【Ubuntu 24.04.3】Quotient Network: experiments_on_cifar10 — resnet44

MSI Cyborg-15-A12VE

Acknowledgments and References

(quotient) wish@wish-Cyborg-15-A12VE:~/Quotient-Networks/experiments_on_cifar10$ python ./src/train.py --model resnet44
Training Progress:   0%|                                | 0/182 [00:00<?, ?it/s]Training: Epoch[001/182] Iteration[050/352] Loss: 2.5719 Acc:12.94%
Training: Epoch[001/182] Iteration[100/352] Loss: 2.3403 Acc:15.70%
Training: Epoch[001/182] Iteration[150/352] Loss: 2.2299 Acc:18.17%
Training: Epoch[001/182] Iteration[200/352] Loss: 2.1613 Acc:20.06%
Training: Epoch[001/182] Iteration[250/352] Loss: 2.1087 Acc:21.61%
Training: Epoch[001/182] Iteration[300/352] Loss: 2.0647 Acc:23.06%
Training: Epoch[001/182] Iteration[350/352] Loss: 2.0280 Acc:24.36%
Training Progress:   0%| | 0/182 [00:17<?, ?it/s, Train Acc=24.38%, Valid Acc=31Epoch[001/182] Train Acc: 24.38% Valid Acc:31.60% Train loss:2.0271 Valid loss:1.7893 LR:0.1
Training Progress:   1%| | 1/182 [00:17<53:11, 17.63s/it, Train Acc=24.38%, ValiTraining: Epoch[002/182] Iteration[050/352] Loss: 1.7663 Acc:33.11%
Training: Epoch[002/182] Iteration[100/352] Loss: 1.7446 Acc:34.56%
Training: Epoch[002/182] Iteration[150/352] Loss: 1.7225 Acc:35.73%
Training: Epoch[002/182] Iteration[200/352] Loss: 1.7076 Acc:36.45%
Training: Epoch[002/182] Iteration[250/352] Loss: 1.6976 Acc:36.77%
Training: Epoch[002/182] Iteration[300/352] Loss: 1.6808 Acc:37.40%
Training: Epoch[002/182] Iteration[350/352] Loss: 1.6671 Acc:38.03%
Training Progress:   1%| | 1/182 [00:35<53:11, 17.63s/it, Train Acc=38.07%, ValiEpoch[002/182] Train Acc: 38.07% Valid Acc:34.66% Train loss:1.6661 Valid loss:1.8543 LR:0.1
Training Progress:   1%| | 2/182 [00:35<52:31, 17.51s/it, Train Acc=38.07%, ValiTraining: Epoch[003/182] Iteration[050/352] Loss: 1.5550 Acc:43.44%
Training: Epoch[003/182] Iteration[100/352] Loss: 1.5328 Acc:44.03%
Training: Epoch[003/182] Iteration[150/352] Loss: 1.5086 Acc:44.44%
Training: Epoch[003/182] Iteration[200/352] Loss: 1.4907 Acc:45.12%
Training: Epoch[003/182] Iteration[250/352] Loss: 1.4756 Acc:45.69%
Training: Epoch[003/182] Iteration[300/352] Loss: 1.4610 Acc:46.19%
Training: Epoch[003/182] Iteration[350/352] Loss: 1.4502 Acc:46.76%
Training Progress:   1%| | 2/182 [00:52<52:31, 17.51s/it, Train Acc=46.78%, ValiEpoch[003/182] Train Acc: 46.78% Valid Acc:46.12% Train loss:1.4491 Valid loss:1.5306 LR:0.1
Training Progress:   2%| | 3/182 [00:52<52:18, 17.53s/it, Train Acc=46.78%, ValiTraining: Epoch[004/182] Iteration[050/352] Loss: 1.3195 Acc:51.94%
Training: Epoch[004/182] Iteration[100/352] Loss: 1.3077 Acc:52.65%
Training: Epoch[004/182] Iteration[150/352] Loss: 1.2949 Acc:52.57%
Training: Epoch[004/182] Iteration[200/352] Loss: 1.2800 Acc:53.11%
Training: Epoch[004/182] Iteration[250/352] Loss: 1.2711 Acc:53.63%
Training: Epoch[004/182] Iteration[300/352] Loss: 1.2552 Acc:54.21%
Training: Epoch[004/182] Iteration[350/352] Loss: 1.2393 Acc:54.92%
Training Progress:   2%| | 3/182 [01:10<52:18, 17.53s/it, Train Acc=54.94%, ValiEpoch[004/182] Train Acc: 54.94% Valid Acc:57.00% Train loss:1.2385 Valid loss:1.2427 LR:0.1
Training Progress:   2%| | 4/182 [01:10<52:11, 17.59s/it, Train Acc=54.94%, ValiTraining: Epoch[005/182] Iteration[050/352] Loss: 1.1231 Acc:60.12%
Training: Epoch[005/182] Iteration[100/352] Loss: 1.1082 Acc:60.43%
Training: Epoch[005/182] Iteration[150/352] Loss: 1.0839 Acc:61.44%
Training: Epoch[005/182] Iteration[200/352] Loss: 1.0624 Acc:62.14%
Training: Epoch[005/182] Iteration[250/352] Loss: 1.0485 Acc:62.66%
Training: Epoch[005/182] Iteration[300/352] Loss: 1.0277 Acc:63.39%
Training: Epoch[005/182] Iteration[350/352] Loss: 1.0175 Acc:63.78%
Training Progress:   2%| | 4/182 [01:28<52:11, 17.59s/it, Train Acc=63.80%, ValiEpoch[005/182] Train Acc: 63.80% Valid Acc:66.58% Train loss:1.0167 Valid loss:0.9599 LR:0.1
Training Progress:   3%| | 5/182 [01:28<52:06, 17.66s/it, Train Acc=63.80%, ValiTraining: Epoch[006/182] Iteration[050/352] Loss: 0.9032 Acc:67.41%
Training: Epoch[006/182] Iteration[100/352] Loss: 0.8888 Acc:68.47%
Training: Epoch[006/182] Iteration[150/352] Loss: 0.8771 Acc:68.92%
Training: Epoch[006/182] Iteration[200/352] Loss: 0.8686 Acc:69.29%
Training: Epoch[006/182] Iteration[250/352] Loss: 0.8522 Acc:69.93%
Training: Epoch[006/182] Iteration[300/352] Loss: 0.8457 Acc:70.22%
Training: Epoch[006/182] Iteration[350/352] Loss: 0.8403 Acc:70.37%
Training Progress:   3%| | 5/182 [01:45<52:06, 17.66s/it, Train Acc=70.38%, ValiEpoch[006/182] Train Acc: 70.38% Valid Acc:74.06% Train loss:0.8402 Valid loss:0.7503 LR:0.1
Training Progress:   3%| | 6/182 [01:45<51:55, 17.70s/it, Train Acc=70.38%, ValiTraining: Epoch[007/182] Iteration[050/352] Loss: 0.7526 Acc:73.67%
Training: Epoch[007/182] Iteration[100/352] Loss: 0.7525 Acc:73.77%
Training: Epoch[007/182] Iteration[150/352] Loss: 0.7432 Acc:74.15%
Training: Epoch[007/182] Iteration[200/352] Loss: 0.7342 Acc:74.46%
Training: Epoch[007/182] Iteration[250/352] Loss: 0.7317 Acc:74.62%
Training: Epoch[007/182] Iteration[300/352] Loss: 0.7272 Acc:74.76%
Training: Epoch[007/182] Iteration[350/352] Loss: 0.7255 Acc:74.81%
Training Progress:   3%| | 6/182 [02:03<51:55, 17.70s/it, Train Acc=74.79%, ValiEpoch[007/182] Train Acc: 74.79% Valid Acc:72.38% Train loss:0.7258 Valid loss:0.8326 LR:0.1
Training Progress:   4%| | 7/182 [02:03<51:49, 17.77s/it, Train Acc=74.79%, ValiTraining: Epoch[008/182] Iteration[050/352] Loss: 0.6875 Acc:75.19%
Training: Epoch[008/182] Iteration[100/352] Loss: 0.6917 Acc:75.33%
Training: Epoch[008/182] Iteration[150/352] Loss: 0.6842 Acc:75.80%
Training: Epoch[008/182] Iteration[200/352] Loss: 0.6740 Acc:76.18%
Training: Epoch[008/182] Iteration[250/352] Loss: 0.6640 Acc:76.54%
Training: Epoch[008/182] Iteration[300/352] Loss: 0.6613 Acc:76.71%
Training: Epoch[008/182] Iteration[350/352] Loss: 0.6571 Acc:76.89%
Training Progress:   4%| | 7/182 [02:21<51:49, 17.77s/it, Train Acc=76.89%, ValiEpoch[008/182] Train Acc: 76.89% Valid Acc:76.76% Train loss:0.6572 Valid loss:0.7255 LR:0.1
Training Progress:   4%| | 8/182 [02:21<51:44, 17.84s/it, Train Acc=76.89%, ValiTraining: Epoch[009/182] Iteration[050/352] Loss: 0.6294 Acc:77.84%
Training: Epoch[009/182] Iteration[100/352] Loss: 0.6085 Acc:78.80%
Training: Epoch[009/182] Iteration[150/352] Loss: 0.6059 Acc:78.79%
Training: Epoch[009/182] Iteration[200/352] Loss: 0.6079 Acc:78.76%
Training: Epoch[009/182] Iteration[250/352] Loss: 0.6072 Acc:78.87%
Training: Epoch[009/182] Iteration[300/352] Loss: 0.6063 Acc:78.87%
Training: Epoch[009/182] Iteration[350/352] Loss: 0.6056 Acc:78.94%
Training Progress:   4%| | 8/182 [02:39<51:44, 17.84s/it, Train Acc=78.94%, ValiEpoch[009/182] Train Acc: 78.94% Valid Acc:79.56% Train loss:0.6061 Valid loss:0.6092 LR:0.1
Training Progress:   5%| | 9/182 [02:39<51:35, 17.89s/it, Train Acc=78.94%, ValiTraining: Epoch[010/182] Iteration[050/352] Loss: 0.5478 Acc:80.83%
Training: Epoch[010/182] Iteration[100/352] Loss: 0.5536 Acc:80.63%
Training: Epoch[010/182] Iteration[150/352] Loss: 0.5511 Acc:80.62%
Training: Epoch[010/182] Iteration[200/352] Loss: 0.5554 Acc:80.59%
Training: Epoch[010/182] Iteration[250/352] Loss: 0.5563 Acc:80.67%
Training: Epoch[010/182] Iteration[300/352] Loss: 0.5532 Acc:80.80%
Training: Epoch[010/182] Iteration[350/352] Loss: 0.5562 Acc:80.63%
Training Progress:   5%| | 9/182 [02:57<51:35, 17.89s/it, Train Acc=80.65%, ValiEpoch[010/182] Train Acc: 80.65% Valid Acc:77.56% Train loss:0.5555 Valid loss:0.6843 LR:0.1
Training Progress:   5%| | 10/182 [02:57<51:31, 17.97s/it, Train Acc=80.65%, ValTraining: Epoch[011/182] Iteration[050/352] Loss: 0.4968 Acc:82.75%
Training: Epoch[011/182] Iteration[100/352] Loss: 0.5109 Acc:82.10%
Training: Epoch[011/182] Iteration[150/352] Loss: 0.5212 Acc:81.74%
Training: Epoch[011/182] Iteration[200/352] Loss: 0.5177 Acc:81.92%
Training: Epoch[011/182] Iteration[250/352] Loss: 0.5258 Acc:81.70%
Training: Epoch[011/182] Iteration[300/352] Loss: 0.5243 Acc:81.81%
Training: Epoch[011/182] Iteration[350/352] Loss: 0.5208 Acc:81.92%
Training Progress:   5%| | 10/182 [03:16<51:31, 17.97s/it, Train Acc=81.91%, ValEpoch[011/182] Train Acc: 81.91% Valid Acc:82.40% Train loss:0.5211 Valid loss:0.5198 LR:0.1
Training Progress:   6%| | 11/182 [03:16<51:20, 18.01s/it, Train Acc=81.91%, ValTraining: Epoch[012/182] Iteration[050/352] Loss: 0.4686 Acc:83.47%
Training: Epoch[012/182] Iteration[100/352] Loss: 0.4873 Acc:82.87%
Training: Epoch[012/182] Iteration[150/352] Loss: 0.4909 Acc:83.01%
Training: Epoch[012/182] Iteration[200/352] Loss: 0.4917 Acc:82.90%
Training: Epoch[012/182] Iteration[250/352] Loss: 0.4913 Acc:82.94%
Training: Epoch[012/182] Iteration[300/352] Loss: 0.4925 Acc:82.96%
Training: Epoch[012/182] Iteration[350/352] Loss: 0.4911 Acc:83.00%
Training Progress:   6%| | 11/182 [03:34<51:20, 18.01s/it, Train Acc=83.00%, ValEpoch[012/182] Train Acc: 83.00% Valid Acc:81.10% Train loss:0.4912 Valid loss:0.5848 LR:0.1
Training Progress:   7%| | 12/182 [03:34<51:13, 18.08s/it, Train Acc=83.00%, ValTraining: Epoch[013/182] Iteration[050/352] Loss: 0.4429 Acc:84.19%
Training: Epoch[013/182] Iteration[100/352] Loss: 0.4548 Acc:84.16%
Training: Epoch[013/182] Iteration[150/352] Loss: 0.4585 Acc:84.03%
Training: Epoch[013/182] Iteration[200/352] Loss: 0.4649 Acc:83.72%
Training: Epoch[013/182] Iteration[250/352] Loss: 0.4643 Acc:83.68%
Training: Epoch[013/182] Iteration[300/352] Loss: 0.4643 Acc:83.65%
Training: Epoch[013/182] Iteration[350/352] Loss: 0.4642 Acc:83.71%
Training Progress:   7%| | 12/182 [03:52<51:13, 18.08s/it, Train Acc=83.71%, ValEpoch[013/182] Train Acc: 83.71% Valid Acc:80.28% Train loss:0.4647 Valid loss:0.5772 LR:0.1
Training Progress:   7%| | 13/182 [03:52<51:03, 18.13s/it, Train Acc=83.71%, ValTraining: Epoch[014/182] Iteration[050/352] Loss: 0.4405 Acc:84.88%
Training: Epoch[014/182] Iteration[100/352] Loss: 0.4428 Acc:84.84%
Training: Epoch[014/182] Iteration[150/352] Loss: 0.4429 Acc:84.76%
Training: Epoch[014/182] Iteration[200/352] Loss: 0.4446 Acc:84.59%
Training: Epoch[014/182] Iteration[250/352] Loss: 0.4443 Acc:84.53%
Training: Epoch[014/182] Iteration[300/352] Loss: 0.4427 Acc:84.68%
Training: Epoch[014/182] Iteration[350/352] Loss: 0.4412 Acc:84.69%
Training Progress:   7%| | 13/182 [04:10<51:03, 18.13s/it, Train Acc=84.69%, ValEpoch[014/182] Train Acc: 84.69% Valid Acc:82.34% Train loss:0.4416 Valid loss:0.5314 LR:0.1
Training Progress:   8%| | 14/182 [04:10<50:54, 18.18s/it, Train Acc=84.69%, ValTraining: Epoch[015/182] Iteration[050/352] Loss: 0.3971 Acc:86.53%
Training: Epoch[015/182] Iteration[100/352] Loss: 0.4019 Acc:86.16%
Training: Epoch[015/182] Iteration[150/352] Loss: 0.4141 Acc:85.54%
Training: Epoch[015/182] Iteration[200/352] Loss: 0.4215 Acc:85.32%
Training: Epoch[015/182] Iteration[250/352] Loss: 0.4219 Acc:85.29%
Training: Epoch[015/182] Iteration[300/352] Loss: 0.4219 Acc:85.27%
Training: Epoch[015/182] Iteration[350/352] Loss: 0.4249 Acc:85.24%
Training Progress:   8%| | 14/182 [04:29<50:54, 18.18s/it, Train Acc=85.24%, ValEpoch[015/182] Train Acc: 85.24% Valid Acc:84.24% Train loss:0.4250 Valid loss:0.5060 LR:0.1
Training Progress:   8%| | 15/182 [04:29<50:40, 18.21s/it, Train Acc=85.24%, ValTraining: Epoch[016/182] Iteration[050/352] Loss: 0.4044 Acc:86.33%
Training: Epoch[016/182] Iteration[100/352] Loss: 0.4044 Acc:86.24%
Training: Epoch[016/182] Iteration[150/352] Loss: 0.4006 Acc:86.22%
Training: Epoch[016/182] Iteration[200/352] Loss: 0.4002 Acc:86.19%
Training: Epoch[016/182] Iteration[250/352] Loss: 0.4018 Acc:86.08%
Training: Epoch[016/182] Iteration[300/352] Loss: 0.4059 Acc:85.97%
Training: Epoch[016/182] Iteration[350/352] Loss: 0.4058 Acc:85.90%
Training Progress:   8%| | 15/182 [04:47<50:40, 18.21s/it, Train Acc=85.91%, ValEpoch[016/182] Train Acc: 85.91% Valid Acc:84.50% Train loss:0.4058 Valid loss:0.4830 LR:0.1
Training Progress:   9%| | 16/182 [04:47<50:25, 18.23s/it, Train Acc=85.91%, ValTraining: Epoch[017/182] Iteration[050/352] Loss: 0.3468 Acc:88.36%
Training: Epoch[017/182] Iteration[100/352] Loss: 0.3639 Acc:87.59%
Training: Epoch[017/182] Iteration[150/352] Loss: 0.3642 Acc:87.47%
Training: Epoch[017/182] Iteration[200/352] Loss: 0.3696 Acc:87.28%
Training: Epoch[017/182] Iteration[250/352] Loss: 0.3761 Acc:87.02%
Training: Epoch[017/182] Iteration[300/352] Loss: 0.3796 Acc:86.85%
Training: Epoch[017/182] Iteration[350/352] Loss: 0.3836 Acc:86.72%
Training Progress:   9%| | 16/182 [05:05<50:25, 18.23s/it, Train Acc=86.72%, ValEpoch[017/182] Train Acc: 86.72% Valid Acc:83.30% Train loss:0.3836 Valid loss:0.5022 LR:0.1
Training Progress:   9%| | 17/182 [05:05<50:17, 18.29s/it, Train Acc=86.72%, ValTraining: Epoch[018/182] Iteration[050/352] Loss: 0.3677 Acc:87.59%
Training: Epoch[018/182] Iteration[100/352] Loss: 0.3756 Acc:87.16%
Training: Epoch[018/182] Iteration[150/352] Loss: 0.3723 Acc:87.29%
Training: Epoch[018/182] Iteration[200/352] Loss: 0.3702 Acc:87.26%
Training: Epoch[018/182] Iteration[250/352] Loss: 0.3716 Acc:87.23%
Training: Epoch[018/182] Iteration[300/352] Loss: 0.3754 Acc:87.13%
Training: Epoch[018/182] Iteration[350/352] Loss: 0.3757 Acc:87.09%
Training Progress:   9%| | 17/182 [05:24<50:17, 18.29s/it, Train Acc=87.10%, ValEpoch[018/182] Train Acc: 87.10% Valid Acc:85.30% Train loss:0.3754 Valid loss:0.4425 LR:0.1
Training Progress:  10%| | 18/182 [05:24<50:11, 18.36s/it, Train Acc=87.10%, ValTraining: Epoch[019/182] Iteration[050/352] Loss: 0.3363 Acc:87.92%
Training: Epoch[019/182] Iteration[100/352] Loss: 0.3488 Acc:87.62%
Training: Epoch[019/182] Iteration[150/352] Loss: 0.3506 Acc:87.72%
Training: Epoch[019/182] Iteration[200/352] Loss: 0.3560 Acc:87.52%
Training: Epoch[019/182] Iteration[250/352] Loss: 0.3552 Acc:87.54%
Training: Epoch[019/182] Iteration[300/352] Loss: 0.3572 Acc:87.46%
Training: Epoch[019/182] Iteration[350/352] Loss: 0.3583 Acc:87.44%
Training Progress:  10%| | 18/182 [05:44<50:11, 18.36s/it, Train Acc=87.43%, ValEpoch[019/182] Train Acc: 87.43% Valid Acc:85.10% Train loss:0.3588 Valid loss:0.4567 LR:0.1
Training Progress:  10%| | 19/182 [05:44<51:00, 18.78s/it, Train Acc=87.43%, ValTraining: Epoch[020/182] Iteration[050/352] Loss: 0.3443 Acc:87.70%
Training: Epoch[020/182] Iteration[100/352] Loss: 0.3561 Acc:87.45%
Training: Epoch[020/182] Iteration[150/352] Loss: 0.3476 Acc:87.79%
Training: Epoch[020/182] Iteration[200/352] Loss: 0.3503 Acc:87.71%
Training: Epoch[020/182] Iteration[250/352] Loss: 0.3513 Acc:87.67%
Training: Epoch[020/182] Iteration[300/352] Loss: 0.3497 Acc:87.78%
Training: Epoch[020/182] Iteration[350/352] Loss: 0.3491 Acc:87.83%
Training Progress:  10%| | 19/182 [06:02<51:00, 18.78s/it, Train Acc=87.83%, ValEpoch[020/182] Train Acc: 87.83% Valid Acc:83.84% Train loss:0.3491 Valid loss:0.5130 LR:0.1
Training Progress:  11%| | 20/182 [06:02<50:24, 18.67s/it, Train Acc=87.83%, ValTraining: Epoch[021/182] Iteration[050/352] Loss: 0.3326 Acc:88.36%
Training: Epoch[021/182] Iteration[100/352] Loss: 0.3319 Acc:88.66%
Training: Epoch[021/182] Iteration[150/352] Loss: 0.3386 Acc:88.42%
Training: Epoch[021/182] Iteration[200/352] Loss: 0.3337 Acc:88.57%
Training: Epoch[021/182] Iteration[250/352] Loss: 0.3359 Acc:88.36%
Training: Epoch[021/182] Iteration[300/352] Loss: 0.3377 Acc:88.30%
Training: Epoch[021/182] Iteration[350/352] Loss: 0.3349 Acc:88.34%
Training Progress:  11%| | 20/182 [06:20<50:24, 18.67s/it, Train Acc=88.33%, ValEpoch[021/182] Train Acc: 88.33% Valid Acc:85.32% Train loss:0.3354 Valid loss:0.4570 LR:0.1
Training Progress:  12%| | 21/182 [06:20<49:53, 18.60s/it, Train Acc=88.33%, ValTraining: Epoch[022/182] Iteration[050/352] Loss: 0.3012 Acc:89.64%
Training: Epoch[022/182] Iteration[100/352] Loss: 0.3129 Acc:89.20%
Training: Epoch[022/182] Iteration[150/352] Loss: 0.3167 Acc:89.06%
Training: Epoch[022/182] Iteration[200/352] Loss: 0.3190 Acc:88.91%
Training: Epoch[022/182] Iteration[250/352] Loss: 0.3212 Acc:88.80%
Training: Epoch[022/182] Iteration[300/352] Loss: 0.3232 Acc:88.69%
Training: Epoch[022/182] Iteration[350/352] Loss: 0.3266 Acc:88.61%
Training Progress:  12%| | 21/182 [06:39<49:53, 18.60s/it, Train Acc=88.62%, ValEpoch[022/182] Train Acc: 88.62% Valid Acc:84.20% Train loss:0.3264 Valid loss:0.5011 LR:0.1
Training Progress:  12%| | 22/182 [06:39<49:30, 18.57s/it, Train Acc=88.62%, ValTraining: Epoch[023/182] Iteration[050/352] Loss: 0.3178 Acc:88.70%
Training: Epoch[023/182] Iteration[100/352] Loss: 0.3167 Acc:88.83%
Training: Epoch[023/182] Iteration[150/352] Loss: 0.3124 Acc:89.11%
Training: Epoch[023/182] Iteration[200/352] Loss: 0.3159 Acc:88.97%
Training: Epoch[023/182] Iteration[250/352] Loss: 0.3176 Acc:88.87%
Training: Epoch[023/182] Iteration[300/352] Loss: 0.3166 Acc:88.95%
Training: Epoch[023/182] Iteration[350/352] Loss: 0.3159 Acc:88.96%
Training Progress:  12%| | 22/182 [06:57<49:30, 18.57s/it, Train Acc=88.97%, ValEpoch[023/182] Train Acc: 88.97% Valid Acc:84.88% Train loss:0.3157 Valid loss:0.4681 LR:0.1
Training Progress:  13%|▏| 23/182 [06:57<49:06, 18.53s/it, Train Acc=88.97%, ValTraining: Epoch[024/182] Iteration[050/352] Loss: 0.3185 Acc:88.75%
Training: Epoch[024/182] Iteration[100/352] Loss: 0.3102 Acc:89.26%
Training: Epoch[024/182] Iteration[150/352] Loss: 0.3060 Acc:89.28%
Training: Epoch[024/182] Iteration[200/352] Loss: 0.3035 Acc:89.45%
Training: Epoch[024/182] Iteration[250/352] Loss: 0.3036 Acc:89.37%
Training: Epoch[024/182] Iteration[300/352] Loss: 0.3081 Acc:89.21%
Training: Epoch[024/182] Iteration[350/352] Loss: 0.3089 Acc:89.17%
Training Progress:  13%|▏| 23/182 [07:16<49:06, 18.53s/it, Train Acc=89.17%, ValEpoch[024/182] Train Acc: 89.17% Valid Acc:83.94% Train loss:0.3088 Valid loss:0.4775 LR:0.1
Training Progress:  13%|▏| 24/182 [07:16<48:46, 18.52s/it, Train Acc=89.17%, ValTraining: Epoch[025/182] Iteration[050/352] Loss: 0.3056 Acc:88.88%
Training: Epoch[025/182] Iteration[100/352] Loss: 0.2959 Acc:89.50%
Training: Epoch[025/182] Iteration[150/352] Loss: 0.2991 Acc:89.45%
Training: Epoch[025/182] Iteration[200/352] Loss: 0.2984 Acc:89.51%
Training: Epoch[025/182] Iteration[250/352] Loss: 0.3006 Acc:89.46%
Training: Epoch[025/182] Iteration[300/352] Loss: 0.3000 Acc:89.47%
Training: Epoch[025/182] Iteration[350/352] Loss: 0.3001 Acc:89.54%
Training Progress:  13%|▏| 24/182 [07:34<48:46, 18.52s/it, Train Acc=89.55%, ValEpoch[025/182] Train Acc: 89.55% Valid Acc:85.48% Train loss:0.3000 Valid loss:0.4213 LR:0.1
Training Progress:  14%|▏| 25/182 [07:34<48:25, 18.51s/it, Train Acc=89.55%, ValTraining: Epoch[026/182] Iteration[050/352] Loss: 0.2789 Acc:90.17%
Training: Epoch[026/182] Iteration[100/352] Loss: 0.2759 Acc:90.35%
Training: Epoch[026/182] Iteration[150/352] Loss: 0.2802 Acc:90.15%
Training: Epoch[026/182] Iteration[200/352] Loss: 0.2814 Acc:90.13%
Training: Epoch[026/182] Iteration[250/352] Loss: 0.2852 Acc:89.98%
Training: Epoch[026/182] Iteration[300/352] Loss: 0.2924 Acc:89.73%
Training: Epoch[026/182] Iteration[350/352] Loss: 0.2931 Acc:89.71%
Training Progress:  14%|▏| 25/182 [07:53<48:25, 18.51s/it, Train Acc=89.70%, ValEpoch[026/182] Train Acc: 89.70% Valid Acc:85.74% Train loss:0.2931 Valid loss:0.4426 LR:0.1
Training Progress:  14%|▏| 26/182 [07:53<48:09, 18.52s/it, Train Acc=89.70%, ValTraining: Epoch[027/182] Iteration[050/352] Loss: 0.2551 Acc:91.06%
Training: Epoch[027/182] Iteration[100/352] Loss: 0.2630 Acc:90.62%
Training: Epoch[027/182] Iteration[150/352] Loss: 0.2715 Acc:90.44%
Training: Epoch[027/182] Iteration[200/352] Loss: 0.2777 Acc:90.28%
Training: Epoch[027/182] Iteration[250/352] Loss: 0.2802 Acc:90.21%
Training: Epoch[027/182] Iteration[300/352] Loss: 0.2816 Acc:90.17%
Training: Epoch[027/182] Iteration[350/352] Loss: 0.2829 Acc:90.12%
Training Progress:  14%|▏| 26/182 [08:11<48:09, 18.52s/it, Train Acc=90.11%, ValEpoch[027/182] Train Acc: 90.11% Valid Acc:86.94% Train loss:0.2831 Valid loss:0.4022 LR:0.1
Training Progress:  15%|▏| 27/182 [08:11<47:49, 18.51s/it, Train Acc=90.11%, ValTraining: Epoch[028/182] Iteration[050/352] Loss: 0.2588 Acc:91.36%
Training: Epoch[028/182] Iteration[100/352] Loss: 0.2705 Acc:90.67%
Training: Epoch[028/182] Iteration[150/352] Loss: 0.2723 Acc:90.53%
Training: Epoch[028/182] Iteration[200/352] Loss: 0.2756 Acc:90.40%
Training: Epoch[028/182] Iteration[250/352] Loss: 0.2747 Acc:90.47%
Training: Epoch[028/182] Iteration[300/352] Loss: 0.2760 Acc:90.42%
Training: Epoch[028/182] Iteration[350/352] Loss: 0.2792 Acc:90.28%
Training Progress:  15%|▏| 27/182 [08:30<47:49, 18.51s/it, Train Acc=90.28%, ValEpoch[028/182] Train Acc: 90.28% Valid Acc:86.06% Train loss:0.2794 Valid loss:0.4497 LR:0.1
Training Progress:  15%|▏| 28/182 [08:30<47:30, 18.51s/it, Train Acc=90.28%, ValTraining: Epoch[029/182] Iteration[050/352] Loss: 0.2672 Acc:90.73%
Training: Epoch[029/182] Iteration[100/352] Loss: 0.2655 Acc:90.73%
Training: Epoch[029/182] Iteration[150/352] Loss: 0.2713 Acc:90.66%
Training: Epoch[029/182] Iteration[200/352] Loss: 0.2699 Acc:90.67%
Training: Epoch[029/182] Iteration[250/352] Loss: 0.2727 Acc:90.60%
Training: Epoch[029/182] Iteration[300/352] Loss: 0.2738 Acc:90.53%
Training: Epoch[029/182] Iteration[350/352] Loss: 0.2742 Acc:90.50%
Training Progress:  15%|▏| 28/182 [08:49<47:30, 18.51s/it, Train Acc=90.52%, ValEpoch[029/182] Train Acc: 90.52% Valid Acc:86.14% Train loss:0.2738 Valid loss:0.4199 LR:0.1
Training Progress:  16%|▏| 29/182 [08:49<47:35, 18.66s/it, Train Acc=90.52%, ValTraining: Epoch[030/182] Iteration[050/352] Loss: 0.2429 Acc:91.58%
Training: Epoch[030/182] Iteration[100/352] Loss: 0.2560 Acc:91.27%
Training: Epoch[030/182] Iteration[150/352] Loss: 0.2647 Acc:90.94%
Training: Epoch[030/182] Iteration[200/352] Loss: 0.2666 Acc:90.87%
Training: Epoch[030/182] Iteration[250/352] Loss: 0.2648 Acc:90.93%
Training: Epoch[030/182] Iteration[300/352] Loss: 0.2661 Acc:90.82%
Training: Epoch[030/182] Iteration[350/352] Loss: 0.2671 Acc:90.76%
Training Progress:  16%|▏| 29/182 [09:08<47:35, 18.66s/it, Train Acc=90.76%, ValEpoch[030/182] Train Acc: 90.76% Valid Acc:82.20% Train loss:0.2671 Valid loss:0.6068 LR:0.1
Training Progress:  16%|▏| 30/182 [09:08<47:14, 18.65s/it, Train Acc=90.76%, ValTraining: Epoch[031/182] Iteration[050/352] Loss: 0.2384 Acc:91.89%
Training: Epoch[031/182] Iteration[100/352] Loss: 0.2455 Acc:91.39%
Training: Epoch[031/182] Iteration[150/352] Loss: 0.2519 Acc:91.12%
Training: Epoch[031/182] Iteration[200/352] Loss: 0.2586 Acc:90.89%
Training: Epoch[031/182] Iteration[250/352] Loss: 0.2612 Acc:90.85%
Training: Epoch[031/182] Iteration[300/352] Loss: 0.2640 Acc:90.74%
Training: Epoch[031/182] Iteration[350/352] Loss: 0.2649 Acc:90.70%
Training Progress:  16%|▏| 30/182 [09:26<47:14, 18.65s/it, Train Acc=90.70%, ValEpoch[031/182] Train Acc: 90.70% Valid Acc:87.22% Train loss:0.2650 Valid loss:0.4207 LR:0.1
Training Progress:  17%|▏| 31/182 [09:26<46:52, 18.63s/it, Train Acc=90.70%, ValTraining: Epoch[032/182] Iteration[050/352] Loss: 0.2504 Acc:91.28%
Training: Epoch[032/182] Iteration[100/352] Loss: 0.2597 Acc:90.80%
Training: Epoch[032/182] Iteration[150/352] Loss: 0.2570 Acc:90.98%
Training: Epoch[032/182] Iteration[200/352] Loss: 0.2578 Acc:90.95%
Training: Epoch[032/182] Iteration[250/352] Loss: 0.2572 Acc:91.03%
Training: Epoch[032/182] Iteration[300/352] Loss: 0.2600 Acc:90.98%
Training: Epoch[032/182] Iteration[350/352] Loss: 0.2607 Acc:91.00%
Training Progress:  17%|▏| 31/182 [09:45<46:52, 18.63s/it, Train Acc=91.01%, ValEpoch[032/182] Train Acc: 91.01% Valid Acc:84.74% Train loss:0.2604 Valid loss:0.5095 LR:0.1
Training Progress:  18%|▏| 32/182 [09:45<46:31, 18.61s/it, Train Acc=91.01%, ValTraining: Epoch[033/182] Iteration[050/352] Loss: 0.2436 Acc:91.77%
Training: Epoch[033/182] Iteration[100/352] Loss: 0.2500 Acc:91.40%
Training: Epoch[033/182] Iteration[150/352] Loss: 0.2497 Acc:91.38%
Training: Epoch[033/182] Iteration[200/352] Loss: 0.2519 Acc:91.30%
Training: Epoch[033/182] Iteration[250/352] Loss: 0.2553 Acc:91.17%
Training: Epoch[033/182] Iteration[300/352] Loss: 0.2564 Acc:91.11%
Training: Epoch[033/182] Iteration[350/352] Loss: 0.2556 Acc:91.11%
Training Progress:  18%|▏| 32/182 [10:03<46:31, 18.61s/it, Train Acc=91.11%, ValEpoch[033/182] Train Acc: 91.11% Valid Acc:85.34% Train loss:0.2555 Valid loss:0.4751 LR:0.1
Training Progress:  18%|▏| 33/182 [10:03<46:11, 18.60s/it, Train Acc=91.11%, ValTraining: Epoch[034/182] Iteration[050/352] Loss: 0.2254 Acc:91.98%
Training: Epoch[034/182] Iteration[100/352] Loss: 0.2334 Acc:91.81%
Training: Epoch[034/182] Iteration[150/352] Loss: 0.2310 Acc:91.92%
Training: Epoch[034/182] Iteration[200/352] Loss: 0.2367 Acc:91.73%
Training: Epoch[034/182] Iteration[250/352] Loss: 0.2432 Acc:91.44%
Training: Epoch[034/182] Iteration[300/352] Loss: 0.2459 Acc:91.37%
Training: Epoch[034/182] Iteration[350/352] Loss: 0.2506 Acc:91.17%
Training Progress:  18%|▏| 33/182 [10:22<46:11, 18.60s/it, Train Acc=91.17%, ValEpoch[034/182] Train Acc: 91.17% Valid Acc:86.40% Train loss:0.2501 Valid loss:0.4265 LR:0.1
Training Progress:  19%|▏| 34/182 [10:22<45:48, 18.57s/it, Train Acc=91.17%, ValTraining: Epoch[035/182] Iteration[050/352] Loss: 0.2327 Acc:91.78%
Training: Epoch[035/182] Iteration[100/352] Loss: 0.2345 Acc:91.75%
Training: Epoch[035/182] Iteration[150/352] Loss: 0.2342 Acc:91.75%
Training: Epoch[035/182] Iteration[200/352] Loss: 0.2362 Acc:91.71%
Training: Epoch[035/182] Iteration[250/352] Loss: 0.2403 Acc:91.56%
Training: Epoch[035/182] Iteration[300/352] Loss: 0.2459 Acc:91.35%
Training: Epoch[035/182] Iteration[350/352] Loss: 0.2467 Acc:91.34%
Training Progress:  19%|▏| 34/182 [10:40<45:48, 18.57s/it, Train Acc=91.34%, ValEpoch[035/182] Train Acc: 91.34% Valid Acc:86.40% Train loss:0.2470 Valid loss:0.4539 LR:0.1
Training Progress:  19%|▏| 35/182 [10:40<45:28, 18.56s/it, Train Acc=91.34%, ValTraining: Epoch[036/182] Iteration[050/352] Loss: 0.2270 Acc:92.00%
Training: Epoch[036/182] Iteration[100/352] Loss: 0.2341 Acc:91.84%
Training: Epoch[036/182] Iteration[150/352] Loss: 0.2334 Acc:91.85%
Training: Epoch[036/182] Iteration[200/352] Loss: 0.2354 Acc:91.64%
Training: Epoch[036/182] Iteration[250/352] Loss: 0.2417 Acc:91.46%
Training: Epoch[036/182] Iteration[300/352] Loss: 0.2448 Acc:91.40%
Training: Epoch[036/182] Iteration[350/352] Loss: 0.2481 Acc:91.30%
Training Progress:  19%|▏| 35/182 [10:59<45:28, 18.56s/it, Train Acc=91.30%, ValEpoch[036/182] Train Acc: 91.30% Valid Acc:83.42% Train loss:0.2481 Valid loss:0.5601 LR:0.1
Training Progress:  20%|▏| 36/182 [10:59<45:09, 18.56s/it, Train Acc=91.30%, ValTraining: Epoch[037/182] Iteration[050/352] Loss: 0.2286 Acc:91.97%
Training: Epoch[037/182] Iteration[100/352] Loss: 0.2268 Acc:91.99%
Training: Epoch[037/182] Iteration[150/352] Loss: 0.2294 Acc:92.09%
Training: Epoch[037/182] Iteration[200/352] Loss: 0.2287 Acc:92.14%
Training: Epoch[037/182] Iteration[250/352] Loss: 0.2327 Acc:91.90%
Training: Epoch[037/182] Iteration[300/352] Loss: 0.2352 Acc:91.75%
Training: Epoch[037/182] Iteration[350/352] Loss: 0.2367 Acc:91.71%
Training Progress:  20%|▏| 36/182 [11:18<45:09, 18.56s/it, Train Acc=91.71%, ValEpoch[037/182] Train Acc: 91.71% Valid Acc:86.08% Train loss:0.2366 Valid loss:0.4722 LR:0.1
Training Progress:  20%|▏| 37/182 [11:18<44:57, 18.60s/it, Train Acc=91.71%, ValTraining: Epoch[038/182] Iteration[050/352] Loss: 0.2169 Acc:92.41%
Training: Epoch[038/182] Iteration[100/352] Loss: 0.2296 Acc:92.11%
Training: Epoch[038/182] Iteration[150/352] Loss: 0.2302 Acc:91.91%
Training: Epoch[038/182] Iteration[200/352] Loss: 0.2322 Acc:91.83%
Training: Epoch[038/182] Iteration[250/352] Loss: 0.2353 Acc:91.74%
Training: Epoch[038/182] Iteration[300/352] Loss: 0.2336 Acc:91.79%
Training: Epoch[038/182] Iteration[350/352] Loss: 0.2356 Acc:91.75%
Training Progress:  20%|▏| 37/182 [11:36<44:57, 18.60s/it, Train Acc=91.75%, ValEpoch[038/182] Train Acc: 91.75% Valid Acc:86.58% Train loss:0.2357 Valid loss:0.4281 LR:0.1
Training Progress:  21%|▏| 38/182 [11:36<44:36, 18.59s/it, Train Acc=91.75%, ValTraining: Epoch[039/182] Iteration[050/352] Loss: 0.2075 Acc:92.91%
Training: Epoch[039/182] Iteration[100/352] Loss: 0.2160 Acc:92.55%
Training: Epoch[039/182] Iteration[150/352] Loss: 0.2158 Acc:92.57%
Training: Epoch[039/182] Iteration[200/352] Loss: 0.2128 Acc:92.70%
Training: Epoch[039/182] Iteration[250/352] Loss: 0.2207 Acc:92.40%
Training: Epoch[039/182] Iteration[300/352] Loss: 0.2257 Acc:92.19%
Training: Epoch[039/182] Iteration[350/352] Loss: 0.2269 Acc:92.12%
Training Progress:  21%|▏| 38/182 [11:55<44:36, 18.59s/it, Train Acc=92.11%, ValEpoch[039/182] Train Acc: 92.11% Valid Acc:85.14% Train loss:0.2272 Valid loss:0.4897 LR:0.1
Training Progress:  21%|▏| 39/182 [11:55<44:16, 18.58s/it, Train Acc=92.11%, ValTraining: Epoch[040/182] Iteration[050/352] Loss: 0.2067 Acc:92.94%
Training: Epoch[040/182] Iteration[100/352] Loss: 0.2115 Acc:92.84%
Training: Epoch[040/182] Iteration[150/352] Loss: 0.2135 Acc:92.66%
Training: Epoch[040/182] Iteration[200/352] Loss: 0.2180 Acc:92.33%
Training: Epoch[040/182] Iteration[250/352] Loss: 0.2197 Acc:92.28%
Training: Epoch[040/182] Iteration[300/352] Loss: 0.2223 Acc:92.15%
Training: Epoch[040/182] Iteration[350/352] Loss: 0.2226 Acc:92.17%
Training Progress:  21%|▏| 39/182 [12:13<44:16, 18.58s/it, Train Acc=92.18%, ValEpoch[040/182] Train Acc: 92.18% Valid Acc:88.08% Train loss:0.2224 Valid loss:0.3801 LR:0.1
Training Progress:  22%|▏| 40/182 [12:13<43:58, 18.58s/it, Train Acc=92.18%, ValTraining: Epoch[041/182] Iteration[050/352] Loss: 0.2001 Acc:93.14%
Training: Epoch[041/182] Iteration[100/352] Loss: 0.2013 Acc:93.02%
Training: Epoch[041/182] Iteration[150/352] Loss: 0.2054 Acc:92.92%
Training: Epoch[041/182] Iteration[200/352] Loss: 0.2103 Acc:92.68%
Training: Epoch[041/182] Iteration[250/352] Loss: 0.2106 Acc:92.64%
Training: Epoch[041/182] Iteration[300/352] Loss: 0.2146 Acc:92.45%
Training: Epoch[041/182] Iteration[350/352] Loss: 0.2180 Acc:92.31%
Training Progress:  22%|▏| 40/182 [12:32<43:58, 18.58s/it, Train Acc=92.31%, ValEpoch[041/182] Train Acc: 92.31% Valid Acc:87.52% Train loss:0.2182 Valid loss:0.4032 LR:0.1
Training Progress:  23%|▏| 41/182 [12:32<43:58, 18.71s/it, Train Acc=92.31%, ValTraining: Epoch[042/182] Iteration[050/352] Loss: 0.2196 Acc:92.20%
Training: Epoch[042/182] Iteration[100/352] Loss: 0.2167 Acc:92.38%
Training: Epoch[042/182] Iteration[150/352] Loss: 0.2133 Acc:92.45%
Training: Epoch[042/182] Iteration[200/352] Loss: 0.2156 Acc:92.43%
Training: Epoch[042/182] Iteration[250/352] Loss: 0.2196 Acc:92.29%
Training: Epoch[042/182] Iteration[300/352] Loss: 0.2214 Acc:92.28%
Training: Epoch[042/182] Iteration[350/352] Loss: 0.2245 Acc:92.15%
Training Progress:  23%|▏| 41/182 [12:51<43:58, 18.71s/it, Train Acc=92.15%, ValEpoch[042/182] Train Acc: 92.15% Valid Acc:86.34% Train loss:0.2243 Valid loss:0.4562 LR:0.1
Training Progress:  23%|▏| 42/182 [12:51<43:45, 18.76s/it, Train Acc=92.15%, ValTraining: Epoch[043/182] Iteration[050/352] Loss: 0.2151 Acc:92.80%
Training: Epoch[043/182] Iteration[100/352] Loss: 0.2092 Acc:92.89%
Training: Epoch[043/182] Iteration[150/352] Loss: 0.2142 Acc:92.67%
Training: Epoch[043/182] Iteration[200/352] Loss: 0.2182 Acc:92.48%
Training: Epoch[043/182] Iteration[250/352] Loss: 0.2226 Acc:92.25%
Training: Epoch[043/182] Iteration[300/352] Loss: 0.2249 Acc:92.15%
Training: Epoch[043/182] Iteration[350/352] Loss: 0.2222 Acc:92.24%
Training Progress:  23%|▏| 42/182 [13:10<43:45, 18.76s/it, Train Acc=92.23%, ValEpoch[043/182] Train Acc: 92.23% Valid Acc:88.24% Train loss:0.2225 Valid loss:0.3744 LR:0.1
Training Progress:  24%|▏| 43/182 [13:10<43:20, 18.71s/it, Train Acc=92.23%, ValTraining: Epoch[044/182] Iteration[050/352] Loss: 0.2071 Acc:92.83%
Training: Epoch[044/182] Iteration[100/352] Loss: 0.2125 Acc:92.60%
Training: Epoch[044/182] Iteration[150/352] Loss: 0.2096 Acc:92.76%
Training: Epoch[044/182] Iteration[200/352] Loss: 0.2117 Acc:92.76%
Training: Epoch[044/182] Iteration[250/352] Loss: 0.2177 Acc:92.59%
Training: Epoch[044/182] Iteration[300/352] Loss: 0.2182 Acc:92.58%
Training: Epoch[044/182] Iteration[350/352] Loss: 0.2195 Acc:92.49%
Training Progress:  24%|▏| 43/182 [13:28<43:20, 18.71s/it, Train Acc=92.47%, ValEpoch[044/182] Train Acc: 92.47% Valid Acc:85.38% Train loss:0.2197 Valid loss:0.4941 LR:0.1
Training Progress:  24%|▏| 44/182 [13:28<42:59, 18.69s/it, Train Acc=92.47%, ValTraining: Epoch[045/182] Iteration[050/352] Loss: 0.2100 Acc:92.66%
Training: Epoch[045/182] Iteration[100/352] Loss: 0.2049 Acc:92.93%
Training: Epoch[045/182] Iteration[150/352] Loss: 0.2069 Acc:92.90%
Training: Epoch[045/182] Iteration[200/352] Loss: 0.2067 Acc:92.84%
Training: Epoch[045/182] Iteration[250/352] Loss: 0.2112 Acc:92.60%
Training: Epoch[045/182] Iteration[300/352] Loss: 0.2140 Acc:92.57%
Training: Epoch[045/182] Iteration[350/352] Loss: 0.2133 Acc:92.58%
Training Progress:  24%|▏| 44/182 [13:47<42:59, 18.69s/it, Train Acc=92.58%, ValEpoch[045/182] Train Acc: 92.58% Valid Acc:88.52% Train loss:0.2131 Valid loss:0.3963 LR:0.1
Training Progress:  25%|▏| 45/182 [13:47<42:51, 18.77s/it, Train Acc=92.58%, ValTraining: Epoch[046/182] Iteration[050/352] Loss: 0.1981 Acc:93.14%
Training: Epoch[046/182] Iteration[100/352] Loss: 0.2030 Acc:92.81%
Training: Epoch[046/182] Iteration[150/352] Loss: 0.2006 Acc:92.91%
Training: Epoch[046/182] Iteration[200/352] Loss: 0.2029 Acc:92.91%
Training: Epoch[046/182] Iteration[250/352] Loss: 0.2083 Acc:92.70%
Training: Epoch[046/182] Iteration[300/352] Loss: 0.2111 Acc:92.58%
Training: Epoch[046/182] Iteration[350/352] Loss: 0.2150 Acc:92.46%
Training Progress:  25%|▏| 45/182 [14:06<42:51, 18.77s/it, Train Acc=92.46%, ValEpoch[046/182] Train Acc: 92.46% Valid Acc:87.62% Train loss:0.2149 Valid loss:0.4024 LR:0.1
Training Progress:  25%|▎| 46/182 [14:06<42:27, 18.73s/it, Train Acc=92.46%, ValTraining: Epoch[047/182] Iteration[050/352] Loss: 0.2066 Acc:93.00%
Training: Epoch[047/182] Iteration[100/352] Loss: 0.1991 Acc:93.23%
Training: Epoch[047/182] Iteration[150/352] Loss: 0.1988 Acc:93.20%
Training: Epoch[047/182] Iteration[200/352] Loss: 0.2035 Acc:92.94%
Training: Epoch[047/182] Iteration[250/352] Loss: 0.2089 Acc:92.71%
Training: Epoch[047/182] Iteration[300/352] Loss: 0.2087 Acc:92.74%
Training: Epoch[047/182] Iteration[350/352] Loss: 0.2092 Acc:92.72%
Training Progress:  25%|▎| 46/182 [14:25<42:27, 18.73s/it, Train Acc=92.70%, ValEpoch[047/182] Train Acc: 92.70% Valid Acc:86.60% Train loss:0.2097 Valid loss:0.4676 LR:0.1
Training Progress:  26%|▎| 47/182 [14:25<42:02, 18.68s/it, Train Acc=92.70%, ValTraining: Epoch[048/182] Iteration[050/352] Loss: 0.2010 Acc:92.89%
Training: Epoch[048/182] Iteration[100/352] Loss: 0.1917 Acc:93.23%
Training: Epoch[048/182] Iteration[150/352] Loss: 0.2025 Acc:92.85%
Training: Epoch[048/182] Iteration[200/352] Loss: 0.2068 Acc:92.78%
Training: Epoch[048/182] Iteration[250/352] Loss: 0.2130 Acc:92.56%
Training: Epoch[048/182] Iteration[300/352] Loss: 0.2118 Acc:92.54%
Training: Epoch[048/182] Iteration[350/352] Loss: 0.2140 Acc:92.47%
Training Progress:  26%|▎| 47/182 [14:43<42:02, 18.68s/it, Train Acc=92.47%, ValEpoch[048/182] Train Acc: 92.47% Valid Acc:86.68% Train loss:0.2141 Valid loss:0.4346 LR:0.1
Training Progress:  26%|▎| 48/182 [14:43<41:39, 18.65s/it, Train Acc=92.47%, ValTraining: Epoch[049/182] Iteration[050/352] Loss: 0.1969 Acc:93.08%
Training: Epoch[049/182] Iteration[100/352] Loss: 0.1968 Acc:93.02%
Training: Epoch[049/182] Iteration[150/352] Loss: 0.1950 Acc:93.14%
Training: Epoch[049/182] Iteration[200/352] Loss: 0.1974 Acc:93.02%
Training: Epoch[049/182] Iteration[250/352] Loss: 0.2005 Acc:92.93%
Training: Epoch[049/182] Iteration[300/352] Loss: 0.2046 Acc:92.83%
Training: Epoch[049/182] Iteration[350/352] Loss: 0.2065 Acc:92.75%
Training Progress:  26%|▎| 48/182 [15:02<41:39, 18.65s/it, Train Acc=92.75%, ValEpoch[049/182] Train Acc: 92.75% Valid Acc:88.32% Train loss:0.2062 Valid loss:0.3805 LR:0.1
Training Progress:  27%|▎| 49/182 [15:02<41:20, 18.65s/it, Train Acc=92.75%, ValTraining: Epoch[050/182] Iteration[050/352] Loss: 0.1989 Acc:92.97%
Training: Epoch[050/182] Iteration[100/352] Loss: 0.1951 Acc:93.16%
Training: Epoch[050/182] Iteration[150/352] Loss: 0.1952 Acc:93.25%
Training: Epoch[050/182] Iteration[200/352] Loss: 0.1954 Acc:93.18%
Training: Epoch[050/182] Iteration[250/352] Loss: 0.1982 Acc:93.11%
Training: Epoch[050/182] Iteration[300/352] Loss: 0.2013 Acc:92.92%
Training: Epoch[050/182] Iteration[350/352] Loss: 0.2050 Acc:92.77%
Training Progress:  27%|▎| 49/182 [15:20<41:20, 18.65s/it, Train Acc=92.76%, ValEpoch[050/182] Train Acc: 92.76% Valid Acc:84.96% Train loss:0.2053 Valid loss:0.4971 LR:0.1
Training Progress:  27%|▎| 50/182 [15:20<40:58, 18.63s/it, Train Acc=92.76%, ValTraining: Epoch[051/182] Iteration[050/352] Loss: 0.1885 Acc:93.34%
Training: Epoch[051/182] Iteration[100/352] Loss: 0.1899 Acc:93.40%
Training: Epoch[051/182] Iteration[150/352] Loss: 0.1937 Acc:93.26%
Training: Epoch[051/182] Iteration[200/352] Loss: 0.1955 Acc:93.17%
Training: Epoch[051/182] Iteration[250/352] Loss: 0.1984 Acc:93.06%
Training: Epoch[051/182] Iteration[300/352] Loss: 0.1980 Acc:93.04%
Training: Epoch[051/182] Iteration[350/352] Loss: 0.2003 Acc:92.97%
Training Progress:  27%|▎| 50/182 [15:39<40:58, 18.63s/it, Train Acc=92.97%, ValEpoch[051/182] Train Acc: 92.97% Valid Acc:87.66% Train loss:0.2002 Valid loss:0.4212 LR:0.1
Training Progress:  28%|▎| 51/182 [15:39<40:40, 18.63s/it, Train Acc=92.97%, ValTraining: Epoch[052/182] Iteration[050/352] Loss: 0.1967 Acc:92.92%
Training: Epoch[052/182] Iteration[100/352] Loss: 0.1958 Acc:93.06%
Training: Epoch[052/182] Iteration[150/352] Loss: 0.1969 Acc:93.08%
Training: Epoch[052/182] Iteration[200/352] Loss: 0.1915 Acc:93.27%
Training: Epoch[052/182] Iteration[250/352] Loss: 0.1918 Acc:93.27%
Training: Epoch[052/182] Iteration[300/352] Loss: 0.1952 Acc:93.17%
Training: Epoch[052/182] Iteration[350/352] Loss: 0.1988 Acc:93.06%
Training Progress:  28%|▎| 51/182 [15:58<40:40, 18.63s/it, Train Acc=93.06%, ValEpoch[052/182] Train Acc: 93.06% Valid Acc:87.62% Train loss:0.1989 Valid loss:0.3879 LR:0.1
Training Progress:  29%|▎| 52/182 [15:58<40:22, 18.64s/it, Train Acc=93.06%, ValTraining: Epoch[053/182] Iteration[050/352] Loss: 0.1812 Acc:93.66%
Training: Epoch[053/182] Iteration[100/352] Loss: 0.1851 Acc:93.55%
Training: Epoch[053/182] Iteration[150/352] Loss: 0.1866 Acc:93.46%
Training: Epoch[053/182] Iteration[200/352] Loss: 0.1897 Acc:93.24%
Training: Epoch[053/182] Iteration[250/352] Loss: 0.1894 Acc:93.24%
Training: Epoch[053/182] Iteration[300/352] Loss: 0.1936 Acc:93.11%
Training: Epoch[053/182] Iteration[350/352] Loss: 0.1973 Acc:93.01%
Training Progress:  29%|▎| 52/182 [16:16<40:22, 18.64s/it, Train Acc=93.00%, ValEpoch[053/182] Train Acc: 93.00% Valid Acc:87.38% Train loss:0.1976 Valid loss:0.4238 LR:0.1
Training Progress:  29%|▎| 53/182 [16:16<40:08, 18.67s/it, Train Acc=93.00%, ValTraining: Epoch[054/182] Iteration[050/352] Loss: 0.1912 Acc:93.36%
Training: Epoch[054/182] Iteration[100/352] Loss: 0.1914 Acc:93.32%
Training: Epoch[054/182] Iteration[150/352] Loss: 0.1921 Acc:93.21%
Training: Epoch[054/182] Iteration[200/352] Loss: 0.1946 Acc:93.11%
Training: Epoch[054/182] Iteration[250/352] Loss: 0.1974 Acc:92.95%
Training: Epoch[054/182] Iteration[300/352] Loss: 0.1974 Acc:92.95%
Training: Epoch[054/182] Iteration[350/352] Loss: 0.1978 Acc:92.95%
Training Progress:  29%|▎| 53/182 [16:35<40:08, 18.67s/it, Train Acc=92.96%, ValEpoch[054/182] Train Acc: 92.96% Valid Acc:86.92% Train loss:0.1976 Valid loss:0.4452 LR:0.1
Training Progress:  30%|▎| 54/182 [16:35<39:47, 18.66s/it, Train Acc=92.96%, ValTraining: Epoch[055/182] Iteration[050/352] Loss: 0.1792 Acc:93.69%
Training: Epoch[055/182] Iteration[100/352] Loss: 0.1773 Acc:93.69%
Training: Epoch[055/182] Iteration[150/352] Loss: 0.1872 Acc:93.30%
Training: Epoch[055/182] Iteration[200/352] Loss: 0.1886 Acc:93.29%
Training: Epoch[055/182] Iteration[250/352] Loss: 0.1923 Acc:93.18%
Training: Epoch[055/182] Iteration[300/352] Loss: 0.1926 Acc:93.19%
Training: Epoch[055/182] Iteration[350/352] Loss: 0.1937 Acc:93.15%
Training Progress:  30%|▎| 54/182 [16:54<39:47, 18.66s/it, Train Acc=93.15%, ValEpoch[055/182] Train Acc: 93.15% Valid Acc:87.58% Train loss:0.1938 Valid loss:0.4050 LR:0.1
Training Progress:  30%|▎| 55/182 [16:54<39:24, 18.62s/it, Train Acc=93.15%, ValTraining: Epoch[056/182] Iteration[050/352] Loss: 0.1807 Acc:93.56%
Training: Epoch[056/182] Iteration[100/352] Loss: 0.1856 Acc:93.44%
Training: Epoch[056/182] Iteration[150/352] Loss: 0.1848 Acc:93.56%
Training: Epoch[056/182] Iteration[200/352] Loss: 0.1850 Acc:93.52%
Training: Epoch[056/182] Iteration[250/352] Loss: 0.1886 Acc:93.37%
Training: Epoch[056/182] Iteration[300/352] Loss: 0.1900 Acc:93.29%
Training: Epoch[056/182] Iteration[350/352] Loss: 0.1912 Acc:93.25%
Training Progress:  30%|▎| 55/182 [17:12<39:24, 18.62s/it, Train Acc=93.25%, ValEpoch[056/182] Train Acc: 93.25% Valid Acc:87.74% Train loss:0.1910 Valid loss:0.4147 LR:0.1
Training Progress:  31%|▎| 56/182 [17:12<39:12, 18.67s/it, Train Acc=93.25%, ValTraining: Epoch[057/182] Iteration[050/352] Loss: 0.1781 Acc:93.84%
Training: Epoch[057/182] Iteration[100/352] Loss: 0.1743 Acc:93.92%
Training: Epoch[057/182] Iteration[150/352] Loss: 0.1709 Acc:94.06%
Training: Epoch[057/182] Iteration[200/352] Loss: 0.1778 Acc:93.76%
Training: Epoch[057/182] Iteration[250/352] Loss: 0.1841 Acc:93.56%
Training: Epoch[057/182] Iteration[300/352] Loss: 0.1900 Acc:93.36%
Training: Epoch[057/182] Iteration[350/352] Loss: 0.1910 Acc:93.30%
Training Progress:  31%|▎| 56/182 [17:31<39:12, 18.67s/it, Train Acc=93.32%, ValEpoch[057/182] Train Acc: 93.32% Valid Acc:85.94% Train loss:0.1906 Valid loss:0.4707 LR:0.1
Training Progress:  31%|▎| 57/182 [17:31<38:53, 18.67s/it, Train Acc=93.32%, ValTraining: Epoch[058/182] Iteration[050/352] Loss: 0.1759 Acc:93.92%
Training: Epoch[058/182] Iteration[100/352] Loss: 0.1919 Acc:93.30%
Training: Epoch[058/182] Iteration[150/352] Loss: 0.1886 Acc:93.26%
Training: Epoch[058/182] Iteration[200/352] Loss: 0.1923 Acc:93.15%
Training: Epoch[058/182] Iteration[250/352] Loss: 0.1930 Acc:93.14%
Training: Epoch[058/182] Iteration[300/352] Loss: 0.1927 Acc:93.18%
Training: Epoch[058/182] Iteration[350/352] Loss: 0.1937 Acc:93.16%
Training Progress:  31%|▎| 57/182 [17:50<38:53, 18.67s/it, Train Acc=93.16%, ValEpoch[058/182] Train Acc: 93.16% Valid Acc:87.56% Train loss:0.1938 Valid loss:0.4143 LR:0.1
Training Progress:  32%|▎| 58/182 [17:50<38:35, 18.67s/it, Train Acc=93.16%, ValTraining: Epoch[059/182] Iteration[050/352] Loss: 0.1863 Acc:93.25%
Training: Epoch[059/182] Iteration[100/352] Loss: 0.1763 Acc:93.87%
Training: Epoch[059/182] Iteration[150/352] Loss: 0.1786 Acc:93.76%
Training: Epoch[059/182] Iteration[200/352] Loss: 0.1813 Acc:93.70%
Training: Epoch[059/182] Iteration[250/352] Loss: 0.1851 Acc:93.54%
Training: Epoch[059/182] Iteration[300/352] Loss: 0.1836 Acc:93.59%
Training: Epoch[059/182] Iteration[350/352] Loss: 0.1847 Acc:93.55%
Training Progress:  32%|▎| 58/182 [18:08<38:35, 18.67s/it, Train Acc=93.54%, ValEpoch[059/182] Train Acc: 93.54% Valid Acc:87.02% Train loss:0.1854 Valid loss:0.4507 LR:0.1
Training Progress:  32%|▎| 59/182 [18:08<38:16, 18.67s/it, Train Acc=93.54%, ValTraining: Epoch[060/182] Iteration[050/352] Loss: 0.1827 Acc:93.73%
Training: Epoch[060/182] Iteration[100/352] Loss: 0.1834 Acc:93.50%
Training: Epoch[060/182] Iteration[150/352] Loss: 0.1845 Acc:93.45%
Training: Epoch[060/182] Iteration[200/352] Loss: 0.1854 Acc:93.40%
Training: Epoch[060/182] Iteration[250/352] Loss: 0.1872 Acc:93.30%
Training: Epoch[060/182] Iteration[300/352] Loss: 0.1875 Acc:93.32%
Training: Epoch[060/182] Iteration[350/352] Loss: 0.1899 Acc:93.21%
Training Progress:  32%|▎| 59/182 [18:27<38:16, 18.67s/it, Train Acc=93.21%, ValEpoch[060/182] Train Acc: 93.21% Valid Acc:88.00% Train loss:0.1900 Valid loss:0.4055 LR:0.1
Training Progress:  33%|▎| 60/182 [18:27<37:57, 18.67s/it, Train Acc=93.21%, ValTraining: Epoch[061/182] Iteration[050/352] Loss: 0.1748 Acc:93.77%
Training: Epoch[061/182] Iteration[100/352] Loss: 0.1692 Acc:94.09%
Training: Epoch[061/182] Iteration[150/352] Loss: 0.1650 Acc:94.22%
Training: Epoch[061/182] Iteration[200/352] Loss: 0.1701 Acc:93.95%
Training: Epoch[061/182] Iteration[250/352] Loss: 0.1765 Acc:93.75%
Training: Epoch[061/182] Iteration[300/352] Loss: 0.1791 Acc:93.67%
Training: Epoch[061/182] Iteration[350/352] Loss: 0.1831 Acc:93.58%
Training Progress:  33%|▎| 60/182 [18:46<37:57, 18.67s/it, Train Acc=93.58%, ValEpoch[061/182] Train Acc: 93.58% Valid Acc:87.46% Train loss:0.1830 Valid loss:0.3951 LR:0.1
Training Progress:  34%|▎| 61/182 [18:46<37:48, 18.75s/it, Train Acc=93.58%, ValTraining: Epoch[062/182] Iteration[050/352] Loss: 0.1843 Acc:93.52%
Training: Epoch[062/182] Iteration[100/352] Loss: 0.1804 Acc:93.52%
Training: Epoch[062/182] Iteration[150/352] Loss: 0.1831 Acc:93.51%
Training: Epoch[062/182] Iteration[200/352] Loss: 0.1846 Acc:93.47%
Training: Epoch[062/182] Iteration[250/352] Loss: 0.1842 Acc:93.48%
Training: Epoch[062/182] Iteration[300/352] Loss: 0.1837 Acc:93.51%
Training: Epoch[062/182] Iteration[350/352] Loss: 0.1855 Acc:93.43%
Training Progress:  34%|▎| 61/182 [19:05<37:48, 18.75s/it, Train Acc=93.42%, ValEpoch[062/182] Train Acc: 93.42% Valid Acc:88.28% Train loss:0.1860 Valid loss:0.3719 LR:0.1
Training Progress:  34%|▎| 62/182 [19:05<37:28, 18.73s/it, Train Acc=93.42%, ValTraining: Epoch[063/182] Iteration[050/352] Loss: 0.1584 Acc:94.56%
Training: Epoch[063/182] Iteration[100/352] Loss: 0.1623 Acc:94.43%
Training: Epoch[063/182] Iteration[150/352] Loss: 0.1675 Acc:94.22%
Training: Epoch[063/182] Iteration[200/352] Loss: 0.1713 Acc:94.04%
Training: Epoch[063/182] Iteration[250/352] Loss: 0.1736 Acc:93.94%
Training: Epoch[063/182] Iteration[300/352] Loss: 0.1760 Acc:93.89%
Training: Epoch[063/182] Iteration[350/352] Loss: 0.1758 Acc:93.86%
Training Progress:  34%|▎| 62/182 [19:24<37:28, 18.73s/it, Train Acc=93.85%, ValEpoch[063/182] Train Acc: 93.85% Valid Acc:88.94% Train loss:0.1759 Valid loss:0.3729 LR:0.1
Training Progress:  35%|▎| 63/182 [19:24<37:17, 18.80s/it, Train Acc=93.85%, ValTraining: Epoch[064/182] Iteration[050/352] Loss: 0.1586 Acc:94.39%
Training: Epoch[064/182] Iteration[100/352] Loss: 0.1672 Acc:94.17%
Training: Epoch[064/182] Iteration[150/352] Loss: 0.1745 Acc:93.82%
Training: Epoch[064/182] Iteration[200/352] Loss: 0.1763 Acc:93.76%
Training: Epoch[064/182] Iteration[250/352] Loss: 0.1775 Acc:93.74%
Training: Epoch[064/182] Iteration[300/352] Loss: 0.1788 Acc:93.69%
Training: Epoch[064/182] Iteration[350/352] Loss: 0.1811 Acc:93.62%
Training Progress:  35%|▎| 63/182 [19:42<37:17, 18.80s/it, Train Acc=93.62%, ValEpoch[064/182] Train Acc: 93.62% Valid Acc:89.28% Train loss:0.1810 Valid loss:0.3489 LR:0.1
Training Progress:  35%|▎| 64/182 [19:42<36:49, 18.72s/it, Train Acc=93.62%, ValTraining: Epoch[065/182] Iteration[050/352] Loss: 0.1542 Acc:94.59%
Training: Epoch[065/182] Iteration[100/352] Loss: 0.1576 Acc:94.50%
Training: Epoch[065/182] Iteration[150/352] Loss: 0.1598 Acc:94.34%
Training: Epoch[065/182] Iteration[200/352] Loss: 0.1653 Acc:94.14%
Training: Epoch[065/182] Iteration[250/352] Loss: 0.1701 Acc:93.96%
Training: Epoch[065/182] Iteration[300/352] Loss: 0.1744 Acc:93.83%
Training: Epoch[065/182] Iteration[350/352] Loss: 0.1776 Acc:93.77%
Training Progress:  35%|▎| 64/182 [20:01<36:49, 18.72s/it, Train Acc=93.77%, ValEpoch[065/182] Train Acc: 93.77% Valid Acc:88.64% Train loss:0.1779 Valid loss:0.3663 LR:0.1
Training Progress:  36%|▎| 65/182 [20:01<36:33, 18.75s/it, Train Acc=93.77%, ValTraining: Epoch[066/182] Iteration[050/352] Loss: 0.1611 Acc:94.31%
Training: Epoch[066/182] Iteration[100/352] Loss: 0.1651 Acc:94.14%
Training: Epoch[066/182] Iteration[150/352] Loss: 0.1648 Acc:94.04%
Training: Epoch[066/182] Iteration[200/352] Loss: 0.1695 Acc:93.94%
Training: Epoch[066/182] Iteration[250/352] Loss: 0.1740 Acc:93.71%
Training: Epoch[066/182] Iteration[300/352] Loss: 0.1753 Acc:93.66%
Training: Epoch[066/182] Iteration[350/352] Loss: 0.1777 Acc:93.54%
Training Progress:  36%|▎| 65/182 [20:20<36:33, 18.75s/it, Train Acc=93.54%, ValEpoch[066/182] Train Acc: 93.54% Valid Acc:88.04% Train loss:0.1775 Valid loss:0.4046 LR:0.1
Training Progress:  36%|▎| 66/182 [20:20<36:12, 18.73s/it, Train Acc=93.54%, ValTraining: Epoch[067/182] Iteration[050/352] Loss: 0.1810 Acc:93.72%
Training: Epoch[067/182] Iteration[100/352] Loss: 0.1772 Acc:93.87%
Training: Epoch[067/182] Iteration[150/352] Loss: 0.1779 Acc:93.76%
Training: Epoch[067/182] Iteration[200/352] Loss: 0.1766 Acc:93.75%
Training: Epoch[067/182] Iteration[250/352] Loss: 0.1775 Acc:93.75%
Training: Epoch[067/182] Iteration[300/352] Loss: 0.1776 Acc:93.71%
Training: Epoch[067/182] Iteration[350/352] Loss: 0.1793 Acc:93.62%
Training Progress:  36%|▎| 66/182 [20:38<36:12, 18.73s/it, Train Acc=93.62%, ValEpoch[067/182] Train Acc: 93.62% Valid Acc:89.06% Train loss:0.1793 Valid loss:0.3719 LR:0.1
Training Progress:  37%|▎| 67/182 [20:38<35:59, 18.78s/it, Train Acc=93.62%, ValTraining: Epoch[068/182] Iteration[050/352] Loss: 0.1517 Acc:94.62%
Training: Epoch[068/182] Iteration[100/352] Loss: 0.1547 Acc:94.56%
Training: Epoch[068/182] Iteration[150/352] Loss: 0.1575 Acc:94.40%
Training: Epoch[068/182] Iteration[200/352] Loss: 0.1662 Acc:94.11%
Training: Epoch[068/182] Iteration[250/352] Loss: 0.1689 Acc:94.12%
Training: Epoch[068/182] Iteration[300/352] Loss: 0.1705 Acc:94.14%
Training: Epoch[068/182] Iteration[350/352] Loss: 0.1740 Acc:93.97%
Training Progress:  37%|▎| 67/182 [20:57<35:59, 18.78s/it, Train Acc=93.96%, ValEpoch[068/182] Train Acc: 93.96% Valid Acc:85.72% Train loss:0.1738 Valid loss:0.4857 LR:0.1
Training Progress:  37%|▎| 68/182 [20:57<35:37, 18.75s/it, Train Acc=93.96%, ValTraining: Epoch[069/182] Iteration[050/352] Loss: 0.1715 Acc:94.33%
Training: Epoch[069/182] Iteration[100/352] Loss: 0.1770 Acc:94.02%
Training: Epoch[069/182] Iteration[150/352] Loss: 0.1831 Acc:93.64%
Training: Epoch[069/182] Iteration[200/352] Loss: 0.1847 Acc:93.53%
Training: Epoch[069/182] Iteration[250/352] Loss: 0.1845 Acc:93.55%
Training: Epoch[069/182] Iteration[300/352] Loss: 0.1833 Acc:93.59%
Training: Epoch[069/182] Iteration[350/352] Loss: 0.1827 Acc:93.54%
Training Progress:  37%|▎| 68/182 [21:16<35:37, 18.75s/it, Train Acc=93.54%, ValEpoch[069/182] Train Acc: 93.54% Valid Acc:84.70% Train loss:0.1827 Valid loss:0.5563 LR:0.1
Training Progress:  38%|▍| 69/182 [21:16<35:13, 18.70s/it, Train Acc=93.54%, ValTraining: Epoch[070/182] Iteration[050/352] Loss: 0.1519 Acc:94.78%
Training: Epoch[070/182] Iteration[100/352] Loss: 0.1512 Acc:94.75%
Training: Epoch[070/182] Iteration[150/352] Loss: 0.1572 Acc:94.43%
Training: Epoch[070/182] Iteration[200/352] Loss: 0.1606 Acc:94.34%
Training: Epoch[070/182] Iteration[250/352] Loss: 0.1677 Acc:94.11%
Training: Epoch[070/182] Iteration[300/352] Loss: 0.1704 Acc:94.02%
Training: Epoch[070/182] Iteration[350/352] Loss: 0.1737 Acc:93.88%
Training Progress:  38%|▍| 69/182 [21:34<35:13, 18.70s/it, Train Acc=93.88%, ValEpoch[070/182] Train Acc: 93.88% Valid Acc:87.60% Train loss:0.1737 Valid loss:0.4230 LR:0.1
Training Progress:  38%|▍| 70/182 [21:34<34:53, 18.69s/it, Train Acc=93.88%, ValTraining: Epoch[071/182] Iteration[050/352] Loss: 0.1708 Acc:94.11%
Training: Epoch[071/182] Iteration[100/352] Loss: 0.1634 Acc:94.42%
Training: Epoch[071/182] Iteration[150/352] Loss: 0.1626 Acc:94.46%
Training: Epoch[071/182] Iteration[200/352] Loss: 0.1633 Acc:94.45%
Training: Epoch[071/182] Iteration[250/352] Loss: 0.1646 Acc:94.38%
Training: Epoch[071/182] Iteration[300/352] Loss: 0.1676 Acc:94.25%
Training: Epoch[071/182] Iteration[350/352] Loss: 0.1707 Acc:94.15%
Training Progress:  38%|▍| 70/182 [21:53<34:53, 18.69s/it, Train Acc=94.14%, ValEpoch[071/182] Train Acc: 94.14% Valid Acc:87.28% Train loss:0.1706 Valid loss:0.4235 LR:0.1
Training Progress:  39%|▍| 71/182 [21:53<34:31, 18.67s/it, Train Acc=94.14%, ValTraining: Epoch[072/182] Iteration[050/352] Loss: 0.1632 Acc:94.48%
Training: Epoch[072/182] Iteration[100/352] Loss: 0.1594 Acc:94.49%
Training: Epoch[072/182] Iteration[150/352] Loss: 0.1660 Acc:94.26%
Training: Epoch[072/182] Iteration[200/352] Loss: 0.1725 Acc:93.98%
Training: Epoch[072/182] Iteration[250/352] Loss: 0.1682 Acc:94.15%
Training: Epoch[072/182] Iteration[300/352] Loss: 0.1695 Acc:94.07%
Training: Epoch[072/182] Iteration[350/352] Loss: 0.1709 Acc:93.99%
Training Progress:  39%|▍| 71/182 [22:12<34:31, 18.67s/it, Train Acc=93.98%, ValEpoch[072/182] Train Acc: 93.98% Valid Acc:85.94% Train loss:0.1714 Valid loss:0.4803 LR:0.1
Training Progress:  40%|▍| 72/182 [22:12<34:12, 18.66s/it, Train Acc=93.98%, ValTraining: Epoch[073/182] Iteration[050/352] Loss: 0.1718 Acc:94.31%
Training: Epoch[073/182] Iteration[100/352] Loss: 0.1690 Acc:94.20%
Training: Epoch[073/182] Iteration[150/352] Loss: 0.1682 Acc:94.25%
Training: Epoch[073/182] Iteration[200/352] Loss: 0.1703 Acc:94.11%
Training: Epoch[073/182] Iteration[250/352] Loss: 0.1767 Acc:93.85%
Training: Epoch[073/182] Iteration[300/352] Loss: 0.1748 Acc:93.96%
Training: Epoch[073/182] Iteration[350/352] Loss: 0.1758 Acc:93.90%
Training Progress:  40%|▍| 72/182 [22:31<34:12, 18.66s/it, Train Acc=93.90%, ValEpoch[073/182] Train Acc: 93.90% Valid Acc:86.74% Train loss:0.1759 Valid loss:0.4578 LR:0.1
Training Progress:  40%|▍| 73/182 [22:31<34:03, 18.74s/it, Train Acc=93.90%, ValTraining: Epoch[074/182] Iteration[050/352] Loss: 0.1615 Acc:94.17%
Training: Epoch[074/182] Iteration[100/352] Loss: 0.1619 Acc:94.35%
Training: Epoch[074/182] Iteration[150/352] Loss: 0.1625 Acc:94.34%
Training: Epoch[074/182] Iteration[200/352] Loss: 0.1633 Acc:94.33%
Training: Epoch[074/182] Iteration[250/352] Loss: 0.1643 Acc:94.34%
Training: Epoch[074/182] Iteration[300/352] Loss: 0.1669 Acc:94.25%
Training: Epoch[074/182] Iteration[350/352] Loss: 0.1668 Acc:94.23%
Training Progress:  40%|▍| 73/182 [22:49<34:03, 18.74s/it, Train Acc=94.23%, ValEpoch[074/182] Train Acc: 94.23% Valid Acc:86.90% Train loss:0.1668 Valid loss:0.4552 LR:0.1
Training Progress:  41%|▍| 74/182 [22:49<33:46, 18.77s/it, Train Acc=94.23%, ValTraining: Epoch[075/182] Iteration[050/352] Loss: 0.1430 Acc:95.11%
Training: Epoch[075/182] Iteration[100/352] Loss: 0.1522 Acc:94.55%
Training: Epoch[075/182] Iteration[150/352] Loss: 0.1643 Acc:94.22%
Training: Epoch[075/182] Iteration[200/352] Loss: 0.1651 Acc:94.23%
Training: Epoch[075/182] Iteration[250/352] Loss: 0.1633 Acc:94.27%
Training: Epoch[075/182] Iteration[300/352] Loss: 0.1644 Acc:94.22%
Training: Epoch[075/182] Iteration[350/352] Loss: 0.1661 Acc:94.18%
Training Progress:  41%|▍| 74/182 [23:08<33:46, 18.77s/it, Train Acc=94.18%, ValEpoch[075/182] Train Acc: 94.18% Valid Acc:87.96% Train loss:0.1658 Valid loss:0.4047 LR:0.1
Training Progress:  41%|▍| 75/182 [23:08<33:23, 18.73s/it, Train Acc=94.18%, ValTraining: Epoch[076/182] Iteration[050/352] Loss: 0.1609 Acc:94.50%
Training: Epoch[076/182] Iteration[100/352] Loss: 0.1599 Acc:94.54%
Training: Epoch[076/182] Iteration[150/352] Loss: 0.1618 Acc:94.53%
Training: Epoch[076/182] Iteration[200/352] Loss: 0.1658 Acc:94.30%
Training: Epoch[076/182] Iteration[250/352] Loss: 0.1656 Acc:94.34%
Training: Epoch[076/182] Iteration[300/352] Loss: 0.1668 Acc:94.29%
Training: Epoch[076/182] Iteration[350/352] Loss: 0.1695 Acc:94.16%
Training Progress:  41%|▍| 75/182 [23:27<33:23, 18.73s/it, Train Acc=94.15%, ValEpoch[076/182] Train Acc: 94.15% Valid Acc:81.78% Train loss:0.1695 Valid loss:0.6869 LR:0.1
Training Progress:  42%|▍| 76/182 [23:27<33:06, 18.74s/it, Train Acc=94.15%, ValTraining: Epoch[077/182] Iteration[050/352] Loss: 0.1646 Acc:94.33%
Training: Epoch[077/182] Iteration[100/352] Loss: 0.1540 Acc:94.59%
Training: Epoch[077/182] Iteration[150/352] Loss: 0.1540 Acc:94.62%
Training: Epoch[077/182] Iteration[200/352] Loss: 0.1591 Acc:94.49%
Training: Epoch[077/182] Iteration[250/352] Loss: 0.1613 Acc:94.40%
Training: Epoch[077/182] Iteration[300/352] Loss: 0.1661 Acc:94.18%
Training: Epoch[077/182] Iteration[350/352] Loss: 0.1698 Acc:94.03%
Training Progress:  42%|▍| 76/182 [23:47<33:06, 18.74s/it, Train Acc=94.02%, ValEpoch[077/182] Train Acc: 94.02% Valid Acc:87.80% Train loss:0.1701 Valid loss:0.3958 LR:0.1
Training Progress:  42%|▍| 77/182 [23:47<33:28, 19.13s/it, Train Acc=94.02%, ValTraining: Epoch[078/182] Iteration[050/352] Loss: 0.1834 Acc:93.67%
Training: Epoch[078/182] Iteration[100/352] Loss: 0.1667 Acc:94.22%
Training: Epoch[078/182] Iteration[150/352] Loss: 0.1662 Acc:94.16%
Training: Epoch[078/182] Iteration[200/352] Loss: 0.1674 Acc:94.03%
Training: Epoch[078/182] Iteration[250/352] Loss: 0.1682 Acc:94.00%
Training: Epoch[078/182] Iteration[300/352] Loss: 0.1711 Acc:93.93%
Training: Epoch[078/182] Iteration[350/352] Loss: 0.1718 Acc:93.88%
Training Progress:  42%|▍| 77/182 [24:06<33:28, 19.13s/it, Train Acc=93.89%, ValEpoch[078/182] Train Acc: 93.89% Valid Acc:88.52% Train loss:0.1714 Valid loss:0.3961 LR:0.1
Training Progress:  43%|▍| 78/182 [24:06<32:54, 18.98s/it, Train Acc=93.89%, ValTraining: Epoch[079/182] Iteration[050/352] Loss: 0.1530 Acc:94.77%
Training: Epoch[079/182] Iteration[100/352] Loss: 0.1600 Acc:94.30%
Training: Epoch[079/182] Iteration[150/352] Loss: 0.1667 Acc:94.09%
Training: Epoch[079/182] Iteration[200/352] Loss: 0.1652 Acc:94.24%
Training: Epoch[079/182] Iteration[250/352] Loss: 0.1640 Acc:94.27%
Training: Epoch[079/182] Iteration[300/352] Loss: 0.1650 Acc:94.18%
Training: Epoch[079/182] Iteration[350/352] Loss: 0.1659 Acc:94.15%
Training Progress:  43%|▍| 78/182 [24:24<32:54, 18.98s/it, Train Acc=94.16%, ValEpoch[079/182] Train Acc: 94.16% Valid Acc:87.94% Train loss:0.1656 Valid loss:0.4320 LR:0.1
Training Progress:  43%|▍| 79/182 [24:24<32:27, 18.90s/it, Train Acc=94.16%, ValTraining: Epoch[080/182] Iteration[050/352] Loss: 0.1591 Acc:94.58%
Training: Epoch[080/182] Iteration[100/352] Loss: 0.1583 Acc:94.50%
Training: Epoch[080/182] Iteration[150/352] Loss: 0.1639 Acc:94.35%
Training: Epoch[080/182] Iteration[200/352] Loss: 0.1679 Acc:94.17%
Training: Epoch[080/182] Iteration[250/352] Loss: 0.1676 Acc:94.17%
Training: Epoch[080/182] Iteration[300/352] Loss: 0.1668 Acc:94.23%
Training: Epoch[080/182] Iteration[350/352] Loss: 0.1664 Acc:94.22%
Training Progress:  43%|▍| 79/182 [24:43<32:27, 18.90s/it, Train Acc=94.22%, ValEpoch[080/182] Train Acc: 94.22% Valid Acc:88.52% Train loss:0.1662 Valid loss:0.4018 LR:0.1
Training Progress:  44%|▍| 80/182 [24:43<32:03, 18.86s/it, Train Acc=94.22%, ValTraining: Epoch[081/182] Iteration[050/352] Loss: 0.1534 Acc:94.73%
Training: Epoch[081/182] Iteration[100/352] Loss: 0.1536 Acc:94.64%
Training: Epoch[081/182] Iteration[150/352] Loss: 0.1489 Acc:94.79%
Training: Epoch[081/182] Iteration[200/352] Loss: 0.1520 Acc:94.62%
Training: Epoch[081/182] Iteration[250/352] Loss: 0.1578 Acc:94.44%
Training: Epoch[081/182] Iteration[300/352] Loss: 0.1621 Acc:94.26%
Training: Epoch[081/182] Iteration[350/352] Loss: 0.1613 Acc:94.28%
Training Progress:  44%|▍| 80/182 [25:02<32:03, 18.86s/it, Train Acc=94.27%, ValEpoch[081/182] Train Acc: 94.27% Valid Acc:89.08% Train loss:0.1616 Valid loss:0.3932 LR:0.1
Training Progress:  45%|▍| 81/182 [25:02<31:39, 18.81s/it, Train Acc=94.27%, ValTraining: Epoch[082/182] Iteration[050/352] Loss: 0.1526 Acc:94.41%
Training: Epoch[082/182] Iteration[100/352] Loss: 0.1649 Acc:94.23%
Training: Epoch[082/182] Iteration[150/352] Loss: 0.1657 Acc:94.22%
Training: Epoch[082/182] Iteration[200/352] Loss: 0.1662 Acc:94.13%
Training: Epoch[082/182] Iteration[250/352] Loss: 0.1638 Acc:94.17%
Training: Epoch[082/182] Iteration[300/352] Loss: 0.1642 Acc:94.11%
Training: Epoch[082/182] Iteration[350/352] Loss: 0.1643 Acc:94.12%
Training Progress:  45%|▍| 81/182 [25:20<31:39, 18.81s/it, Train Acc=94.12%, ValEpoch[082/182] Train Acc: 94.12% Valid Acc:88.88% Train loss:0.1644 Valid loss:0.3793 LR:0.1
Training Progress:  45%|▍| 82/182 [25:20<31:18, 18.78s/it, Train Acc=94.12%, ValTraining: Epoch[083/182] Iteration[050/352] Loss: 0.1294 Acc:95.80%
Training: Epoch[083/182] Iteration[100/352] Loss: 0.1486 Acc:94.92%
Training: Epoch[083/182] Iteration[150/352] Loss: 0.1582 Acc:94.48%
Training: Epoch[083/182] Iteration[200/352] Loss: 0.1642 Acc:94.15%
Training: Epoch[083/182] Iteration[250/352] Loss: 0.1652 Acc:94.11%
Training: Epoch[083/182] Iteration[300/352] Loss: 0.1650 Acc:94.15%
Training: Epoch[083/182] Iteration[350/352] Loss: 0.1647 Acc:94.19%
Training Progress:  45%|▍| 82/182 [25:39<31:18, 18.78s/it, Train Acc=94.18%, ValEpoch[083/182] Train Acc: 94.18% Valid Acc:86.76% Train loss:0.1648 Valid loss:0.4755 LR:0.1
Training Progress:  46%|▍| 83/182 [25:39<30:55, 18.75s/it, Train Acc=94.18%, ValTraining: Epoch[084/182] Iteration[050/352] Loss: 0.1499 Acc:94.89%
Training: Epoch[084/182] Iteration[100/352] Loss: 0.1565 Acc:94.66%
Training: Epoch[084/182] Iteration[150/352] Loss: 0.1565 Acc:94.47%
Training: Epoch[084/182] Iteration[200/352] Loss: 0.1614 Acc:94.29%
Training: Epoch[084/182] Iteration[250/352] Loss: 0.1642 Acc:94.17%
Training: Epoch[084/182] Iteration[300/352] Loss: 0.1652 Acc:94.17%
Training: Epoch[084/182] Iteration[350/352] Loss: 0.1657 Acc:94.14%
Training Progress:  46%|▍| 83/182 [25:58<30:55, 18.75s/it, Train Acc=94.14%, ValEpoch[084/182] Train Acc: 94.14% Valid Acc:89.06% Train loss:0.1657 Valid loss:0.3907 LR:0.1
Training Progress:  46%|▍| 84/182 [25:58<30:44, 18.82s/it, Train Acc=94.14%, ValTraining: Epoch[085/182] Iteration[050/352] Loss: 0.1387 Acc:95.17%
Training: Epoch[085/182] Iteration[100/352] Loss: 0.1423 Acc:95.13%
Training: Epoch[085/182] Iteration[150/352] Loss: 0.1522 Acc:94.78%
Training: Epoch[085/182] Iteration[200/352] Loss: 0.1542 Acc:94.64%
Training: Epoch[085/182] Iteration[250/352] Loss: 0.1562 Acc:94.56%
Training: Epoch[085/182] Iteration[300/352] Loss: 0.1593 Acc:94.43%
Training: Epoch[085/182] Iteration[350/352] Loss: 0.1571 Acc:94.52%
Training Progress:  46%|▍| 84/182 [26:17<30:44, 18.82s/it, Train Acc=94.53%, ValEpoch[085/182] Train Acc: 94.53% Valid Acc:88.22% Train loss:0.1569 Valid loss:0.3873 LR:0.1
Training Progress:  47%|▍| 85/182 [26:17<30:21, 18.78s/it, Train Acc=94.53%, ValTraining: Epoch[086/182] Iteration[050/352] Loss: 0.1400 Acc:95.34%
Training: Epoch[086/182] Iteration[100/352] Loss: 0.1403 Acc:95.24%
Training: Epoch[086/182] Iteration[150/352] Loss: 0.1446 Acc:95.03%
Training: Epoch[086/182] Iteration[200/352] Loss: 0.1488 Acc:94.90%
Training: Epoch[086/182] Iteration[250/352] Loss: 0.1519 Acc:94.75%
Training: Epoch[086/182] Iteration[300/352] Loss: 0.1574 Acc:94.51%
Training: Epoch[086/182] Iteration[350/352] Loss: 0.1578 Acc:94.49%
Training Progress:  47%|▍| 85/182 [26:36<30:21, 18.78s/it, Train Acc=94.48%, ValEpoch[086/182] Train Acc: 94.48% Valid Acc:88.64% Train loss:0.1579 Valid loss:0.3973 LR:0.1
Training Progress:  47%|▍| 86/182 [26:36<30:03, 18.79s/it, Train Acc=94.48%, ValTraining: Epoch[087/182] Iteration[050/352] Loss: 0.1572 Acc:94.58%
Training: Epoch[087/182] Iteration[100/352] Loss: 0.1469 Acc:94.91%
Training: Epoch[087/182] Iteration[150/352] Loss: 0.1605 Acc:94.42%
Training: Epoch[087/182] Iteration[200/352] Loss: 0.1609 Acc:94.44%
Training: Epoch[087/182] Iteration[250/352] Loss: 0.1574 Acc:94.54%
Training: Epoch[087/182] Iteration[300/352] Loss: 0.1586 Acc:94.50%
Training: Epoch[087/182] Iteration[350/352] Loss: 0.1616 Acc:94.36%
Training Progress:  47%|▍| 86/182 [26:54<30:03, 18.79s/it, Train Acc=94.36%, ValEpoch[087/182] Train Acc: 94.36% Valid Acc:88.38% Train loss:0.1616 Valid loss:0.4155 LR:0.1
Training Progress:  48%|▍| 87/182 [26:54<29:40, 18.74s/it, Train Acc=94.36%, ValTraining: Epoch[088/182] Iteration[050/352] Loss: 0.1473 Acc:94.91%
Training: Epoch[088/182] Iteration[100/352] Loss: 0.1614 Acc:94.27%
Training: Epoch[088/182] Iteration[150/352] Loss: 0.1590 Acc:94.44%
Training: Epoch[088/182] Iteration[200/352] Loss: 0.1558 Acc:94.60%
Training: Epoch[088/182] Iteration[250/352] Loss: 0.1536 Acc:94.67%
Training: Epoch[088/182] Iteration[300/352] Loss: 0.1573 Acc:94.55%
Training: Epoch[088/182] Iteration[350/352] Loss: 0.1615 Acc:94.36%
Training Progress:  48%|▍| 87/182 [27:13<29:40, 18.74s/it, Train Acc=94.38%, ValEpoch[088/182] Train Acc: 94.38% Valid Acc:89.46% Train loss:0.1612 Valid loss:0.3581 LR:0.1
Training Progress:  48%|▍| 88/182 [27:13<29:20, 18.73s/it, Train Acc=94.38%, ValTraining: Epoch[089/182] Iteration[050/352] Loss: 0.1453 Acc:95.14%
Training: Epoch[089/182] Iteration[100/352] Loss: 0.1581 Acc:94.51%
Training: Epoch[089/182] Iteration[150/352] Loss: 0.1620 Acc:94.30%
Training: Epoch[089/182] Iteration[200/352] Loss: 0.1603 Acc:94.39%
Training: Epoch[089/182] Iteration[250/352] Loss: 0.1573 Acc:94.55%
Training: Epoch[089/182] Iteration[300/352] Loss: 0.1629 Acc:94.35%
Training: Epoch[089/182] Iteration[350/352] Loss: 0.1646 Acc:94.30%
Training Progress:  48%|▍| 88/182 [27:32<29:20, 18.73s/it, Train Acc=94.29%, ValEpoch[089/182] Train Acc: 94.29% Valid Acc:87.06% Train loss:0.1648 Valid loss:0.4796 LR:0.1
Training Progress:  49%|▍| 89/182 [27:32<28:59, 18.71s/it, Train Acc=94.29%, ValTraining: Epoch[090/182] Iteration[050/352] Loss: 0.1749 Acc:93.97%
Training: Epoch[090/182] Iteration[100/352] Loss: 0.1651 Acc:94.09%
Training: Epoch[090/182] Iteration[150/352] Loss: 0.1604 Acc:94.33%
Training: Epoch[090/182] Iteration[200/352] Loss: 0.1620 Acc:94.25%
Training: Epoch[090/182] Iteration[250/352] Loss: 0.1604 Acc:94.38%
Training: Epoch[090/182] Iteration[300/352] Loss: 0.1588 Acc:94.44%
Training: Epoch[090/182] Iteration[350/352] Loss: 0.1599 Acc:94.40%
Training Progress:  49%|▍| 89/182 [27:50<28:59, 18.71s/it, Train Acc=94.38%, ValEpoch[090/182] Train Acc: 94.38% Valid Acc:89.02% Train loss:0.1603 Valid loss:0.3763 LR:0.1
Training Progress:  49%|▍| 90/182 [27:50<28:41, 18.71s/it, Train Acc=94.38%, ValTraining: Epoch[091/182] Iteration[050/352] Loss: 0.1572 Acc:94.39%
Training: Epoch[091/182] Iteration[100/352] Loss: 0.1491 Acc:94.70%
Training: Epoch[091/182] Iteration[150/352] Loss: 0.1509 Acc:94.57%
Training: Epoch[091/182] Iteration[200/352] Loss: 0.1533 Acc:94.49%
Training: Epoch[091/182] Iteration[250/352] Loss: 0.1574 Acc:94.42%
Training: Epoch[091/182] Iteration[300/352] Loss: 0.1595 Acc:94.31%
Training: Epoch[091/182] Iteration[350/352] Loss: 0.1609 Acc:94.30%
Training Progress:  49%|▍| 90/182 [28:09<28:41, 18.71s/it, Train Acc=94.30%, ValEpoch[091/182] Train Acc: 94.30% Valid Acc:88.02% Train loss:0.1609 Valid loss:0.4081 LR:0.1
Training Progress:  50%|▌| 91/182 [28:09<28:21, 18.69s/it, Train Acc=94.30%, ValTraining: Epoch[092/182] Iteration[050/352] Loss: 0.1369 Acc:95.30%
Training: Epoch[092/182] Iteration[100/352] Loss: 0.1377 Acc:95.32%
Training: Epoch[092/182] Iteration[150/352] Loss: 0.1456 Acc:94.95%
Training: Epoch[092/182] Iteration[200/352] Loss: 0.1495 Acc:94.79%
Training: Epoch[092/182] Iteration[250/352] Loss: 0.1546 Acc:94.65%
Training: Epoch[092/182] Iteration[300/352] Loss: 0.1571 Acc:94.54%
Training: Epoch[092/182] Iteration[350/352] Loss: 0.1557 Acc:94.60%
Training Progress:  50%|▌| 91/182 [28:28<28:21, 18.69s/it, Train Acc=94.59%, ValEpoch[092/182] Train Acc: 94.59% Valid Acc:89.50% Train loss:0.1556 Valid loss:0.3450 LR:0.1
Training Progress:  51%|▌| 92/182 [28:28<28:01, 18.68s/it, Train Acc=94.59%, ValTraining: Epoch[093/182] Iteration[050/352] Loss: 0.1105 Acc:96.12%
Training: Epoch[093/182] Iteration[100/352] Loss: 0.0960 Acc:96.59%
Training: Epoch[093/182] Iteration[150/352] Loss: 0.0904 Acc:96.84%
Training: Epoch[093/182] Iteration[200/352] Loss: 0.0871 Acc:96.96%
Training: Epoch[093/182] Iteration[250/352] Loss: 0.0837 Acc:97.12%
Training: Epoch[093/182] Iteration[300/352] Loss: 0.0809 Acc:97.24%
Training: Epoch[093/182] Iteration[350/352] Loss: 0.0795 Acc:97.30%
Training Progress:  51%|▌| 92/182 [28:46<28:01, 18.68s/it, Train Acc=97.31%, ValEpoch[093/182] Train Acc: 97.31% Valid Acc:92.24% Train loss:0.0793 Valid loss:0.2533 LR:0.010000000000000002
Training Progress:  51%|▌| 93/182 [28:46<27:47, 18.73s/it, Train Acc=97.31%, ValTraining: Epoch[094/182] Iteration[050/352] Loss: 0.0593 Acc:98.25%
Training: Epoch[094/182] Iteration[100/352] Loss: 0.0590 Acc:98.17%
Training: Epoch[094/182] Iteration[150/352] Loss: 0.0580 Acc:98.20%
Training: Epoch[094/182] Iteration[200/352] Loss: 0.0568 Acc:98.20%
Training: Epoch[094/182] Iteration[250/352] Loss: 0.0567 Acc:98.19%
Training: Epoch[094/182] Iteration[300/352] Loss: 0.0565 Acc:98.17%
Training: Epoch[094/182] Iteration[350/352] Loss: 0.0561 Acc:98.19%
Training Progress:  51%|▌| 93/182 [29:05<27:47, 18.73s/it, Train Acc=98.18%, ValEpoch[094/182] Train Acc: 98.18% Valid Acc:92.50% Train loss:0.0562 Valid loss:0.2474 LR:0.010000000000000002
Training Progress:  52%|▌| 94/182 [29:05<27:24, 18.69s/it, Train Acc=98.18%, ValTraining: Epoch[095/182] Iteration[050/352] Loss: 0.0504 Acc:98.39%
Training: Epoch[095/182] Iteration[100/352] Loss: 0.0485 Acc:98.48%
Training: Epoch[095/182] Iteration[150/352] Loss: 0.0461 Acc:98.59%
Training: Epoch[095/182] Iteration[200/352] Loss: 0.0465 Acc:98.56%
Training: Epoch[095/182] Iteration[250/352] Loss: 0.0470 Acc:98.54%
Training: Epoch[095/182] Iteration[300/352] Loss: 0.0461 Acc:98.59%
Training: Epoch[095/182] Iteration[350/352] Loss: 0.0460 Acc:98.59%
Training Progress:  52%|▌| 94/182 [29:24<27:24, 18.69s/it, Train Acc=98.59%, ValEpoch[095/182] Train Acc: 98.59% Valid Acc:92.60% Train loss:0.0459 Valid loss:0.2553 LR:0.010000000000000002
Training Progress:  52%|▌| 95/182 [29:24<27:08, 18.71s/it, Train Acc=98.59%, ValTraining: Epoch[096/182] Iteration[050/352] Loss: 0.0406 Acc:98.91%
Training: Epoch[096/182] Iteration[100/352] Loss: 0.0380 Acc:99.00%
Training: Epoch[096/182] Iteration[150/352] Loss: 0.0405 Acc:98.88%
Training: Epoch[096/182] Iteration[200/352] Loss: 0.0409 Acc:98.85%
Training: Epoch[096/182] Iteration[250/352] Loss: 0.0410 Acc:98.84%
Training: Epoch[096/182] Iteration[300/352] Loss: 0.0410 Acc:98.80%
Training: Epoch[096/182] Iteration[350/352] Loss: 0.0405 Acc:98.82%
Training Progress:  52%|▌| 95/182 [29:42<27:08, 18.71s/it, Train Acc=98.82%, ValEpoch[096/182] Train Acc: 98.82% Valid Acc:92.56% Train loss:0.0406 Valid loss:0.2556 LR:0.010000000000000002
Training Progress:  53%|▌| 96/182 [29:42<26:45, 18.67s/it, Train Acc=98.82%, ValTraining: Epoch[097/182] Iteration[050/352] Loss: 0.0399 Acc:98.83%
Training: Epoch[097/182] Iteration[100/352] Loss: 0.0386 Acc:98.80%
Training: Epoch[097/182] Iteration[150/352] Loss: 0.0388 Acc:98.80%
Training: Epoch[097/182] Iteration[200/352] Loss: 0.0375 Acc:98.85%
Training: Epoch[097/182] Iteration[250/352] Loss: 0.0372 Acc:98.84%
Training: Epoch[097/182] Iteration[300/352] Loss: 0.0376 Acc:98.82%
Training: Epoch[097/182] Iteration[350/352] Loss: 0.0370 Acc:98.84%
Training Progress:  53%|▌| 96/182 [30:01<26:45, 18.67s/it, Train Acc=98.85%, ValEpoch[097/182] Train Acc: 98.85% Valid Acc:92.66% Train loss:0.0369 Valid loss:0.2591 LR:0.010000000000000002
Training Progress:  53%|▌| 97/182 [30:01<26:32, 18.74s/it, Train Acc=98.85%, ValTraining: Epoch[098/182] Iteration[050/352] Loss: 0.0345 Acc:98.81%
Training: Epoch[098/182] Iteration[100/352] Loss: 0.0334 Acc:98.85%
Training: Epoch[098/182] Iteration[150/352] Loss: 0.0342 Acc:98.85%
Training: Epoch[098/182] Iteration[200/352] Loss: 0.0340 Acc:98.93%
Training: Epoch[098/182] Iteration[250/352] Loss: 0.0342 Acc:98.92%
Training: Epoch[098/182] Iteration[300/352] Loss: 0.0338 Acc:98.96%
Training: Epoch[098/182] Iteration[350/352] Loss: 0.0338 Acc:98.96%
Training Progress:  53%|▌| 97/182 [30:20<26:32, 18.74s/it, Train Acc=98.96%, ValEpoch[098/182] Train Acc: 98.96% Valid Acc:92.66% Train loss:0.0338 Valid loss:0.2655 LR:0.010000000000000002
Training Progress:  54%|▌| 98/182 [30:20<26:23, 18.86s/it, Train Acc=98.96%, ValTraining: Epoch[099/182] Iteration[050/352] Loss: 0.0300 Acc:99.17%
Training: Epoch[099/182] Iteration[100/352] Loss: 0.0300 Acc:99.14%
Training: Epoch[099/182] Iteration[150/352] Loss: 0.0293 Acc:99.15%
Training: Epoch[099/182] Iteration[200/352] Loss: 0.0307 Acc:99.10%
Training: Epoch[099/182] Iteration[250/352] Loss: 0.0312 Acc:99.07%
Training: Epoch[099/182] Iteration[300/352] Loss: 0.0311 Acc:99.09%
Training: Epoch[099/182] Iteration[350/352] Loss: 0.0311 Acc:99.09%
Training Progress:  54%|▌| 98/182 [30:39<26:23, 18.86s/it, Train Acc=99.09%, ValEpoch[099/182] Train Acc: 99.09% Valid Acc:92.62% Train loss:0.0309 Valid loss:0.2641 LR:0.010000000000000002
Training Progress:  54%|▌| 99/182 [30:39<25:58, 18.78s/it, Train Acc=99.09%, ValTraining: Epoch[100/182] Iteration[050/352] Loss: 0.0279 Acc:99.19%
Training: Epoch[100/182] Iteration[100/352] Loss: 0.0285 Acc:99.16%
Training: Epoch[100/182] Iteration[150/352] Loss: 0.0279 Acc:99.16%
Training: Epoch[100/182] Iteration[200/352] Loss: 0.0281 Acc:99.17%
Training: Epoch[100/182] Iteration[250/352] Loss: 0.0282 Acc:99.19%
Training: Epoch[100/182] Iteration[300/352] Loss: 0.0282 Acc:99.19%
Training: Epoch[100/182] Iteration[350/352] Loss: 0.0284 Acc:99.17%
Training Progress:  54%|▌| 99/182 [30:58<25:58, 18.78s/it, Train Acc=99.17%, ValEpoch[100/182] Train Acc: 99.17% Valid Acc:92.78% Train loss:0.0284 Valid loss:0.2712 LR:0.010000000000000002
Training Progress:  55%|▌| 100/182 [30:58<25:37, 18.75s/it, Train Acc=99.17%, VaTraining: Epoch[101/182] Iteration[050/352] Loss: 0.0243 Acc:99.33%
Training: Epoch[101/182] Iteration[100/352] Loss: 0.0254 Acc:99.29%
Training: Epoch[101/182] Iteration[150/352] Loss: 0.0260 Acc:99.29%
Training: Epoch[101/182] Iteration[200/352] Loss: 0.0262 Acc:99.24%
Training: Epoch[101/182] Iteration[250/352] Loss: 0.0264 Acc:99.24%
Training: Epoch[101/182] Iteration[300/352] Loss: 0.0269 Acc:99.22%
Training: Epoch[101/182] Iteration[350/352] Loss: 0.0271 Acc:99.21%
Training Progress:  55%|▌| 100/182 [31:16<25:37, 18.75s/it, Train Acc=99.20%, VaEpoch[101/182] Train Acc: 99.20% Valid Acc:92.76% Train loss:0.0271 Valid loss:0.2718 LR:0.010000000000000002
Training Progress:  55%|▌| 101/182 [31:16<25:17, 18.74s/it, Train Acc=99.20%, VaTraining: Epoch[102/182] Iteration[050/352] Loss: 0.0230 Acc:99.34%
Training: Epoch[102/182] Iteration[100/352] Loss: 0.0224 Acc:99.35%
Training: Epoch[102/182] Iteration[150/352] Loss: 0.0228 Acc:99.34%
Training: Epoch[102/182] Iteration[200/352] Loss: 0.0233 Acc:99.32%
Training: Epoch[102/182] Iteration[250/352] Loss: 0.0233 Acc:99.33%
Training: Epoch[102/182] Iteration[300/352] Loss: 0.0232 Acc:99.34%
Training: Epoch[102/182] Iteration[350/352] Loss: 0.0233 Acc:99.33%
Training Progress:  55%|▌| 101/182 [31:35<25:17, 18.74s/it, Train Acc=99.33%, VaEpoch[102/182] Train Acc: 99.33% Valid Acc:92.66% Train loss:0.0234 Valid loss:0.2787 LR:0.010000000000000002
Training Progress:  56%|▌| 102/182 [31:35<24:58, 18.73s/it, Train Acc=99.33%, VaTraining: Epoch[103/182] Iteration[050/352] Loss: 0.0219 Acc:99.52%
Training: Epoch[103/182] Iteration[100/352] Loss: 0.0217 Acc:99.43%
Training: Epoch[103/182] Iteration[150/352] Loss: 0.0216 Acc:99.46%
Training: Epoch[103/182] Iteration[200/352] Loss: 0.0217 Acc:99.45%
Training: Epoch[103/182] Iteration[250/352] Loss: 0.0219 Acc:99.44%
Training: Epoch[103/182] Iteration[300/352] Loss: 0.0218 Acc:99.45%
Training: Epoch[103/182] Iteration[350/352] Loss: 0.0219 Acc:99.44%
Training Progress:  56%|▌| 102/182 [31:54<24:58, 18.73s/it, Train Acc=99.44%, VaEpoch[103/182] Train Acc: 99.44% Valid Acc:92.70% Train loss:0.0219 Valid loss:0.2842 LR:0.010000000000000002
Training Progress:  57%|▌| 103/182 [31:54<24:37, 18.70s/it, Train Acc=99.44%, VaTraining: Epoch[104/182] Iteration[050/352] Loss: 0.0190 Acc:99.52%
Training: Epoch[104/182] Iteration[100/352] Loss: 0.0203 Acc:99.46%
Training: Epoch[104/182] Iteration[150/352] Loss: 0.0203 Acc:99.46%
Training: Epoch[104/182] Iteration[200/352] Loss: 0.0206 Acc:99.43%
Training: Epoch[104/182] Iteration[250/352] Loss: 0.0205 Acc:99.45%
Training: Epoch[104/182] Iteration[300/352] Loss: 0.0208 Acc:99.44%
Training: Epoch[104/182] Iteration[350/352] Loss: 0.0207 Acc:99.44%
Training Progress:  57%|▌| 103/182 [32:12<24:37, 18.70s/it, Train Acc=99.44%, VaEpoch[104/182] Train Acc: 99.44% Valid Acc:92.58% Train loss:0.0208 Valid loss:0.2915 LR:0.010000000000000002
Training Progress:  57%|▌| 104/182 [32:12<24:16, 18.67s/it, Train Acc=99.44%, VaTraining: Epoch[105/182] Iteration[050/352] Loss: 0.0214 Acc:99.38%
Training: Epoch[105/182] Iteration[100/352] Loss: 0.0215 Acc:99.35%
Training: Epoch[105/182] Iteration[150/352] Loss: 0.0207 Acc:99.41%
Training: Epoch[105/182] Iteration[200/352] Loss: 0.0201 Acc:99.45%
Training: Epoch[105/182] Iteration[250/352] Loss: 0.0199 Acc:99.47%
Training: Epoch[105/182] Iteration[300/352] Loss: 0.0200 Acc:99.45%
Training: Epoch[105/182] Iteration[350/352] Loss: 0.0199 Acc:99.47%
Training Progress:  57%|▌| 104/182 [32:31<24:16, 18.67s/it, Train Acc=99.47%, VaEpoch[105/182] Train Acc: 99.47% Valid Acc:92.64% Train loss:0.0198 Valid loss:0.2859 LR:0.010000000000000002
Training Progress:  58%|▌| 105/182 [32:31<24:01, 18.72s/it, Train Acc=99.47%, VaTraining: Epoch[106/182] Iteration[050/352] Loss: 0.0194 Acc:99.45%
Training: Epoch[106/182] Iteration[100/352] Loss: 0.0192 Acc:99.52%
Training: Epoch[106/182] Iteration[150/352] Loss: 0.0198 Acc:99.48%
Training: Epoch[106/182] Iteration[200/352] Loss: 0.0200 Acc:99.47%
Training: Epoch[106/182] Iteration[250/352] Loss: 0.0197 Acc:99.49%
Training: Epoch[106/182] Iteration[300/352] Loss: 0.0197 Acc:99.48%
Training: Epoch[106/182] Iteration[350/352] Loss: 0.0196 Acc:99.49%
Training Progress:  58%|▌| 105/182 [32:50<24:01, 18.72s/it, Train Acc=99.49%, VaEpoch[106/182] Train Acc: 99.49% Valid Acc:92.66% Train loss:0.0196 Valid loss:0.2902 LR:0.010000000000000002
Training Progress:  58%|▌| 106/182 [32:50<23:44, 18.74s/it, Train Acc=99.49%, VaTraining: Epoch[107/182] Iteration[050/352] Loss: 0.0175 Acc:99.55%
Training: Epoch[107/182] Iteration[100/352] Loss: 0.0180 Acc:99.53%
Training: Epoch[107/182] Iteration[150/352] Loss: 0.0176 Acc:99.52%
Training: Epoch[107/182] Iteration[200/352] Loss: 0.0177 Acc:99.53%
Training: Epoch[107/182] Iteration[250/352] Loss: 0.0179 Acc:99.52%
Training: Epoch[107/182] Iteration[300/352] Loss: 0.0177 Acc:99.52%
Training: Epoch[107/182] Iteration[350/352] Loss: 0.0177 Acc:99.52%
Training Progress:  58%|▌| 106/182 [33:09<23:44, 18.74s/it, Train Acc=99.52%, VaEpoch[107/182] Train Acc: 99.52% Valid Acc:92.78% Train loss:0.0177 Valid loss:0.2921 LR:0.010000000000000002
Training Progress:  59%|▌| 107/182 [33:09<23:22, 18.70s/it, Train Acc=99.52%, VaTraining: Epoch[108/182] Iteration[050/352] Loss: 0.0185 Acc:99.56%
Training: Epoch[108/182] Iteration[100/352] Loss: 0.0178 Acc:99.59%
Training: Epoch[108/182] Iteration[150/352] Loss: 0.0177 Acc:99.57%
Training: Epoch[108/182] Iteration[200/352] Loss: 0.0173 Acc:99.58%
Training: Epoch[108/182] Iteration[250/352] Loss: 0.0175 Acc:99.55%
Training: Epoch[108/182] Iteration[300/352] Loss: 0.0175 Acc:99.55%
Training: Epoch[108/182] Iteration[350/352] Loss: 0.0172 Acc:99.57%
Training Progress:  59%|▌| 107/182 [33:27<23:22, 18.70s/it, Train Acc=99.57%, VaEpoch[108/182] Train Acc: 99.57% Valid Acc:92.70% Train loss:0.0172 Valid loss:0.2930 LR:0.010000000000000002
Training Progress:  59%|▌| 108/182 [33:27<23:03, 18.69s/it, Train Acc=99.57%, VaTraining: Epoch[109/182] Iteration[050/352] Loss: 0.0159 Acc:99.53%
Training: Epoch[109/182] Iteration[100/352] Loss: 0.0156 Acc:99.58%
Training: Epoch[109/182] Iteration[150/352] Loss: 0.0152 Acc:99.62%
Training: Epoch[109/182] Iteration[200/352] Loss: 0.0148 Acc:99.65%
Training: Epoch[109/182] Iteration[250/352] Loss: 0.0154 Acc:99.62%
Training: Epoch[109/182] Iteration[300/352] Loss: 0.0160 Acc:99.59%
Training: Epoch[109/182] Iteration[350/352] Loss: 0.0159 Acc:99.59%
Training Progress:  59%|▌| 108/182 [33:46<23:03, 18.69s/it, Train Acc=99.60%, VaEpoch[109/182] Train Acc: 99.60% Valid Acc:92.70% Train loss:0.0158 Valid loss:0.2968 LR:0.010000000000000002
Training Progress:  60%|▌| 109/182 [33:46<22:42, 18.66s/it, Train Acc=99.60%, VaTraining: Epoch[110/182] Iteration[050/352] Loss: 0.0172 Acc:99.52%
Training: Epoch[110/182] Iteration[100/352] Loss: 0.0157 Acc:99.56%
Training: Epoch[110/182] Iteration[150/352] Loss: 0.0158 Acc:99.56%
Training: Epoch[110/182] Iteration[200/352] Loss: 0.0155 Acc:99.59%
Training: Epoch[110/182] Iteration[250/352] Loss: 0.0156 Acc:99.57%
Training: Epoch[110/182] Iteration[300/352] Loss: 0.0157 Acc:99.57%
Training: Epoch[110/182] Iteration[350/352] Loss: 0.0157 Acc:99.56%
Training Progress:  60%|▌| 109/182 [34:04<22:42, 18.66s/it, Train Acc=99.56%, VaEpoch[110/182] Train Acc: 99.56% Valid Acc:92.74% Train loss:0.0158 Valid loss:0.2956 LR:0.010000000000000002
Training Progress:  60%|▌| 110/182 [34:04<22:23, 18.66s/it, Train Acc=99.56%, VaTraining: Epoch[111/182] Iteration[050/352] Loss: 0.0131 Acc:99.75%
Training: Epoch[111/182] Iteration[100/352] Loss: 0.0131 Acc:99.72%
Training: Epoch[111/182] Iteration[150/352] Loss: 0.0129 Acc:99.71%
Training: Epoch[111/182] Iteration[200/352] Loss: 0.0137 Acc:99.68%
Training: Epoch[111/182] Iteration[250/352] Loss: 0.0139 Acc:99.66%
Training: Epoch[111/182] Iteration[300/352] Loss: 0.0144 Acc:99.65%
Training: Epoch[111/182] Iteration[350/352] Loss: 0.0147 Acc:99.63%
Training Progress:  60%|▌| 110/182 [34:23<22:23, 18.66s/it, Train Acc=99.63%, VaEpoch[111/182] Train Acc: 99.63% Valid Acc:92.78% Train loss:0.0147 Valid loss:0.2958 LR:0.010000000000000002
Training Progress:  61%|▌| 111/182 [34:23<22:06, 18.68s/it, Train Acc=99.63%, VaTraining: Epoch[112/182] Iteration[050/352] Loss: 0.0146 Acc:99.62%
Training: Epoch[112/182] Iteration[100/352] Loss: 0.0129 Acc:99.73%
Training: Epoch[112/182] Iteration[150/352] Loss: 0.0125 Acc:99.73%
Training: Epoch[112/182] Iteration[200/352] Loss: 0.0128 Acc:99.71%
Training: Epoch[112/182] Iteration[250/352] Loss: 0.0137 Acc:99.68%
Training: Epoch[112/182] Iteration[300/352] Loss: 0.0143 Acc:99.64%
Training: Epoch[112/182] Iteration[350/352] Loss: 0.0138 Acc:99.65%
Training Progress:  61%|▌| 111/182 [34:42<22:06, 18.68s/it, Train Acc=99.65%, VaEpoch[112/182] Train Acc: 99.65% Valid Acc:92.80% Train loss:0.0139 Valid loss:0.3028 LR:0.010000000000000002
Training Progress:  62%|▌| 112/182 [34:42<21:49, 18.71s/it, Train Acc=99.65%, VaTraining: Epoch[113/182] Iteration[050/352] Loss: 0.0126 Acc:99.77%
Training: Epoch[113/182] Iteration[100/352] Loss: 0.0120 Acc:99.77%
Training: Epoch[113/182] Iteration[150/352] Loss: 0.0122 Acc:99.76%
Training: Epoch[113/182] Iteration[200/352] Loss: 0.0121 Acc:99.74%
Training: Epoch[113/182] Iteration[250/352] Loss: 0.0121 Acc:99.73%
Training: Epoch[113/182] Iteration[300/352] Loss: 0.0123 Acc:99.72%
Training: Epoch[113/182] Iteration[350/352] Loss: 0.0122 Acc:99.72%
Training Progress:  62%|▌| 112/182 [35:01<21:49, 18.71s/it, Train Acc=99.72%, VaEpoch[113/182] Train Acc: 99.72% Valid Acc:92.78% Train loss:0.0122 Valid loss:0.3041 LR:0.010000000000000002
Training Progress:  62%|▌| 113/182 [35:01<21:27, 18.67s/it, Train Acc=99.72%, VaTraining: Epoch[114/182] Iteration[050/352] Loss: 0.0133 Acc:99.69%
Training: Epoch[114/182] Iteration[100/352] Loss: 0.0124 Acc:99.66%
Training: Epoch[114/182] Iteration[150/352] Loss: 0.0132 Acc:99.62%
Training: Epoch[114/182] Iteration[200/352] Loss: 0.0132 Acc:99.62%
Training: Epoch[114/182] Iteration[250/352] Loss: 0.0132 Acc:99.64%
Training: Epoch[114/182] Iteration[300/352] Loss: 0.0131 Acc:99.65%
Training: Epoch[114/182] Iteration[350/352] Loss: 0.0129 Acc:99.66%
Training Progress:  62%|▌| 113/182 [35:19<21:27, 18.67s/it, Train Acc=99.66%, VaEpoch[114/182] Train Acc: 99.66% Valid Acc:92.48% Train loss:0.0130 Valid loss:0.3122 LR:0.010000000000000002
Training Progress:  63%|▋| 114/182 [35:19<21:06, 18.62s/it, Train Acc=99.66%, VaTraining: Epoch[115/182] Iteration[050/352] Loss: 0.0104 Acc:99.81%
Training: Epoch[115/182] Iteration[100/352] Loss: 0.0119 Acc:99.77%
Training: Epoch[115/182] Iteration[150/352] Loss: 0.0122 Acc:99.75%
Training: Epoch[115/182] Iteration[200/352] Loss: 0.0124 Acc:99.75%
Training: Epoch[115/182] Iteration[250/352] Loss: 0.0122 Acc:99.74%
Training: Epoch[115/182] Iteration[300/352] Loss: 0.0125 Acc:99.73%
Training: Epoch[115/182] Iteration[350/352] Loss: 0.0126 Acc:99.72%
Training Progress:  63%|▋| 114/182 [35:38<21:06, 18.62s/it, Train Acc=99.72%, VaEpoch[115/182] Train Acc: 99.72% Valid Acc:92.46% Train loss:0.0126 Valid loss:0.3091 LR:0.010000000000000002
Training Progress:  63%|▋| 115/182 [35:38<20:46, 18.60s/it, Train Acc=99.72%, VaTraining: Epoch[116/182] Iteration[050/352] Loss: 0.0134 Acc:99.64%
Training: Epoch[116/182] Iteration[100/352] Loss: 0.0134 Acc:99.66%
Training: Epoch[116/182] Iteration[150/352] Loss: 0.0132 Acc:99.66%
Training: Epoch[116/182] Iteration[200/352] Loss: 0.0126 Acc:99.68%
Training: Epoch[116/182] Iteration[250/352] Loss: 0.0127 Acc:99.67%
Training: Epoch[116/182] Iteration[300/352] Loss: 0.0125 Acc:99.67%
Training: Epoch[116/182] Iteration[350/352] Loss: 0.0126 Acc:99.67%
Training Progress:  63%|▋| 115/182 [35:56<20:46, 18.60s/it, Train Acc=99.67%, VaEpoch[116/182] Train Acc: 99.67% Valid Acc:92.54% Train loss:0.0126 Valid loss:0.3060 LR:0.010000000000000002
Training Progress:  64%|▋| 116/182 [35:56<20:25, 18.58s/it, Train Acc=99.67%, VaTraining: Epoch[117/182] Iteration[050/352] Loss: 0.0116 Acc:99.78%
Training: Epoch[117/182] Iteration[100/352] Loss: 0.0116 Acc:99.76%
Training: Epoch[117/182] Iteration[150/352] Loss: 0.0114 Acc:99.76%
Training: Epoch[117/182] Iteration[200/352] Loss: 0.0119 Acc:99.72%
Training: Epoch[117/182] Iteration[250/352] Loss: 0.0118 Acc:99.71%
Training: Epoch[117/182] Iteration[300/352] Loss: 0.0118 Acc:99.71%
Training: Epoch[117/182] Iteration[350/352] Loss: 0.0119 Acc:99.72%
Training Progress:  64%|▋| 116/182 [36:15<20:25, 18.58s/it, Train Acc=99.72%, VaEpoch[117/182] Train Acc: 99.72% Valid Acc:92.78% Train loss:0.0119 Valid loss:0.3069 LR:0.010000000000000002
Training Progress:  64%|▋| 117/182 [36:15<20:08, 18.59s/it, Train Acc=99.72%, VaTraining: Epoch[118/182] Iteration[050/352] Loss: 0.0109 Acc:99.70%
Training: Epoch[118/182] Iteration[100/352] Loss: 0.0103 Acc:99.79%
Training: Epoch[118/182] Iteration[150/352] Loss: 0.0106 Acc:99.77%
Training: Epoch[118/182] Iteration[200/352] Loss: 0.0111 Acc:99.74%
Training: Epoch[118/182] Iteration[250/352] Loss: 0.0112 Acc:99.72%
Training: Epoch[118/182] Iteration[300/352] Loss: 0.0116 Acc:99.71%
Training: Epoch[118/182] Iteration[350/352] Loss: 0.0115 Acc:99.72%
Training Progress:  64%|▋| 117/182 [36:33<20:08, 18.59s/it, Train Acc=99.72%, VaEpoch[118/182] Train Acc: 99.72% Valid Acc:92.58% Train loss:0.0116 Valid loss:0.3125 LR:0.010000000000000002
Training Progress:  65%|▋| 118/182 [36:33<19:50, 18.60s/it, Train Acc=99.72%, VaTraining: Epoch[119/182] Iteration[050/352] Loss: 0.0118 Acc:99.69%
Training: Epoch[119/182] Iteration[100/352] Loss: 0.0117 Acc:99.73%
Training: Epoch[119/182] Iteration[150/352] Loss: 0.0112 Acc:99.74%
Training: Epoch[119/182] Iteration[200/352] Loss: 0.0111 Acc:99.75%
Training: Epoch[119/182] Iteration[250/352] Loss: 0.0115 Acc:99.72%
Training: Epoch[119/182] Iteration[300/352] Loss: 0.0114 Acc:99.73%
Training: Epoch[119/182] Iteration[350/352] Loss: 0.0114 Acc:99.72%
Training Progress:  65%|▋| 118/182 [36:52<19:50, 18.60s/it, Train Acc=99.72%, VaEpoch[119/182] Train Acc: 99.72% Valid Acc:92.68% Train loss:0.0114 Valid loss:0.3072 LR:0.010000000000000002
Training Progress:  65%|▋| 119/182 [36:52<19:31, 18.59s/it, Train Acc=99.72%, VaTraining: Epoch[120/182] Iteration[050/352] Loss: 0.0112 Acc:99.73%
Training: Epoch[120/182] Iteration[100/352] Loss: 0.0115 Acc:99.76%
Training: Epoch[120/182] Iteration[150/352] Loss: 0.0110 Acc:99.77%
Training: Epoch[120/182] Iteration[200/352] Loss: 0.0106 Acc:99.78%
Training: Epoch[120/182] Iteration[250/352] Loss: 0.0108 Acc:99.76%
Training: Epoch[120/182] Iteration[300/352] Loss: 0.0111 Acc:99.75%
Training: Epoch[120/182] Iteration[350/352] Loss: 0.0112 Acc:99.74%
Training Progress:  65%|▋| 119/182 [37:11<19:31, 18.59s/it, Train Acc=99.74%, VaEpoch[120/182] Train Acc: 99.74% Valid Acc:92.88% Train loss:0.0112 Valid loss:0.3113 LR:0.010000000000000002
Training Progress:  66%|▋| 120/182 [37:11<19:13, 18.60s/it, Train Acc=99.74%, VaTraining: Epoch[121/182] Iteration[050/352] Loss: 0.0086 Acc:99.83%
Training: Epoch[121/182] Iteration[100/352] Loss: 0.0097 Acc:99.76%
Training: Epoch[121/182] Iteration[150/352] Loss: 0.0098 Acc:99.77%
Training: Epoch[121/182] Iteration[200/352] Loss: 0.0100 Acc:99.75%
Training: Epoch[121/182] Iteration[250/352] Loss: 0.0100 Acc:99.77%
Training: Epoch[121/182] Iteration[300/352] Loss: 0.0100 Acc:99.77%
Training: Epoch[121/182] Iteration[350/352] Loss: 0.0100 Acc:99.77%
Training Progress:  66%|▋| 120/182 [37:29<19:13, 18.60s/it, Train Acc=99.77%, VaEpoch[121/182] Train Acc: 99.77% Valid Acc:93.00% Train loss:0.0099 Valid loss:0.3039 LR:0.010000000000000002
Training Progress:  66%|▋| 121/182 [37:29<18:53, 18.57s/it, Train Acc=99.77%, VaTraining: Epoch[122/182] Iteration[050/352] Loss: 0.0095 Acc:99.80%
Training: Epoch[122/182] Iteration[100/352] Loss: 0.0091 Acc:99.81%
Training: Epoch[122/182] Iteration[150/352] Loss: 0.0093 Acc:99.81%
Training: Epoch[122/182] Iteration[200/352] Loss: 0.0089 Acc:99.82%
Training: Epoch[122/182] Iteration[250/352] Loss: 0.0092 Acc:99.80%
Training: Epoch[122/182] Iteration[300/352] Loss: 0.0092 Acc:99.81%
Training: Epoch[122/182] Iteration[350/352] Loss: 0.0091 Acc:99.82%
Training Progress:  66%|▋| 121/182 [37:48<18:53, 18.57s/it, Train Acc=99.82%, VaEpoch[122/182] Train Acc: 99.82% Valid Acc:92.76% Train loss:0.0091 Valid loss:0.3102 LR:0.010000000000000002
Training Progress:  67%|▋| 122/182 [37:48<18:35, 18.58s/it, Train Acc=99.82%, VaTraining: Epoch[123/182] Iteration[050/352] Loss: 0.0096 Acc:99.73%
Training: Epoch[123/182] Iteration[100/352] Loss: 0.0101 Acc:99.73%
Training: Epoch[123/182] Iteration[150/352] Loss: 0.0093 Acc:99.77%
Training: Epoch[123/182] Iteration[200/352] Loss: 0.0099 Acc:99.74%
Training: Epoch[123/182] Iteration[250/352] Loss: 0.0100 Acc:99.75%
Training: Epoch[123/182] Iteration[300/352] Loss: 0.0096 Acc:99.77%
Training: Epoch[123/182] Iteration[350/352] Loss: 0.0095 Acc:99.78%
Training Progress:  67%|▋| 122/182 [38:06<18:35, 18.58s/it, Train Acc=99.78%, VaEpoch[123/182] Train Acc: 99.78% Valid Acc:92.74% Train loss:0.0095 Valid loss:0.3057 LR:0.010000000000000002
Training Progress:  68%|▋| 123/182 [38:06<18:15, 18.57s/it, Train Acc=99.78%, VaTraining: Epoch[124/182] Iteration[050/352] Loss: 0.0094 Acc:99.75%
Training: Epoch[124/182] Iteration[100/352] Loss: 0.0103 Acc:99.73%
Training: Epoch[124/182] Iteration[150/352] Loss: 0.0102 Acc:99.74%
Training: Epoch[124/182] Iteration[200/352] Loss: 0.0098 Acc:99.77%
Training: Epoch[124/182] Iteration[250/352] Loss: 0.0097 Acc:99.79%
Training: Epoch[124/182] Iteration[300/352] Loss: 0.0099 Acc:99.77%
Training: Epoch[124/182] Iteration[350/352] Loss: 0.0098 Acc:99.78%
Training Progress:  68%|▋| 123/182 [38:25<18:15, 18.57s/it, Train Acc=99.77%, VaEpoch[124/182] Train Acc: 99.77% Valid Acc:92.64% Train loss:0.0099 Valid loss:0.3175 LR:0.010000000000000002
Training Progress:  68%|▋| 124/182 [38:25<17:55, 18.55s/it, Train Acc=99.77%, VaTraining: Epoch[125/182] Iteration[050/352] Loss: 0.0124 Acc:99.64%
Training: Epoch[125/182] Iteration[100/352] Loss: 0.0116 Acc:99.68%
Training: Epoch[125/182] Iteration[150/352] Loss: 0.0107 Acc:99.72%
Training: Epoch[125/182] Iteration[200/352] Loss: 0.0103 Acc:99.76%
Training: Epoch[125/182] Iteration[250/352] Loss: 0.0102 Acc:99.76%
Training: Epoch[125/182] Iteration[300/352] Loss: 0.0104 Acc:99.75%
Training: Epoch[125/182] Iteration[350/352] Loss: 0.0105 Acc:99.74%
Training Progress:  68%|▋| 124/182 [38:43<17:55, 18.55s/it, Train Acc=99.74%, VaEpoch[125/182] Train Acc: 99.74% Valid Acc:92.92% Train loss:0.0107 Valid loss:0.3127 LR:0.010000000000000002
Training Progress:  69%|▋| 125/182 [38:43<17:36, 18.54s/it, Train Acc=99.74%, VaTraining: Epoch[126/182] Iteration[050/352] Loss: 0.0097 Acc:99.81%
Training: Epoch[126/182] Iteration[100/352] Loss: 0.0095 Acc:99.84%
Training: Epoch[126/182] Iteration[150/352] Loss: 0.0100 Acc:99.79%
Training: Epoch[126/182] Iteration[200/352] Loss: 0.0092 Acc:99.81%
Training: Epoch[126/182] Iteration[250/352] Loss: 0.0090 Acc:99.82%
Training: Epoch[126/182] Iteration[300/352] Loss: 0.0089 Acc:99.82%
Training: Epoch[126/182] Iteration[350/352] Loss: 0.0087 Acc:99.82%
Training Progress:  69%|▋| 125/182 [39:02<17:36, 18.54s/it, Train Acc=99.82%, VaEpoch[126/182] Train Acc: 99.82% Valid Acc:92.90% Train loss:0.0087 Valid loss:0.3156 LR:0.010000000000000002
Training Progress:  69%|▋| 126/182 [39:02<17:19, 18.56s/it, Train Acc=99.82%, VaTraining: Epoch[127/182] Iteration[050/352] Loss: 0.0076 Acc:99.86%
Training: Epoch[127/182] Iteration[100/352] Loss: 0.0078 Acc:99.84%
Training: Epoch[127/182] Iteration[150/352] Loss: 0.0079 Acc:99.82%
Training: Epoch[127/182] Iteration[200/352] Loss: 0.0082 Acc:99.82%
Training: Epoch[127/182] Iteration[250/352] Loss: 0.0086 Acc:99.81%
Training: Epoch[127/182] Iteration[300/352] Loss: 0.0085 Acc:99.81%
Training: Epoch[127/182] Iteration[350/352] Loss: 0.0086 Acc:99.80%
Training Progress:  69%|▋| 126/182 [39:20<17:19, 18.56s/it, Train Acc=99.80%, VaEpoch[127/182] Train Acc: 99.80% Valid Acc:92.64% Train loss:0.0086 Valid loss:0.3221 LR:0.010000000000000002
Training Progress:  70%|▋| 127/182 [39:20<16:59, 18.53s/it, Train Acc=99.80%, VaTraining: Epoch[128/182] Iteration[050/352] Loss: 0.0096 Acc:99.80%
Training: Epoch[128/182] Iteration[100/352] Loss: 0.0084 Acc:99.83%
Training: Epoch[128/182] Iteration[150/352] Loss: 0.0088 Acc:99.82%
Training: Epoch[128/182] Iteration[200/352] Loss: 0.0083 Acc:99.85%
Training: Epoch[128/182] Iteration[250/352] Loss: 0.0085 Acc:99.83%
Training: Epoch[128/182] Iteration[300/352] Loss: 0.0086 Acc:99.83%
Training: Epoch[128/182] Iteration[350/352] Loss: 0.0088 Acc:99.81%
Training Progress:  70%|▋| 127/182 [39:39<16:59, 18.53s/it, Train Acc=99.81%, VaEpoch[128/182] Train Acc: 99.81% Valid Acc:92.82% Train loss:0.0088 Valid loss:0.3210 LR:0.010000000000000002
Training Progress:  70%|▋| 128/182 [39:39<16:40, 18.52s/it, Train Acc=99.81%, VaTraining: Epoch[129/182] Iteration[050/352] Loss: 0.0097 Acc:99.78%
Training: Epoch[129/182] Iteration[100/352] Loss: 0.0088 Acc:99.80%
Training: Epoch[129/182] Iteration[150/352] Loss: 0.0087 Acc:99.83%
Training: Epoch[129/182] Iteration[200/352] Loss: 0.0084 Acc:99.83%
Training: Epoch[129/182] Iteration[250/352] Loss: 0.0086 Acc:99.81%
Training: Epoch[129/182] Iteration[300/352] Loss: 0.0085 Acc:99.82%
Training: Epoch[129/182] Iteration[350/352] Loss: 0.0085 Acc:99.81%
Training Progress:  70%|▋| 128/182 [39:57<16:40, 18.52s/it, Train Acc=99.81%, VaEpoch[129/182] Train Acc: 99.81% Valid Acc:92.80% Train loss:0.0085 Valid loss:0.3216 LR:0.010000000000000002
Training Progress:  71%|▋| 129/182 [39:57<16:21, 18.52s/it, Train Acc=99.81%, VaTraining: Epoch[130/182] Iteration[050/352] Loss: 0.0086 Acc:99.78%
Training: Epoch[130/182] Iteration[100/352] Loss: 0.0087 Acc:99.78%
Training: Epoch[130/182] Iteration[150/352] Loss: 0.0089 Acc:99.79%
Training: Epoch[130/182] Iteration[200/352] Loss: 0.0087 Acc:99.79%
Training: Epoch[130/182] Iteration[250/352] Loss: 0.0085 Acc:99.80%
Training: Epoch[130/182] Iteration[300/352] Loss: 0.0083 Acc:99.81%
Training: Epoch[130/182] Iteration[350/352] Loss: 0.0082 Acc:99.81%
Training Progress:  71%|▋| 129/182 [40:16<16:21, 18.52s/it, Train Acc=99.81%, VaEpoch[130/182] Train Acc: 99.81% Valid Acc:92.86% Train loss:0.0081 Valid loss:0.3191 LR:0.010000000000000002
Training Progress:  71%|▋| 130/182 [40:16<16:02, 18.51s/it, Train Acc=99.81%, VaTraining: Epoch[131/182] Iteration[050/352] Loss: 0.0058 Acc:99.94%
Training: Epoch[131/182] Iteration[100/352] Loss: 0.0067 Acc:99.87%
Training: Epoch[131/182] Iteration[150/352] Loss: 0.0072 Acc:99.85%
Training: Epoch[131/182] Iteration[200/352] Loss: 0.0075 Acc:99.86%
Training: Epoch[131/182] Iteration[250/352] Loss: 0.0075 Acc:99.85%
Training: Epoch[131/182] Iteration[300/352] Loss: 0.0078 Acc:99.84%
Training: Epoch[131/182] Iteration[350/352] Loss: 0.0077 Acc:99.84%
Training Progress:  71%|▋| 130/182 [40:34<16:02, 18.51s/it, Train Acc=99.84%, VaEpoch[131/182] Train Acc: 99.84% Valid Acc:92.80% Train loss:0.0077 Valid loss:0.3181 LR:0.010000000000000002
Training Progress:  72%|▋| 131/182 [40:34<15:45, 18.53s/it, Train Acc=99.84%, VaTraining: Epoch[132/182] Iteration[050/352] Loss: 0.0097 Acc:99.78%
Training: Epoch[132/182] Iteration[100/352] Loss: 0.0089 Acc:99.81%
Training: Epoch[132/182] Iteration[150/352] Loss: 0.0082 Acc:99.82%
Training: Epoch[132/182] Iteration[200/352] Loss: 0.0084 Acc:99.81%
Training: Epoch[132/182] Iteration[250/352] Loss: 0.0085 Acc:99.80%
Training: Epoch[132/182] Iteration[300/352] Loss: 0.0083 Acc:99.82%
Training: Epoch[132/182] Iteration[350/352] Loss: 0.0080 Acc:99.83%
Training Progress:  72%|▋| 131/182 [40:53<15:45, 18.53s/it, Train Acc=99.83%, VaEpoch[132/182] Train Acc: 99.83% Valid Acc:92.92% Train loss:0.0080 Valid loss:0.3194 LR:0.010000000000000002
Training Progress:  73%|▋| 132/182 [40:53<15:26, 18.53s/it, Train Acc=99.83%, VaTraining: Epoch[133/182] Iteration[050/352] Loss: 0.0076 Acc:99.83%
Training: Epoch[133/182] Iteration[100/352] Loss: 0.0085 Acc:99.80%
Training: Epoch[133/182] Iteration[150/352] Loss: 0.0079 Acc:99.81%
Training: Epoch[133/182] Iteration[200/352] Loss: 0.0078 Acc:99.81%
Training: Epoch[133/182] Iteration[250/352] Loss: 0.0079 Acc:99.82%
Training: Epoch[133/182] Iteration[300/352] Loss: 0.0076 Acc:99.83%
Training: Epoch[133/182] Iteration[350/352] Loss: 0.0076 Acc:99.83%
Training Progress:  73%|▋| 132/182 [41:12<15:26, 18.53s/it, Train Acc=99.83%, VaEpoch[133/182] Train Acc: 99.83% Valid Acc:92.78% Train loss:0.0076 Valid loss:0.3201 LR:0.010000000000000002
Training Progress:  73%|▋| 133/182 [41:12<15:08, 18.55s/it, Train Acc=99.83%, VaTraining: Epoch[134/182] Iteration[050/352] Loss: 0.0067 Acc:99.86%
Training: Epoch[134/182] Iteration[100/352] Loss: 0.0074 Acc:99.84%
Training: Epoch[134/182] Iteration[150/352] Loss: 0.0074 Acc:99.85%
Training: Epoch[134/182] Iteration[200/352] Loss: 0.0074 Acc:99.85%
Training: Epoch[134/182] Iteration[250/352] Loss: 0.0076 Acc:99.85%
Training: Epoch[134/182] Iteration[300/352] Loss: 0.0079 Acc:99.84%
Training: Epoch[134/182] Iteration[350/352] Loss: 0.0079 Acc:99.84%
Training Progress:  73%|▋| 133/182 [41:30<15:08, 18.55s/it, Train Acc=99.84%, VaEpoch[134/182] Train Acc: 99.84% Valid Acc:92.72% Train loss:0.0079 Valid loss:0.3262 LR:0.010000000000000002
Training Progress:  74%|▋| 134/182 [41:30<14:48, 18.50s/it, Train Acc=99.84%, VaTraining: Epoch[135/182] Iteration[050/352] Loss: 0.0063 Acc:99.89%
Training: Epoch[135/182] Iteration[100/352] Loss: 0.0071 Acc:99.87%
Training: Epoch[135/182] Iteration[150/352] Loss: 0.0070 Acc:99.88%
Training: Epoch[135/182] Iteration[200/352] Loss: 0.0074 Acc:99.85%
Training: Epoch[135/182] Iteration[250/352] Loss: 0.0071 Acc:99.87%
Training: Epoch[135/182] Iteration[300/352] Loss: 0.0070 Acc:99.87%
Training: Epoch[135/182] Iteration[350/352] Loss: 0.0071 Acc:99.87%
Training Progress:  74%|▋| 134/182 [41:48<14:48, 18.50s/it, Train Acc=99.87%, VaEpoch[135/182] Train Acc: 99.87% Valid Acc:92.72% Train loss:0.0071 Valid loss:0.3262 LR:0.010000000000000002
Training Progress:  74%|▋| 135/182 [41:48<14:28, 18.48s/it, Train Acc=99.87%, VaTraining: Epoch[136/182] Iteration[050/352] Loss: 0.0071 Acc:99.75%
Training: Epoch[136/182] Iteration[100/352] Loss: 0.0077 Acc:99.75%
Training: Epoch[136/182] Iteration[150/352] Loss: 0.0083 Acc:99.75%
Training: Epoch[136/182] Iteration[200/352] Loss: 0.0079 Acc:99.78%
Training: Epoch[136/182] Iteration[250/352] Loss: 0.0083 Acc:99.78%
Training: Epoch[136/182] Iteration[300/352] Loss: 0.0085 Acc:99.78%
Training: Epoch[136/182] Iteration[350/352] Loss: 0.0085 Acc:99.77%
Training Progress:  74%|▋| 135/182 [42:07<14:28, 18.48s/it, Train Acc=99.77%, VaEpoch[136/182] Train Acc: 99.77% Valid Acc:92.56% Train loss:0.0086 Valid loss:0.3261 LR:0.010000000000000002
Training Progress:  75%|▋| 136/182 [42:07<14:10, 18.49s/it, Train Acc=99.77%, VaTraining: Epoch[137/182] Iteration[050/352] Loss: 0.0069 Acc:99.88%
Training: Epoch[137/182] Iteration[100/352] Loss: 0.0064 Acc:99.87%
Training: Epoch[137/182] Iteration[150/352] Loss: 0.0067 Acc:99.87%
Training: Epoch[137/182] Iteration[200/352] Loss: 0.0068 Acc:99.86%
Training: Epoch[137/182] Iteration[250/352] Loss: 0.0067 Acc:99.86%
Training: Epoch[137/182] Iteration[300/352] Loss: 0.0068 Acc:99.86%
Training: Epoch[137/182] Iteration[350/352] Loss: 0.0070 Acc:99.85%
Training Progress:  75%|▋| 136/182 [42:25<14:10, 18.49s/it, Train Acc=99.85%, VaEpoch[137/182] Train Acc: 99.85% Valid Acc:92.74% Train loss:0.0070 Valid loss:0.3230 LR:0.0010000000000000002
Training Progress:  75%|▊| 137/182 [42:25<13:54, 18.54s/it, Train Acc=99.85%, VaTraining: Epoch[138/182] Iteration[050/352] Loss: 0.0063 Acc:99.89%
Training: Epoch[138/182] Iteration[100/352] Loss: 0.0066 Acc:99.90%
Training: Epoch[138/182] Iteration[150/352] Loss: 0.0064 Acc:99.92%
Training: Epoch[138/182] Iteration[200/352] Loss: 0.0068 Acc:99.89%
Training: Epoch[138/182] Iteration[250/352] Loss: 0.0067 Acc:99.90%
Training: Epoch[138/182] Iteration[300/352] Loss: 0.0067 Acc:99.89%
Training: Epoch[138/182] Iteration[350/352] Loss: 0.0065 Acc:99.90%
Training Progress:  75%|▊| 137/182 [42:44<13:54, 18.54s/it, Train Acc=99.90%, VaEpoch[138/182] Train Acc: 99.90% Valid Acc:92.76% Train loss:0.0065 Valid loss:0.3221 LR:0.0010000000000000002
Training Progress:  76%|▊| 138/182 [42:44<13:36, 18.56s/it, Train Acc=99.90%, VaTraining: Epoch[139/182] Iteration[050/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[139/182] Iteration[100/352] Loss: 0.0058 Acc:99.88%
Training: Epoch[139/182] Iteration[150/352] Loss: 0.0062 Acc:99.85%
Training: Epoch[139/182] Iteration[200/352] Loss: 0.0063 Acc:99.86%
Training: Epoch[139/182] Iteration[250/352] Loss: 0.0066 Acc:99.86%
Training: Epoch[139/182] Iteration[300/352] Loss: 0.0064 Acc:99.87%
Training: Epoch[139/182] Iteration[350/352] Loss: 0.0063 Acc:99.88%
Training Progress:  76%|▊| 138/182 [43:03<13:36, 18.56s/it, Train Acc=99.88%, VaEpoch[139/182] Train Acc: 99.88% Valid Acc:92.86% Train loss:0.0063 Valid loss:0.3236 LR:0.0010000000000000002
Training Progress:  76%|▊| 139/182 [43:03<13:17, 18.55s/it, Train Acc=99.88%, VaTraining: Epoch[140/182] Iteration[050/352] Loss: 0.0064 Acc:99.89%
Training: Epoch[140/182] Iteration[100/352] Loss: 0.0063 Acc:99.88%
Training: Epoch[140/182] Iteration[150/352] Loss: 0.0064 Acc:99.87%
Training: Epoch[140/182] Iteration[200/352] Loss: 0.0062 Acc:99.88%
Training: Epoch[140/182] Iteration[250/352] Loss: 0.0062 Acc:99.90%
Training: Epoch[140/182] Iteration[300/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[140/182] Iteration[350/352] Loss: 0.0060 Acc:99.90%
Training Progress:  76%|▊| 139/182 [43:21<13:17, 18.55s/it, Train Acc=99.90%, VaEpoch[140/182] Train Acc: 99.90% Valid Acc:92.74% Train loss:0.0060 Valid loss:0.3191 LR:0.0010000000000000002
Training Progress:  77%|▊| 140/182 [43:21<12:58, 18.53s/it, Train Acc=99.90%, VaTraining: Epoch[141/182] Iteration[050/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[141/182] Iteration[100/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[141/182] Iteration[150/352] Loss: 0.0057 Acc:99.92%
Training: Epoch[141/182] Iteration[200/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[141/182] Iteration[250/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[141/182] Iteration[300/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[141/182] Iteration[350/352] Loss: 0.0057 Acc:99.90%
Training Progress:  77%|▊| 140/182 [43:40<12:58, 18.53s/it, Train Acc=99.89%, VaEpoch[141/182] Train Acc: 99.89% Valid Acc:92.86% Train loss:0.0058 Valid loss:0.3219 LR:0.0010000000000000002
Training Progress:  77%|▊| 141/182 [43:40<12:39, 18.52s/it, Train Acc=99.89%, VaTraining: Epoch[142/182] Iteration[050/352] Loss: 0.0055 Acc:99.89%
Training: Epoch[142/182] Iteration[100/352] Loss: 0.0054 Acc:99.88%
Training: Epoch[142/182] Iteration[150/352] Loss: 0.0057 Acc:99.88%
Training: Epoch[142/182] Iteration[200/352] Loss: 0.0060 Acc:99.87%
Training: Epoch[142/182] Iteration[250/352] Loss: 0.0061 Acc:99.87%
Training: Epoch[142/182] Iteration[300/352] Loss: 0.0061 Acc:99.88%
Training: Epoch[142/182] Iteration[350/352] Loss: 0.0061 Acc:99.88%
Training Progress:  77%|▊| 141/182 [43:58<12:39, 18.52s/it, Train Acc=99.88%, VaEpoch[142/182] Train Acc: 99.88% Valid Acc:92.78% Train loss:0.0061 Valid loss:0.3206 LR:0.0010000000000000002
Training Progress:  78%|▊| 142/182 [43:58<12:22, 18.56s/it, Train Acc=99.88%, VaTraining: Epoch[143/182] Iteration[050/352] Loss: 0.0070 Acc:99.83%
Training: Epoch[143/182] Iteration[100/352] Loss: 0.0060 Acc:99.87%
Training: Epoch[143/182] Iteration[150/352] Loss: 0.0061 Acc:99.85%
Training: Epoch[143/182] Iteration[200/352] Loss: 0.0060 Acc:99.87%
Training: Epoch[143/182] Iteration[250/352] Loss: 0.0061 Acc:99.87%
Training: Epoch[143/182] Iteration[300/352] Loss: 0.0059 Acc:99.88%
Training: Epoch[143/182] Iteration[350/352] Loss: 0.0060 Acc:99.87%
Training Progress:  78%|▊| 142/182 [44:17<12:22, 18.56s/it, Train Acc=99.87%, VaEpoch[143/182] Train Acc: 99.87% Valid Acc:92.72% Train loss:0.0060 Valid loss:0.3203 LR:0.0010000000000000002
Training Progress:  79%|▊| 143/182 [44:17<12:04, 18.56s/it, Train Acc=99.87%, VaTraining: Epoch[144/182] Iteration[050/352] Loss: 0.0065 Acc:99.84%
Training: Epoch[144/182] Iteration[100/352] Loss: 0.0062 Acc:99.87%
Training: Epoch[144/182] Iteration[150/352] Loss: 0.0058 Acc:99.89%
Training: Epoch[144/182] Iteration[200/352] Loss: 0.0057 Acc:99.89%
Training: Epoch[144/182] Iteration[250/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[144/182] Iteration[300/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[144/182] Iteration[350/352] Loss: 0.0057 Acc:99.90%
Training Progress:  79%|▊| 143/182 [44:35<12:04, 18.56s/it, Train Acc=99.90%, VaEpoch[144/182] Train Acc: 99.90% Valid Acc:92.92% Train loss:0.0057 Valid loss:0.3214 LR:0.0010000000000000002
Training Progress:  79%|▊| 144/182 [44:35<11:43, 18.53s/it, Train Acc=99.90%, VaTraining: Epoch[145/182] Iteration[050/352] Loss: 0.0062 Acc:99.86%
Training: Epoch[145/182] Iteration[100/352] Loss: 0.0063 Acc:99.85%
Training: Epoch[145/182] Iteration[150/352] Loss: 0.0061 Acc:99.86%
Training: Epoch[145/182] Iteration[200/352] Loss: 0.0059 Acc:99.88%
Training: Epoch[145/182] Iteration[250/352] Loss: 0.0059 Acc:99.89%
Training: Epoch[145/182] Iteration[300/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[145/182] Iteration[350/352] Loss: 0.0058 Acc:99.90%
Training Progress:  79%|▊| 144/182 [44:54<11:43, 18.53s/it, Train Acc=99.90%, VaEpoch[145/182] Train Acc: 99.90% Valid Acc:92.76% Train loss:0.0057 Valid loss:0.3215 LR:0.0010000000000000002
Training Progress:  80%|▊| 145/182 [44:54<11:24, 18.51s/it, Train Acc=99.90%, VaTraining: Epoch[146/182] Iteration[050/352] Loss: 0.0062 Acc:99.86%
Training: Epoch[146/182] Iteration[100/352] Loss: 0.0059 Acc:99.89%
Training: Epoch[146/182] Iteration[150/352] Loss: 0.0059 Acc:99.91%
Training: Epoch[146/182] Iteration[200/352] Loss: 0.0058 Acc:99.91%
Training: Epoch[146/182] Iteration[250/352] Loss: 0.0059 Acc:99.90%
Training: Epoch[146/182] Iteration[300/352] Loss: 0.0058 Acc:99.90%
Training: Epoch[146/182] Iteration[350/352] Loss: 0.0057 Acc:99.91%
Training Progress:  80%|▊| 145/182 [45:12<11:24, 18.51s/it, Train Acc=99.91%, VaEpoch[146/182] Train Acc: 99.91% Valid Acc:92.76% Train loss:0.0057 Valid loss:0.3229 LR:0.0010000000000000002
Training Progress:  80%|▊| 146/182 [45:12<11:06, 18.51s/it, Train Acc=99.91%, VaTraining: Epoch[147/182] Iteration[050/352] Loss: 0.0057 Acc:99.89%
Training: Epoch[147/182] Iteration[100/352] Loss: 0.0060 Acc:99.88%
Training: Epoch[147/182] Iteration[150/352] Loss: 0.0057 Acc:99.89%
Training: Epoch[147/182] Iteration[200/352] Loss: 0.0060 Acc:99.88%
Training: Epoch[147/182] Iteration[250/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[147/182] Iteration[300/352] Loss: 0.0057 Acc:99.90%
Training: Epoch[147/182] Iteration[350/352] Loss: 0.0056 Acc:99.90%
Training Progress:  80%|▊| 146/182 [45:31<11:06, 18.51s/it, Train Acc=99.90%, VaEpoch[147/182] Train Acc: 99.90% Valid Acc:92.78% Train loss:0.0056 Valid loss:0.3194 LR:0.0010000000000000002
Training Progress:  81%|▊| 147/182 [45:31<10:48, 18.52s/it, Train Acc=99.90%, VaTraining: Epoch[148/182] Iteration[050/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[148/182] Iteration[100/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[148/182] Iteration[150/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[148/182] Iteration[200/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[148/182] Iteration[250/352] Loss: 0.0054 Acc:99.90%
Training: Epoch[148/182] Iteration[300/352] Loss: 0.0054 Acc:99.90%
Training: Epoch[148/182] Iteration[350/352] Loss: 0.0054 Acc:99.90%
Training Progress:  81%|▊| 147/182 [45:49<10:48, 18.52s/it, Train Acc=99.90%, VaEpoch[148/182] Train Acc: 99.90% Valid Acc:92.82% Train loss:0.0054 Valid loss:0.3215 LR:0.0010000000000000002
Training Progress:  81%|▊| 148/182 [45:49<10:30, 18.54s/it, Train Acc=99.90%, VaTraining: Epoch[149/182] Iteration[050/352] Loss: 0.0052 Acc:99.89%
Training: Epoch[149/182] Iteration[100/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[149/182] Iteration[150/352] Loss: 0.0055 Acc:99.92%
Training: Epoch[149/182] Iteration[200/352] Loss: 0.0055 Acc:99.92%
Training: Epoch[149/182] Iteration[250/352] Loss: 0.0058 Acc:99.91%
Training: Epoch[149/182] Iteration[300/352] Loss: 0.0059 Acc:99.90%
Training: Epoch[149/182] Iteration[350/352] Loss: 0.0059 Acc:99.90%
Training Progress:  81%|▊| 148/182 [46:09<10:30, 18.54s/it, Train Acc=99.90%, VaEpoch[149/182] Train Acc: 99.90% Valid Acc:92.82% Train loss:0.0060 Valid loss:0.3223 LR:0.0010000000000000002
Training Progress:  82%|▊| 149/182 [46:09<10:25, 18.95s/it, Train Acc=99.90%, VaTraining: Epoch[150/182] Iteration[050/352] Loss: 0.0046 Acc:99.92%
Training: Epoch[150/182] Iteration[100/352] Loss: 0.0047 Acc:99.94%
Training: Epoch[150/182] Iteration[150/352] Loss: 0.0049 Acc:99.94%
Training: Epoch[150/182] Iteration[200/352] Loss: 0.0053 Acc:99.92%
Training: Epoch[150/182] Iteration[250/352] Loss: 0.0053 Acc:99.92%
Training: Epoch[150/182] Iteration[300/352] Loss: 0.0055 Acc:99.91%
Training: Epoch[150/182] Iteration[350/352] Loss: 0.0055 Acc:99.91%
Training Progress:  82%|▊| 149/182 [46:35<10:25, 18.95s/it, Train Acc=99.91%, VaEpoch[150/182] Train Acc: 99.91% Valid Acc:92.92% Train loss:0.0055 Valid loss:0.3189 LR:0.0010000000000000002
Training Progress:  82%|▊| 150/182 [46:35<11:15, 21.10s/it, Train Acc=99.91%, VaTraining: Epoch[151/182] Iteration[050/352] Loss: 0.0047 Acc:99.92%
Training: Epoch[151/182] Iteration[100/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[151/182] Iteration[150/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[151/182] Iteration[200/352] Loss: 0.0053 Acc:99.92%
Training: Epoch[151/182] Iteration[250/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[151/182] Iteration[300/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[151/182] Iteration[350/352] Loss: 0.0056 Acc:99.92%
Training Progress:  82%|▊| 150/182 [46:56<11:15, 21.10s/it, Train Acc=99.92%, VaEpoch[151/182] Train Acc: 99.92% Valid Acc:92.84% Train loss:0.0056 Valid loss:0.3184 LR:0.0010000000000000002
Training Progress:  83%|▊| 151/182 [46:56<10:48, 20.93s/it, Train Acc=99.92%, VaTraining: Epoch[152/182] Iteration[050/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[152/182] Iteration[100/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[152/182] Iteration[150/352] Loss: 0.0049 Acc:99.93%
Training: Epoch[152/182] Iteration[200/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[152/182] Iteration[250/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[152/182] Iteration[300/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[152/182] Iteration[350/352] Loss: 0.0050 Acc:99.93%
Training Progress:  83%|▊| 151/182 [47:14<10:48, 20.93s/it, Train Acc=99.93%, VaEpoch[152/182] Train Acc: 99.93% Valid Acc:92.72% Train loss:0.0050 Valid loss:0.3208 LR:0.0010000000000000002
Training Progress:  84%|▊| 152/182 [47:14<10:04, 20.16s/it, Train Acc=99.93%, VaTraining: Epoch[153/182] Iteration[050/352] Loss: 0.0054 Acc:99.92%
Training: Epoch[153/182] Iteration[100/352] Loss: 0.0054 Acc:99.91%
Training: Epoch[153/182] Iteration[150/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[153/182] Iteration[200/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[153/182] Iteration[250/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[153/182] Iteration[300/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[153/182] Iteration[350/352] Loss: 0.0052 Acc:99.91%
Training Progress:  84%|▊| 152/182 [47:38<10:04, 20.16s/it, Train Acc=99.91%, VaEpoch[153/182] Train Acc: 99.91% Valid Acc:92.78% Train loss:0.0052 Valid loss:0.3197 LR:0.0010000000000000002
Training Progress:  84%|▊| 153/182 [47:38<10:12, 21.13s/it, Train Acc=99.91%, VaTraining: Epoch[154/182] Iteration[050/352] Loss: 0.0049 Acc:99.95%
Training: Epoch[154/182] Iteration[100/352] Loss: 0.0045 Acc:99.98%
Training: Epoch[154/182] Iteration[150/352] Loss: 0.0050 Acc:99.95%
Training: Epoch[154/182] Iteration[200/352] Loss: 0.0048 Acc:99.96%
Training: Epoch[154/182] Iteration[250/352] Loss: 0.0047 Acc:99.97%
Training: Epoch[154/182] Iteration[300/352] Loss: 0.0048 Acc:99.96%
Training: Epoch[154/182] Iteration[350/352] Loss: 0.0048 Acc:99.95%
Training Progress:  84%|▊| 153/182 [47:58<10:12, 21.13s/it, Train Acc=99.95%, VaEpoch[154/182] Train Acc: 99.95% Valid Acc:92.66% Train loss:0.0048 Valid loss:0.3184 LR:0.0010000000000000002
Training Progress:  85%|▊| 154/182 [47:58<09:44, 20.89s/it, Train Acc=99.95%, VaTraining: Epoch[155/182] Iteration[050/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[155/182] Iteration[100/352] Loss: 0.0043 Acc:99.95%
Training: Epoch[155/182] Iteration[150/352] Loss: 0.0048 Acc:99.94%
Training: Epoch[155/182] Iteration[200/352] Loss: 0.0053 Acc:99.92%
Training: Epoch[155/182] Iteration[250/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[155/182] Iteration[300/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[155/182] Iteration[350/352] Loss: 0.0052 Acc:99.92%
Training Progress:  85%|▊| 154/182 [48:17<09:44, 20.89s/it, Train Acc=99.92%, VaEpoch[155/182] Train Acc: 99.92% Valid Acc:92.82% Train loss:0.0052 Valid loss:0.3197 LR:0.0010000000000000002
Training Progress:  85%|▊| 155/182 [48:17<09:07, 20.27s/it, Train Acc=99.92%, VaTraining: Epoch[156/182] Iteration[050/352] Loss: 0.0052 Acc:99.89%
Training: Epoch[156/182] Iteration[100/352] Loss: 0.0054 Acc:99.90%
Training: Epoch[156/182] Iteration[150/352] Loss: 0.0056 Acc:99.90%
Training: Epoch[156/182] Iteration[200/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[156/182] Iteration[250/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[156/182] Iteration[300/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[156/182] Iteration[350/352] Loss: 0.0054 Acc:99.91%
Training Progress:  85%|▊| 155/182 [48:35<09:07, 20.27s/it, Train Acc=99.91%, VaEpoch[156/182] Train Acc: 99.91% Valid Acc:92.68% Train loss:0.0054 Valid loss:0.3193 LR:0.0010000000000000002
Training Progress:  86%|▊| 156/182 [48:35<08:32, 19.71s/it, Train Acc=99.91%, VaTraining: Epoch[157/182] Iteration[050/352] Loss: 0.0050 Acc:99.94%
Training: Epoch[157/182] Iteration[100/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[157/182] Iteration[150/352] Loss: 0.0056 Acc:99.90%
Training: Epoch[157/182] Iteration[200/352] Loss: 0.0055 Acc:99.91%
Training: Epoch[157/182] Iteration[250/352] Loss: 0.0056 Acc:99.90%
Training: Epoch[157/182] Iteration[300/352] Loss: 0.0056 Acc:99.90%
Training: Epoch[157/182] Iteration[350/352] Loss: 0.0056 Acc:99.90%
Training Progress:  86%|▊| 156/182 [48:54<08:32, 19.71s/it, Train Acc=99.90%, VaEpoch[157/182] Train Acc: 99.90% Valid Acc:92.76% Train loss:0.0055 Valid loss:0.3194 LR:0.0010000000000000002
Training Progress:  86%|▊| 157/182 [48:54<08:03, 19.34s/it, Train Acc=99.90%, VaTraining: Epoch[158/182] Iteration[050/352] Loss: 0.0046 Acc:99.89%
Training: Epoch[158/182] Iteration[100/352] Loss: 0.0049 Acc:99.89%
Training: Epoch[158/182] Iteration[150/352] Loss: 0.0048 Acc:99.90%
Training: Epoch[158/182] Iteration[200/352] Loss: 0.0049 Acc:99.90%
Training: Epoch[158/182] Iteration[250/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[158/182] Iteration[300/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[158/182] Iteration[350/352] Loss: 0.0049 Acc:99.91%
Training Progress:  86%|▊| 157/182 [49:12<08:03, 19.34s/it, Train Acc=99.91%, VaEpoch[158/182] Train Acc: 99.91% Valid Acc:92.80% Train loss:0.0049 Valid loss:0.3184 LR:0.0010000000000000002
Training Progress:  87%|▊| 158/182 [49:12<07:39, 19.14s/it, Train Acc=99.91%, VaTraining: Epoch[159/182] Iteration[050/352] Loss: 0.0048 Acc:99.97%
Training: Epoch[159/182] Iteration[100/352] Loss: 0.0046 Acc:99.96%
Training: Epoch[159/182] Iteration[150/352] Loss: 0.0048 Acc:99.95%
Training: Epoch[159/182] Iteration[200/352] Loss: 0.0051 Acc:99.94%
Training: Epoch[159/182] Iteration[250/352] Loss: 0.0050 Acc:99.94%
Training: Epoch[159/182] Iteration[300/352] Loss: 0.0048 Acc:99.95%
Training: Epoch[159/182] Iteration[350/352] Loss: 0.0048 Acc:99.95%
Training Progress:  87%|▊| 158/182 [49:31<07:39, 19.14s/it, Train Acc=99.95%, VaEpoch[159/182] Train Acc: 99.95% Valid Acc:92.70% Train loss:0.0048 Valid loss:0.3203 LR:0.0010000000000000002
Training Progress:  87%|▊| 159/182 [49:31<07:15, 18.94s/it, Train Acc=99.95%, VaTraining: Epoch[160/182] Iteration[050/352] Loss: 0.0060 Acc:99.88%
Training: Epoch[160/182] Iteration[100/352] Loss: 0.0054 Acc:99.91%
Training: Epoch[160/182] Iteration[150/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[160/182] Iteration[200/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[160/182] Iteration[250/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[160/182] Iteration[300/352] Loss: 0.0052 Acc:99.89%
Training: Epoch[160/182] Iteration[350/352] Loss: 0.0053 Acc:99.89%
Training Progress:  87%|▊| 159/182 [49:49<07:15, 18.94s/it, Train Acc=99.89%, VaEpoch[160/182] Train Acc: 99.89% Valid Acc:92.78% Train loss:0.0053 Valid loss:0.3200 LR:0.0010000000000000002
Training Progress:  88%|▉| 160/182 [49:49<06:54, 18.83s/it, Train Acc=99.89%, VaTraining: Epoch[161/182] Iteration[050/352] Loss: 0.0040 Acc:99.97%
Training: Epoch[161/182] Iteration[100/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[161/182] Iteration[150/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[161/182] Iteration[200/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[161/182] Iteration[250/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[161/182] Iteration[300/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[161/182] Iteration[350/352] Loss: 0.0050 Acc:99.92%
Training Progress:  88%|▉| 160/182 [50:08<06:54, 18.83s/it, Train Acc=99.92%, VaEpoch[161/182] Train Acc: 99.92% Valid Acc:92.86% Train loss:0.0050 Valid loss:0.3211 LR:0.0010000000000000002
Training Progress:  88%|▉| 161/182 [50:08<06:33, 18.72s/it, Train Acc=99.92%, VaTraining: Epoch[162/182] Iteration[050/352] Loss: 0.0050 Acc:99.86%
Training: Epoch[162/182] Iteration[100/352] Loss: 0.0053 Acc:99.86%
Training: Epoch[162/182] Iteration[150/352] Loss: 0.0057 Acc:99.85%
Training: Epoch[162/182] Iteration[200/352] Loss: 0.0055 Acc:99.87%
Training: Epoch[162/182] Iteration[250/352] Loss: 0.0054 Acc:99.88%
Training: Epoch[162/182] Iteration[300/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[162/182] Iteration[350/352] Loss: 0.0052 Acc:99.89%
Training Progress:  88%|▉| 161/182 [50:26<06:33, 18.72s/it, Train Acc=99.89%, VaEpoch[162/182] Train Acc: 99.89% Valid Acc:92.64% Train loss:0.0052 Valid loss:0.3209 LR:0.0010000000000000002
Training Progress:  89%|▉| 162/182 [50:26<06:12, 18.63s/it, Train Acc=99.89%, VaTraining: Epoch[163/182] Iteration[050/352] Loss: 0.0056 Acc:99.89%
Training: Epoch[163/182] Iteration[100/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[163/182] Iteration[150/352] Loss: 0.0055 Acc:99.91%
Training: Epoch[163/182] Iteration[200/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[163/182] Iteration[250/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[163/182] Iteration[300/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[163/182] Iteration[350/352] Loss: 0.0052 Acc:99.92%
Training Progress:  89%|▉| 162/182 [50:45<06:12, 18.63s/it, Train Acc=99.92%, VaEpoch[163/182] Train Acc: 99.92% Valid Acc:92.84% Train loss:0.0052 Valid loss:0.3206 LR:0.0010000000000000002
Training Progress:  90%|▉| 163/182 [50:45<05:54, 18.64s/it, Train Acc=99.92%, VaTraining: Epoch[164/182] Iteration[050/352] Loss: 0.0056 Acc:99.91%
Training: Epoch[164/182] Iteration[100/352] Loss: 0.0056 Acc:99.90%
Training: Epoch[164/182] Iteration[150/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[164/182] Iteration[200/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[164/182] Iteration[250/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[164/182] Iteration[300/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[164/182] Iteration[350/352] Loss: 0.0050 Acc:99.92%
Training Progress:  90%|▉| 163/182 [51:04<05:54, 18.64s/it, Train Acc=99.92%, VaEpoch[164/182] Train Acc: 99.92% Valid Acc:92.78% Train loss:0.0050 Valid loss:0.3233 LR:0.0010000000000000002
Training Progress:  90%|▉| 164/182 [51:04<05:35, 18.62s/it, Train Acc=99.92%, VaTraining: Epoch[165/182] Iteration[050/352] Loss: 0.0050 Acc:99.91%
Training: Epoch[165/182] Iteration[100/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[165/182] Iteration[150/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[165/182] Iteration[200/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[165/182] Iteration[250/352] Loss: 0.0053 Acc:99.90%
Training: Epoch[165/182] Iteration[300/352] Loss: 0.0053 Acc:99.90%
Training: Epoch[165/182] Iteration[350/352] Loss: 0.0052 Acc:99.90%
Training Progress:  90%|▉| 164/182 [51:22<05:35, 18.62s/it, Train Acc=99.90%, VaEpoch[165/182] Train Acc: 99.90% Valid Acc:92.66% Train loss:0.0052 Valid loss:0.3237 LR:0.0010000000000000002
Training Progress:  91%|▉| 165/182 [51:22<05:17, 18.67s/it, Train Acc=99.90%, VaTraining: Epoch[166/182] Iteration[050/352] Loss: 0.0044 Acc:99.91%
Training: Epoch[166/182] Iteration[100/352] Loss: 0.0048 Acc:99.94%
Training: Epoch[166/182] Iteration[150/352] Loss: 0.0049 Acc:99.94%
Training: Epoch[166/182] Iteration[200/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[166/182] Iteration[250/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[166/182] Iteration[300/352] Loss: 0.0049 Acc:99.94%
Training: Epoch[166/182] Iteration[350/352] Loss: 0.0050 Acc:99.94%
Training Progress:  91%|▉| 165/182 [51:41<05:17, 18.67s/it, Train Acc=99.94%, VaEpoch[166/182] Train Acc: 99.94% Valid Acc:92.78% Train loss:0.0050 Valid loss:0.3242 LR:0.0010000000000000002
Training Progress:  91%|▉| 166/182 [51:41<04:58, 18.66s/it, Train Acc=99.94%, VaTraining: Epoch[167/182] Iteration[050/352] Loss: 0.0039 Acc:99.97%
Training: Epoch[167/182] Iteration[100/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[167/182] Iteration[150/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[167/182] Iteration[200/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[167/182] Iteration[250/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[167/182] Iteration[300/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[167/182] Iteration[350/352] Loss: 0.0051 Acc:99.92%
Training Progress:  91%|▉| 166/182 [52:00<04:58, 18.66s/it, Train Acc=99.92%, VaEpoch[167/182] Train Acc: 99.92% Valid Acc:92.72% Train loss:0.0051 Valid loss:0.3215 LR:0.0010000000000000002
Training Progress:  92%|▉| 167/182 [52:00<04:39, 18.62s/it, Train Acc=99.92%, VaTraining: Epoch[168/182] Iteration[050/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[168/182] Iteration[100/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[168/182] Iteration[150/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[168/182] Iteration[200/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[168/182] Iteration[250/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[168/182] Iteration[300/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[168/182] Iteration[350/352] Loss: 0.0046 Acc:99.94%
Training Progress:  92%|▉| 167/182 [52:18<04:39, 18.62s/it, Train Acc=99.94%, VaEpoch[168/182] Train Acc: 99.94% Valid Acc:92.74% Train loss:0.0046 Valid loss:0.3193 LR:0.0010000000000000002
Training Progress:  92%|▉| 168/182 [52:18<04:20, 18.59s/it, Train Acc=99.94%, VaTraining: Epoch[169/182] Iteration[050/352] Loss: 0.0038 Acc:99.97%
Training: Epoch[169/182] Iteration[100/352] Loss: 0.0041 Acc:99.96%
Training: Epoch[169/182] Iteration[150/352] Loss: 0.0043 Acc:99.96%
Training: Epoch[169/182] Iteration[200/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[169/182] Iteration[250/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[169/182] Iteration[300/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[169/182] Iteration[350/352] Loss: 0.0046 Acc:99.94%
Training Progress:  92%|▉| 168/182 [52:37<04:20, 18.59s/it, Train Acc=99.94%, VaEpoch[169/182] Train Acc: 99.94% Valid Acc:92.72% Train loss:0.0046 Valid loss:0.3194 LR:0.0010000000000000002
Training Progress:  93%|▉| 169/182 [52:37<04:01, 18.57s/it, Train Acc=99.94%, VaTraining: Epoch[170/182] Iteration[050/352] Loss: 0.0041 Acc:99.95%
Training: Epoch[170/182] Iteration[100/352] Loss: 0.0047 Acc:99.96%
Training: Epoch[170/182] Iteration[150/352] Loss: 0.0050 Acc:99.94%
Training: Epoch[170/182] Iteration[200/352] Loss: 0.0053 Acc:99.92%
Training: Epoch[170/182] Iteration[250/352] Loss: 0.0052 Acc:99.92%
Training: Epoch[170/182] Iteration[300/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[170/182] Iteration[350/352] Loss: 0.0052 Acc:99.92%
Training Progress:  93%|▉| 169/182 [52:55<04:01, 18.57s/it, Train Acc=99.92%, VaEpoch[170/182] Train Acc: 99.92% Valid Acc:92.88% Train loss:0.0052 Valid loss:0.3210 LR:0.0010000000000000002
Training Progress:  93%|▉| 170/182 [52:55<03:43, 18.60s/it, Train Acc=99.92%, VaTraining: Epoch[171/182] Iteration[050/352] Loss: 0.0056 Acc:99.88%
Training: Epoch[171/182] Iteration[100/352] Loss: 0.0053 Acc:99.90%
Training: Epoch[171/182] Iteration[150/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[171/182] Iteration[200/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[171/182] Iteration[250/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[171/182] Iteration[300/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[171/182] Iteration[350/352] Loss: 0.0050 Acc:99.92%
Training Progress:  93%|▉| 170/182 [53:14<03:43, 18.60s/it, Train Acc=99.92%, VaEpoch[171/182] Train Acc: 99.92% Valid Acc:92.86% Train loss:0.0050 Valid loss:0.3225 LR:0.0010000000000000002
Training Progress:  94%|▉| 171/182 [53:14<03:24, 18.57s/it, Train Acc=99.92%, VaTraining: Epoch[172/182] Iteration[050/352] Loss: 0.0060 Acc:99.94%
Training: Epoch[172/182] Iteration[100/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[172/182] Iteration[150/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[172/182] Iteration[200/352] Loss: 0.0054 Acc:99.89%
Training: Epoch[172/182] Iteration[250/352] Loss: 0.0055 Acc:99.89%
Training: Epoch[172/182] Iteration[300/352] Loss: 0.0053 Acc:99.90%
Training: Epoch[172/182] Iteration[350/352] Loss: 0.0052 Acc:99.90%
Training Progress:  94%|▉| 171/182 [53:32<03:24, 18.57s/it, Train Acc=99.90%, VaEpoch[172/182] Train Acc: 99.90% Valid Acc:92.74% Train loss:0.0052 Valid loss:0.3205 LR:0.0010000000000000002
Training Progress:  95%|▉| 172/182 [53:32<03:05, 18.55s/it, Train Acc=99.90%, VaTraining: Epoch[173/182] Iteration[050/352] Loss: 0.0060 Acc:99.83%
Training: Epoch[173/182] Iteration[100/352] Loss: 0.0051 Acc:99.88%
Training: Epoch[173/182] Iteration[150/352] Loss: 0.0050 Acc:99.89%
Training: Epoch[173/182] Iteration[200/352] Loss: 0.0050 Acc:99.90%
Training: Epoch[173/182] Iteration[250/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[173/182] Iteration[300/352] Loss: 0.0050 Acc:99.91%
Training: Epoch[173/182] Iteration[350/352] Loss: 0.0049 Acc:99.92%
Training Progress:  95%|▉| 172/182 [53:51<03:05, 18.55s/it, Train Acc=99.92%, VaEpoch[173/182] Train Acc: 99.92% Valid Acc:92.78% Train loss:0.0049 Valid loss:0.3200 LR:0.0010000000000000002
Training Progress:  95%|▉| 173/182 [53:51<02:46, 18.54s/it, Train Acc=99.92%, VaTraining: Epoch[174/182] Iteration[050/352] Loss: 0.0055 Acc:99.92%
Training: Epoch[174/182] Iteration[100/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[174/182] Iteration[150/352] Loss: 0.0051 Acc:99.90%
Training: Epoch[174/182] Iteration[200/352] Loss: 0.0050 Acc:99.90%
Training: Epoch[174/182] Iteration[250/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[174/182] Iteration[300/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[174/182] Iteration[350/352] Loss: 0.0049 Acc:99.92%
Training Progress:  95%|▉| 173/182 [54:09<02:46, 18.54s/it, Train Acc=99.92%, VaEpoch[174/182] Train Acc: 99.92% Valid Acc:92.68% Train loss:0.0049 Valid loss:0.3174 LR:0.0010000000000000002
Training Progress:  96%|▉| 174/182 [54:09<02:28, 18.53s/it, Train Acc=99.92%, VaTraining: Epoch[175/182] Iteration[050/352] Loss: 0.0044 Acc:99.94%
Training: Epoch[175/182] Iteration[100/352] Loss: 0.0043 Acc:99.95%
Training: Epoch[175/182] Iteration[150/352] Loss: 0.0043 Acc:99.94%
Training: Epoch[175/182] Iteration[200/352] Loss: 0.0044 Acc:99.95%
Training: Epoch[175/182] Iteration[250/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[175/182] Iteration[300/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[175/182] Iteration[350/352] Loss: 0.0048 Acc:99.93%
Training Progress:  96%|▉| 174/182 [54:28<02:28, 18.53s/it, Train Acc=99.93%, VaEpoch[175/182] Train Acc: 99.93% Valid Acc:92.74% Train loss:0.0048 Valid loss:0.3201 LR:0.0010000000000000002
Training Progress:  96%|▉| 175/182 [54:28<02:09, 18.53s/it, Train Acc=99.93%, VaTraining: Epoch[176/182] Iteration[050/352] Loss: 0.0044 Acc:99.91%
Training: Epoch[176/182] Iteration[100/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[176/182] Iteration[150/352] Loss: 0.0051 Acc:99.90%
Training: Epoch[176/182] Iteration[200/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[176/182] Iteration[250/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[176/182] Iteration[300/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[176/182] Iteration[350/352] Loss: 0.0049 Acc:99.93%
Training Progress:  96%|▉| 175/182 [54:46<02:09, 18.53s/it, Train Acc=99.93%, VaEpoch[176/182] Train Acc: 99.93% Valid Acc:92.78% Train loss:0.0049 Valid loss:0.3212 LR:0.0010000000000000002
Training Progress:  97%|▉| 176/182 [54:46<01:51, 18.51s/it, Train Acc=99.93%, VaTraining: Epoch[177/182] Iteration[050/352] Loss: 0.0041 Acc:99.94%
Training: Epoch[177/182] Iteration[100/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[177/182] Iteration[150/352] Loss: 0.0043 Acc:99.94%
Training: Epoch[177/182] Iteration[200/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[177/182] Iteration[250/352] Loss: 0.0045 Acc:99.92%
Training: Epoch[177/182] Iteration[300/352] Loss: 0.0047 Acc:99.92%
Training: Epoch[177/182] Iteration[350/352] Loss: 0.0047 Acc:99.91%
Training Progress:  97%|▉| 176/182 [55:05<01:51, 18.51s/it, Train Acc=99.91%, VaEpoch[177/182] Train Acc: 99.91% Valid Acc:92.74% Train loss:0.0047 Valid loss:0.3202 LR:0.0010000000000000002
Training Progress:  97%|▉| 177/182 [55:05<01:32, 18.55s/it, Train Acc=99.91%, VaTraining: Epoch[178/182] Iteration[050/352] Loss: 0.0047 Acc:99.97%
Training: Epoch[178/182] Iteration[100/352] Loss: 0.0043 Acc:99.97%
Training: Epoch[178/182] Iteration[150/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[178/182] Iteration[200/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[178/182] Iteration[250/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[178/182] Iteration[300/352] Loss: 0.0045 Acc:99.95%
Training: Epoch[178/182] Iteration[350/352] Loss: 0.0044 Acc:99.94%
Training Progress:  97%|▉| 177/182 [55:24<01:32, 18.55s/it, Train Acc=99.94%, VaEpoch[178/182] Train Acc: 99.94% Valid Acc:92.64% Train loss:0.0044 Valid loss:0.3210 LR:0.0010000000000000002
Training Progress:  98%|▉| 178/182 [55:24<01:15, 18.85s/it, Train Acc=99.94%, VaTraining: Epoch[179/182] Iteration[050/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[179/182] Iteration[100/352] Loss: 0.0050 Acc:99.91%
Training: Epoch[179/182] Iteration[150/352] Loss: 0.0053 Acc:99.91%
Training: Epoch[179/182] Iteration[200/352] Loss: 0.0051 Acc:99.92%
Training: Epoch[179/182] Iteration[250/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[179/182] Iteration[300/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[179/182] Iteration[350/352] Loss: 0.0047 Acc:99.93%
Training Progress:  98%|▉| 178/182 [55:49<01:15, 18.85s/it, Train Acc=99.93%, VaEpoch[179/182] Train Acc: 99.93% Valid Acc:92.82% Train loss:0.0047 Valid loss:0.3197 LR:0.0010000000000000002
Training Progress:  98%|▉| 179/182 [55:49<01:01, 20.48s/it, Train Acc=99.93%, VaTraining: Epoch[180/182] Iteration[050/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[180/182] Iteration[100/352] Loss: 0.0046 Acc:99.92%
Training: Epoch[180/182] Iteration[150/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[180/182] Iteration[200/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[180/182] Iteration[250/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[180/182] Iteration[300/352] Loss: 0.0045 Acc:99.93%
Training: Epoch[180/182] Iteration[350/352] Loss: 0.0044 Acc:99.94%
Training Progress:  98%|▉| 179/182 [56:11<01:01, 20.48s/it, Train Acc=99.94%, VaEpoch[180/182] Train Acc: 99.94% Valid Acc:92.68% Train loss:0.0044 Valid loss:0.3257 LR:0.0010000000000000002
Training Progress:  99%|▉| 180/182 [56:11<00:41, 20.93s/it, Train Acc=99.94%, VaTraining: Epoch[181/182] Iteration[050/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[181/182] Iteration[100/352] Loss: 0.0045 Acc:99.94%
Training: Epoch[181/182] Iteration[150/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[181/182] Iteration[200/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[181/182] Iteration[250/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[181/182] Iteration[300/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[181/182] Iteration[350/352] Loss: 0.0049 Acc:99.92%
Training Progress:  99%|▉| 180/182 [56:31<00:41, 20.93s/it, Train Acc=99.92%, VaEpoch[181/182] Train Acc: 99.92% Valid Acc:92.66% Train loss:0.0049 Valid loss:0.3248 LR:0.0010000000000000002
Training Progress:  99%|▉| 181/182 [56:31<00:20, 20.70s/it, Train Acc=99.92%, VaTraining: Epoch[182/182] Iteration[050/352] Loss: 0.0049 Acc:99.95%
Training: Epoch[182/182] Iteration[100/352] Loss: 0.0050 Acc:99.93%
Training: Epoch[182/182] Iteration[150/352] Loss: 0.0047 Acc:99.94%
Training: Epoch[182/182] Iteration[200/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[182/182] Iteration[250/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[182/182] Iteration[300/352] Loss: 0.0047 Acc:99.94%
Training: Epoch[182/182] Iteration[350/352] Loss: 0.0047 Acc:99.93%
Training Progress:  99%|▉| 181/182 [56:51<00:20, 20.70s/it, Train Acc=99.93%, VaEpoch[182/182] Train Acc: 99.93% Valid Acc:92.78% Train loss:0.0047 Valid loss:0.3214 LR:0.0010000000000000002
class:plane     , total num:4508.0, correct num:4504.0  Recall: 99.91% Precision: 99.91%
class:car       , total num:4520.0, correct num:4517.0  Recall: 99.93% Precision: 99.98%
class:bird      , total num:4534.0, correct num:4533.0  Recall: 99.98% Precision: 99.93%
class:cat       , total num:4494.0, correct num:4487.0  Recall: 99.84% Precision: 99.93%
class:deer      , total num:4480.0, correct num:4477.0  Recall: 99.93% Precision: 99.93%
class:dog       , total num:4514.0, correct num:4510.0  Recall: 99.91% Precision: 99.86%
class:frog      , total num:4490.0, correct num:4489.0  Recall: 99.98% Precision: 99.98%
class:horse     , total num:4459.0, correct num:4457.0  Recall: 99.95% Precision: 99.93%
class:ship      , total num:4519.0, correct num:4517.0  Recall: 99.95% Precision: 99.95%
class:truck     , total num:4482.0, correct num:4479.0  Recall: 99.93% Precision: 99.91%
class:plane     , total num:492.0 , correct num:459.0  Recall: 93.27% Precision: 93.08%
class:car       , total num:480.0 , correct num:465.0  Recall: 96.85% Precision: 96.25%
class:bird      , total num:466.0 , correct num:414.0  Recall: 88.82% Precision: 91.57%
class:cat       , total num:506.0 , correct num:423.0  Recall: 83.58% Precision: 83.42%
class:deer      , total num:520.0 , correct num:485.0  Recall: 93.25% Precision: 93.79%
class:dog       , total num:486.0 , correct num:430.0  Recall: 88.46% Precision: 86.50%
class:frog      , total num:510.0 , correct num:483.0  Recall: 94.69% Precision: 94.69%
class:horse     , total num:541.0 , correct num:520.0  Recall: 96.10% Precision: 95.05%
class:ship      , total num:481.0 , correct num:459.0  Recall: 95.41% Precision: 96.41%
class:truck     , total num:518.0 , correct num:501.0  Recall: 96.70% Precision: 96.70%
Training Progress: 100%|█| 182/182 [56:52<00:00, 18.75s/it, Train Acc=99.93%, Va

================ Training Finished ================
Finished Time      : 05-18_14-48
Best Validation Acc: 0.93
Best Epoch         : 120
Best Test Acc      : 0.9264
Total Training Time: 3412.57 sec (56.88 min)
===================================================

Acknowledgments and References

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

↪Back to the content⤴