 [4:00:02<1:41:03, 112.29s/it, Train Acc=99.95Epoch[129/182] Train Acc: 99.95% Valid Acc:73.68% Train loss:0.0037 Valid loss:1.8003 LR:0.010000000000000002
Training Progress:  71%|▋| 129/182 [4:00:02<1:39:11, 112.29s/it, Train Acc=99.95Training: Epoch[130/182] Iteration[050/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[130/182] Iteration[100/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[130/182] Iteration[150/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[130/182] Iteration[200/352] Loss: 0.0038 Acc:99.95%
Training: Epoch[130/182] Iteration[250/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[130/182] Iteration[300/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[130/182] Iteration[350/352] Loss: 0.0039 Acc:99.94%
Training Progress:  71%|▋| 129/182 [4:01:54<1:39:11, 112.29s/it, Train Acc=99.94Epoch[130/182] Train Acc: 99.94% Valid Acc:73.54% Train loss:0.0039 Valid loss:1.7953 LR:0.010000000000000002
Training Progress:  71%|▋| 130/182 [4:01:54<1:37:18, 112.29s/it, Train Acc=99.94Training: Epoch[131/182] Iteration[050/352] Loss: 0.0038 Acc:99.95%
Training: Epoch[131/182] Iteration[100/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[131/182] Iteration[150/352] Loss: 0.0041 Acc:99.93%
Training: Epoch[131/182] Iteration[200/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[131/182] Iteration[250/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[131/182] Iteration[300/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[131/182] Iteration[350/352] Loss: 0.0039 Acc:99.94%
Training Progress:  71%|▋| 130/182 [4:03:46<1:37:18, 112.29s/it, Train Acc=99.94Epoch[131/182] Train Acc: 99.94% Valid Acc:73.76% Train loss:0.0039 Valid loss:1.7942 LR:0.010000000000000002
Training Progress:  72%|▋| 131/182 [4:03:46<1:35:25, 112.26s/it, Train Acc=99.94Training: Epoch[132/182] Iteration[050/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[132/182] Iteration[100/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[132/182] Iteration[150/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[132/182] Iteration[200/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[132/182] Iteration[250/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[132/182] Iteration[300/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[132/182] Iteration[350/352] Loss: 0.0036 Acc:99.94%
Training Progress:  72%|▋| 131/182 [4:05:39<1:35:25, 112.26s/it, Train Acc=99.94Epoch[132/182] Train Acc: 99.94% Valid Acc:73.76% Train loss:0.0036 Valid loss:1.7805 LR:0.010000000000000002
Training Progress:  73%|▋| 132/182 [4:05:39<1:33:32, 112.24s/it, Train Acc=99.94Training: Epoch[133/182] Iteration[050/352] Loss: 0.0041 Acc:99.92%
Training: Epoch[133/182] Iteration[100/352] Loss: 0.0039 Acc:99.94%
Training: Epoch[133/182] Iteration[150/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[133/182] Iteration[200/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[133/182] Iteration[250/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[133/182] Iteration[300/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[133/182] Iteration[350/352] Loss: 0.0039 Acc:99.93%
Training Progress:  73%|▋| 132/182 [4:07:31<1:33:32, 112.24s/it, Train Acc=99.93Epoch[133/182] Train Acc: 99.93% Valid Acc:73.86% Train loss:0.0039 Valid loss:1.8015 LR:0.010000000000000002
Training Progress:  73%|▋| 133/182 [4:07:31<1:31:41, 112.27s/it, Train Acc=99.93Training: Epoch[134/182] Iteration[050/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[134/182] Iteration[100/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[134/182] Iteration[150/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[134/182] Iteration[200/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[134/182] Iteration[250/352] Loss: 0.0033 Acc:99.97%
Training: Epoch[134/182] Iteration[300/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[134/182] Iteration[350/352] Loss: 0.0034 Acc:99.95%
Training Progress:  73%|▋| 133/182 [4:09:24<1:31:41, 112.27s/it, Train Acc=99.95Epoch[134/182] Train Acc: 99.95% Valid Acc:73.88% Train loss:0.0034 Valid loss:1.7930 LR:0.010000000000000002
Training Progress:  74%|▋| 134/182 [4:09:24<1:30:01, 112.54s/it, Train Acc=99.95Training: Epoch[135/182] Iteration[050/352] Loss: 0.0044 Acc:99.89%
Training: Epoch[135/182] Iteration[100/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[135/182] Iteration[150/352] Loss: 0.0035 Acc:99.94%
Training: Epoch[135/182] Iteration[200/352] Loss: 0.0037 Acc:99.93%
Training: Epoch[135/182] Iteration[250/352] Loss: 0.0037 Acc:99.93%
Training: Epoch[135/182] Iteration[300/352] Loss: 0.0036 Acc:99.93%
Training: Epoch[135/182] Iteration[350/352] Loss: 0.0036 Acc:99.94%
Training Progress:  74%|▋| 134/182 [4:11:17<1:30:01, 112.54s/it, Train Acc=99.94Epoch[135/182] Train Acc: 99.94% Valid Acc:73.66% Train loss:0.0036 Valid loss:1.7946 LR:0.010000000000000002
Training Progress:  74%|▋| 135/182 [4:11:17<1:28:10, 112.57s/it, Train Acc=99.94Training: Epoch[136/182] Iteration[050/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[136/182] Iteration[100/352] Loss: 0.0025 Acc:99.99%
Training: Epoch[136/182] Iteration[150/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[136/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[136/182] Iteration[250/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[136/182] Iteration[300/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[136/182] Iteration[350/352] Loss: 0.0034 Acc:99.95%
Training Progress:  74%|▋| 135/182 [4:13:09<1:28:10, 112.57s/it, Train Acc=99.95Epoch[136/182] Train Acc: 99.95% Valid Acc:73.88% Train loss:0.0034 Valid loss:1.7907 LR:0.010000000000000002
Training Progress:  75%|▋| 136/182 [4:13:09<1:26:13, 112.46s/it, Train Acc=99.95Training: Epoch[137/182] Iteration[050/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[137/182] Iteration[100/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[137/182] Iteration[150/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[137/182] Iteration[200/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[137/182] Iteration[250/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[137/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[137/182] Iteration[350/352] Loss: 0.0032 Acc:99.96%
Training Progress:  75%|▋| 136/182 [4:15:06<1:26:13, 112.46s/it, Train Acc=99.96Epoch[137/182] Train Acc: 99.96% Valid Acc:73.80% Train loss:0.0032 Valid loss:1.7920 LR:0.0010000000000000002
Training Progress:  75%|▊| 137/182 [4:15:06<1:25:16, 113.70s/it, Train Acc=99.96Training: Epoch[138/182] Iteration[050/352] Loss: 0.0032 Acc:99.98%
Training: Epoch[138/182] Iteration[100/352] Loss: 0.0037 Acc:99.96%
Training: Epoch[138/182] Iteration[150/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[138/182] Iteration[200/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[138/182] Iteration[250/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[138/182] Iteration[300/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[138/182] Iteration[350/352] Loss: 0.0036 Acc:99.94%
Training Progress:  75%|▊| 137/182 [4:17:01<1:25:16, 113.70s/it, Train Acc=99.94Epoch[138/182] Train Acc: 99.94% Valid Acc:73.82% Train loss:0.0036 Valid loss:1.7833 LR:0.0010000000000000002
Training Progress:  76%|▊| 138/182 [4:17:01<1:23:42, 114.15s/it, Train Acc=99.94Training: Epoch[139/182] Iteration[050/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[139/182] Iteration[100/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[139/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[139/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[139/182] Iteration[250/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[139/182] Iteration[300/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[139/182] Iteration[350/352] Loss: 0.0031 Acc:99.96%
Training Progress:  76%|▊| 138/182 [4:18:53<1:23:42, 114.15s/it, Train Acc=99.96Epoch[139/182] Train Acc: 99.96% Valid Acc:73.70% Train loss:0.0031 Valid loss:1.7835 LR:0.0010000000000000002
Training Progress:  76%|▊| 139/182 [4:18:53<1:21:21, 113.52s/it, Train Acc=99.96Training: Epoch[140/182] Iteration[050/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[140/182] Iteration[100/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[140/182] Iteration[150/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[140/182] Iteration[200/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[140/182] Iteration[250/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[140/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[140/182] Iteration[350/352] Loss: 0.0033 Acc:99.96%
Training Progress:  76%|▊| 139/182 [4:20:45<1:21:21, 113.52s/it, Train Acc=99.96Epoch[140/182] Train Acc: 99.96% Valid Acc:74.04% Train loss:0.0033 Valid loss:1.7875 LR:0.0010000000000000002
Training Progress:  77%|▊| 140/182 [4:20:45<1:19:10, 113.11s/it, Train Acc=99.96Training: Epoch[141/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[141/182] Iteration[100/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[141/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[141/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[141/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[141/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[141/182] Iteration[350/352] Loss: 0.0031 Acc:99.96%
Training Progress:  77%|▊| 140/182 [4:22:37<1:19:10, 113.11s/it, Train Acc=99.96Epoch[141/182] Train Acc: 99.96% Valid Acc:73.72% Train loss:0.0031 Valid loss:1.7862 LR:0.0010000000000000002
Training Progress:  77%|▊| 141/182 [4:22:37<1:17:02, 112.75s/it, Train Acc=99.96Training: Epoch[142/182] Iteration[050/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[142/182] Iteration[100/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[142/182] Iteration[150/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[142/182] Iteration[200/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[142/182] Iteration[250/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[142/182] Iteration[300/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[142/182] Iteration[350/352] Loss: 0.0032 Acc:99.97%
Training Progress:  77%|▊| 141/182 [4:24:29<1:17:02, 112.75s/it, Train Acc=99.97Epoch[142/182] Train Acc: 99.97% Valid Acc:73.68% Train loss:0.0032 Valid loss:1.7878 LR:0.0010000000000000002
Training Progress:  78%|▊| 142/182 [4:24:29<1:14:59, 112.49s/it, Train Acc=99.97Training: Epoch[143/182] Iteration[050/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[143/182] Iteration[100/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[143/182] Iteration[150/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[143/182] Iteration[200/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[143/182] Iteration[250/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[143/182] Iteration[300/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[143/182] Iteration[350/352] Loss: 0.0032 Acc:99.96%
Training Progress:  78%|▊| 142/182 [4:26:21<1:14:59, 112.49s/it, Train Acc=99.96Epoch[143/182] Train Acc: 99.96% Valid Acc:73.92% Train loss:0.0032 Valid loss:1.7856 LR:0.0010000000000000002
Training Progress:  79%|▊| 143/182 [4:26:21<1:12:58, 112.27s/it, Train Acc=99.96Training: Epoch[144/182] Iteration[050/352] Loss: 0.0033 Acc:99.97%
Training: Epoch[144/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[144/182] Iteration[150/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[144/182] Iteration[200/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[144/182] Iteration[250/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[144/182] Iteration[300/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[144/182] Iteration[350/352] Loss: 0.0031 Acc:99.96%
Training Progress:  79%|▊| 143/182 [4:28:12<1:12:58, 112.27s/it, Train Acc=99.96Epoch[144/182] Train Acc: 99.96% Valid Acc:73.72% Train loss:0.0031 Valid loss:1.7761 LR:0.0010000000000000002
Training Progress:  79%|▊| 144/182 [4:28:12<1:10:59, 112.10s/it, Train Acc=99.96Training: Epoch[145/182] Iteration[050/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[145/182] Iteration[100/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[145/182] Iteration[150/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[145/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[145/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[145/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[145/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  79%|▊| 144/182 [4:30:04<1:10:59, 112.10s/it, Train Acc=99.97Epoch[145/182] Train Acc: 99.97% Valid Acc:73.88% Train loss:0.0029 Valid loss:1.7806 LR:0.0010000000000000002
Training Progress:  80%|▊| 145/182 [4:30:04<1:09:04, 112.01s/it, Train Acc=99.97Training: Epoch[146/182] Iteration[050/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[146/182] Iteration[100/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[146/182] Iteration[150/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[146/182] Iteration[200/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[146/182] Iteration[250/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[146/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[146/182] Iteration[350/352] Loss: 0.0032 Acc:99.96%
Training Progress:  80%|▊| 145/182 [4:31:56<1:09:04, 112.01s/it, Train Acc=99.96Epoch[146/182] Train Acc: 99.96% Valid Acc:73.76% Train loss:0.0032 Valid loss:1.7830 LR:0.0010000000000000002
Training Progress:  80%|▊| 146/182 [4:31:56<1:07:09, 111.94s/it, Train Acc=99.96Training: Epoch[147/182] Iteration[050/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[147/182] Iteration[100/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[147/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[147/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[147/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[147/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[147/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  80%|▊| 146/182 [4:33:48<1:07:09, 111.94s/it, Train Acc=99.96Epoch[147/182] Train Acc: 99.96% Valid Acc:73.78% Train loss:0.0029 Valid loss:1.7886 LR:0.0010000000000000002
Training Progress:  81%|▊| 147/182 [4:33:48<1:05:16, 111.91s/it, Train Acc=99.96Training: Epoch[148/182] Iteration[050/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[148/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[148/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[148/182] Iteration[200/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[148/182] Iteration[250/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[148/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[148/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  81%|▊| 147/182 [4:35:40<1:05:16, 111.91s/it, Train Acc=99.96Epoch[148/182] Train Acc: 99.96% Valid Acc:73.92% Train loss:0.0029 Valid loss:1.7815 LR:0.0010000000000000002
Training Progress:  81%|▊| 148/182 [4:35:40<1:03:24, 111.89s/it, Train Acc=99.96Training: Epoch[149/182] Iteration[050/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[149/182] Iteration[100/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[149/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[149/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[149/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[149/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[149/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  81%|▊| 148/182 [4:37:31<1:03:24, 111.89s/it, Train Acc=99.96Epoch[149/182] Train Acc: 99.96% Valid Acc:73.90% Train loss:0.0030 Valid loss:1.7802 LR:0.0010000000000000002
Training Progress:  82%|▊| 149/182 [4:37:31<1:01:32, 111.89s/it, Train Acc=99.96Training: Epoch[150/182] Iteration[050/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[150/182] Iteration[100/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[150/182] Iteration[150/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[150/182] Iteration[200/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[150/182] Iteration[250/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[150/182] Iteration[300/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[150/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  82%|▊| 149/182 [4:39:23<1:01:32, 111.89s/it, Train Acc=99.96Epoch[150/182] Train Acc: 99.96% Valid Acc:73.80% Train loss:0.0030 Valid loss:1.7813 LR:0.0010000000000000002
Training Progress:  82%|▊| 150/182 [4:39:23<59:40, 111.88s/it, Train Acc=99.96%,Training: Epoch[151/182] Iteration[050/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[151/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[151/182] Iteration[150/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[151/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[151/182] Iteration[250/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[151/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[151/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  82%|▊| 150/182 [4:41:15<59:40, 111.88s/it, Train Acc=99.96%,Epoch[151/182] Train Acc: 99.96% Valid Acc:73.78% Train loss:0.0028 Valid loss:1.7825 LR:0.0010000000000000002
Training Progress:  83%|▊| 151/182 [4:41:15<57:48, 111.88s/it, Train Acc=99.96%,Training: Epoch[152/182] Iteration[050/352] Loss: 0.0032 Acc:99.98%
Training: Epoch[152/182] Iteration[100/352] Loss: 0.0031 Acc:99.98%
Training: Epoch[152/182] Iteration[150/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[152/182] Iteration[200/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[152/182] Iteration[250/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[152/182] Iteration[300/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[152/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  83%|▊| 151/182 [4:43:07<57:48, 111.88s/it, Train Acc=99.97%,Epoch[152/182] Train Acc: 99.97% Valid Acc:73.90% Train loss:0.0029 Valid loss:1.7887 LR:0.0010000000000000002
Training Progress:  84%|▊| 152/182 [4:43:07<55:56, 111.87s/it, Train Acc=99.97%,Training: Epoch[153/182] Iteration[050/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[153/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[153/182] Iteration[150/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[153/182] Iteration[200/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[153/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[153/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[153/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  84%|▊| 152/182 [4:44:59<55:56, 111.87s/it, Train Acc=99.97%,Epoch[153/182] Train Acc: 99.97% Valid Acc:73.86% Train loss:0.0029 Valid loss:1.7830 LR:0.0010000000000000002
Training Progress:  84%|▊| 153/182 [4:44:59<54:03, 111.86s/it, Train Acc=99.97%,Training: Epoch[154/182] Iteration[050/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[154/182] Iteration[100/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[154/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[154/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[154/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[154/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[154/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  84%|▊| 153/182 [4:46:51<54:03, 111.86s/it, Train Acc=99.96%,Epoch[154/182] Train Acc: 99.96% Valid Acc:73.96% Train loss:0.0030 Valid loss:1.7796 LR:0.0010000000000000002
Training Progress:  85%|▊| 154/182 [4:46:51<52:12, 111.87s/it, Train Acc=99.96%,Training: Epoch[155/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[155/182] Iteration[100/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[155/182] Iteration[150/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[155/182] Iteration[200/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[155/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[155/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[155/182] Iteration[350/352] Loss: 0.0031 Acc:99.96%
Training Progress:  85%|▊| 154/182 [4:48:43<52:12, 111.87s/it, Train Acc=99.96%,Epoch[155/182] Train Acc: 99.96% Valid Acc:74.00% Train loss:0.0031 Valid loss:1.7864 LR:0.0010000000000000002
Training Progress:  85%|▊| 155/182 [4:48:43<50:20, 111.87s/it, Train Acc=99.96%,Training: Epoch[156/182] Iteration[050/352] Loss: 0.0037 Acc:99.91%
Training: Epoch[156/182] Iteration[100/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[156/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[156/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[156/182] Iteration[250/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[156/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[156/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  85%|▊| 155/182 [4:50:34<50:20, 111.87s/it, Train Acc=99.96%,Epoch[156/182] Train Acc: 99.96% Valid Acc:73.84% Train loss:0.0029 Valid loss:1.7833 LR:0.0010000000000000002
Training Progress:  86%|▊| 156/182 [4:50:34<48:28, 111.87s/it, Train Acc=99.96%,Training: Epoch[157/182] Iteration[050/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[157/182] Iteration[100/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[157/182] Iteration[150/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[157/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[157/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[157/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[157/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  86%|▊| 156/182 [4:52:26<48:28, 111.87s/it, Train Acc=99.97%,Epoch[157/182] Train Acc: 99.97% Valid Acc:73.90% Train loss:0.0029 Valid loss:1.7842 LR:0.0010000000000000002
Training Progress:  86%|▊| 157/182 [4:52:26<46:36, 111.87s/it, Train Acc=99.97%,Training: Epoch[158/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[158/182] Iteration[100/352] Loss: 0.0035 Acc:99.97%
Training: Epoch[158/182] Iteration[150/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[158/182] Iteration[200/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[158/182] Iteration[250/352] Loss: 0.0032 Acc:99.96%
Training: Epoch[158/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[158/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  86%|▊| 157/182 [4:54:18<46:36, 111.87s/it, Train Acc=99.96%,Epoch[158/182] Train Acc: 99.96% Valid Acc:73.82% Train loss:0.0030 Valid loss:1.7829 LR:0.0010000000000000002
Training Progress:  87%|▊| 158/182 [4:54:18<44:45, 111.91s/it, Train Acc=99.96%,Training: Epoch[159/182] Iteration[050/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[159/182] Iteration[100/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[159/182] Iteration[150/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[159/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[159/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[159/182] Iteration[300/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[159/182] Iteration[350/352] Loss: 0.0030 Acc:99.97%
Training Progress:  87%|▊| 158/182 [4:56:10<44:45, 111.91s/it, Train Acc=99.97%,Epoch[159/182] Train Acc: 99.97% Valid Acc:73.98% Train loss:0.0031 Valid loss:1.7786 LR:0.0010000000000000002
Training Progress:  87%|▊| 159/182 [4:56:10<42:54, 111.94s/it, Train Acc=99.97%,Training: Epoch[160/182] Iteration[050/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[160/182] Iteration[100/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[160/182] Iteration[150/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[160/182] Iteration[200/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[160/182] Iteration[250/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[160/182] Iteration[300/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[160/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  87%|▊| 159/182 [4:58:02<42:54, 111.94s/it, Train Acc=99.96%,Epoch[160/182] Train Acc: 99.96% Valid Acc:73.94% Train loss:0.0028 Valid loss:1.7882 LR:0.0010000000000000002
Training Progress:  88%|▉| 160/182 [4:58:02<41:02, 111.94s/it, Train Acc=99.96%,Training: Epoch[161/182] Iteration[050/352] Loss: 0.0035 Acc:99.92%
Training: Epoch[161/182] Iteration[100/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[161/182] Iteration[150/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[161/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[161/182] Iteration[250/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[161/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[161/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  88%|▉| 160/182 [4:59:54<41:02, 111.94s/it, Train Acc=99.97%,Epoch[161/182] Train Acc: 99.97% Valid Acc:73.74% Train loss:0.0029 Valid loss:1.7823 LR:0.0010000000000000002
Training Progress:  88%|▉| 161/182 [4:59:54<39:11, 111.96s/it, Train Acc=99.97%,Training: Epoch[162/182] Iteration[050/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[162/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[162/182] Iteration[150/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[162/182] Iteration[200/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[162/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[162/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[162/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  88%|▉| 161/182 [5:01:46<39:11, 111.96s/it, Train Acc=99.96%,Epoch[162/182] Train Acc: 99.96% Valid Acc:73.88% Train loss:0.0030 Valid loss:1.7864 LR:0.0010000000000000002
Training Progress:  89%|▉| 162/182 [5:01:46<37:19, 111.96s/it, Train Acc=99.96%,Training: Epoch[163/182] Iteration[050/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[163/182] Iteration[100/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[163/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[163/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[163/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[163/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[163/182] Iteration[350/352] Loss: 0.0028 Acc:99.97%
Training Progress:  89%|▉| 162/182 [5:03:38<37:19, 111.96s/it, Train Acc=99.96%,Epoch[163/182] Train Acc: 99.96% Valid Acc:73.84% Train loss:0.0028 Valid loss:1.7839 LR:0.0010000000000000002
Training Progress:  90%|▉| 163/182 [5:03:38<35:27, 111.98s/it, Train Acc=99.96%,Training: Epoch[164/182] Iteration[050/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[164/182] Iteration[100/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[164/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[164/182] Iteration[200/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[164/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[164/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[164/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  90%|▉| 163/182 [5:05:30<35:27, 111.98s/it, Train Acc=99.96%,Epoch[164/182] Train Acc: 99.96% Valid Acc:74.02% Train loss:0.0030 Valid loss:1.7892 LR:0.0010000000000000002
Training Progress:  90%|▉| 164/182 [5:05:30<33:35, 111.99s/it, Train Acc=99.96%,Training: Epoch[165/182] Iteration[050/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[165/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[165/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[165/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[165/182] Iteration[250/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[165/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[165/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  90%|▉| 164/182 [5:07:22<33:35, 111.99s/it, Train Acc=99.96%,Epoch[165/182] Train Acc: 99.96% Valid Acc:73.94% Train loss:0.0030 Valid loss:1.7868 LR:0.0010000000000000002
Training Progress:  91%|▉| 165/182 [5:07:22<31:44, 112.02s/it, Train Acc=99.96%,Training: Epoch[166/182] Iteration[050/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[166/182] Iteration[100/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[166/182] Iteration[150/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[166/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[166/182] Iteration[250/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[166/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[166/182] Iteration[350/352] Loss: 0.0029 Acc:99.97%
Training Progress:  91%|▉| 165/182 [5:09:15<31:44, 112.02s/it, Train Acc=99.97%,Epoch[166/182] Train Acc: 99.97% Valid Acc:73.98% Train loss:0.0029 Valid loss:1.7832 LR:0.0010000000000000002
Training Progress:  91%|▉| 166/182 [5:09:15<29:52, 112.06s/it, Train Acc=99.97%,Training: Epoch[167/182] Iteration[050/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[167/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[167/182] Iteration[150/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[167/182] Iteration[200/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[167/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[167/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[167/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  91%|▉| 166/182 [5:11:07<29:52, 112.06s/it, Train Acc=99.96%,Epoch[167/182] Train Acc: 99.96% Valid Acc:74.02% Train loss:0.0029 Valid loss:1.7851 LR:0.0010000000000000002
Training Progress:  92%|▉| 167/182 [5:11:07<28:01, 112.09s/it, Train Acc=99.96%,Training: Epoch[168/182] Iteration[050/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[168/182] Iteration[100/352] Loss: 0.0025 Acc:99.99%
Training: Epoch[168/182] Iteration[150/352] Loss: 0.0026 Acc:99.99%
Training: Epoch[168/182] Iteration[200/352] Loss: 0.0027 Acc:99.99%
Training: Epoch[168/182] Iteration[250/352] Loss: 0.0027 Acc:99.99%
Training: Epoch[168/182] Iteration[300/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[168/182] Iteration[350/352] Loss: 0.0029 Acc:99.98%
Training Progress:  92%|▉| 167/182 [5:12:59<28:01, 112.09s/it, Train Acc=99.98%,Epoch[168/182] Train Acc: 99.98% Valid Acc:73.88% Train loss:0.0029 Valid loss:1.7819 LR:0.0010000000000000002
Training Progress:  92%|▉| 168/182 [5:12:59<26:09, 112.12s/it, Train Acc=99.98%,Training: Epoch[169/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[169/182] Iteration[100/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[169/182] Iteration[150/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[169/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[169/182] Iteration[250/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[169/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[169/182] Iteration[350/352] Loss: 0.0030 Acc:99.95%
Training Progress:  92%|▉| 168/182 [5:14:51<26:09, 112.12s/it, Train Acc=99.95%,Epoch[169/182] Train Acc: 99.95% Valid Acc:73.98% Train loss:0.0030 Valid loss:1.7776 LR:0.0010000000000000002
Training Progress:  93%|▉| 169/182 [5:14:51<24:17, 112.15s/it, Train Acc=99.95%,Training: Epoch[170/182] Iteration[050/352] Loss: 0.0025 Acc:100.00%
Training: Epoch[170/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[170/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[170/182] Iteration[200/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[170/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[170/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[170/182] Iteration[350/352] Loss: 0.0028 Acc:99.98%
Training Progress:  93%|▉| 169/182 [5:16:43<24:17, 112.15s/it, Train Acc=99.98%,Epoch[170/182] Train Acc: 99.98% Valid Acc:73.90% Train loss:0.0028 Valid loss:1.7872 LR:0.0010000000000000002
Training Progress:  93%|▉| 170/182 [5:16:43<22:26, 112.19s/it, Train Acc=99.98%,Training: Epoch[171/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[171/182] Iteration[100/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[171/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[171/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[171/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[171/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[171/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  93%|▉| 170/182 [5:18:36<22:26, 112.19s/it, Train Acc=99.96%,Epoch[171/182] Train Acc: 99.96% Valid Acc:73.88% Train loss:0.0028 Valid loss:1.7831 LR:0.0010000000000000002
Training Progress:  94%|▉| 171/182 [5:18:36<20:34, 112.22s/it, Train Acc=99.96%,Training: Epoch[172/182] Iteration[050/352] Loss: 0.0029 Acc:99.94%
Training: Epoch[172/182] Iteration[100/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[172/182] Iteration[150/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[172/182] Iteration[200/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[172/182] Iteration[250/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[172/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[172/182] Iteration[350/352] Loss: 0.0030 Acc:99.95%
Training Progress:  94%|▉| 171/182 [5:20:28<20:34, 112.22s/it, Train Acc=99.95%,Epoch[172/182] Train Acc: 99.95% Valid Acc:73.84% Train loss:0.0030 Valid loss:1.7867 LR:0.0010000000000000002
Training Progress:  95%|▉| 172/182 [5:20:28<18:42, 112.23s/it, Train Acc=99.95%,Training: Epoch[173/182] Iteration[050/352] Loss: 0.0033 Acc:99.95%
Training: Epoch[173/182] Iteration[100/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[173/182] Iteration[150/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[173/182] Iteration[200/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[173/182] Iteration[250/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[173/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[173/182] Iteration[350/352] Loss: 0.0029 Acc:99.98%
Training Progress:  95%|▉| 172/182 [5:22:20<18:42, 112.23s/it, Train Acc=99.98%,Epoch[173/182] Train Acc: 99.98% Valid Acc:73.92% Train loss:0.0029 Valid loss:1.7889 LR:0.0010000000000000002
Training Progress:  95%|▉| 173/182 [5:22:20<16:50, 112.22s/it, Train Acc=99.98%,Training: Epoch[174/182] Iteration[050/352] Loss: 0.0044 Acc:99.94%
Training: Epoch[174/182] Iteration[100/352] Loss: 0.0034 Acc:99.97%
Training: Epoch[174/182] Iteration[150/352] Loss: 0.0033 Acc:99.97%
Training: Epoch[174/182] Iteration[200/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[174/182] Iteration[250/352] Loss: 0.0031 Acc:99.98%
Training: Epoch[174/182] Iteration[300/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[174/182] Iteration[350/352] Loss: 0.0030 Acc:99.98%
Training Progress:  95%|▉| 173/182 [5:24:12<16:50, 112.22s/it, Train Acc=99.98%,Epoch[174/182] Train Acc: 99.98% Valid Acc:74.00% Train loss:0.0030 Valid loss:1.7833 LR:0.0010000000000000002
Training Progress:  96%|▉| 174/182 [5:24:12<14:58, 112.25s/it, Train Acc=99.98%,Training: Epoch[175/182] Iteration[050/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[175/182] Iteration[100/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[175/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[175/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[175/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[175/182] Iteration[300/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[175/182] Iteration[350/352] Loss: 0.0028 Acc:99.97%
Training Progress:  96%|▉| 174/182 [5:26:05<14:58, 112.25s/it, Train Acc=99.97%,Epoch[175/182] Train Acc: 99.97% Valid Acc:73.92% Train loss:0.0028 Valid loss:1.7801 LR:0.0010000000000000002
Training Progress:  96%|▉| 175/182 [5:26:05<13:05, 112.27s/it, Train Acc=99.97%,Training: Epoch[176/182] Iteration[050/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[176/182] Iteration[100/352] Loss: 0.0027 Acc:99.98%
Training: Epoch[176/182] Iteration[150/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[176/182] Iteration[200/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[176/182] Iteration[250/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[176/182] Iteration[300/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[176/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  96%|▉| 175/182 [5:27:57<13:05, 112.27s/it, Train Acc=99.96%,Epoch[176/182] Train Acc: 99.96% Valid Acc:73.84% Train loss:0.0029 Valid loss:1.7811 LR:0.0010000000000000002
Training Progress:  97%|▉| 176/182 [5:27:57<11:13, 112.30s/it, Train Acc=99.96%,Training: Epoch[177/182] Iteration[050/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[177/182] Iteration[100/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[177/182] Iteration[150/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[177/182] Iteration[200/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[177/182] Iteration[250/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[177/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[177/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  97%|▉| 176/182 [5:29:50<11:13, 112.30s/it, Train Acc=99.96%,Epoch[177/182] Train Acc: 99.96% Valid Acc:73.96% Train loss:0.0029 Valid loss:1.7761 LR:0.0010000000000000002
Training Progress:  97%|▉| 177/182 [5:29:50<09:21, 112.34s/it, Train Acc=99.96%,Training: Epoch[178/182] Iteration[050/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[178/182] Iteration[100/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[178/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[178/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[178/182] Iteration[250/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[178/182] Iteration[300/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[178/182] Iteration[350/352] Loss: 0.0030 Acc:99.96%
Training Progress:  97%|▉| 177/182 [5:31:42<09:21, 112.34s/it, Train Acc=99.96%,Epoch[178/182] Train Acc: 99.96% Valid Acc:73.96% Train loss:0.0030 Valid loss:1.7804 LR:0.0010000000000000002
Training Progress:  98%|▉| 178/182 [5:31:42<07:29, 112.35s/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: 0.0026 Acc:99.98%
Training: Epoch[179/182] Iteration[150/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[179/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[179/182] Iteration[250/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[179/182] Iteration[300/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[179/182] Iteration[350/352] Loss: 0.0028 Acc:99.97%
Training Progress:  98%|▉| 178/182 [5:33:34<07:29, 112.35s/it, Train Acc=99.97%,Epoch[179/182] Train Acc: 99.97% Valid Acc:73.82% Train loss:0.0028 Valid loss:1.7780 LR:0.0010000000000000002
Training Progress:  98%|▉| 179/182 [5:33:34<05:37, 112.37s/it, Train Acc=99.97%,Training: Epoch[180/182] Iteration[050/352] Loss: 0.0025 Acc:100.00%
Training: Epoch[180/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[180/182] Iteration[150/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[180/182] Iteration[200/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[180/182] Iteration[250/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[180/182] Iteration[300/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[180/182] Iteration[350/352] Loss: 0.0028 Acc:99.96%
Training Progress:  98%|▉| 179/182 [5:35:27<05:37, 112.37s/it, Train Acc=99.96%,Epoch[180/182] Train Acc: 99.96% Valid Acc:74.04% Train loss:0.0028 Valid loss:1.7839 LR:0.0010000000000000002
Training Progress:  99%|▉| 180/182 [5:35:27<03:44, 112.35s/it, Train Acc=99.96%,Training: Epoch[181/182] Iteration[050/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[181/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[181/182] Iteration[150/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[181/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[181/182] Iteration[250/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[181/182] Iteration[300/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[181/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  99%|▉| 180/182 [5:37:19<03:44, 112.35s/it, Train Acc=99.96%,Epoch[181/182] Train Acc: 99.96% Valid Acc:73.78% Train loss:0.0028 Valid loss:1.7823 LR:0.0010000000000000002
Training Progress:  99%|▉| 181/182 [5:37:19<01:52, 112.35s/it, Train Acc=99.96%,Training: Epoch[182/182] Iteration[050/352] Loss: 0.0031 Acc:99.97%
Training: Epoch[182/182] Iteration[100/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[182/182] Iteration[150/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[182/182] Iteration[200/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[182/182] Iteration[250/352] Loss: 0.0028 Acc:99.98%
Training: Epoch[182/182] Iteration[300/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[182/182] Iteration[350/352] Loss: 0.0029 Acc:99.98%
Training Progress:  99%|▉| 181/182 [5:39:11<01:52, 112.35s/it, Train Acc=99.98%,Epoch[182/182] Train Acc: 99.98% Valid Acc:73.76% Train loss:0.0029 Valid loss:1.7803 LR:0.0010000000000000002
Training Progress: 100%|█| 182/182 [5:39:12<00:00, 111.83s/it, Train Acc=99.98%,

================ Training Finished ================
Finished Time      : 05-20_15-22
Best Validation Acc: 0.7404
Best Epoch         : 139
Best Test Acc      : 0.731
Total Training Time: 20352.32 sec (339.21 min)
===================================================

python ./src/eval.py --model q110 --check_point ./results/05-20_09-43/checkpoint_best.pkl

Acknowledgments and References

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

↪Back to the content⤴