【Ubuntu 24.04.3】Quotient Network: experiments_on_cifar10 — resnet110

MSI Cyborg-15-A12VE

Acknowledgments and References

(quotient) wish@wish-Cyborg-15-A12VE:~/Quotient-Networks/experiments_on_cifar10$ python ./src/train.py --model resnet110
Training Progress:   0%|                                | 0/182 [00:00<?, ?it/s]Training: Epoch[001/182] Iteration[050/352] Loss: 2.6753 Acc:10.23%
Training: Epoch[001/182] Iteration[100/352] Loss: 2.4898 Acc:10.16%
Training: Epoch[001/182] Iteration[150/352] Loss: 2.4261 Acc:10.78%
Training: Epoch[001/182] Iteration[200/352] Loss: 2.3834 Acc:11.56%
Training: Epoch[001/182] Iteration[250/352] Loss: 2.3306 Acc:12.98%
Training: Epoch[001/182] Iteration[300/352] Loss: 2.2818 Acc:14.43%
Training: Epoch[001/182] Iteration[350/352] Loss: 2.2420 Acc:15.75%
Training Progress:   0%| | 0/182 [00:42<?, ?it/s, Train Acc=15.78%, Valid Acc=24Epoch[001/182] Train Acc: 15.78% Valid Acc:24.52% Train loss:2.2408 Valid loss:1.9685 LR:0.1
Training Progress:   1%| | 1/182 [00:42<2:08:21, 42.55s/it, Train Acc=15.78%, VaTraining: Epoch[002/182] Iteration[050/352] Loss: 1.9420 Acc:25.02%
Training: Epoch[002/182] Iteration[100/352] Loss: 1.9419 Acc:25.10%
Training: Epoch[002/182] Iteration[150/352] Loss: 1.9258 Acc:25.89%
Training: Epoch[002/182] Iteration[200/352] Loss: 1.9107 Acc:26.32%
Training: Epoch[002/182] Iteration[250/352] Loss: 1.8996 Acc:26.87%
Training: Epoch[002/182] Iteration[300/352] Loss: 1.8838 Acc:27.53%
Training: Epoch[002/182] Iteration[350/352] Loss: 1.8663 Acc:28.31%
Training Progress:   1%| | 1/182 [01:25<2:08:21, 42.55s/it, Train Acc=28.33%, VaEpoch[002/182] Train Acc: 28.33% Valid Acc:33.10% Train loss:1.8657 Valid loss:1.7678 LR:0.1
Training Progress:   1%| | 2/182 [01:25<2:07:43, 42.58s/it, Train Acc=28.33%, VaTraining: Epoch[003/182] Iteration[050/352] Loss: 1.7504 Acc:33.83%
Training: Epoch[003/182] Iteration[100/352] Loss: 1.7506 Acc:33.81%
Training: Epoch[003/182] Iteration[150/352] Loss: 1.7418 Acc:34.42%
Training: Epoch[003/182] Iteration[200/352] Loss: 1.7187 Acc:35.30%
Training: Epoch[003/182] Iteration[250/352] Loss: 1.7051 Acc:35.82%
Training: Epoch[003/182] Iteration[300/352] Loss: 1.6896 Acc:36.50%
Training: Epoch[003/182] Iteration[350/352] Loss: 1.6785 Acc:36.91%
Training Progress:   1%| | 2/182 [02:07<2:07:43, 42.58s/it, Train Acc=36.92%, VaEpoch[003/182] Train Acc: 36.92% Valid Acc:38.72% Train loss:1.6784 Valid loss:1.6787 LR:0.1
Training Progress:   2%| | 3/182 [02:07<2:07:09, 42.63s/it, Train Acc=36.92%, VaTraining: Epoch[004/182] Iteration[050/352] Loss: 1.5832 Acc:40.52%
Training: Epoch[004/182] Iteration[100/352] Loss: 1.5856 Acc:40.88%
Training: Epoch[004/182] Iteration[150/352] Loss: 1.5704 Acc:41.47%
Training: Epoch[004/182] Iteration[200/352] Loss: 1.5672 Acc:41.62%
Training: Epoch[004/182] Iteration[250/352] Loss: 1.5541 Acc:42.28%
Training: Epoch[004/182] Iteration[300/352] Loss: 1.5429 Acc:42.74%
Training: Epoch[004/182] Iteration[350/352] Loss: 1.5308 Acc:43.34%
Training Progress:   2%| | 3/182 [02:50<2:07:09, 42.63s/it, Train Acc=43.39%, VaEpoch[004/182] Train Acc: 43.39% Valid Acc:46.42% Train loss:1.5296 Valid loss:1.4563 LR:0.1
Training Progress:   2%| | 4/182 [02:50<2:06:41, 42.70s/it, Train Acc=43.39%, VaTraining: Epoch[005/182] Iteration[050/352] Loss: 1.4264 Acc:47.44%
Training: Epoch[005/182] Iteration[100/352] Loss: 1.4160 Acc:47.34%
Training: Epoch[005/182] Iteration[150/352] Loss: 1.4072 Acc:47.82%
Training: Epoch[005/182] Iteration[200/352] Loss: 1.3893 Acc:48.74%
Training: Epoch[005/182] Iteration[250/352] Loss: 1.3715 Acc:49.51%
Training: Epoch[005/182] Iteration[300/352] Loss: 1.3551 Acc:50.20%
Training: Epoch[005/182] Iteration[350/352] Loss: 1.3393 Acc:50.94%
Training Progress:   2%| | 4/182 [03:33<2:06:41, 42.70s/it, Train Acc=50.97%, VaEpoch[005/182] Train Acc: 50.97% Valid Acc:57.02% Train loss:1.3390 Valid loss:1.2019 LR:0.1
Training Progress:   3%| | 5/182 [03:33<2:06:12, 42.78s/it, Train Acc=50.97%, VaTraining: Epoch[006/182] Iteration[050/352] Loss: 1.2212 Acc:56.41%
Training: Epoch[006/182] Iteration[100/352] Loss: 1.1970 Acc:57.42%
Training: Epoch[006/182] Iteration[150/352] Loss: 1.1838 Acc:57.93%
Training: Epoch[006/182] Iteration[200/352] Loss: 1.1707 Acc:58.31%
Training: Epoch[006/182] Iteration[250/352] Loss: 1.1529 Acc:58.99%
Training: Epoch[006/182] Iteration[300/352] Loss: 1.1338 Acc:59.67%
Training: Epoch[006/182] Iteration[350/352] Loss: 1.1209 Acc:60.17%
Training Progress:   3%| | 5/182 [04:16<2:06:12, 42.78s/it, Train Acc=60.18%, VaEpoch[006/182] Train Acc: 60.18% Valid Acc:64.08% Train loss:1.1202 Valid loss:1.0393 LR:0.1
Training Progress:   3%| | 6/182 [04:16<2:05:41, 42.85s/it, Train Acc=60.18%, VaTraining: Epoch[007/182] Iteration[050/352] Loss: 0.9881 Acc:65.00%
Training: Epoch[007/182] Iteration[100/352] Loss: 0.9773 Acc:65.04%
Training: Epoch[007/182] Iteration[150/352] Loss: 0.9715 Acc:65.56%
Training: Epoch[007/182] Iteration[200/352] Loss: 0.9592 Acc:66.02%
Training: Epoch[007/182] Iteration[250/352] Loss: 0.9492 Acc:66.56%
Training: Epoch[007/182] Iteration[300/352] Loss: 0.9406 Acc:66.89%
Training: Epoch[007/182] Iteration[350/352] Loss: 0.9290 Acc:67.22%
Training Progress:   3%| | 6/182 [04:59<2:05:41, 42.85s/it, Train Acc=67.20%, VaEpoch[007/182] Train Acc: 67.20% Valid Acc:68.48% Train loss:0.9287 Valid loss:0.9286 LR:0.1
Training Progress:   4%| | 7/182 [04:59<2:05:12, 42.93s/it, Train Acc=67.20%, VaTraining: Epoch[008/182] Iteration[050/352] Loss: 0.7961 Acc:72.39%
Training: Epoch[008/182] Iteration[100/352] Loss: 0.8097 Acc:71.70%
Training: Epoch[008/182] Iteration[150/352] Loss: 0.8107 Acc:71.77%
Training: Epoch[008/182] Iteration[200/352] Loss: 0.8032 Acc:72.11%
Training: Epoch[008/182] Iteration[250/352] Loss: 0.7973 Acc:72.28%
Training: Epoch[008/182] Iteration[300/352] Loss: 0.7952 Acc:72.36%
Training: Epoch[008/182] Iteration[350/352] Loss: 0.7890 Acc:72.63%
Training Progress:   4%| | 7/182 [05:42<2:05:12, 42.93s/it, Train Acc=72.65%, VaEpoch[008/182] Train Acc: 72.65% Valid Acc:69.48% Train loss:0.7882 Valid loss:0.8864 LR:0.1
Training Progress:   4%| | 8/182 [05:42<2:04:41, 43.00s/it, Train Acc=72.65%, VaTraining: Epoch[009/182] Iteration[050/352] Loss: 0.7346 Acc:74.58%
Training: Epoch[009/182] Iteration[100/352] Loss: 0.7293 Acc:74.55%
Training: Epoch[009/182] Iteration[150/352] Loss: 0.7352 Acc:74.32%
Training: Epoch[009/182] Iteration[200/352] Loss: 0.7251 Acc:74.67%
Training: Epoch[009/182] Iteration[250/352] Loss: 0.7232 Acc:74.76%
Training: Epoch[009/182] Iteration[300/352] Loss: 0.7150 Acc:75.02%
Training: Epoch[009/182] Iteration[350/352] Loss: 0.7081 Acc:75.29%
Training Progress:   4%| | 8/182 [06:25<2:04:41, 43.00s/it, Train Acc=75.30%, VaEpoch[009/182] Train Acc: 75.30% Valid Acc:73.44% Train loss:0.7084 Valid loss:0.7813 LR:0.1
Training Progress:   5%| | 9/182 [06:25<2:04:07, 43.05s/it, Train Acc=75.30%, VaTraining: Epoch[010/182] Iteration[050/352] Loss: 0.6617 Acc:76.86%
Training: Epoch[010/182] Iteration[100/352] Loss: 0.6500 Acc:77.34%
Training: Epoch[010/182] Iteration[150/352] Loss: 0.6331 Acc:77.89%
Training: Epoch[010/182] Iteration[200/352] Loss: 0.6377 Acc:77.90%
Training: Epoch[010/182] Iteration[250/352] Loss: 0.6416 Acc:77.83%
Training: Epoch[010/182] Iteration[300/352] Loss: 0.6407 Acc:77.86%
Training: Epoch[010/182] Iteration[350/352] Loss: 0.6402 Acc:77.90%
Training Progress:   5%| | 9/182 [07:09<2:04:07, 43.05s/it, Train Acc=77.91%, VaEpoch[010/182] Train Acc: 77.91% Valid Acc:76.60% Train loss:0.6397 Valid loss:0.7045 LR:0.1
Training Progress:   5%| | 10/182 [07:09<2:03:31, 43.09s/it, Train Acc=77.91%, VTraining: Epoch[011/182] Iteration[050/352] Loss: 0.6009 Acc:79.28%
Training: Epoch[011/182] Iteration[100/352] Loss: 0.5974 Acc:79.25%
Training: Epoch[011/182] Iteration[150/352] Loss: 0.6030 Acc:79.06%
Training: Epoch[011/182] Iteration[200/352] Loss: 0.5941 Acc:79.41%
Training: Epoch[011/182] Iteration[250/352] Loss: 0.5921 Acc:79.52%
Training: Epoch[011/182] Iteration[300/352] Loss: 0.5911 Acc:79.50%
Training: Epoch[011/182] Iteration[350/352] Loss: 0.5856 Acc:79.74%
Training Progress:   5%| | 10/182 [07:52<2:03:31, 43.09s/it, Train Acc=79.77%, VEpoch[011/182] Train Acc: 79.77% Valid Acc:75.48% Train loss:0.5850 Valid loss:0.7670 LR:0.1
Training Progress:   6%| | 11/182 [07:52<2:02:51, 43.11s/it, Train Acc=79.77%, VTraining: Epoch[012/182] Iteration[050/352] Loss: 0.5349 Acc:81.52%
Training: Epoch[012/182] Iteration[100/352] Loss: 0.5524 Acc:81.13%
Training: Epoch[012/182] Iteration[150/352] Loss: 0.5460 Acc:81.20%
Training: Epoch[012/182] Iteration[200/352] Loss: 0.5396 Acc:81.45%
Training: Epoch[012/182] Iteration[250/352] Loss: 0.5434 Acc:81.31%
Training: Epoch[012/182] Iteration[300/352] Loss: 0.5426 Acc:81.28%
Training: Epoch[012/182] Iteration[350/352] Loss: 0.5437 Acc:81.15%
Training Progress:   6%| | 11/182 [08:35<2:02:51, 43.11s/it, Train Acc=81.16%, VEpoch[012/182] Train Acc: 81.16% Valid Acc:76.72% Train loss:0.5440 Valid loss:0.7036 LR:0.1
Training Progress:   7%| | 12/182 [08:35<2:02:15, 43.15s/it, Train Acc=81.16%, VTraining: Epoch[013/182] Iteration[050/352] Loss: 0.5022 Acc:82.20%
Training: Epoch[013/182] Iteration[100/352] Loss: 0.5139 Acc:81.97%
Training: Epoch[013/182] Iteration[150/352] Loss: 0.5138 Acc:81.96%
Training: Epoch[013/182] Iteration[200/352] Loss: 0.5116 Acc:82.20%
Training: Epoch[013/182] Iteration[250/352] Loss: 0.5111 Acc:82.36%
Training: Epoch[013/182] Iteration[300/352] Loss: 0.5176 Acc:82.13%
Training: Epoch[013/182] Iteration[350/352] Loss: 0.5153 Acc:82.21%
Training Progress:   7%| | 12/182 [09:18<2:02:15, 43.15s/it, Train Acc=82.22%, VEpoch[013/182] Train Acc: 82.22% Valid Acc:81.92% Train loss:0.5150 Valid loss:0.5453 LR:0.1
Training Progress:   7%| | 13/182 [09:18<2:01:38, 43.19s/it, Train Acc=82.22%, VTraining: Epoch[014/182] Iteration[050/352] Loss: 0.4714 Acc:83.36%
Training: Epoch[014/182] Iteration[100/352] Loss: 0.4704 Acc:83.59%
Training: Epoch[014/182] Iteration[150/352] Loss: 0.4746 Acc:83.46%
Training: Epoch[014/182] Iteration[200/352] Loss: 0.4758 Acc:83.45%
Training: Epoch[014/182] Iteration[250/352] Loss: 0.4773 Acc:83.32%
Training: Epoch[014/182] Iteration[300/352] Loss: 0.4825 Acc:83.19%
Training: Epoch[014/182] Iteration[350/352] Loss: 0.4794 Acc:83.33%
Training Progress:   7%| | 13/182 [10:02<2:01:38, 43.19s/it, Train Acc=83.32%, VEpoch[014/182] Train Acc: 83.32% Valid Acc:81.78% Train loss:0.4794 Valid loss:0.5506 LR:0.1
Training Progress:   8%| | 14/182 [10:02<2:01:01, 43.22s/it, Train Acc=83.32%, VTraining: Epoch[015/182] Iteration[050/352] Loss: 0.4542 Acc:84.30%
Training: Epoch[015/182] Iteration[100/352] Loss: 0.4529 Acc:84.27%
Training: Epoch[015/182] Iteration[150/352] Loss: 0.4480 Acc:84.38%
Training: Epoch[015/182] Iteration[200/352] Loss: 0.4463 Acc:84.44%
Training: Epoch[015/182] Iteration[250/352] Loss: 0.4522 Acc:84.23%
Training: Epoch[015/182] Iteration[300/352] Loss: 0.4498 Acc:84.36%
Training: Epoch[015/182] Iteration[350/352] Loss: 0.4524 Acc:84.24%
Training Progress:   8%| | 14/182 [10:45<2:01:01, 43.22s/it, Train Acc=84.24%, VEpoch[015/182] Train Acc: 84.24% Valid Acc:81.84% Train loss:0.4528 Valid loss:0.5850 LR:0.1
Training Progress:   8%| | 15/182 [10:45<2:00:21, 43.24s/it, Train Acc=84.24%, VTraining: Epoch[016/182] Iteration[050/352] Loss: 0.4122 Acc:86.02%
Training: Epoch[016/182] Iteration[100/352] Loss: 0.4107 Acc:85.99%
Training: Epoch[016/182] Iteration[150/352] Loss: 0.4156 Acc:85.78%
Training: Epoch[016/182] Iteration[200/352] Loss: 0.4222 Acc:85.64%
Training: Epoch[016/182] Iteration[250/352] Loss: 0.4206 Acc:85.70%
Training: Epoch[016/182] Iteration[300/352] Loss: 0.4202 Acc:85.61%
Training: Epoch[016/182] Iteration[350/352] Loss: 0.4250 Acc:85.40%
Training Progress:   8%| | 15/182 [11:28<2:00:21, 43.24s/it, Train Acc=85.38%, VEpoch[016/182] Train Acc: 85.38% Valid Acc:82.50% Train loss:0.4256 Valid loss:0.5519 LR:0.1
Training Progress:   9%| | 16/182 [11:28<1:59:42, 43.27s/it, Train Acc=85.38%, VTraining: Epoch[017/182] Iteration[050/352] Loss: 0.4064 Acc:85.89%
Training: Epoch[017/182] Iteration[100/352] Loss: 0.4110 Acc:85.77%
Training: Epoch[017/182] Iteration[150/352] Loss: 0.4105 Acc:85.63%
Training: Epoch[017/182] Iteration[200/352] Loss: 0.4154 Acc:85.57%
Training: Epoch[017/182] Iteration[250/352] Loss: 0.4114 Acc:85.67%
Training: Epoch[017/182] Iteration[300/352] Loss: 0.4129 Acc:85.68%
Training: Epoch[017/182] Iteration[350/352] Loss: 0.4121 Acc:85.72%
Training Progress:   9%| | 16/182 [12:12<1:59:42, 43.27s/it, Train Acc=85.72%, VEpoch[017/182] Train Acc: 85.72% Valid Acc:84.88% Train loss:0.4120 Valid loss:0.4565 LR:0.1
Training Progress:   9%| | 17/182 [12:12<1:59:03, 43.29s/it, Train Acc=85.72%, VTraining: Epoch[018/182] Iteration[050/352] Loss: 0.3817 Acc:86.78%
Training: Epoch[018/182] Iteration[100/352] Loss: 0.3870 Acc:86.73%
Training: Epoch[018/182] Iteration[150/352] Loss: 0.3921 Acc:86.55%
Training: Epoch[018/182] Iteration[200/352] Loss: 0.3947 Acc:86.44%
Training: Epoch[018/182] Iteration[250/352] Loss: 0.3913 Acc:86.58%
Training: Epoch[018/182] Iteration[300/352] Loss: 0.3917 Acc:86.57%
Training: Epoch[018/182] Iteration[350/352] Loss: 0.3941 Acc:86.47%
Training Progress:   9%| | 17/182 [12:55<1:59:03, 43.29s/it, Train Acc=86.46%, VEpoch[018/182] Train Acc: 86.46% Valid Acc:82.40% Train loss:0.3944 Valid loss:0.5460 LR:0.1
Training Progress:  10%| | 18/182 [12:55<1:58:36, 43.39s/it, Train Acc=86.46%, VTraining: Epoch[019/182] Iteration[050/352] Loss: 0.3621 Acc:87.14%
Training: Epoch[019/182] Iteration[100/352] Loss: 0.3798 Acc:86.60%
Training: Epoch[019/182] Iteration[150/352] Loss: 0.3747 Acc:86.77%
Training: Epoch[019/182] Iteration[200/352] Loss: 0.3746 Acc:86.79%
Training: Epoch[019/182] Iteration[250/352] Loss: 0.3756 Acc:86.86%
Training: Epoch[019/182] Iteration[300/352] Loss: 0.3743 Acc:86.88%
Training: Epoch[019/182] Iteration[350/352] Loss: 0.3767 Acc:86.80%
Training Progress:  10%| | 18/182 [13:38<1:58:36, 43.39s/it, Train Acc=86.79%, VEpoch[019/182] Train Acc: 86.79% Valid Acc:84.36% Train loss:0.3768 Valid loss:0.4733 LR:0.1
Training Progress:  10%| | 19/182 [13:38<1:57:47, 43.36s/it, Train Acc=86.79%, VTraining: Epoch[020/182] Iteration[050/352] Loss: 0.3449 Acc:88.02%
Training: Epoch[020/182] Iteration[100/352] Loss: 0.3545 Acc:87.84%
Training: Epoch[020/182] Iteration[150/352] Loss: 0.3561 Acc:87.68%
Training: Epoch[020/182] Iteration[200/352] Loss: 0.3560 Acc:87.69%
Training: Epoch[020/182] Iteration[250/352] Loss: 0.3607 Acc:87.40%
Training: Epoch[020/182] Iteration[300/352] Loss: 0.3623 Acc:87.33%
Training: Epoch[020/182] Iteration[350/352] Loss: 0.3644 Acc:87.28%
Training Progress:  10%| | 19/182 [14:22<1:57:47, 43.36s/it, Train Acc=87.28%, VEpoch[020/182] Train Acc: 87.28% Valid Acc:82.94% Train loss:0.3641 Valid loss:0.5245 LR:0.1
Training Progress:  11%| | 20/182 [14:22<1:57:08, 43.39s/it, Train Acc=87.28%, VTraining: Epoch[021/182] Iteration[050/352] Loss: 0.3269 Acc:88.91%
Training: Epoch[021/182] Iteration[100/352] Loss: 0.3328 Acc:88.73%
Training: Epoch[021/182] Iteration[150/352] Loss: 0.3376 Acc:88.40%
Training: Epoch[021/182] Iteration[200/352] Loss: 0.3390 Acc:88.38%
Training: Epoch[021/182] Iteration[250/352] Loss: 0.3401 Acc:88.26%
Training: Epoch[021/182] Iteration[300/352] Loss: 0.3424 Acc:88.17%
Training: Epoch[021/182] Iteration[350/352] Loss: 0.3421 Acc:88.16%
Training Progress:  11%| | 20/182 [15:05<1:57:08, 43.39s/it, Train Acc=88.14%, VEpoch[021/182] Train Acc: 88.14% Valid Acc:84.72% Train loss:0.3431 Valid loss:0.4953 LR:0.1
Training Progress:  12%| | 21/182 [15:05<1:56:27, 43.40s/it, Train Acc=88.14%, VTraining: Epoch[022/182] Iteration[050/352] Loss: 0.3236 Acc:88.80%
Training: Epoch[022/182] Iteration[100/352] Loss: 0.3311 Acc:88.60%
Training: Epoch[022/182] Iteration[150/352] Loss: 0.3308 Acc:88.55%
Training: Epoch[022/182] Iteration[200/352] Loss: 0.3368 Acc:88.38%
Training: Epoch[022/182] Iteration[250/352] Loss: 0.3407 Acc:88.25%
Training: Epoch[022/182] Iteration[300/352] Loss: 0.3426 Acc:88.12%
Training: Epoch[022/182] Iteration[350/352] Loss: 0.3427 Acc:88.14%
Training Progress:  12%| | 21/182 [15:49<1:56:27, 43.40s/it, Train Acc=88.14%, VEpoch[022/182] Train Acc: 88.14% Valid Acc:84.98% Train loss:0.3428 Valid loss:0.4542 LR:0.1
Training Progress:  12%| | 22/182 [15:49<1:55:43, 43.40s/it, Train Acc=88.14%, VTraining: Epoch[023/182] Iteration[050/352] Loss: 0.3169 Acc:89.08%
Training: Epoch[023/182] Iteration[100/352] Loss: 0.3107 Acc:89.29%
Training: Epoch[023/182] Iteration[150/352] Loss: 0.3203 Acc:88.97%
Training: Epoch[023/182] Iteration[200/352] Loss: 0.3257 Acc:88.64%
Training: Epoch[023/182] Iteration[250/352] Loss: 0.3257 Acc:88.59%
Training: Epoch[023/182] Iteration[300/352] Loss: 0.3251 Acc:88.64%
Training: Epoch[023/182] Iteration[350/352] Loss: 0.3282 Acc:88.53%
Training Progress:  12%| | 22/182 [16:32<1:55:43, 43.40s/it, Train Acc=88.52%, VEpoch[023/182] Train Acc: 88.52% Valid Acc:85.00% Train loss:0.3286 Valid loss:0.4665 LR:0.1
Training Progress:  13%|▏| 23/182 [16:32<1:54:58, 43.39s/it, Train Acc=88.52%, VTraining: Epoch[024/182] Iteration[050/352] Loss: 0.2837 Acc:90.03%
Training: Epoch[024/182] Iteration[100/352] Loss: 0.2904 Acc:89.89%
Training: Epoch[024/182] Iteration[150/352] Loss: 0.2988 Acc:89.73%
Training: Epoch[024/182] Iteration[200/352] Loss: 0.3014 Acc:89.64%
Training: Epoch[024/182] Iteration[250/352] Loss: 0.2990 Acc:89.67%
Training: Epoch[024/182] Iteration[300/352] Loss: 0.3047 Acc:89.41%
Training: Epoch[024/182] Iteration[350/352] Loss: 0.3106 Acc:89.24%
Training Progress:  13%|▏| 23/182 [17:16<1:54:58, 43.39s/it, Train Acc=89.24%, VEpoch[024/182] Train Acc: 89.24% Valid Acc:86.54% Train loss:0.3103 Valid loss:0.4122 LR:0.1
Training Progress:  13%|▏| 24/182 [17:16<1:54:14, 43.38s/it, Train Acc=89.24%, VTraining: Epoch[025/182] Iteration[050/352] Loss: 0.2896 Acc:89.98%
Training: Epoch[025/182] Iteration[100/352] Loss: 0.2969 Acc:89.48%
Training: Epoch[025/182] Iteration[150/352] Loss: 0.2964 Acc:89.42%
Training: Epoch[025/182] Iteration[200/352] Loss: 0.3010 Acc:89.19%
Training: Epoch[025/182] Iteration[250/352] Loss: 0.3016 Acc:89.21%
Training: Epoch[025/182] Iteration[300/352] Loss: 0.3028 Acc:89.20%
Training: Epoch[025/182] Iteration[350/352] Loss: 0.3065 Acc:89.16%
Training Progress:  13%|▏| 24/182 [17:59<1:54:14, 43.38s/it, Train Acc=89.16%, VEpoch[025/182] Train Acc: 89.16% Valid Acc:83.52% Train loss:0.3066 Valid loss:0.5373 LR:0.1
Training Progress:  14%|▏| 25/182 [17:59<1:53:33, 43.40s/it, Train Acc=89.16%, VTraining: Epoch[026/182] Iteration[050/352] Loss: 0.2637 Acc:90.62%
Training: Epoch[026/182] Iteration[100/352] Loss: 0.2824 Acc:89.93%
Training: Epoch[026/182] Iteration[150/352] Loss: 0.2837 Acc:89.91%
Training: Epoch[026/182] Iteration[200/352] Loss: 0.2835 Acc:89.98%
Training: Epoch[026/182] Iteration[250/352] Loss: 0.2869 Acc:89.89%
Training: Epoch[026/182] Iteration[300/352] Loss: 0.2911 Acc:89.78%
Training: Epoch[026/182] Iteration[350/352] Loss: 0.2914 Acc:89.74%
Training Progress:  14%|▏| 25/182 [18:42<1:53:33, 43.40s/it, Train Acc=89.75%, VEpoch[026/182] Train Acc: 89.75% Valid Acc:86.72% Train loss:0.2913 Valid loss:0.4287 LR:0.1
Training Progress:  14%|▏| 26/182 [18:42<1:52:48, 43.39s/it, Train Acc=89.75%, VTraining: Epoch[027/182] Iteration[050/352] Loss: 0.2738 Acc:90.12%
Training: Epoch[027/182] Iteration[100/352] Loss: 0.2852 Acc:89.97%
Training: Epoch[027/182] Iteration[150/352] Loss: 0.2811 Acc:90.24%
Training: Epoch[027/182] Iteration[200/352] Loss: 0.2777 Acc:90.25%
Training: Epoch[027/182] Iteration[250/352] Loss: 0.2820 Acc:90.16%
Training: Epoch[027/182] Iteration[300/352] Loss: 0.2843 Acc:90.07%
Training: Epoch[027/182] Iteration[350/352] Loss: 0.2860 Acc:90.02%
Training Progress:  14%|▏| 26/182 [19:26<1:52:48, 43.39s/it, Train Acc=90.02%, VEpoch[027/182] Train Acc: 90.02% Valid Acc:87.30% Train loss:0.2862 Valid loss:0.4046 LR:0.1
Training Progress:  15%|▏| 27/182 [19:26<1:52:08, 43.41s/it, Train Acc=90.02%, VTraining: Epoch[028/182] Iteration[050/352] Loss: 0.2579 Acc:90.94%
Training: Epoch[028/182] Iteration[100/352] Loss: 0.2609 Acc:90.87%
Training: Epoch[028/182] Iteration[150/352] Loss: 0.2656 Acc:90.77%
Training: Epoch[028/182] Iteration[200/352] Loss: 0.2769 Acc:90.34%
Training: Epoch[028/182] Iteration[250/352] Loss: 0.2793 Acc:90.27%
Training: Epoch[028/182] Iteration[300/352] Loss: 0.2795 Acc:90.27%
Training: Epoch[028/182] Iteration[350/352] Loss: 0.2797 Acc:90.25%
Training Progress:  15%|▏| 27/182 [20:09<1:52:08, 43.41s/it, Train Acc=90.24%, VEpoch[028/182] Train Acc: 90.24% Valid Acc:87.30% Train loss:0.2803 Valid loss:0.4356 LR:0.1
Training Progress:  15%|▏| 28/182 [20:09<1:51:24, 43.41s/it, Train Acc=90.24%, VTraining: Epoch[029/182] Iteration[050/352] Loss: 0.2499 Acc:91.52%
Training: Epoch[029/182] Iteration[100/352] Loss: 0.2633 Acc:91.05%
Training: Epoch[029/182] Iteration[150/352] Loss: 0.2663 Acc:90.93%
Training: Epoch[029/182] Iteration[200/352] Loss: 0.2664 Acc:90.88%
Training: Epoch[029/182] Iteration[250/352] Loss: 0.2658 Acc:90.85%
Training: Epoch[029/182] Iteration[300/352] Loss: 0.2659 Acc:90.82%
Training: Epoch[029/182] Iteration[350/352] Loss: 0.2696 Acc:90.70%
Training Progress:  15%|▏| 28/182 [20:53<1:51:24, 43.41s/it, Train Acc=90.70%, VEpoch[029/182] Train Acc: 90.70% Valid Acc:86.16% Train loss:0.2695 Valid loss:0.4416 LR:0.1
Training Progress:  16%|▏| 29/182 [20:53<1:50:43, 43.42s/it, Train Acc=90.70%, VTraining: Epoch[030/182] Iteration[050/352] Loss: 0.2421 Acc:91.81%
Training: Epoch[030/182] Iteration[100/352] Loss: 0.2480 Acc:91.36%
Training: Epoch[030/182] Iteration[150/352] Loss: 0.2505 Acc:91.21%
Training: Epoch[030/182] Iteration[200/352] Loss: 0.2534 Acc:91.06%
Training: Epoch[030/182] Iteration[250/352] Loss: 0.2559 Acc:90.97%
Training: Epoch[030/182] Iteration[300/352] Loss: 0.2584 Acc:90.95%
Training: Epoch[030/182] Iteration[350/352] Loss: 0.2603 Acc:90.89%
Training Progress:  16%|▏| 29/182 [21:36<1:50:43, 43.42s/it, Train Acc=90.89%, VEpoch[030/182] Train Acc: 90.89% Valid Acc:85.84% Train loss:0.2600 Valid loss:0.4670 LR:0.1
Training Progress:  16%|▏| 30/182 [21:36<1:50:02, 43.44s/it, Train Acc=90.89%, VTraining: Epoch[031/182] Iteration[050/352] Loss: 0.2319 Acc:91.94%
Training: Epoch[031/182] Iteration[100/352] Loss: 0.2457 Acc:91.41%
Training: Epoch[031/182] Iteration[150/352] Loss: 0.2539 Acc:91.12%
Training: Epoch[031/182] Iteration[200/352] Loss: 0.2551 Acc:91.04%
Training: Epoch[031/182] Iteration[250/352] Loss: 0.2576 Acc:91.03%
Training: Epoch[031/182] Iteration[300/352] Loss: 0.2571 Acc:91.01%
Training: Epoch[031/182] Iteration[350/352] Loss: 0.2584 Acc:91.00%
Training Progress:  16%|▏| 30/182 [22:20<1:50:02, 43.44s/it, Train Acc=90.99%, VEpoch[031/182] Train Acc: 90.99% Valid Acc:84.66% Train loss:0.2587 Valid loss:0.5464 LR:0.1
Training Progress:  17%|▏| 31/182 [22:20<1:49:23, 43.47s/it, Train Acc=90.99%, VTraining: Epoch[032/182] Iteration[050/352] Loss: 0.2415 Acc:91.30%
Training: Epoch[032/182] Iteration[100/352] Loss: 0.2493 Acc:91.25%
Training: Epoch[032/182] Iteration[150/352] Loss: 0.2552 Acc:91.10%
Training: Epoch[032/182] Iteration[200/352] Loss: 0.2559 Acc:91.05%
Training: Epoch[032/182] Iteration[250/352] Loss: 0.2552 Acc:91.06%
Training: Epoch[032/182] Iteration[300/352] Loss: 0.2547 Acc:91.06%
Training: Epoch[032/182] Iteration[350/352] Loss: 0.2549 Acc:91.06%
Training Progress:  17%|▏| 31/182 [23:03<1:49:23, 43.47s/it, Train Acc=91.05%, VEpoch[032/182] Train Acc: 91.05% Valid Acc:85.36% Train loss:0.2553 Valid loss:0.4982 LR:0.1
Training Progress:  18%|▏| 32/182 [23:03<1:48:36, 43.45s/it, Train Acc=91.05%, VTraining: Epoch[033/182] Iteration[050/352] Loss: 0.2402 Acc:91.61%
Training: Epoch[033/182] Iteration[100/352] Loss: 0.2432 Acc:91.26%
Training: Epoch[033/182] Iteration[150/352] Loss: 0.2446 Acc:91.28%
Training: Epoch[033/182] Iteration[200/352] Loss: 0.2460 Acc:91.24%
Training: Epoch[033/182] Iteration[250/352] Loss: 0.2431 Acc:91.41%
Training: Epoch[033/182] Iteration[300/352] Loss: 0.2453 Acc:91.33%
Training: Epoch[033/182] Iteration[350/352] Loss: 0.2467 Acc:91.30%
Training Progress:  18%|▏| 32/182 [23:46<1:48:36, 43.45s/it, Train Acc=91.29%, VEpoch[033/182] Train Acc: 91.29% Valid Acc:87.34% Train loss:0.2468 Valid loss:0.3996 LR:0.1
Training Progress:  18%|▏| 33/182 [23:46<1:47:52, 43.44s/it, Train Acc=91.29%, VTraining: Epoch[034/182] Iteration[050/352] Loss: 0.2349 Acc:91.73%
Training: Epoch[034/182] Iteration[100/352] Loss: 0.2300 Acc:91.91%
Training: Epoch[034/182] Iteration[150/352] Loss: 0.2293 Acc:91.97%
Training: Epoch[034/182] Iteration[200/352] Loss: 0.2311 Acc:91.90%
Training: Epoch[034/182] Iteration[250/352] Loss: 0.2350 Acc:91.74%
Training: Epoch[034/182] Iteration[300/352] Loss: 0.2391 Acc:91.60%
Training: Epoch[034/182] Iteration[350/352] Loss: 0.2427 Acc:91.52%
Training Progress:  18%|▏| 33/182 [24:30<1:47:52, 43.44s/it, Train Acc=91.52%, VEpoch[034/182] Train Acc: 91.52% Valid Acc:87.12% Train loss:0.2431 Valid loss:0.4159 LR:0.1
Training Progress:  19%|▏| 34/182 [24:30<1:47:09, 43.45s/it, Train Acc=91.52%, VTraining: Epoch[035/182] Iteration[050/352] Loss: 0.2163 Acc:92.58%
Training: Epoch[035/182] Iteration[100/352] Loss: 0.2126 Acc:92.82%
Training: Epoch[035/182] Iteration[150/352] Loss: 0.2227 Acc:92.35%
Training: Epoch[035/182] Iteration[200/352] Loss: 0.2212 Acc:92.35%
Training: Epoch[035/182] Iteration[250/352] Loss: 0.2278 Acc:92.07%
Training: Epoch[035/182] Iteration[300/352] Loss: 0.2283 Acc:92.03%
Training: Epoch[035/182] Iteration[350/352] Loss: 0.2310 Acc:91.94%
Training Progress:  19%|▏| 34/182 [25:13<1:47:09, 43.45s/it, Train Acc=91.94%, VEpoch[035/182] Train Acc: 91.94% Valid Acc:85.06% Train loss:0.2309 Valid loss:0.4983 LR:0.1
Training Progress:  19%|▏| 35/182 [25:13<1:46:25, 43.44s/it, Train Acc=91.94%, VTraining: Epoch[036/182] Iteration[050/352] Loss: 0.2143 Acc:92.45%
Training: Epoch[036/182] Iteration[100/352] Loss: 0.2277 Acc:91.95%
Training: Epoch[036/182] Iteration[150/352] Loss: 0.2289 Acc:91.92%
Training: Epoch[036/182] Iteration[200/352] Loss: 0.2365 Acc:91.65%
Training: Epoch[036/182] Iteration[250/352] Loss: 0.2344 Acc:91.70%
Training: Epoch[036/182] Iteration[300/352] Loss: 0.2371 Acc:91.61%
Training: Epoch[036/182] Iteration[350/352] Loss: 0.2381 Acc:91.61%
Training Progress:  19%|▏| 35/182 [25:57<1:46:25, 43.44s/it, Train Acc=91.62%, VEpoch[036/182] Train Acc: 91.62% Valid Acc:85.44% Train loss:0.2381 Valid loss:0.5053 LR:0.1
Training Progress:  20%|▏| 36/182 [25:57<1:45:42, 43.44s/it, Train Acc=91.62%, VTraining: Epoch[037/182] Iteration[050/352] Loss: 0.1945 Acc:93.05%
Training: Epoch[037/182] Iteration[100/352] Loss: 0.1986 Acc:93.03%
Training: Epoch[037/182] Iteration[150/352] Loss: 0.2066 Acc:92.83%
Training: Epoch[037/182] Iteration[200/352] Loss: 0.2155 Acc:92.60%
Training: Epoch[037/182] Iteration[250/352] Loss: 0.2215 Acc:92.39%
Training: Epoch[037/182] Iteration[300/352] Loss: 0.2246 Acc:92.27%
Training: Epoch[037/182] Iteration[350/352] Loss: 0.2280 Acc:92.12%
Training Progress:  20%|▏| 36/182 [26:40<1:45:42, 43.44s/it, Train Acc=92.10%, VEpoch[037/182] Train Acc: 92.10% Valid Acc:82.40% Train loss:0.2287 Valid loss:0.6290 LR:0.1
Training Progress:  20%|▏| 37/182 [26:40<1:44:59, 43.45s/it, Train Acc=92.10%, VTraining: Epoch[038/182] Iteration[050/352] Loss: 0.2153 Acc:92.45%
Training: Epoch[038/182] Iteration[100/352] Loss: 0.2059 Acc:92.66%
Training: Epoch[038/182] Iteration[150/352] Loss: 0.2134 Acc:92.50%
Training: Epoch[038/182] Iteration[200/352] Loss: 0.2159 Acc:92.45%
Training: Epoch[038/182] Iteration[250/352] Loss: 0.2161 Acc:92.45%
Training: Epoch[038/182] Iteration[300/352] Loss: 0.2194 Acc:92.35%
Training: Epoch[038/182] Iteration[350/352] Loss: 0.2241 Acc:92.22%
Training Progress:  20%|▏| 37/182 [27:24<1:44:59, 43.45s/it, Train Acc=92.21%, VEpoch[038/182] Train Acc: 92.21% Valid Acc:86.46% Train loss:0.2243 Valid loss:0.4371 LR:0.1
Training Progress:  21%|▏| 38/182 [27:24<1:44:23, 43.50s/it, Train Acc=92.21%, VTraining: Epoch[039/182] Iteration[050/352] Loss: 0.2156 Acc:92.52%
Training: Epoch[039/182] Iteration[100/352] Loss: 0.2106 Acc:92.59%
Training: Epoch[039/182] Iteration[150/352] Loss: 0.2102 Acc:92.79%
Training: Epoch[039/182] Iteration[200/352] Loss: 0.2146 Acc:92.61%
Training: Epoch[039/182] Iteration[250/352] Loss: 0.2158 Acc:92.58%
Training: Epoch[039/182] Iteration[300/352] Loss: 0.2161 Acc:92.52%
Training: Epoch[039/182] Iteration[350/352] Loss: 0.2215 Acc:92.36%
Training Progress:  21%|▏| 38/182 [28:07<1:44:23, 43.50s/it, Train Acc=92.34%, VEpoch[039/182] Train Acc: 92.34% Valid Acc:87.10% Train loss:0.2220 Valid loss:0.4282 LR:0.1
Training Progress:  21%|▏| 39/182 [28:07<1:43:40, 43.50s/it, Train Acc=92.34%, VTraining: Epoch[040/182] Iteration[050/352] Loss: 0.1874 Acc:92.92%
Training: Epoch[040/182] Iteration[100/352] Loss: 0.1882 Acc:93.14%
Training: Epoch[040/182] Iteration[150/352] Loss: 0.1965 Acc:92.92%
Training: Epoch[040/182] Iteration[200/352] Loss: 0.2013 Acc:92.80%
Training: Epoch[040/182] Iteration[250/352] Loss: 0.2018 Acc:92.77%
Training: Epoch[040/182] Iteration[300/352] Loss: 0.2068 Acc:92.62%
Training: Epoch[040/182] Iteration[350/352] Loss: 0.2094 Acc:92.56%
Training Progress:  21%|▏| 39/182 [28:51<1:43:40, 43.50s/it, Train Acc=92.54%, VEpoch[040/182] Train Acc: 92.54% Valid Acc:88.88% Train loss:0.2098 Valid loss:0.3724 LR:0.1
Training Progress:  22%|▏| 40/182 [28:51<1:42:57, 43.50s/it, Train Acc=92.54%, VTraining: Epoch[041/182] Iteration[050/352] Loss: 0.1949 Acc:93.08%
Training: Epoch[041/182] Iteration[100/352] Loss: 0.1960 Acc:93.20%
Training: Epoch[041/182] Iteration[150/352] Loss: 0.1986 Acc:93.12%
Training: Epoch[041/182] Iteration[200/352] Loss: 0.2009 Acc:93.02%
Training: Epoch[041/182] Iteration[250/352] Loss: 0.2069 Acc:92.78%
Training: Epoch[041/182] Iteration[300/352] Loss: 0.2061 Acc:92.83%
Training: Epoch[041/182] Iteration[350/352] Loss: 0.2095 Acc:92.71%
Training Progress:  22%|▏| 40/182 [29:34<1:42:57, 43.50s/it, Train Acc=92.70%, VEpoch[041/182] Train Acc: 92.70% Valid Acc:88.12% Train loss:0.2097 Valid loss:0.4076 LR:0.1
Training Progress:  23%|▏| 41/182 [29:34<1:42:11, 43.49s/it, Train Acc=92.70%, VTraining: Epoch[042/182] Iteration[050/352] Loss: 0.1929 Acc:93.42%
Training: Epoch[042/182] Iteration[100/352] Loss: 0.1990 Acc:93.10%
Training: Epoch[042/182] Iteration[150/352] Loss: 0.2013 Acc:92.90%
Training: Epoch[042/182] Iteration[200/352] Loss: 0.2056 Acc:92.75%
Training: Epoch[042/182] Iteration[250/352] Loss: 0.2060 Acc:92.67%
Training: Epoch[042/182] Iteration[300/352] Loss: 0.2103 Acc:92.55%
Training: Epoch[042/182] Iteration[350/352] Loss: 0.2108 Acc:92.54%
Training Progress:  23%|▏| 41/182 [30:18<1:42:11, 43.49s/it, Train Acc=92.54%, VEpoch[042/182] Train Acc: 92.54% Valid Acc:86.30% Train loss:0.2109 Valid loss:0.5025 LR:0.1
Training Progress:  23%|▏| 42/182 [30:18<1:41:26, 43.48s/it, Train Acc=92.54%, VTraining: Epoch[043/182] Iteration[050/352] Loss: 0.2140 Acc:92.31%
Training: Epoch[043/182] Iteration[100/352] Loss: 0.2016 Acc:92.90%
Training: Epoch[043/182] Iteration[150/352] Loss: 0.1939 Acc:93.18%
Training: Epoch[043/182] Iteration[200/352] Loss: 0.1972 Acc:93.08%
Training: Epoch[043/182] Iteration[250/352] Loss: 0.2039 Acc:92.81%
Training: Epoch[043/182] Iteration[300/352] Loss: 0.2055 Acc:92.80%
Training: Epoch[043/182] Iteration[350/352] Loss: 0.2065 Acc:92.78%
Training Progress:  23%|▏| 42/182 [31:01<1:41:26, 43.48s/it, Train Acc=92.78%, VEpoch[043/182] Train Acc: 92.78% Valid Acc:82.72% Train loss:0.2065 Valid loss:0.5810 LR:0.1
Training Progress:  24%|▏| 43/182 [31:01<1:40:45, 43.49s/it, Train Acc=92.78%, VTraining: Epoch[044/182] Iteration[050/352] Loss: 0.2061 Acc:92.70%
Training: Epoch[044/182] Iteration[100/352] Loss: 0.1966 Acc:93.12%
Training: Epoch[044/182] Iteration[150/352] Loss: 0.2002 Acc:92.94%
Training: Epoch[044/182] Iteration[200/352] Loss: 0.2019 Acc:92.90%
Training: Epoch[044/182] Iteration[250/352] Loss: 0.2033 Acc:92.83%
Training: Epoch[044/182] Iteration[300/352] Loss: 0.2039 Acc:92.84%
Training: Epoch[044/182] Iteration[350/352] Loss: 0.2092 Acc:92.69%
Training Progress:  24%|▏| 43/182 [31:45<1:40:45, 43.49s/it, Train Acc=92.70%, VEpoch[044/182] Train Acc: 92.70% Valid Acc:88.26% Train loss:0.2092 Valid loss:0.4060 LR:0.1
Training Progress:  24%|▏| 44/182 [31:45<1:40:03, 43.50s/it, Train Acc=92.70%, VTraining: Epoch[045/182] Iteration[050/352] Loss: 0.1864 Acc:93.36%
Training: Epoch[045/182] Iteration[100/352] Loss: 0.1835 Acc:93.36%
Training: Epoch[045/182] Iteration[150/352] Loss: 0.1866 Acc:93.33%
Training: Epoch[045/182] Iteration[200/352] Loss: 0.1912 Acc:93.18%
Training: Epoch[045/182] Iteration[250/352] Loss: 0.1962 Acc:93.02%
Training: Epoch[045/182] Iteration[300/352] Loss: 0.1950 Acc:93.07%
Training: Epoch[045/182] Iteration[350/352] Loss: 0.1947 Acc:93.11%
Training Progress:  24%|▏| 44/182 [32:28<1:40:03, 43.50s/it, Train Acc=93.12%, VEpoch[045/182] Train Acc: 93.12% Valid Acc:87.24% Train loss:0.1947 Valid loss:0.4060 LR:0.1
Training Progress:  25%|▏| 45/182 [32:28<1:39:18, 43.49s/it, Train Acc=93.12%, VTraining: Epoch[046/182] Iteration[050/352] Loss: 0.1875 Acc:93.61%
Training: Epoch[046/182] Iteration[100/352] Loss: 0.1859 Acc:93.67%
Training: Epoch[046/182] Iteration[150/352] Loss: 0.1856 Acc:93.58%
Training: Epoch[046/182] Iteration[200/352] Loss: 0.1889 Acc:93.43%
Training: Epoch[046/182] Iteration[250/352] Loss: 0.1950 Acc:93.28%
Training: Epoch[046/182] Iteration[300/352] Loss: 0.1995 Acc:93.12%
Training: Epoch[046/182] Iteration[350/352] Loss: 0.1998 Acc:93.08%
Training Progress:  25%|▏| 45/182 [33:12<1:39:18, 43.49s/it, Train Acc=93.06%, VEpoch[046/182] Train Acc: 93.06% Valid Acc:87.82% Train loss:0.2000 Valid loss:0.4133 LR:0.1
Training Progress:  25%|▎| 46/182 [33:12<1:38:34, 43.49s/it, Train Acc=93.06%, VTraining: Epoch[047/182] Iteration[050/352] Loss: 0.1721 Acc:93.59%
Training: Epoch[047/182] Iteration[100/352] Loss: 0.1783 Acc:93.59%
Training: Epoch[047/182] Iteration[150/352] Loss: 0.1853 Acc:93.35%
Training: Epoch[047/182] Iteration[200/352] Loss: 0.1853 Acc:93.41%
Training: Epoch[047/182] Iteration[250/352] Loss: 0.1885 Acc:93.34%
Training: Epoch[047/182] Iteration[300/352] Loss: 0.1965 Acc:93.08%
Training: Epoch[047/182] Iteration[350/352] Loss: 0.2001 Acc:92.96%
Training Progress:  25%|▎| 46/182 [33:55<1:38:34, 43.49s/it, Train Acc=92.95%, VEpoch[047/182] Train Acc: 92.95% Valid Acc:88.68% Train loss:0.2002 Valid loss:0.3722 LR:0.1
Training Progress:  26%|▎| 47/182 [33:55<1:37:52, 43.50s/it, Train Acc=92.95%, VTraining: Epoch[048/182] Iteration[050/352] Loss: 0.1833 Acc:93.62%
Training: Epoch[048/182] Iteration[100/352] Loss: 0.1824 Acc:93.66%
Training: Epoch[048/182] Iteration[150/352] Loss: 0.1826 Acc:93.64%
Training: Epoch[048/182] Iteration[200/352] Loss: 0.1885 Acc:93.51%
Training: Epoch[048/182] Iteration[250/352] Loss: 0.1865 Acc:93.56%
Training: Epoch[048/182] Iteration[300/352] Loss: 0.1890 Acc:93.44%
Training: Epoch[048/182] Iteration[350/352] Loss: 0.1930 Acc:93.31%
Training Progress:  26%|▎| 47/182 [34:39<1:37:52, 43.50s/it, Train Acc=93.30%, VEpoch[048/182] Train Acc: 93.30% Valid Acc:86.68% Train loss:0.1935 Valid loss:0.4970 LR:0.1
Training Progress:  26%|▎| 48/182 [34:39<1:37:10, 43.51s/it, Train Acc=93.30%, VTraining: Epoch[049/182] Iteration[050/352] Loss: 0.1779 Acc:93.83%
Training: Epoch[049/182] Iteration[100/352] Loss: 0.1646 Acc:94.23%
Training: Epoch[049/182] Iteration[150/352] Loss: 0.1705 Acc:93.94%
Training: Epoch[049/182] Iteration[200/352] Loss: 0.1814 Acc:93.66%
Training: Epoch[049/182] Iteration[250/352] Loss: 0.1814 Acc:93.63%
Training: Epoch[049/182] Iteration[300/352] Loss: 0.1840 Acc:93.49%
Training: Epoch[049/182] Iteration[350/352] Loss: 0.1889 Acc:93.30%
Training Progress:  26%|▎| 48/182 [35:22<1:37:10, 43.51s/it, Train Acc=93.30%, VEpoch[049/182] Train Acc: 93.30% Valid Acc:87.24% Train loss:0.1888 Valid loss:0.4304 LR:0.1
Training Progress:  27%|▎| 49/182 [35:22<1:36:23, 43.48s/it, Train Acc=93.30%, VTraining: Epoch[050/182] Iteration[050/352] Loss: 0.1702 Acc:94.20%
Training: Epoch[050/182] Iteration[100/352] Loss: 0.1776 Acc:93.92%
Training: Epoch[050/182] Iteration[150/352] Loss: 0.1800 Acc:93.73%
Training: Epoch[050/182] Iteration[200/352] Loss: 0.1790 Acc:93.77%
Training: Epoch[050/182] Iteration[250/352] Loss: 0.1822 Acc:93.62%
Training: Epoch[050/182] Iteration[300/352] Loss: 0.1876 Acc:93.48%
Training: Epoch[050/182] Iteration[350/352] Loss: 0.1896 Acc:93.46%
Training Progress:  27%|▎| 49/182 [36:06<1:36:23, 43.48s/it, Train Acc=93.45%, VEpoch[050/182] Train Acc: 93.45% Valid Acc:88.48% Train loss:0.1897 Valid loss:0.3670 LR:0.1
Training Progress:  27%|▎| 50/182 [36:06<1:35:41, 43.50s/it, Train Acc=93.45%, VTraining: Epoch[051/182] Iteration[050/352] Loss: 0.1520 Acc:94.62%
Training: Epoch[051/182] Iteration[100/352] Loss: 0.1509 Acc:94.70%
Training: Epoch[051/182] Iteration[150/352] Loss: 0.1558 Acc:94.53%
Training: Epoch[051/182] Iteration[200/352] Loss: 0.1634 Acc:94.27%
Training: Epoch[051/182] Iteration[250/352] Loss: 0.1706 Acc:93.99%
Training: Epoch[051/182] Iteration[300/352] Loss: 0.1754 Acc:93.84%
Training: Epoch[051/182] Iteration[350/352] Loss: 0.1758 Acc:93.83%
Training Progress:  27%|▎| 50/182 [36:49<1:35:41, 43.50s/it, Train Acc=93.81%, VEpoch[051/182] Train Acc: 93.81% Valid Acc:87.42% Train loss:0.1762 Valid loss:0.4244 LR:0.1
Training Progress:  28%|▎| 51/182 [36:49<1:34:58, 43.50s/it, Train Acc=93.81%, VTraining: Epoch[052/182] Iteration[050/352] Loss: 0.1614 Acc:94.19%
Training: Epoch[052/182] Iteration[100/352] Loss: 0.1665 Acc:94.02%
Training: Epoch[052/182] Iteration[150/352] Loss: 0.1752 Acc:93.79%
Training: Epoch[052/182] Iteration[200/352] Loss: 0.1801 Acc:93.65%
Training: Epoch[052/182] Iteration[250/352] Loss: 0.1854 Acc:93.50%
Training: Epoch[052/182] Iteration[300/352] Loss: 0.1829 Acc:93.59%
Training: Epoch[052/182] Iteration[350/352] Loss: 0.1832 Acc:93.60%
Training Progress:  28%|▎| 51/182 [37:33<1:34:58, 43.50s/it, Train Acc=93.60%, VEpoch[052/182] Train Acc: 93.60% Valid Acc:89.06% Train loss:0.1830 Valid loss:0.3824 LR:0.1
Training Progress:  29%|▎| 52/182 [37:33<1:34:15, 43.51s/it, Train Acc=93.60%, VTraining: Epoch[053/182] Iteration[050/352] Loss: 0.1644 Acc:94.25%
Training: Epoch[053/182] Iteration[100/352] Loss: 0.1643 Acc:94.41%
Training: Epoch[053/182] Iteration[150/352] Loss: 0.1590 Acc:94.52%
Training: Epoch[053/182] Iteration[200/352] Loss: 0.1681 Acc:94.16%
Training: Epoch[053/182] Iteration[250/352] Loss: 0.1724 Acc:94.02%
Training: Epoch[053/182] Iteration[300/352] Loss: 0.1734 Acc:93.98%
Training: Epoch[053/182] Iteration[350/352] Loss: 0.1755 Acc:93.87%
Training Progress:  29%|▎| 52/182 [38:16<1:34:15, 43.51s/it, Train Acc=93.88%, VEpoch[053/182] Train Acc: 93.88% Valid Acc:89.38% Train loss:0.1753 Valid loss:0.3774 LR:0.1
Training Progress:  29%|▎| 53/182 [38:16<1:33:31, 43.50s/it, Train Acc=93.88%, VTraining: Epoch[054/182] Iteration[050/352] Loss: 0.1737 Acc:93.56%
Training: Epoch[054/182] Iteration[100/352] Loss: 0.1721 Acc:93.83%
Training: Epoch[054/182] Iteration[150/352] Loss: 0.1752 Acc:93.71%
Training: Epoch[054/182] Iteration[200/352] Loss: 0.1758 Acc:93.77%
Training: Epoch[054/182] Iteration[250/352] Loss: 0.1751 Acc:93.80%
Training: Epoch[054/182] Iteration[300/352] Loss: 0.1770 Acc:93.72%
Training: Epoch[054/182] Iteration[350/352] Loss: 0.1798 Acc:93.64%
Training Progress:  29%|▎| 53/182 [39:00<1:33:31, 43.50s/it, Train Acc=93.64%, VEpoch[054/182] Train Acc: 93.64% Valid Acc:87.52% Train loss:0.1798 Valid loss:0.4082 LR:0.1
Training Progress:  30%|▎| 54/182 [39:00<1:32:47, 43.49s/it, Train Acc=93.64%, VTraining: Epoch[055/182] Iteration[050/352] Loss: 0.1683 Acc:94.17%
Training: Epoch[055/182] Iteration[100/352] Loss: 0.1620 Acc:94.48%
Training: Epoch[055/182] Iteration[150/352] Loss: 0.1636 Acc:94.32%
Training: Epoch[055/182] Iteration[200/352] Loss: 0.1665 Acc:94.23%
Training: Epoch[055/182] Iteration[250/352] Loss: 0.1703 Acc:94.08%
Training: Epoch[055/182] Iteration[300/352] Loss: 0.1740 Acc:93.96%
Training: Epoch[055/182] Iteration[350/352] Loss: 0.1772 Acc:93.86%
Training Progress:  30%|▎| 54/182 [39:43<1:32:47, 43.49s/it, Train Acc=93.84%, VEpoch[055/182] Train Acc: 93.84% Valid Acc:87.62% Train loss:0.1782 Valid loss:0.4472 LR:0.1
Training Progress:  30%|▎| 55/182 [39:43<1:32:06, 43.51s/it, Train Acc=93.84%, VTraining: Epoch[056/182] Iteration[050/352] Loss: 0.1659 Acc:93.94%
Training: Epoch[056/182] Iteration[100/352] Loss: 0.1706 Acc:93.84%
Training: Epoch[056/182] Iteration[150/352] Loss: 0.1717 Acc:93.82%
Training: Epoch[056/182] Iteration[200/352] Loss: 0.1757 Acc:93.72%
Training: Epoch[056/182] Iteration[250/352] Loss: 0.1791 Acc:93.65%
Training: Epoch[056/182] Iteration[300/352] Loss: 0.1803 Acc:93.61%
Training: Epoch[056/182] Iteration[350/352] Loss: 0.1815 Acc:93.56%
Training Progress:  30%|▎| 55/182 [40:27<1:32:06, 43.51s/it, Train Acc=93.55%, VEpoch[056/182] Train Acc: 93.55% Valid Acc:87.60% Train loss:0.1818 Valid loss:0.4104 LR:0.1
Training Progress:  31%|▎| 56/182 [40:27<1:31:26, 43.54s/it, Train Acc=93.55%, VTraining: Epoch[057/182] Iteration[050/352] Loss: 0.1643 Acc:94.16%
Training: Epoch[057/182] Iteration[100/352] Loss: 0.1611 Acc:94.55%
Training: Epoch[057/182] Iteration[150/352] Loss: 0.1594 Acc:94.57%
Training: Epoch[057/182] Iteration[200/352] Loss: 0.1625 Acc:94.30%
Training: Epoch[057/182] Iteration[250/352] Loss: 0.1673 Acc:94.13%
Training: Epoch[057/182] Iteration[300/352] Loss: 0.1692 Acc:94.08%
Training: Epoch[057/182] Iteration[350/352] Loss: 0.1734 Acc:93.92%
Training Progress:  31%|▎| 56/182 [41:11<1:31:26, 43.54s/it, Train Acc=93.92%, VEpoch[057/182] Train Acc: 93.92% Valid Acc:89.58% Train loss:0.1733 Valid loss:0.3544 LR:0.1
Training Progress:  31%|▎| 57/182 [41:11<1:30:44, 43.56s/it, Train Acc=93.92%, VTraining: Epoch[058/182] Iteration[050/352] Loss: 0.1470 Acc:94.64%
Training: Epoch[058/182] Iteration[100/352] Loss: 0.1426 Acc:94.89%
Training: Epoch[058/182] Iteration[150/352] Loss: 0.1483 Acc:94.81%
Training: Epoch[058/182] Iteration[200/352] Loss: 0.1493 Acc:94.79%
Training: Epoch[058/182] Iteration[250/352] Loss: 0.1564 Acc:94.58%
Training: Epoch[058/182] Iteration[300/352] Loss: 0.1637 Acc:94.27%
Training: Epoch[058/182] Iteration[350/352] Loss: 0.1670 Acc:94.14%
Training Progress:  31%|▎| 57/182 [41:54<1:30:44, 43.56s/it, Train Acc=94.14%, VEpoch[058/182] Train Acc: 94.14% Valid Acc:87.04% Train loss:0.1671 Valid loss:0.4373 LR:0.1
Training Progress:  32%|▎| 58/182 [41:54<1:30:02, 43.57s/it, Train Acc=94.14%, VTraining: Epoch[059/182] Iteration[050/352] Loss: 0.1586 Acc:94.47%
Training: Epoch[059/182] Iteration[100/352] Loss: 0.1598 Acc:94.45%
Training: Epoch[059/182] Iteration[150/352] Loss: 0.1627 Acc:94.29%
Training: Epoch[059/182] Iteration[200/352] Loss: 0.1642 Acc:94.18%
Training: Epoch[059/182] Iteration[250/352] Loss: 0.1665 Acc:94.17%
Training: Epoch[059/182] Iteration[300/352] Loss: 0.1700 Acc:94.02%
Training: Epoch[059/182] Iteration[350/352] Loss: 0.1717 Acc:93.98%
Training Progress:  32%|▎| 58/182 [42:38<1:30:02, 43.57s/it, Train Acc=93.97%, VEpoch[059/182] Train Acc: 93.97% Valid Acc:87.52% Train loss:0.1717 Valid loss:0.4191 LR:0.1
Training Progress:  32%|▎| 59/182 [42:38<1:29:15, 43.54s/it, Train Acc=93.97%, VTraining: Epoch[060/182] Iteration[050/352] Loss: 0.1328 Acc:95.56%
Training: Epoch[060/182] Iteration[100/352] Loss: 0.1426 Acc:95.21%
Training: Epoch[060/182] Iteration[150/352] Loss: 0.1494 Acc:94.88%
Training: Epoch[060/182] Iteration[200/352] Loss: 0.1582 Acc:94.57%
Training: Epoch[060/182] Iteration[250/352] Loss: 0.1626 Acc:94.44%
Training: Epoch[060/182] Iteration[300/352] Loss: 0.1661 Acc:94.31%
Training: Epoch[060/182] Iteration[350/352] Loss: 0.1664 Acc:94.27%
Training Progress:  32%|▎| 59/182 [43:21<1:29:15, 43.54s/it, Train Acc=94.27%, VEpoch[060/182] Train Acc: 94.27% Valid Acc:87.16% Train loss:0.1665 Valid loss:0.4816 LR:0.1
Training Progress:  33%|▎| 60/182 [43:21<1:28:32, 43.54s/it, Train Acc=94.27%, VTraining: Epoch[061/182] Iteration[050/352] Loss: 0.1578 Acc:94.45%
Training: Epoch[061/182] Iteration[100/352] Loss: 0.1594 Acc:94.50%
Training: Epoch[061/182] Iteration[150/352] Loss: 0.1595 Acc:94.51%
Training: Epoch[061/182] Iteration[200/352] Loss: 0.1639 Acc:94.20%
Training: Epoch[061/182] Iteration[250/352] Loss: 0.1685 Acc:94.05%
Training: Epoch[061/182] Iteration[300/352] Loss: 0.1714 Acc:93.93%
Training: Epoch[061/182] Iteration[350/352] Loss: 0.1740 Acc:93.83%
Training Progress:  33%|▎| 60/182 [44:05<1:28:32, 43.54s/it, Train Acc=93.82%, VEpoch[061/182] Train Acc: 93.82% Valid Acc:88.64% Train loss:0.1741 Valid loss:0.3891 LR:0.1
Training Progress:  34%|▎| 61/182 [44:05<1:27:49, 43.55s/it, Train Acc=93.82%, VTraining: Epoch[062/182] Iteration[050/352] Loss: 0.1541 Acc:94.64%
Training: Epoch[062/182] Iteration[100/352] Loss: 0.1526 Acc:94.73%
Training: Epoch[062/182] Iteration[150/352] Loss: 0.1557 Acc:94.57%
Training: Epoch[062/182] Iteration[200/352] Loss: 0.1614 Acc:94.30%
Training: Epoch[062/182] Iteration[250/352] Loss: 0.1630 Acc:94.23%
Training: Epoch[062/182] Iteration[300/352] Loss: 0.1654 Acc:94.10%
Training: Epoch[062/182] Iteration[350/352] Loss: 0.1684 Acc:94.00%
Training Progress:  34%|▎| 61/182 [44:48<1:27:49, 43.55s/it, Train Acc=94.00%, VEpoch[062/182] Train Acc: 94.00% Valid Acc:88.40% Train loss:0.1681 Valid loss:0.3963 LR:0.1
Training Progress:  34%|▎| 62/182 [44:48<1:27:05, 43.55s/it, Train Acc=94.00%, VTraining: Epoch[063/182] Iteration[050/352] Loss: 0.1445 Acc:94.70%
Training: Epoch[063/182] Iteration[100/352] Loss: 0.1504 Acc:94.69%
Training: Epoch[063/182] Iteration[150/352] Loss: 0.1521 Acc:94.53%
Training: Epoch[063/182] Iteration[200/352] Loss: 0.1557 Acc:94.41%
Training: Epoch[063/182] Iteration[250/352] Loss: 0.1583 Acc:94.32%
Training: Epoch[063/182] Iteration[300/352] Loss: 0.1609 Acc:94.28%
Training: Epoch[063/182] Iteration[350/352] Loss: 0.1605 Acc:94.29%
Training Progress:  34%|▎| 62/182 [45:32<1:27:05, 43.55s/it, Train Acc=94.28%, VEpoch[063/182] Train Acc: 94.28% Valid Acc:88.70% Train loss:0.1608 Valid loss:0.3871 LR:0.1
Training Progress:  35%|▎| 63/182 [45:32<1:26:18, 43.52s/it, Train Acc=94.28%, VTraining: Epoch[064/182] Iteration[050/352] Loss: 0.1493 Acc:94.77%
Training: Epoch[064/182] Iteration[100/352] Loss: 0.1541 Acc:94.67%
Training: Epoch[064/182] Iteration[150/352] Loss: 0.1554 Acc:94.55%
Training: Epoch[064/182] Iteration[200/352] Loss: 0.1583 Acc:94.49%
Training: Epoch[064/182] Iteration[250/352] Loss: 0.1581 Acc:94.49%
Training: Epoch[064/182] Iteration[300/352] Loss: 0.1595 Acc:94.43%
Training: Epoch[064/182] Iteration[350/352] Loss: 0.1617 Acc:94.34%
Training Progress:  35%|▎| 63/182 [46:15<1:26:18, 43.52s/it, Train Acc=94.33%, VEpoch[064/182] Train Acc: 94.33% Valid Acc:87.02% Train loss:0.1619 Valid loss:0.4625 LR:0.1
Training Progress:  35%|▎| 64/182 [46:15<1:25:33, 43.51s/it, Train Acc=94.33%, VTraining: Epoch[065/182] Iteration[050/352] Loss: 0.1667 Acc:94.08%
Training: Epoch[065/182] Iteration[100/352] Loss: 0.1614 Acc:94.26%
Training: Epoch[065/182] Iteration[150/352] Loss: 0.1637 Acc:94.10%
Training: Epoch[065/182] Iteration[200/352] Loss: 0.1607 Acc:94.29%
Training: Epoch[065/182] Iteration[250/352] Loss: 0.1594 Acc:94.39%
Training: Epoch[065/182] Iteration[300/352] Loss: 0.1612 Acc:94.29%
Training: Epoch[065/182] Iteration[350/352] Loss: 0.1645 Acc:94.22%
Training Progress:  35%|▎| 64/182 [46:59<1:25:33, 43.51s/it, Train Acc=94.21%, VEpoch[065/182] Train Acc: 94.21% Valid Acc:88.48% Train loss:0.1649 Valid loss:0.4079 LR:0.1
Training Progress:  36%|▎| 65/182 [46:59<1:24:49, 43.50s/it, Train Acc=94.21%, VTraining: Epoch[066/182] Iteration[050/352] Loss: 0.1556 Acc:94.30%
Training: Epoch[066/182] Iteration[100/352] Loss: 0.1565 Acc:94.31%
Training: Epoch[066/182] Iteration[150/352] Loss: 0.1554 Acc:94.35%
Training: Epoch[066/182] Iteration[200/352] Loss: 0.1577 Acc:94.32%
Training: Epoch[066/182] Iteration[250/352] Loss: 0.1585 Acc:94.29%
Training: Epoch[066/182] Iteration[300/352] Loss: 0.1616 Acc:94.17%
Training: Epoch[066/182] Iteration[350/352] Loss: 0.1618 Acc:94.25%
Training Progress:  36%|▎| 65/182 [47:42<1:24:49, 43.50s/it, Train Acc=94.25%, VEpoch[066/182] Train Acc: 94.25% Valid Acc:88.84% Train loss:0.1620 Valid loss:0.3995 LR:0.1
Training Progress:  36%|▎| 66/182 [47:42<1:24:07, 43.52s/it, Train Acc=94.25%, VTraining: Epoch[067/182] Iteration[050/352] Loss: 0.1322 Acc:95.45%
Training: Epoch[067/182] Iteration[100/352] Loss: 0.1361 Acc:95.20%
Training: Epoch[067/182] Iteration[150/352] Loss: 0.1370 Acc:95.14%
Training: Epoch[067/182] Iteration[200/352] Loss: 0.1400 Acc:95.01%
Training: Epoch[067/182] Iteration[250/352] Loss: 0.1420 Acc:94.92%
Training: Epoch[067/182] Iteration[300/352] Loss: 0.1441 Acc:94.89%
Training: Epoch[067/182] Iteration[350/352] Loss: 0.1484 Acc:94.71%
Training Progress:  36%|▎| 66/182 [48:26<1:24:07, 43.52s/it, Train Acc=94.70%, VEpoch[067/182] Train Acc: 94.70% Valid Acc:89.44% Train loss:0.1489 Valid loss:0.3711 LR:0.1
Training Progress:  37%|▎| 67/182 [48:26<1:23:23, 43.51s/it, Train Acc=94.70%, VTraining: Epoch[068/182] Iteration[050/352] Loss: 0.1446 Acc:95.05%
Training: Epoch[068/182] Iteration[100/352] Loss: 0.1428 Acc:95.14%
Training: Epoch[068/182] Iteration[150/352] Loss: 0.1465 Acc:94.98%
Training: Epoch[068/182] Iteration[200/352] Loss: 0.1499 Acc:94.83%
Training: Epoch[068/182] Iteration[250/352] Loss: 0.1524 Acc:94.75%
Training: Epoch[068/182] Iteration[300/352] Loss: 0.1534 Acc:94.74%
Training: Epoch[068/182] Iteration[350/352] Loss: 0.1553 Acc:94.60%
Training Progress:  37%|▎| 67/182 [49:09<1:23:23, 43.51s/it, Train Acc=94.60%, VEpoch[068/182] Train Acc: 94.60% Valid Acc:87.62% Train loss:0.1558 Valid loss:0.4707 LR:0.1
Training Progress:  37%|▎| 68/182 [49:09<1:22:39, 43.51s/it, Train Acc=94.60%, VTraining: Epoch[069/182] Iteration[050/352] Loss: 0.1493 Acc:94.77%
Training: Epoch[069/182] Iteration[100/352] Loss: 0.1463 Acc:94.95%
Training: Epoch[069/182] Iteration[150/352] Loss: 0.1485 Acc:94.96%
Training: Epoch[069/182] Iteration[200/352] Loss: 0.1494 Acc:94.95%
Training: Epoch[069/182] Iteration[250/352] Loss: 0.1520 Acc:94.79%
Training: Epoch[069/182] Iteration[300/352] Loss: 0.1507 Acc:94.80%
Training: Epoch[069/182] Iteration[350/352] Loss: 0.1527 Acc:94.71%
Training Progress:  37%|▎| 68/182 [49:53<1:22:39, 43.51s/it, Train Acc=94.70%, VEpoch[069/182] Train Acc: 94.70% Valid Acc:89.00% Train loss:0.1533 Valid loss:0.3603 LR:0.1
Training Progress:  38%|▍| 69/182 [49:53<1:21:57, 43.51s/it, Train Acc=94.70%, VTraining: Epoch[070/182] Iteration[050/352] Loss: 0.1641 Acc:94.42%
Training: Epoch[070/182] Iteration[100/352] Loss: 0.1523 Acc:94.82%
Training: Epoch[070/182] Iteration[150/352] Loss: 0.1494 Acc:94.78%
Training: Epoch[070/182] Iteration[200/352] Loss: 0.1500 Acc:94.80%
Training: Epoch[070/182] Iteration[250/352] Loss: 0.1539 Acc:94.71%
Training: Epoch[070/182] Iteration[300/352] Loss: 0.1541 Acc:94.66%
Training: Epoch[070/182] Iteration[350/352] Loss: 0.1548 Acc:94.63%
Training Progress:  38%|▍| 69/182 [50:36<1:21:57, 43.51s/it, Train Acc=94.63%, VEpoch[070/182] Train Acc: 94.63% Valid Acc:88.42% Train loss:0.1548 Valid loss:0.4145 LR:0.1
Training Progress:  38%|▍| 70/182 [50:36<1:21:13, 43.52s/it, Train Acc=94.63%, VTraining: Epoch[071/182] Iteration[050/352] Loss: 0.1293 Acc:95.75%
Training: Epoch[071/182] Iteration[100/352] Loss: 0.1280 Acc:95.60%
Training: Epoch[071/182] Iteration[150/352] Loss: 0.1347 Acc:95.38%
Training: Epoch[071/182] Iteration[200/352] Loss: 0.1365 Acc:95.28%
Training: Epoch[071/182] Iteration[250/352] Loss: 0.1406 Acc:95.09%
Training: Epoch[071/182] Iteration[300/352] Loss: 0.1435 Acc:95.04%
Training: Epoch[071/182] Iteration[350/352] Loss: 0.1468 Acc:94.92%
Training Progress:  38%|▍| 70/182 [51:20<1:21:13, 43.52s/it, Train Acc=94.91%, VEpoch[071/182] Train Acc: 94.91% Valid Acc:89.06% Train loss:0.1472 Valid loss:0.4021 LR:0.1
Training Progress:  39%|▍| 71/182 [51:20<1:20:33, 43.55s/it, Train Acc=94.91%, VTraining: Epoch[072/182] Iteration[050/352] Loss: 0.1483 Acc:95.08%
Training: Epoch[072/182] Iteration[100/352] Loss: 0.1434 Acc:95.09%
Training: Epoch[072/182] Iteration[150/352] Loss: 0.1426 Acc:95.04%
Training: Epoch[072/182] Iteration[200/352] Loss: 0.1408 Acc:95.10%
Training: Epoch[072/182] Iteration[250/352] Loss: 0.1434 Acc:94.98%
Training: Epoch[072/182] Iteration[300/352] Loss: 0.1471 Acc:94.82%
Training: Epoch[072/182] Iteration[350/352] Loss: 0.1496 Acc:94.72%
Training Progress:  39%|▍| 71/182 [52:03<1:20:33, 43.55s/it, Train Acc=94.70%, VEpoch[072/182] Train Acc: 94.70% Valid Acc:84.82% Train loss:0.1502 Valid loss:0.5515 LR:0.1
Training Progress:  40%|▍| 72/182 [52:03<1:19:51, 43.56s/it, Train Acc=94.70%, VTraining: Epoch[073/182] Iteration[050/352] Loss: 0.1416 Acc:95.06%
Training: Epoch[073/182] Iteration[100/352] Loss: 0.1341 Acc:95.30%
Training: Epoch[073/182] Iteration[150/352] Loss: 0.1374 Acc:95.28%
Training: Epoch[073/182] Iteration[200/352] Loss: 0.1425 Acc:95.13%
Training: Epoch[073/182] Iteration[250/352] Loss: 0.1467 Acc:94.96%
Training: Epoch[073/182] Iteration[300/352] Loss: 0.1484 Acc:94.87%
Training: Epoch[073/182] Iteration[350/352] Loss: 0.1522 Acc:94.71%
Training Progress:  40%|▍| 72/182 [52:47<1:19:51, 43.56s/it, Train Acc=94.70%, VEpoch[073/182] Train Acc: 94.70% Valid Acc:88.26% Train loss:0.1523 Valid loss:0.4307 LR:0.1
Training Progress:  40%|▍| 73/182 [52:47<1:19:08, 43.56s/it, Train Acc=94.70%, VTraining: Epoch[074/182] Iteration[050/352] Loss: 0.1546 Acc:94.89%
Training: Epoch[074/182] Iteration[100/352] Loss: 0.1518 Acc:94.84%
Training: Epoch[074/182] Iteration[150/352] Loss: 0.1494 Acc:94.86%
Training: Epoch[074/182] Iteration[200/352] Loss: 0.1515 Acc:94.74%
Training: Epoch[074/182] Iteration[250/352] Loss: 0.1522 Acc:94.68%
Training: Epoch[074/182] Iteration[300/352] Loss: 0.1514 Acc:94.69%
Training: Epoch[074/182] Iteration[350/352] Loss: 0.1520 Acc:94.70%
Training Progress:  40%|▍| 73/182 [53:31<1:19:08, 43.56s/it, Train Acc=94.69%, VEpoch[074/182] Train Acc: 94.69% Valid Acc:89.06% Train loss:0.1520 Valid loss:0.3972 LR:0.1
Training Progress:  41%|▍| 74/182 [53:31<1:18:26, 43.58s/it, Train Acc=94.69%, VTraining: Epoch[075/182] Iteration[050/352] Loss: 0.1337 Acc:95.41%
Training: Epoch[075/182] Iteration[100/352] Loss: 0.1257 Acc:95.58%
Training: Epoch[075/182] Iteration[150/352] Loss: 0.1286 Acc:95.54%
Training: Epoch[075/182] Iteration[200/352] Loss: 0.1310 Acc:95.54%
Training: Epoch[075/182] Iteration[250/352] Loss: 0.1366 Acc:95.27%
Training: Epoch[075/182] Iteration[300/352] Loss: 0.1393 Acc:95.16%
Training: Epoch[075/182] Iteration[350/352] Loss: 0.1424 Acc:95.07%
Training Progress:  41%|▍| 74/182 [54:14<1:18:26, 43.58s/it, Train Acc=95.07%, VEpoch[075/182] Train Acc: 95.07% Valid Acc:88.26% Train loss:0.1426 Valid loss:0.4271 LR:0.1
Training Progress:  41%|▍| 75/182 [54:14<1:17:45, 43.61s/it, Train Acc=95.07%, VTraining: Epoch[076/182] Iteration[050/352] Loss: 0.1449 Acc:94.98%
Training: Epoch[076/182] Iteration[100/352] Loss: 0.1421 Acc:95.12%
Training: Epoch[076/182] Iteration[150/352] Loss: 0.1455 Acc:94.84%
Training: Epoch[076/182] Iteration[200/352] Loss: 0.1495 Acc:94.74%
Training: Epoch[076/182] Iteration[250/352] Loss: 0.1520 Acc:94.67%
Training: Epoch[076/182] Iteration[300/352] Loss: 0.1543 Acc:94.61%
Training: Epoch[076/182] Iteration[350/352] Loss: 0.1549 Acc:94.59%
Training Progress:  41%|▍| 75/182 [54:58<1:17:45, 43.61s/it, Train Acc=94.59%, VEpoch[076/182] Train Acc: 94.59% Valid Acc:88.22% Train loss:0.1549 Valid loss:0.4329 LR:0.1
Training Progress:  42%|▍| 76/182 [54:58<1:17:07, 43.65s/it, Train Acc=94.59%, VTraining: Epoch[077/182] Iteration[050/352] Loss: 0.1467 Acc:94.94%
Training: Epoch[077/182] Iteration[100/352] Loss: 0.1417 Acc:95.13%
Training: Epoch[077/182] Iteration[150/352] Loss: 0.1385 Acc:95.20%
Training: Epoch[077/182] Iteration[200/352] Loss: 0.1413 Acc:95.09%
Training: Epoch[077/182] Iteration[250/352] Loss: 0.1456 Acc:94.86%
Training: Epoch[077/182] Iteration[300/352] Loss: 0.1501 Acc:94.73%
Training: Epoch[077/182] Iteration[350/352] Loss: 0.1505 Acc:94.72%
Training Progress:  42%|▍| 76/182 [55:42<1:17:07, 43.65s/it, Train Acc=94.72%, VEpoch[077/182] Train Acc: 94.72% Valid Acc:87.46% Train loss:0.1506 Valid loss:0.4473 LR:0.1
Training Progress:  42%|▍| 77/182 [55:42<1:16:26, 43.68s/it, Train Acc=94.72%, VTraining: Epoch[078/182] Iteration[050/352] Loss: 0.1316 Acc:95.56%
Training: Epoch[078/182] Iteration[100/352] Loss: 0.1401 Acc:95.26%
Training: Epoch[078/182] Iteration[150/352] Loss: 0.1442 Acc:95.06%
Training: Epoch[078/182] Iteration[200/352] Loss: 0.1517 Acc:94.74%
Training: Epoch[078/182] Iteration[250/352] Loss: 0.1535 Acc:94.66%
Training: Epoch[078/182] Iteration[300/352] Loss: 0.1508 Acc:94.78%
Training: Epoch[078/182] Iteration[350/352] Loss: 0.1513 Acc:94.80%
Training Progress:  42%|▍| 77/182 [56:26<1:16:26, 43.68s/it, Train Acc=94.80%, VEpoch[078/182] Train Acc: 94.80% Valid Acc:87.96% Train loss:0.1512 Valid loss:0.4367 LR:0.1
Training Progress:  43%|▍| 78/182 [56:26<1:15:54, 43.79s/it, Train Acc=94.80%, VTraining: Epoch[079/182] Iteration[050/352] Loss: 0.1240 Acc:95.25%
Training: Epoch[079/182] Iteration[100/352] Loss: 0.1280 Acc:95.20%
Training: Epoch[079/182] Iteration[150/352] Loss: 0.1315 Acc:95.08%
Training: Epoch[079/182] Iteration[200/352] Loss: 0.1357 Acc:95.03%
Training: Epoch[079/182] Iteration[250/352] Loss: 0.1408 Acc:94.93%
Training: Epoch[079/182] Iteration[300/352] Loss: 0.1444 Acc:94.81%
Training: Epoch[079/182] Iteration[350/352] Loss: 0.1446 Acc:94.80%
Training Progress:  43%|▍| 78/182 [57:09<1:15:54, 43.79s/it, Train Acc=94.81%, VEpoch[079/182] Train Acc: 94.81% Valid Acc:88.06% Train loss:0.1443 Valid loss:0.4101 LR:0.1
Training Progress:  43%|▍| 79/182 [57:09<1:15:01, 43.71s/it, Train Acc=94.81%, VTraining: Epoch[080/182] Iteration[050/352] Loss: 0.1232 Acc:95.39%
Training: Epoch[080/182] Iteration[100/352] Loss: 0.1280 Acc:95.40%
Training: Epoch[080/182] Iteration[150/352] Loss: 0.1287 Acc:95.43%
Training: Epoch[080/182] Iteration[200/352] Loss: 0.1355 Acc:95.26%
Training: Epoch[080/182] Iteration[250/352] Loss: 0.1379 Acc:95.18%
Training: Epoch[080/182] Iteration[300/352] Loss: 0.1397 Acc:95.15%
Training: Epoch[080/182] Iteration[350/352] Loss: 0.1426 Acc:95.04%
Training Progress:  43%|▍| 79/182 [57:53<1:15:01, 43.71s/it, Train Acc=95.03%, VEpoch[080/182] Train Acc: 95.03% Valid Acc:86.40% Train loss:0.1431 Valid loss:0.5349 LR:0.1
Training Progress:  44%|▍| 80/182 [57:53<1:14:13, 43.67s/it, Train Acc=95.03%, VTraining: Epoch[081/182] Iteration[050/352] Loss: 0.1418 Acc:94.81%
Training: Epoch[081/182] Iteration[100/352] Loss: 0.1321 Acc:95.19%
Training: Epoch[081/182] Iteration[150/352] Loss: 0.1265 Acc:95.40%
Training: Epoch[081/182] Iteration[200/352] Loss: 0.1348 Acc:95.10%
Training: Epoch[081/182] Iteration[250/352] Loss: 0.1402 Acc:94.96%
Training: Epoch[081/182] Iteration[300/352] Loss: 0.1382 Acc:95.02%
Training: Epoch[081/182] Iteration[350/352] Loss: 0.1435 Acc:94.83%
Training Progress:  44%|▍| 80/182 [58:36<1:14:13, 43.67s/it, Train Acc=94.83%, VEpoch[081/182] Train Acc: 94.83% Valid Acc:85.02% Train loss:0.1438 Valid loss:0.5416 LR:0.1
Training Progress:  45%|▍| 81/182 [58:36<1:13:25, 43.62s/it, Train Acc=94.83%, VTraining: Epoch[082/182] Iteration[050/352] Loss: 0.1512 Acc:94.48%
Training: Epoch[082/182] Iteration[100/352] Loss: 0.1426 Acc:95.03%
Training: Epoch[082/182] Iteration[150/352] Loss: 0.1379 Acc:95.28%
Training: Epoch[082/182] Iteration[200/352] Loss: 0.1368 Acc:95.29%
Training: Epoch[082/182] Iteration[250/352] Loss: 0.1403 Acc:95.12%
Training: Epoch[082/182] Iteration[300/352] Loss: 0.1433 Acc:95.02%
Training: Epoch[082/182] Iteration[350/352] Loss: 0.1439 Acc:94.99%
Training Progress:  45%|▍| 81/182 [59:20<1:13:25, 43.62s/it, Train Acc=94.98%, VEpoch[082/182] Train Acc: 94.98% Valid Acc:89.64% Train loss:0.1443 Valid loss:0.3836 LR:0.1
Training Progress:  45%|▍| 82/182 [59:20<1:12:41, 43.61s/it, Train Acc=94.98%, VTraining: Epoch[083/182] Iteration[050/352] Loss: 0.1423 Acc:95.20%
Training: Epoch[083/182] Iteration[100/352] Loss: 0.1389 Acc:95.26%
Training: Epoch[083/182] Iteration[150/352] Loss: 0.1434 Acc:95.05%
Training: Epoch[083/182] Iteration[200/352] Loss: 0.1435 Acc:95.04%
Training: Epoch[083/182] Iteration[250/352] Loss: 0.1435 Acc:95.06%
Training: Epoch[083/182] Iteration[300/352] Loss: 0.1468 Acc:94.95%
Training: Epoch[083/182] Iteration[350/352] Loss: 0.1480 Acc:94.90%
Training Progress:  45%|▍| 82/182 [1:00:04<1:12:41, 43.61s/it, Train Acc=94.89%,Epoch[083/182] Train Acc: 94.89% Valid Acc:85.34% Train loss:0.1480 Valid loss:0.5928 LR:0.1
Training Progress:  46%|▍| 83/182 [1:00:04<1:12:00, 43.64s/it, Train Acc=94.89%,Training: Epoch[084/182] Iteration[050/352] Loss: 0.1551 Acc:94.61%
Training: Epoch[084/182] Iteration[100/352] Loss: 0.1512 Acc:94.78%
Training: Epoch[084/182] Iteration[150/352] Loss: 0.1407 Acc:95.14%
Training: Epoch[084/182] Iteration[200/352] Loss: 0.1385 Acc:95.22%
Training: Epoch[084/182] Iteration[250/352] Loss: 0.1369 Acc:95.28%
Training: Epoch[084/182] Iteration[300/352] Loss: 0.1363 Acc:95.25%
Training: Epoch[084/182] Iteration[350/352] Loss: 0.1365 Acc:95.23%
Training Progress:  46%|▍| 83/182 [1:00:47<1:12:00, 43.64s/it, Train Acc=95.22%,Epoch[084/182] Train Acc: 95.22% Valid Acc:87.48% Train loss:0.1370 Valid loss:0.4635 LR:0.1
Training Progress:  46%|▍| 84/182 [1:00:47<1:11:18, 43.66s/it, Train Acc=95.22%,Training: Epoch[085/182] Iteration[050/352] Loss: 0.1374 Acc:95.42%
Training: Epoch[085/182] Iteration[100/352] Loss: 0.1344 Acc:95.44%
Training: Epoch[085/182] Iteration[150/352] Loss: 0.1332 Acc:95.45%
Training: Epoch[085/182] Iteration[200/352] Loss: 0.1352 Acc:95.35%
Training: Epoch[085/182] Iteration[250/352] Loss: 0.1360 Acc:95.35%
Training: Epoch[085/182] Iteration[300/352] Loss: 0.1375 Acc:95.26%
Training: Epoch[085/182] Iteration[350/352] Loss: 0.1366 Acc:95.27%
Training Progress:  46%|▍| 84/182 [1:01:31<1:11:18, 43.66s/it, Train Acc=95.26%,Epoch[085/182] Train Acc: 95.26% Valid Acc:90.24% Train loss:0.1370 Valid loss:0.3550 LR:0.1
Training Progress:  47%|▍| 85/182 [1:01:31<1:10:38, 43.70s/it, Train Acc=95.26%,Training: Epoch[086/182] Iteration[050/352] Loss: 0.1415 Acc:94.91%
Training: Epoch[086/182] Iteration[100/352] Loss: 0.1445 Acc:94.85%
Training: Epoch[086/182] Iteration[150/352] Loss: 0.1396 Acc:95.07%
Training: Epoch[086/182] Iteration[200/352] Loss: 0.1372 Acc:95.21%
Training: Epoch[086/182] Iteration[250/352] Loss: 0.1387 Acc:95.12%
Training: Epoch[086/182] Iteration[300/352] Loss: 0.1420 Acc:95.01%
Training: Epoch[086/182] Iteration[350/352] Loss: 0.1436 Acc:94.95%
Training Progress:  47%|▍| 85/182 [1:02:15<1:10:38, 43.70s/it, Train Acc=94.94%,Epoch[086/182] Train Acc: 94.94% Valid Acc:90.34% Train loss:0.1439 Valid loss:0.3557 LR:0.1
Training Progress:  47%|▍| 86/182 [1:02:15<1:09:50, 43.65s/it, Train Acc=94.94%,Training: Epoch[087/182] Iteration[050/352] Loss: 0.1119 Acc:96.05%
Training: Epoch[087/182] Iteration[100/352] Loss: 0.1227 Acc:95.72%
Training: Epoch[087/182] Iteration[150/352] Loss: 0.1243 Acc:95.59%
Training: Epoch[087/182] Iteration[200/352] Loss: 0.1261 Acc:95.50%
Training: Epoch[087/182] Iteration[250/352] Loss: 0.1297 Acc:95.38%
Training: Epoch[087/182] Iteration[300/352] Loss: 0.1314 Acc:95.29%
Training: Epoch[087/182] Iteration[350/352] Loss: 0.1348 Acc:95.23%
Training Progress:  47%|▍| 86/182 [1:02:58<1:09:50, 43.65s/it, Train Acc=95.22%,Epoch[087/182] Train Acc: 95.22% Valid Acc:89.42% Train loss:0.1353 Valid loss:0.3794 LR:0.1
Training Progress:  48%|▍| 87/182 [1:02:58<1:09:05, 43.64s/it, Train Acc=95.22%,Training: Epoch[088/182] Iteration[050/352] Loss: 0.1398 Acc:95.23%
Training: Epoch[088/182] Iteration[100/352] Loss: 0.1323 Acc:95.54%
Training: Epoch[088/182] Iteration[150/352] Loss: 0.1330 Acc:95.36%
Training: Epoch[088/182] Iteration[200/352] Loss: 0.1331 Acc:95.42%
Training: Epoch[088/182] Iteration[250/352] Loss: 0.1334 Acc:95.35%
Training: Epoch[088/182] Iteration[300/352] Loss: 0.1353 Acc:95.28%
Training: Epoch[088/182] Iteration[350/352] Loss: 0.1378 Acc:95.20%
Training Progress:  48%|▍| 87/182 [1:03:42<1:09:05, 43.64s/it, Train Acc=95.21%,Epoch[088/182] Train Acc: 95.21% Valid Acc:87.14% Train loss:0.1376 Valid loss:0.4700 LR:0.1
Training Progress:  48%|▍| 88/182 [1:03:42<1:08:20, 43.62s/it, Train Acc=95.21%,Training: Epoch[089/182] Iteration[050/352] Loss: 0.1241 Acc:95.81%
Training: Epoch[089/182] Iteration[100/352] Loss: 0.1331 Acc:95.45%
Training: Epoch[089/182] Iteration[150/352] Loss: 0.1366 Acc:95.15%
Training: Epoch[089/182] Iteration[200/352] Loss: 0.1363 Acc:95.08%
Training: Epoch[089/182] Iteration[250/352] Loss: 0.1370 Acc:95.04%
Training: Epoch[089/182] Iteration[300/352] Loss: 0.1397 Acc:94.94%
Training: Epoch[089/182] Iteration[350/352] Loss: 0.1430 Acc:94.83%
Training Progress:  48%|▍| 88/182 [1:04:26<1:08:20, 43.62s/it, Train Acc=94.83%,Epoch[089/182] Train Acc: 94.83% Valid Acc:85.24% Train loss:0.1430 Valid loss:0.5373 LR:0.1
Training Progress:  49%|▍| 89/182 [1:04:26<1:07:35, 43.61s/it, Train Acc=94.83%,Training: Epoch[090/182] Iteration[050/352] Loss: 0.1390 Acc:94.91%
Training: Epoch[090/182] Iteration[100/352] Loss: 0.1302 Acc:95.27%
Training: Epoch[090/182] Iteration[150/352] Loss: 0.1335 Acc:95.24%
Training: Epoch[090/182] Iteration[200/352] Loss: 0.1348 Acc:95.32%
Training: Epoch[090/182] Iteration[250/352] Loss: 0.1384 Acc:95.17%
Training: Epoch[090/182] Iteration[300/352] Loss: 0.1386 Acc:95.14%
Training: Epoch[090/182] Iteration[350/352] Loss: 0.1384 Acc:95.17%
Training Progress:  49%|▍| 89/182 [1:05:09<1:07:35, 43.61s/it, Train Acc=95.16%,Epoch[090/182] Train Acc: 95.16% Valid Acc:85.58% Train loss:0.1387 Valid loss:0.5704 LR:0.1
Training Progress:  49%|▍| 90/182 [1:05:09<1:06:54, 43.63s/it, Train Acc=95.16%,Training: Epoch[091/182] Iteration[050/352] Loss: 0.1366 Acc:95.41%
Training: Epoch[091/182] Iteration[100/352] Loss: 0.1235 Acc:95.80%
Training: Epoch[091/182] Iteration[150/352] Loss: 0.1244 Acc:95.73%
Training: Epoch[091/182] Iteration[200/352] Loss: 0.1284 Acc:95.55%
Training: Epoch[091/182] Iteration[250/352] Loss: 0.1306 Acc:95.44%
Training: Epoch[091/182] Iteration[300/352] Loss: 0.1325 Acc:95.39%
Training: Epoch[091/182] Iteration[350/352] Loss: 0.1338 Acc:95.36%
Training Progress:  49%|▍| 90/182 [1:05:53<1:06:54, 43.63s/it, Train Acc=95.36%,Epoch[091/182] Train Acc: 95.36% Valid Acc:88.90% Train loss:0.1338 Valid loss:0.4290 LR:0.1
Training Progress:  50%|▌| 91/182 [1:05:53<1:06:10, 43.63s/it, Train Acc=95.36%,Training: Epoch[092/182] Iteration[050/352] Loss: 0.1353 Acc:95.33%
Training: Epoch[092/182] Iteration[100/352] Loss: 0.1217 Acc:95.78%
Training: Epoch[092/182] Iteration[150/352] Loss: 0.1241 Acc:95.69%
Training: Epoch[092/182] Iteration[200/352] Loss: 0.1314 Acc:95.44%
Training: Epoch[092/182] Iteration[250/352] Loss: 0.1348 Acc:95.25%
Training: Epoch[092/182] Iteration[300/352] Loss: 0.1374 Acc:95.16%
Training: Epoch[092/182] Iteration[350/352] Loss: 0.1398 Acc:95.08%
Training Progress:  50%|▌| 91/182 [1:06:36<1:06:10, 43.63s/it, Train Acc=95.08%,Epoch[092/182] Train Acc: 95.08% Valid Acc:87.28% Train loss:0.1397 Valid loss:0.4817 LR:0.1
Training Progress:  51%|▌| 92/182 [1:06:36<1:05:24, 43.61s/it, Train Acc=95.08%,Training: Epoch[093/182] Iteration[050/352] Loss: 0.1038 Acc:96.64%
Training: Epoch[093/182] Iteration[100/352] Loss: 0.0906 Acc:97.12%
Training: Epoch[093/182] Iteration[150/352] Loss: 0.0816 Acc:97.41%
Training: Epoch[093/182] Iteration[200/352] Loss: 0.0774 Acc:97.54%
Training: Epoch[093/182] Iteration[250/352] Loss: 0.0723 Acc:97.70%
Training: Epoch[093/182] Iteration[300/352] Loss: 0.0691 Acc:97.78%
Training: Epoch[093/182] Iteration[350/352] Loss: 0.0661 Acc:97.90%
Training Progress:  51%|▌| 92/182 [1:07:20<1:05:24, 43.61s/it, Train Acc=97.90%,Epoch[093/182] Train Acc: 97.90% Valid Acc:92.84% Train loss:0.0659 Valid loss:0.2370 LR:0.010000000000000002
Training Progress:  51%|▌| 93/182 [1:07:20<1:04:43, 43.64s/it, Train Acc=97.90%,Training: Epoch[094/182] Iteration[050/352] Loss: 0.0402 Acc:98.67%
Training: Epoch[094/182] Iteration[100/352] Loss: 0.0408 Acc:98.74%
Training: Epoch[094/182] Iteration[150/352] Loss: 0.0408 Acc:98.78%
Training: Epoch[094/182] Iteration[200/352] Loss: 0.0403 Acc:98.79%
Training: Epoch[094/182] Iteration[250/352] Loss: 0.0393 Acc:98.81%
Training: Epoch[094/182] Iteration[300/352] Loss: 0.0389 Acc:98.83%
Training: Epoch[094/182] Iteration[350/352] Loss: 0.0386 Acc:98.83%
Training Progress:  51%|▌| 93/182 [1:08:04<1:04:43, 43.64s/it, Train Acc=98.84%,Epoch[094/182] Train Acc: 98.84% Valid Acc:93.20% Train loss:0.0386 Valid loss:0.2371 LR:0.010000000000000002
Training Progress:  52%|▌| 94/182 [1:08:04<1:04:02, 43.67s/it, Train Acc=98.84%,Training: Epoch[095/182] Iteration[050/352] Loss: 0.0329 Acc:99.06%
Training: Epoch[095/182] Iteration[100/352] Loss: 0.0315 Acc:99.11%
Training: Epoch[095/182] Iteration[150/352] Loss: 0.0321 Acc:99.08%
Training: Epoch[095/182] Iteration[200/352] Loss: 0.0309 Acc:99.12%
Training: Epoch[095/182] Iteration[250/352] Loss: 0.0306 Acc:99.13%
Training: Epoch[095/182] Iteration[300/352] Loss: 0.0307 Acc:99.13%
Training: Epoch[095/182] Iteration[350/352] Loss: 0.0306 Acc:99.13%
Training Progress:  52%|▌| 94/182 [1:08:48<1:04:02, 43.67s/it, Train Acc=99.13%,Epoch[095/182] Train Acc: 99.13% Valid Acc:93.30% Train loss:0.0307 Valid loss:0.2423 LR:0.010000000000000002
Training Progress:  52%|▌| 95/182 [1:08:48<1:03:29, 43.79s/it, Train Acc=99.13%,Training: Epoch[096/182] Iteration[050/352] Loss: 0.0275 Acc:99.23%
Training: Epoch[096/182] Iteration[100/352] Loss: 0.0270 Acc:99.24%
Training: Epoch[096/182] Iteration[150/352] Loss: 0.0273 Acc:99.24%
Training: Epoch[096/182] Iteration[200/352] Loss: 0.0268 Acc:99.28%
Training: Epoch[096/182] Iteration[250/352] Loss: 0.0265 Acc:99.28%
Training: Epoch[096/182] Iteration[300/352] Loss: 0.0263 Acc:99.29%
Training: Epoch[096/182] Iteration[350/352] Loss: 0.0265 Acc:99.27%
Training Progress:  52%|▌| 95/182 [1:09:32<1:03:29, 43.79s/it, Train Acc=99.27%,Epoch[096/182] Train Acc: 99.27% Valid Acc:93.48% Train loss:0.0265 Valid loss:0.2475 LR:0.010000000000000002
Training Progress:  53%|▌| 96/182 [1:09:32<1:02:51, 43.85s/it, Train Acc=99.27%,Training: Epoch[097/182] Iteration[050/352] Loss: 0.0213 Acc:99.42%
Training: Epoch[097/182] Iteration[100/352] Loss: 0.0226 Acc:99.37%
Training: Epoch[097/182] Iteration[150/352] Loss: 0.0218 Acc:99.41%
Training: Epoch[097/182] Iteration[200/352] Loss: 0.0218 Acc:99.41%
Training: Epoch[097/182] Iteration[250/352] Loss: 0.0223 Acc:99.38%
Training: Epoch[097/182] Iteration[300/352] Loss: 0.0222 Acc:99.40%
Training: Epoch[097/182] Iteration[350/352] Loss: 0.0217 Acc:99.42%
Training Progress:  53%|▌| 96/182 [1:10:16<1:02:51, 43.85s/it, Train Acc=99.42%,Epoch[097/182] Train Acc: 99.42% Valid Acc:93.60% Train loss:0.0216 Valid loss:0.2480 LR:0.010000000000000002
Training Progress:  53%|▌| 97/182 [1:10:16<1:02:13, 43.93s/it, Train Acc=99.42%,Training: Epoch[098/182] Iteration[050/352] Loss: 0.0209 Acc:99.38%
Training: Epoch[098/182] Iteration[100/352] Loss: 0.0197 Acc:99.46%
Training: Epoch[098/182] Iteration[150/352] Loss: 0.0196 Acc:99.49%
Training: Epoch[098/182] Iteration[200/352] Loss: 0.0199 Acc:99.46%
Training: Epoch[098/182] Iteration[250/352] Loss: 0.0200 Acc:99.45%
Training: Epoch[098/182] Iteration[300/352] Loss: 0.0200 Acc:99.45%
Training: Epoch[098/182] Iteration[350/352] Loss: 0.0197 Acc:99.46%
Training Progress:  53%|▌| 97/182 [1:11:00<1:02:13, 43.93s/it, Train Acc=99.46%,Epoch[098/182] Train Acc: 99.46% Valid Acc:93.50% Train loss:0.0196 Valid loss:0.2491 LR:0.010000000000000002
Training Progress:  54%|▌| 98/182 [1:11:00<1:01:22, 43.84s/it, Train Acc=99.46%,Training: Epoch[099/182] Iteration[050/352] Loss: 0.0164 Acc:99.66%
Training: Epoch[099/182] Iteration[100/352] Loss: 0.0162 Acc:99.63%
Training: Epoch[099/182] Iteration[150/352] Loss: 0.0166 Acc:99.58%
Training: Epoch[099/182] Iteration[200/352] Loss: 0.0172 Acc:99.55%
Training: Epoch[099/182] Iteration[250/352] Loss: 0.0172 Acc:99.54%
Training: Epoch[099/182] Iteration[300/352] Loss: 0.0173 Acc:99.53%
Training: Epoch[099/182] Iteration[350/352] Loss: 0.0176 Acc:99.52%
Training Progress:  54%|▌| 98/182 [1:11:43<1:01:22, 43.84s/it, Train Acc=99.52%,Epoch[099/182] Train Acc: 99.52% Valid Acc:93.18% Train loss:0.0177 Valid loss:0.2615 LR:0.010000000000000002
Training Progress:  54%|▌| 99/182 [1:11:43<1:00:33, 43.78s/it, Train Acc=99.52%,Training: Epoch[100/182] Iteration[050/352] Loss: 0.0137 Acc:99.67%
Training: Epoch[100/182] Iteration[100/352] Loss: 0.0140 Acc:99.70%
Training: Epoch[100/182] Iteration[150/352] Loss: 0.0151 Acc:99.64%
Training: Epoch[100/182] Iteration[200/352] Loss: 0.0162 Acc:99.57%
Training: Epoch[100/182] Iteration[250/352] Loss: 0.0158 Acc:99.60%
Training: Epoch[100/182] Iteration[300/352] Loss: 0.0155 Acc:99.62%
Training: Epoch[100/182] Iteration[350/352] Loss: 0.0156 Acc:99.60%
Training Progress:  54%|▌| 99/182 [1:12:27<1:00:33, 43.78s/it, Train Acc=99.60%,Epoch[100/182] Train Acc: 99.60% Valid Acc:93.42% Train loss:0.0156 Valid loss:0.2577 LR:0.010000000000000002
Training Progress:  55%|▌| 100/182 [1:12:27<59:53, 43.82s/it, Train Acc=99.60%, Training: Epoch[101/182] Iteration[050/352] Loss: 0.0127 Acc:99.75%
Training: Epoch[101/182] Iteration[100/352] Loss: 0.0132 Acc:99.71%
Training: Epoch[101/182] Iteration[150/352] Loss: 0.0135 Acc:99.70%
Training: Epoch[101/182] Iteration[200/352] Loss: 0.0136 Acc:99.71%
Training: Epoch[101/182] Iteration[250/352] Loss: 0.0138 Acc:99.69%
Training: Epoch[101/182] Iteration[300/352] Loss: 0.0139 Acc:99.68%
Training: Epoch[101/182] Iteration[350/352] Loss: 0.0142 Acc:99.67%
Training Progress:  55%|▌| 100/182 [1:13:11<59:53, 43.82s/it, Train Acc=99.67%, Epoch[101/182] Train Acc: 99.67% Valid Acc:93.44% Train loss:0.0143 Valid loss:0.2592 LR:0.010000000000000002
Training Progress:  55%|▌| 101/182 [1:13:11<59:12, 43.86s/it, Train Acc=99.67%, Training: Epoch[102/182] Iteration[050/352] Loss: 0.0146 Acc:99.56%
Training: Epoch[102/182] Iteration[100/352] Loss: 0.0135 Acc:99.62%
Training: Epoch[102/182] Iteration[150/352] Loss: 0.0130 Acc:99.64%
Training: Epoch[102/182] Iteration[200/352] Loss: 0.0130 Acc:99.65%
Training: Epoch[102/182] Iteration[250/352] Loss: 0.0131 Acc:99.66%
Training: Epoch[102/182] Iteration[300/352] Loss: 0.0136 Acc:99.63%
Training: Epoch[102/182] Iteration[350/352] Loss: 0.0135 Acc:99.64%
Training Progress:  55%|▌| 101/182 [1:13:55<59:12, 43.86s/it, Train Acc=99.64%, Epoch[102/182] Train Acc: 99.64% Valid Acc:93.54% Train loss:0.0137 Valid loss:0.2597 LR:0.010000000000000002
Training Progress:  56%|▌| 102/182 [1:13:55<58:22, 43.78s/it, Train Acc=99.64%, Training: Epoch[103/182] Iteration[050/352] Loss: 0.0115 Acc:99.80%
Training: Epoch[103/182] Iteration[100/352] Loss: 0.0129 Acc:99.70%
Training: Epoch[103/182] Iteration[150/352] Loss: 0.0128 Acc:99.70%
Training: Epoch[103/182] Iteration[200/352] Loss: 0.0129 Acc:99.70%
Training: Epoch[103/182] Iteration[250/352] Loss: 0.0128 Acc:99.70%
Training: Epoch[103/182] Iteration[300/352] Loss: 0.0131 Acc:99.68%
Training: Epoch[103/182] Iteration[350/352] Loss: 0.0129 Acc:99.69%
Training Progress:  56%|▌| 102/182 [1:14:39<58:22, 43.78s/it, Train Acc=99.69%, Epoch[103/182] Train Acc: 99.69% Valid Acc:93.64% Train loss:0.0129 Valid loss:0.2667 LR:0.010000000000000002
Training Progress:  57%|▌| 103/182 [1:14:39<57:38, 43.78s/it, Train Acc=99.69%, Training: Epoch[104/182] Iteration[050/352] Loss: 0.0141 Acc:99.72%
Training: Epoch[104/182] Iteration[100/352] Loss: 0.0118 Acc:99.77%
Training: Epoch[104/182] Iteration[150/352] Loss: 0.0121 Acc:99.73%
Training: Epoch[104/182] Iteration[200/352] Loss: 0.0127 Acc:99.69%
Training: Epoch[104/182] Iteration[250/352] Loss: 0.0123 Acc:99.70%
Training: Epoch[104/182] Iteration[300/352] Loss: 0.0119 Acc:99.71%
Training: Epoch[104/182] Iteration[350/352] Loss: 0.0120 Acc:99.70%
Training Progress:  57%|▌| 103/182 [1:15:22<57:38, 43.78s/it, Train Acc=99.70%, Epoch[104/182] Train Acc: 99.70% Valid Acc:93.40% Train loss:0.0121 Valid loss:0.2606 LR:0.010000000000000002
Training Progress:  57%|▌| 104/182 [1:15:22<56:51, 43.74s/it, Train Acc=99.70%, Training: Epoch[105/182] Iteration[050/352] Loss: 0.0130 Acc:99.75%
Training: Epoch[105/182] Iteration[100/352] Loss: 0.0117 Acc:99.77%
Training: Epoch[105/182] Iteration[150/352] Loss: 0.0113 Acc:99.76%
Training: Epoch[105/182] Iteration[200/352] Loss: 0.0109 Acc:99.78%
Training: Epoch[105/182] Iteration[250/352] Loss: 0.0108 Acc:99.78%
Training: Epoch[105/182] Iteration[300/352] Loss: 0.0106 Acc:99.77%
Training: Epoch[105/182] Iteration[350/352] Loss: 0.0110 Acc:99.76%
Training Progress:  57%|▌| 104/182 [1:16:06<56:51, 43.74s/it, Train Acc=99.76%, Epoch[105/182] Train Acc: 99.76% Valid Acc:93.42% Train loss:0.0110 Valid loss:0.2664 LR:0.010000000000000002
Training Progress:  58%|▌| 105/182 [1:16:06<56:04, 43.70s/it, Train Acc=99.76%, Training: Epoch[106/182] Iteration[050/352] Loss: 0.0086 Acc:99.77%
Training: Epoch[106/182] Iteration[100/352] Loss: 0.0094 Acc:99.74%
Training: Epoch[106/182] Iteration[150/352] Loss: 0.0089 Acc:99.79%
Training: Epoch[106/182] Iteration[200/352] Loss: 0.0090 Acc:99.80%
Training: Epoch[106/182] Iteration[250/352] Loss: 0.0091 Acc:99.78%
Training: Epoch[106/182] Iteration[300/352] Loss: 0.0091 Acc:99.79%
Training: Epoch[106/182] Iteration[350/352] Loss: 0.0095 Acc:99.78%
Training Progress:  58%|▌| 105/182 [1:16:50<56:04, 43.70s/it, Train Acc=99.78%, Epoch[106/182] Train Acc: 99.78% Valid Acc:93.58% Train loss:0.0095 Valid loss:0.2677 LR:0.010000000000000002
Training Progress:  58%|▌| 106/182 [1:16:50<55:20, 43.70s/it, Train Acc=99.78%, Training: Epoch[107/182] Iteration[050/352] Loss: 0.0075 Acc:99.83%
Training: Epoch[107/182] Iteration[100/352] Loss: 0.0077 Acc:99.85%
Training: Epoch[107/182] Iteration[150/352] Loss: 0.0088 Acc:99.82%
Training: Epoch[107/182] Iteration[200/352] Loss: 0.0089 Acc:99.81%
Training: Epoch[107/182] Iteration[250/352] Loss: 0.0087 Acc:99.82%
Training: Epoch[107/182] Iteration[300/352] Loss: 0.0090 Acc:99.79%
Training: Epoch[107/182] Iteration[350/352] Loss: 0.0089 Acc:99.80%
Training Progress:  58%|▌| 106/182 [1:17:33<55:20, 43.70s/it, Train Acc=99.80%, Epoch[107/182] Train Acc: 99.80% Valid Acc:93.54% Train loss:0.0089 Valid loss:0.2715 LR:0.010000000000000002
Training Progress:  59%|▌| 107/182 [1:17:33<54:35, 43.67s/it, Train Acc=99.80%, Training: Epoch[108/182] Iteration[050/352] Loss: 0.0077 Acc:99.84%
Training: Epoch[108/182] Iteration[100/352] Loss: 0.0081 Acc:99.81%
Training: Epoch[108/182] Iteration[150/352] Loss: 0.0088 Acc:99.80%
Training: Epoch[108/182] Iteration[200/352] Loss: 0.0086 Acc:99.80%
Training: Epoch[108/182] Iteration[250/352] Loss: 0.0084 Acc:99.80%
Training: Epoch[108/182] Iteration[300/352] Loss: 0.0084 Acc:99.81%
Training: Epoch[108/182] Iteration[350/352] Loss: 0.0084 Acc:99.81%
Training Progress:  59%|▌| 107/182 [1:18:17<54:35, 43.67s/it, Train Acc=99.81%, Epoch[108/182] Train Acc: 99.81% Valid Acc:93.66% Train loss:0.0083 Valid loss:0.2698 LR:0.010000000000000002
Training Progress:  59%|▌| 108/182 [1:18:17<53:51, 43.67s/it, Train Acc=99.81%, Training: Epoch[109/182] Iteration[050/352] Loss: 0.0097 Acc:99.70%
Training: Epoch[109/182] Iteration[100/352] Loss: 0.0087 Acc:99.77%
Training: Epoch[109/182] Iteration[150/352] Loss: 0.0089 Acc:99.78%
Training: Epoch[109/182] Iteration[200/352] Loss: 0.0088 Acc:99.80%
Training: Epoch[109/182] Iteration[250/352] Loss: 0.0086 Acc:99.80%
Training: Epoch[109/182] Iteration[300/352] Loss: 0.0084 Acc:99.81%
Training: Epoch[109/182] Iteration[350/352] Loss: 0.0083 Acc:99.82%
Training Progress:  59%|▌| 108/182 [1:19:00<53:51, 43.67s/it, Train Acc=99.82%, Epoch[109/182] Train Acc: 99.82% Valid Acc:93.56% Train loss:0.0083 Valid loss:0.2758 LR:0.010000000000000002
Training Progress:  60%|▌| 109/182 [1:19:00<53:07, 43.67s/it, Train Acc=99.82%, Training: Epoch[110/182] Iteration[050/352] Loss: 0.0088 Acc:99.86%
Training: Epoch[110/182] Iteration[100/352] Loss: 0.0081 Acc:99.84%
Training: Epoch[110/182] Iteration[150/352] Loss: 0.0077 Acc:99.83%
Training: Epoch[110/182] Iteration[200/352] Loss: 0.0072 Acc:99.86%
Training: Epoch[110/182] Iteration[250/352] Loss: 0.0071 Acc:99.87%
Training: Epoch[110/182] Iteration[300/352] Loss: 0.0072 Acc:99.86%
Training: Epoch[110/182] Iteration[350/352] Loss: 0.0072 Acc:99.86%
Training Progress:  60%|▌| 109/182 [1:19:44<53:07, 43.67s/it, Train Acc=99.86%, Epoch[110/182] Train Acc: 99.86% Valid Acc:93.60% Train loss:0.0072 Valid loss:0.2776 LR:0.010000000000000002
Training Progress:  60%|▌| 110/182 [1:19:44<52:23, 43.66s/it, Train Acc=99.86%, Training: Epoch[111/182] Iteration[050/352] Loss: 0.0073 Acc:99.81%
Training: Epoch[111/182] Iteration[100/352] Loss: 0.0070 Acc:99.83%
Training: Epoch[111/182] Iteration[150/352] Loss: 0.0070 Acc:99.84%
Training: Epoch[111/182] Iteration[200/352] Loss: 0.0073 Acc:99.85%
Training: Epoch[111/182] Iteration[250/352] Loss: 0.0076 Acc:99.83%
Training: Epoch[111/182] Iteration[300/352] Loss: 0.0075 Acc:99.84%
Training: Epoch[111/182] Iteration[350/352] Loss: 0.0075 Acc:99.83%
Training Progress:  60%|▌| 110/182 [1:20:28<52:23, 43.66s/it, Train Acc=99.83%, Epoch[111/182] Train Acc: 99.83% Valid Acc:93.54% Train loss:0.0074 Valid loss:0.2747 LR:0.010000000000000002
Training Progress:  61%|▌| 111/182 [1:20:28<51:38, 43.64s/it, Train Acc=99.83%, Training: Epoch[112/182] Iteration[050/352] Loss: 0.0069 Acc:99.91%
Training: Epoch[112/182] Iteration[100/352] Loss: 0.0067 Acc:99.91%
Training: Epoch[112/182] Iteration[150/352] Loss: 0.0072 Acc:99.87%
Training: Epoch[112/182] Iteration[200/352] Loss: 0.0074 Acc:99.84%
Training: Epoch[112/182] Iteration[250/352] Loss: 0.0074 Acc:99.85%
Training: Epoch[112/182] Iteration[300/352] Loss: 0.0074 Acc:99.85%
Training: Epoch[112/182] Iteration[350/352] Loss: 0.0074 Acc:99.85%
Training Progress:  61%|▌| 111/182 [1:21:11<51:38, 43.64s/it, Train Acc=99.85%, Epoch[112/182] Train Acc: 99.85% Valid Acc:93.66% Train loss:0.0074 Valid loss:0.2802 LR:0.010000000000000002
Training Progress:  62%|▌| 112/182 [1:21:11<50:54, 43.63s/it, Train Acc=99.85%, Training: Epoch[113/182] Iteration[050/352] Loss: 0.0056 Acc:99.94%
Training: Epoch[113/182] Iteration[100/352] Loss: 0.0060 Acc:99.92%
Training: Epoch[113/182] Iteration[150/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[113/182] Iteration[200/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[113/182] Iteration[250/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[113/182] Iteration[300/352] Loss: 0.0060 Acc:99.89%
Training: Epoch[113/182] Iteration[350/352] Loss: 0.0061 Acc:99.88%
Training Progress:  62%|▌| 112/182 [1:21:55<50:54, 43.63s/it, Train Acc=99.88%, Epoch[113/182] Train Acc: 99.88% Valid Acc:93.78% Train loss:0.0061 Valid loss:0.2787 LR:0.010000000000000002
Training Progress:  62%|▌| 113/182 [1:21:55<50:11, 43.65s/it, Train Acc=99.88%, Training: Epoch[114/182] Iteration[050/352] Loss: 0.0066 Acc:99.88%
Training: Epoch[114/182] Iteration[100/352] Loss: 0.0064 Acc:99.88%
Training: Epoch[114/182] Iteration[150/352] Loss: 0.0062 Acc:99.88%
Training: Epoch[114/182] Iteration[200/352] Loss: 0.0062 Acc:99.88%
Training: Epoch[114/182] Iteration[250/352] Loss: 0.0061 Acc:99.88%
Training: Epoch[114/182] Iteration[300/352] Loss: 0.0062 Acc:99.88%
Training: Epoch[114/182] Iteration[350/352] Loss: 0.0060 Acc:99.89%
Training Progress:  62%|▌| 113/182 [1:22:39<50:11, 43.65s/it, Train Acc=99.89%, Epoch[114/182] Train Acc: 99.89% Valid Acc:93.72% Train loss:0.0060 Valid loss:0.2806 LR:0.010000000000000002
Training Progress:  63%|▋| 114/182 [1:22:39<49:26, 43.63s/it, Train Acc=99.89%, Training: Epoch[115/182] Iteration[050/352] Loss: 0.0058 Acc:99.91%
Training: Epoch[115/182] Iteration[100/352] Loss: 0.0061 Acc:99.89%
Training: Epoch[115/182] Iteration[150/352] Loss: 0.0057 Acc:99.91%
Training: Epoch[115/182] Iteration[200/352] Loss: 0.0055 Acc:99.90%
Training: Epoch[115/182] Iteration[250/352] Loss: 0.0057 Acc:99.89%
Training: Epoch[115/182] Iteration[300/352] Loss: 0.0057 Acc:99.89%
Training: Epoch[115/182] Iteration[350/352] Loss: 0.0056 Acc:99.89%
Training Progress:  63%|▋| 114/182 [1:23:22<49:26, 43.63s/it, Train Acc=99.89%, Epoch[115/182] Train Acc: 99.89% Valid Acc:93.64% Train loss:0.0056 Valid loss:0.2764 LR:0.010000000000000002
Training Progress:  63%|▋| 115/182 [1:23:22<48:41, 43.61s/it, Train Acc=99.89%, Training: Epoch[116/182] Iteration[050/352] Loss: 0.0058 Acc:99.86%
Training: Epoch[116/182] Iteration[100/352] Loss: 0.0058 Acc:99.88%
Training: Epoch[116/182] Iteration[150/352] Loss: 0.0067 Acc:99.85%
Training: Epoch[116/182] Iteration[200/352] Loss: 0.0066 Acc:99.86%
Training: Epoch[116/182] Iteration[250/352] Loss: 0.0068 Acc:99.86%
Training: Epoch[116/182] Iteration[300/352] Loss: 0.0068 Acc:99.86%
Training: Epoch[116/182] Iteration[350/352] Loss: 0.0065 Acc:99.86%
Training Progress:  63%|▋| 115/182 [1:24:06<48:41, 43.61s/it, Train Acc=99.86%, Epoch[116/182] Train Acc: 99.86% Valid Acc:93.62% Train loss:0.0065 Valid loss:0.2808 LR:0.010000000000000002
Training Progress:  64%|▋| 116/182 [1:24:06<47:58, 43.61s/it, Train Acc=99.86%, Training: Epoch[117/182] Iteration[050/352] Loss: 0.0050 Acc:99.89%
Training: Epoch[117/182] Iteration[100/352] Loss: 0.0054 Acc:99.89%
Training: Epoch[117/182] Iteration[150/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[117/182] Iteration[200/352] Loss: 0.0058 Acc:99.88%
Training: Epoch[117/182] Iteration[250/352] Loss: 0.0060 Acc:99.86%
Training: Epoch[117/182] Iteration[300/352] Loss: 0.0060 Acc:99.85%
Training: Epoch[117/182] Iteration[350/352] Loss: 0.0060 Acc:99.86%
Training Progress:  64%|▋| 116/182 [1:24:50<47:58, 43.61s/it, Train Acc=99.86%, Epoch[117/182] Train Acc: 99.86% Valid Acc:93.70% Train loss:0.0059 Valid loss:0.2826 LR:0.010000000000000002
Training Progress:  64%|▋| 117/182 [1:24:50<47:20, 43.71s/it, Train Acc=99.86%, Training: Epoch[118/182] Iteration[050/352] Loss: 0.0048 Acc:99.88%
Training: Epoch[118/182] Iteration[100/352] Loss: 0.0049 Acc:99.89%
Training: Epoch[118/182] Iteration[150/352] Loss: 0.0056 Acc:99.88%
Training: Epoch[118/182] Iteration[200/352] Loss: 0.0055 Acc:99.89%
Training: Epoch[118/182] Iteration[250/352] Loss: 0.0055 Acc:99.90%
Training: Epoch[118/182] Iteration[300/352] Loss: 0.0055 Acc:99.90%
Training: Epoch[118/182] Iteration[350/352] Loss: 0.0055 Acc:99.90%
Training Progress:  64%|▋| 117/182 [1:25:33<47:20, 43.71s/it, Train Acc=99.90%, Epoch[118/182] Train Acc: 99.90% Valid Acc:93.66% Train loss:0.0054 Valid loss:0.2833 LR:0.010000000000000002
Training Progress:  65%|▋| 118/182 [1:25:33<46:38, 43.72s/it, Train Acc=99.90%, Training: Epoch[119/182] Iteration[050/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[119/182] Iteration[100/352] Loss: 0.0048 Acc:99.90%
Training: Epoch[119/182] Iteration[150/352] Loss: 0.0047 Acc:99.91%
Training: Epoch[119/182] Iteration[200/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[119/182] Iteration[250/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[119/182] Iteration[300/352] Loss: 0.0049 Acc:99.91%
Training: Epoch[119/182] Iteration[350/352] Loss: 0.0050 Acc:99.90%
Training Progress:  65%|▋| 118/182 [1:26:17<46:38, 43.72s/it, Train Acc=99.90%, Epoch[119/182] Train Acc: 99.90% Valid Acc:93.72% Train loss:0.0050 Valid loss:0.2885 LR:0.010000000000000002
Training Progress:  65%|▋| 119/182 [1:26:17<45:51, 43.67s/it, Train Acc=99.90%, Training: Epoch[120/182] Iteration[050/352] Loss: 0.0042 Acc:99.94%
Training: Epoch[120/182] Iteration[100/352] Loss: 0.0038 Acc:99.96%
Training: Epoch[120/182] Iteration[150/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[120/182] Iteration[200/352] Loss: 0.0048 Acc:99.93%
Training: Epoch[120/182] Iteration[250/352] Loss: 0.0050 Acc:99.92%
Training: Epoch[120/182] Iteration[300/352] Loss: 0.0052 Acc:99.91%
Training: Epoch[120/182] Iteration[350/352] Loss: 0.0051 Acc:99.91%
Training Progress:  65%|▋| 119/182 [1:27:01<45:51, 43.67s/it, Train Acc=99.91%, Epoch[120/182] Train Acc: 99.91% Valid Acc:93.78% Train loss:0.0052 Valid loss:0.2876 LR:0.010000000000000002
Training Progress:  66%|▋| 120/182 [1:27:01<45:06, 43.66s/it, Train Acc=99.91%, Training: Epoch[121/182] Iteration[050/352] Loss: 0.0047 Acc:99.92%
Training: Epoch[121/182] Iteration[100/352] Loss: 0.0051 Acc:99.91%
Training: Epoch[121/182] Iteration[150/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[121/182] Iteration[200/352] Loss: 0.0048 Acc:99.91%
Training: Epoch[121/182] Iteration[250/352] Loss: 0.0048 Acc:99.92%
Training: Epoch[121/182] Iteration[300/352] Loss: 0.0047 Acc:99.93%
Training: Epoch[121/182] Iteration[350/352] Loss: 0.0046 Acc:99.93%
Training Progress:  66%|▋| 120/182 [1:27:44<45:06, 43.66s/it, Train Acc=99.93%, Epoch[121/182] Train Acc: 99.93% Valid Acc:93.52% Train loss:0.0046 Valid loss:0.2853 LR:0.010000000000000002
Training Progress:  66%|▋| 121/182 [1:27:44<44:22, 43.64s/it, Train Acc=99.93%, Training: Epoch[122/182] Iteration[050/352] Loss: 0.0056 Acc:99.88%
Training: Epoch[122/182] Iteration[100/352] Loss: 0.0050 Acc:99.89%
Training: Epoch[122/182] Iteration[150/352] Loss: 0.0048 Acc:99.89%
Training: Epoch[122/182] Iteration[200/352] Loss: 0.0051 Acc:99.88%
Training: Epoch[122/182] Iteration[250/352] Loss: 0.0050 Acc:99.89%
Training: Epoch[122/182] Iteration[300/352] Loss: 0.0048 Acc:99.89%
Training: Epoch[122/182] Iteration[350/352] Loss: 0.0048 Acc:99.90%
Training Progress:  66%|▋| 121/182 [1:28:28<44:22, 43.64s/it, Train Acc=99.90%, Epoch[122/182] Train Acc: 99.90% Valid Acc:93.52% Train loss:0.0047 Valid loss:0.2893 LR:0.010000000000000002
Training Progress:  67%|▋| 122/182 [1:28:28<43:37, 43.63s/it, Train Acc=99.90%, Training: Epoch[123/182] Iteration[050/352] Loss: 0.0041 Acc:99.97%
Training: Epoch[123/182] Iteration[100/352] Loss: 0.0042 Acc:99.95%
Training: Epoch[123/182] Iteration[150/352] Loss: 0.0041 Acc:99.95%
Training: Epoch[123/182] Iteration[200/352] Loss: 0.0045 Acc:99.93%
Training: Epoch[123/182] Iteration[250/352] Loss: 0.0043 Acc:99.94%
Training: Epoch[123/182] Iteration[300/352] Loss: 0.0044 Acc:99.93%
Training: Epoch[123/182] Iteration[350/352] Loss: 0.0044 Acc:99.94%
Training Progress:  67%|▋| 122/182 [1:29:12<43:37, 43.63s/it, Train Acc=99.94%, Epoch[123/182] Train Acc: 99.94% Valid Acc:93.60% Train loss:0.0044 Valid loss:0.2836 LR:0.010000000000000002
Training Progress:  68%|▋| 123/182 [1:29:12<42:58, 43.70s/it, Train Acc=99.94%, Training: Epoch[124/182] Iteration[050/352] Loss: 0.0053 Acc:99.89%
Training: Epoch[124/182] Iteration[100/352] Loss: 0.0052 Acc:99.90%
Training: Epoch[124/182] Iteration[150/352] Loss: 0.0046 Acc:99.92%
Training: Epoch[124/182] Iteration[200/352] Loss: 0.0042 Acc:99.93%
Training: Epoch[124/182] Iteration[250/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[124/182] Iteration[300/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[124/182] Iteration[350/352] Loss: 0.0043 Acc:99.92%
Training Progress:  68%|▋| 123/182 [1:29:55<42:58, 43.70s/it, Train Acc=99.92%, Epoch[124/182] Train Acc: 99.92% Valid Acc:93.70% Train loss:0.0043 Valid loss:0.2846 LR:0.010000000000000002
Training Progress:  68%|▋| 124/182 [1:29:55<42:12, 43.67s/it, Train Acc=99.92%, Training: Epoch[125/182] Iteration[050/352] Loss: 0.0046 Acc:99.94%
Training: Epoch[125/182] Iteration[100/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[125/182] Iteration[150/352] Loss: 0.0046 Acc:99.93%
Training: Epoch[125/182] Iteration[200/352] Loss: 0.0045 Acc:99.93%
Training: Epoch[125/182] Iteration[250/352] Loss: 0.0043 Acc:99.93%
Training: Epoch[125/182] Iteration[300/352] Loss: 0.0042 Acc:99.93%
Training: Epoch[125/182] Iteration[350/352] Loss: 0.0042 Acc:99.93%
Training Progress:  68%|▋| 124/182 [1:30:39<42:12, 43.67s/it, Train Acc=99.93%, Epoch[125/182] Train Acc: 99.93% Valid Acc:93.60% Train loss:0.0042 Valid loss:0.2911 LR:0.010000000000000002
Training Progress:  69%|▋| 125/182 [1:30:39<41:27, 43.64s/it, Train Acc=99.93%, Training: Epoch[126/182] Iteration[050/352] Loss: 0.0045 Acc:99.86%
Training: Epoch[126/182] Iteration[100/352] Loss: 0.0041 Acc:99.88%
Training: Epoch[126/182] Iteration[150/352] Loss: 0.0041 Acc:99.90%
Training: Epoch[126/182] Iteration[200/352] Loss: 0.0040 Acc:99.91%
Training: Epoch[126/182] Iteration[250/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[126/182] Iteration[300/352] Loss: 0.0040 Acc:99.92%
Training: Epoch[126/182] Iteration[350/352] Loss: 0.0042 Acc:99.92%
Training Progress:  69%|▋| 125/182 [1:31:23<41:27, 43.64s/it, Train Acc=99.91%, Epoch[126/182] Train Acc: 99.91% Valid Acc:93.46% Train loss:0.0043 Valid loss:0.2947 LR:0.010000000000000002
Training Progress:  69%|▋| 126/182 [1:31:23<40:43, 43.64s/it, Train Acc=99.91%, Training: Epoch[127/182] Iteration[050/352] Loss: 0.0038 Acc:99.94%
Training: Epoch[127/182] Iteration[100/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[127/182] Iteration[150/352] Loss: 0.0045 Acc:99.92%
Training: Epoch[127/182] Iteration[200/352] Loss: 0.0045 Acc:99.91%
Training: Epoch[127/182] Iteration[250/352] Loss: 0.0045 Acc:99.91%
Training: Epoch[127/182] Iteration[300/352] Loss: 0.0046 Acc:99.91%
Training: Epoch[127/182] Iteration[350/352] Loss: 0.0046 Acc:99.91%
Training Progress:  69%|▋| 126/182 [1:32:07<40:43, 43.64s/it, Train Acc=99.91%, Epoch[127/182] Train Acc: 99.91% Valid Acc:93.56% Train loss:0.0046 Valid loss:0.2964 LR:0.010000000000000002
Training Progress:  70%|▋| 127/182 [1:32:07<40:06, 43.75s/it, Train Acc=99.91%, Training: Epoch[128/182] Iteration[050/352] Loss: 0.0042 Acc:99.94%
Training: Epoch[128/182] Iteration[100/352] Loss: 0.0039 Acc:99.95%
Training: Epoch[128/182] Iteration[150/352] Loss: 0.0035 Acc:99.96%
Training: Epoch[128/182] Iteration[200/352] Loss: 0.0037 Acc:99.95%
Training: Epoch[128/182] Iteration[250/352] Loss: 0.0036 Acc:99.96%
Training: Epoch[128/182] Iteration[300/352] Loss: 0.0036 Acc:99.96%
Training: Epoch[128/182] Iteration[350/352] Loss: 0.0037 Acc:99.95%
Training Progress:  70%|▋| 127/182 [1:32:51<40:06, 43.75s/it, Train Acc=99.95%, Epoch[128/182] Train Acc: 99.95% Valid Acc:93.78% Train loss:0.0037 Valid loss:0.2882 LR:0.010000000000000002
Training Progress:  70%|▋| 128/182 [1:32:51<39:32, 43.94s/it, Train Acc=99.95%, Training: Epoch[129/182] Iteration[050/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[129/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[129/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[129/182] Iteration[200/352] Loss: 0.0035 Acc:99.93%
Training: Epoch[129/182] Iteration[250/352] Loss: 0.0035 Acc:99.94%
Training: Epoch[129/182] Iteration[300/352] Loss: 0.0035 Acc:99.94%
Training: Epoch[129/182] Iteration[350/352] Loss: 0.0035 Acc:99.94%
Training Progress:  70%|▋| 128/182 [1:33:36<39:32, 43.94s/it, Train Acc=99.94%, Epoch[129/182] Train Acc: 99.94% Valid Acc:93.80% Train loss:0.0035 Valid loss:0.2936 LR:0.010000000000000002
Training Progress:  71%|▋| 129/182 [1:33:36<39:13, 44.41s/it, Train Acc=99.94%, Training: Epoch[130/182] Iteration[050/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[130/182] Iteration[100/352] Loss: 0.0040 Acc:99.93%
Training: Epoch[130/182] Iteration[150/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[130/182] Iteration[200/352] Loss: 0.0041 Acc:99.92%
Training: Epoch[130/182] Iteration[250/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[130/182] Iteration[300/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[130/182] Iteration[350/352] Loss: 0.0036 Acc:99.94%
Training Progress:  71%|▋| 129/182 [1:34:22<39:13, 44.41s/it, Train Acc=99.94%, Epoch[130/182] Train Acc: 99.94% Valid Acc:93.64% Train loss:0.0036 Valid loss:0.2950 LR:0.010000000000000002
Training Progress:  71%|▋| 130/182 [1:34:22<38:41, 44.64s/it, Train Acc=99.94%, Training: Epoch[131/182] Iteration[050/352] Loss: 0.0040 Acc:99.94%
Training: Epoch[131/182] Iteration[100/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[131/182] Iteration[150/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[131/182] Iteration[200/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[131/182] Iteration[250/352] Loss: 0.0037 Acc:99.94%
Training: Epoch[131/182] Iteration[300/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[131/182] Iteration[350/352] Loss: 0.0039 Acc:99.93%
Training Progress:  71%|▋| 130/182 [1:35:08<38:41, 44.64s/it, Train Acc=99.93%, Epoch[131/182] Train Acc: 99.93% Valid Acc:93.48% Train loss:0.0039 Valid loss:0.2963 LR:0.010000000000000002
Training Progress:  72%|▋| 131/182 [1:35:08<38:25, 45.21s/it, Train Acc=99.93%, Training: Epoch[132/182] Iteration[050/352] Loss: 0.0038 Acc:99.89%
Training: Epoch[132/182] Iteration[100/352] Loss: 0.0035 Acc:99.92%
Training: Epoch[132/182] Iteration[150/352] Loss: 0.0034 Acc:99.93%
Training: Epoch[132/182] Iteration[200/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[132/182] Iteration[250/352] Loss: 0.0036 Acc:99.93%
Training: Epoch[132/182] Iteration[300/352] Loss: 0.0037 Acc:99.93%
Training: Epoch[132/182] Iteration[350/352] Loss: 0.0037 Acc:99.93%
Training Progress:  72%|▋| 131/182 [1:35:54<38:25, 45.21s/it, Train Acc=99.93%, Epoch[132/182] Train Acc: 99.93% Valid Acc:93.58% Train loss:0.0036 Valid loss:0.2932 LR:0.010000000000000002
Training Progress:  73%|▋| 132/182 [1:35:54<37:56, 45.52s/it, Train Acc=99.93%, Training: Epoch[133/182] Iteration[050/352] Loss: 0.0043 Acc:99.89%
Training: Epoch[133/182] Iteration[100/352] Loss: 0.0036 Acc:99.92%
Training: Epoch[133/182] Iteration[150/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[133/182] Iteration[200/352] Loss: 0.0035 Acc:99.94%
Training: Epoch[133/182] Iteration[250/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[133/182] Iteration[300/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[133/182] Iteration[350/352] Loss: 0.0034 Acc:99.94%
Training Progress:  73%|▋| 132/182 [1:36:42<37:56, 45.52s/it, Train Acc=99.94%, Epoch[133/182] Train Acc: 99.94% Valid Acc:93.80% Train loss:0.0034 Valid loss:0.2898 LR:0.010000000000000002
Training Progress:  73%|▋| 133/182 [1:36:42<37:39, 46.12s/it, Train Acc=99.94%, Training: Epoch[134/182] Iteration[050/352] Loss: 0.0034 Acc:99.97%
Training: Epoch[134/182] Iteration[100/352] Loss: 0.0034 Acc:99.96%
Training: Epoch[134/182] Iteration[150/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[134/182] Iteration[200/352] Loss: 0.0036 Acc:99.95%
Training: Epoch[134/182] Iteration[250/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[134/182] Iteration[300/352] Loss: 0.0038 Acc:99.92%
Training: Epoch[134/182] Iteration[350/352] Loss: 0.0038 Acc:99.92%
Training Progress:  73%|▋| 133/182 [1:37:29<37:39, 46.12s/it, Train Acc=99.92%, Epoch[134/182] Train Acc: 99.92% Valid Acc:93.70% Train loss:0.0038 Valid loss:0.2923 LR:0.010000000000000002
Training Progress:  74%|▋| 134/182 [1:37:29<37:07, 46.41s/it, Train Acc=99.92%, Training: Epoch[135/182] Iteration[050/352] Loss: 0.0028 Acc:100.00%
Training: Epoch[135/182] Iteration[100/352] Loss: 0.0030 Acc:99.98%
Training: Epoch[135/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[135/182] Iteration[200/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[135/182] Iteration[250/352] Loss: 0.0031 Acc:99.96%
Training: Epoch[135/182] Iteration[300/352] Loss: 0.0032 Acc:99.95%
Training: Epoch[135/182] Iteration[350/352] Loss: 0.0034 Acc:99.94%
Training Progress:  74%|▋| 134/182 [1:38:16<37:07, 46.41s/it, Train Acc=99.94%, Epoch[135/182] Train Acc: 99.94% Valid Acc:93.70% Train loss:0.0034 Valid loss:0.2957 LR:0.010000000000000002
Training Progress:  74%|▋| 135/182 [1:38:16<36:32, 46.65s/it, Train Acc=99.94%, Training: Epoch[136/182] Iteration[050/352] Loss: 0.0049 Acc:99.89%
Training: Epoch[136/182] Iteration[100/352] Loss: 0.0043 Acc:99.92%
Training: Epoch[136/182] Iteration[150/352] Loss: 0.0039 Acc:99.93%
Training: Epoch[136/182] Iteration[200/352] Loss: 0.0038 Acc:99.93%
Training: Epoch[136/182] Iteration[250/352] Loss: 0.0036 Acc:99.93%
Training: Epoch[136/182] Iteration[300/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[136/182] Iteration[350/352] Loss: 0.0035 Acc:99.94%
Training Progress:  74%|▋| 135/182 [1:39:05<36:32, 46.65s/it, Train Acc=99.94%, Epoch[136/182] Train Acc: 99.94% Valid Acc:93.68% Train loss:0.0035 Valid loss:0.2900 LR:0.010000000000000002
Training Progress:  75%|▋| 136/182 [1:39:05<36:12, 47.23s/it, Train Acc=99.94%, Training: Epoch[137/182] Iteration[050/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[137/182] Iteration[100/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[137/182] Iteration[150/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[137/182] Iteration[200/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[137/182] Iteration[250/352] Loss: 0.0030 Acc:99.94%
Training: Epoch[137/182] Iteration[300/352] Loss: 0.0030 Acc:99.94%
Training: Epoch[137/182] Iteration[350/352] Loss: 0.0029 Acc:99.94%
Training Progress:  75%|▋| 136/182 [1:39:55<36:12, 47.23s/it, Train Acc=99.94%, Epoch[137/182] Train Acc: 99.94% Valid Acc:93.68% Train loss:0.0029 Valid loss:0.2925 LR:0.0010000000000000002
Training Progress:  75%|▊| 137/182 [1:39:55<36:03, 48.08s/it, Train Acc=99.94%, Training: Epoch[138/182] Iteration[050/352] Loss: 0.0039 Acc:99.92%
Training: Epoch[138/182] Iteration[100/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[138/182] Iteration[150/352] Loss: 0.0033 Acc:99.96%
Training: Epoch[138/182] Iteration[200/352] Loss: 0.0035 Acc:99.95%
Training: Epoch[138/182] Iteration[250/352] Loss: 0.0036 Acc:99.94%
Training: Epoch[138/182] Iteration[300/352] Loss: 0.0034 Acc:99.95%
Training: Epoch[138/182] Iteration[350/352] Loss: 0.0033 Acc:99.95%
Training Progress:  75%|▊| 137/182 [1:40:45<36:03, 48.08s/it, Train Acc=99.95%, Epoch[138/182] Train Acc: 99.95% Valid Acc:93.72% Train loss:0.0033 Valid loss:0.2932 LR:0.0010000000000000002
Training Progress:  76%|▊| 138/182 [1:40:45<35:40, 48.65s/it, Train Acc=99.95%, Training: Epoch[139/182] Iteration[050/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[139/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[139/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[139/182] Iteration[200/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[139/182] Iteration[250/352] Loss: 0.0029 Acc:99.96%
Training: Epoch[139/182] Iteration[300/352] Loss: 0.0030 Acc:99.96%
Training: Epoch[139/182] Iteration[350/352] Loss: 0.0029 Acc:99.96%
Training Progress:  76%|▊| 138/182 [1:41:37<35:40, 48.65s/it, Train Acc=99.96%, Epoch[139/182] Train Acc: 99.96% Valid Acc:93.76% Train loss:0.0029 Valid loss:0.2899 LR:0.0010000000000000002
Training Progress:  76%|▊| 139/182 [1:41:37<35:32, 49.60s/it, Train Acc=99.96%, Training: Epoch[140/182] Iteration[050/352] Loss: 0.0032 Acc:99.97%
Training: Epoch[140/182] Iteration[100/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[140/182] Iteration[150/352] Loss: 0.0031 Acc:99.95%
Training: Epoch[140/182] Iteration[200/352] Loss: 0.0032 Acc:99.94%
Training: Epoch[140/182] Iteration[250/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[140/182] Iteration[300/352] Loss: 0.0030 Acc:99.95%
Training: Epoch[140/182] Iteration[350/352] Loss: 0.0029 Acc:99.95%
Training Progress:  76%|▊| 139/182 [1:42:25<35:32, 49.60s/it, Train Acc=99.95%, Epoch[140/182] Train Acc: 99.95% Valid Acc:93.76% Train loss:0.0029 Valid loss:0.2902 LR:0.0010000000000000002
Training Progress:  77%|▊| 140/182 [1:42:25<34:22, 49.10s/it, Train Acc=99.95%, Training: Epoch[141/182] Iteration[050/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[141/182] Iteration[100/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[141/182] Iteration[150/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[141/182] Iteration[200/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[141/182] Iteration[250/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[141/182] Iteration[300/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[141/182] Iteration[350/352] Loss: 0.0026 Acc:99.97%
Training Progress:  77%|▊| 140/182 [1:43:13<34:22, 49.10s/it, Train Acc=99.97%, Epoch[141/182] Train Acc: 99.97% Valid Acc:93.58% Train loss:0.0027 Valid loss:0.2926 LR:0.0010000000000000002
Training Progress:  77%|▊| 141/182 [1:43:13<33:28, 48.98s/it, Train Acc=99.97%, Training: Epoch[142/182] Iteration[050/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[142/182] Iteration[100/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[142/182] Iteration[150/352] Loss: 0.0028 Acc:99.97%
Training: Epoch[142/182] Iteration[200/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[142/182] Iteration[250/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[142/182] Iteration[300/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[142/182] Iteration[350/352] Loss: 0.0027 Acc:99.97%
Training Progress:  77%|▊| 141/182 [1:44:04<33:28, 48.98s/it, Train Acc=99.97%, Epoch[142/182] Train Acc: 99.97% Valid Acc:93.68% Train loss:0.0027 Valid loss:0.2923 LR:0.0010000000000000002
Training Progress:  78%|▊| 142/182 [1:44:04<33:03, 49.59s/it, Train Acc=99.97%, Training: Epoch[143/182] Iteration[050/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[143/182] Iteration[100/352] Loss: 0.0034 Acc:99.94%
Training: Epoch[143/182] Iteration[150/352] Loss: 0.0034 Acc:99.93%
Training: Epoch[143/182] Iteration[200/352] Loss: 0.0034 Acc:99.93%
Training: Epoch[143/182] Iteration[250/352] Loss: 0.0034 Acc:99.92%
Training: Epoch[143/182] Iteration[300/352] Loss: 0.0032 Acc:99.93%
Training: Epoch[143/182] Iteration[350/352] Loss: 0.0031 Acc:99.94%
Training Progress:  78%|▊| 142/182 [1:44:54<33:03, 49.59s/it, Train Acc=99.94%, Epoch[143/182] Train Acc: 99.94% Valid Acc:93.62% Train loss:0.0031 Valid loss:0.2940 LR:0.0010000000000000002
Training Progress:  79%|▊| 143/182 [1:44:54<32:19, 49.72s/it, Train Acc=99.94%, Training: Epoch[144/182] Iteration[050/352] Loss: 0.0033 Acc:99.94%
Training: Epoch[144/182] Iteration[100/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[144/182] Iteration[150/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[144/182] Iteration[200/352] Loss: 0.0031 Acc:99.94%
Training: Epoch[144/182] Iteration[250/352] Loss: 0.0029 Acc:99.94%
Training: Epoch[144/182] Iteration[300/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[144/182] Iteration[350/352] Loss: 0.0029 Acc:99.95%
Training Progress:  79%|▊| 143/182 [1:45:44<32:19, 49.72s/it, Train Acc=99.95%, Epoch[144/182] Train Acc: 99.95% Valid Acc:93.74% Train loss:0.0029 Valid loss:0.2890 LR:0.0010000000000000002
Training Progress:  79%|▊| 144/182 [1:45:44<31:26, 49.65s/it, Train Acc=99.95%, Training: Epoch[145/182] Iteration[050/352] Loss: 0.0021 Acc:100.00%
Training: Epoch[145/182] Iteration[100/352] Loss: 0.0020 Acc:100.00%
Training: Epoch[145/182] Iteration[150/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[145/182] Iteration[200/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[145/182] Iteration[250/352] Loss: 0.0022 Acc:99.99%
Training: Epoch[145/182] Iteration[300/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[145/182] Iteration[350/352] Loss: 0.0024 Acc:99.98%
Training Progress:  79%|▊| 144/182 [1:46:35<31:26, 49.65s/it, Train Acc=99.98%, Epoch[145/182] Train Acc: 99.98% Valid Acc:93.82% Train loss:0.0024 Valid loss:0.2878 LR:0.0010000000000000002
Training Progress:  80%|▊| 145/182 [1:46:35<30:57, 50.21s/it, Train Acc=99.98%, Training: Epoch[146/182] Iteration[050/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[146/182] Iteration[100/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[146/182] Iteration[150/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[146/182] Iteration[200/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[146/182] Iteration[250/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[146/182] Iteration[300/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[146/182] Iteration[350/352] Loss: 0.0026 Acc:99.97%
Training Progress:  80%|▊| 145/182 [1:47:27<30:57, 50.21s/it, Train Acc=99.97%, Epoch[146/182] Train Acc: 99.97% Valid Acc:93.72% Train loss:0.0027 Valid loss:0.2977 LR:0.0010000000000000002
Training Progress:  80%|▊| 146/182 [1:47:27<30:21, 50.60s/it, Train Acc=99.97%, Training: Epoch[147/182] Iteration[050/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[147/182] Iteration[100/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[147/182] Iteration[150/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[147/182] Iteration[200/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[147/182] Iteration[250/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[147/182] Iteration[300/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[147/182] Iteration[350/352] Loss: 0.0026 Acc:99.98%
Training Progress:  80%|▊| 146/182 [1:48:19<30:21, 50.60s/it, Train Acc=99.98%, Epoch[147/182] Train Acc: 99.98% Valid Acc:93.68% Train loss:0.0026 Valid loss:0.2884 LR:0.0010000000000000002
Training Progress:  81%|▊| 147/182 [1:48:19<29:47, 51.06s/it, Train Acc=99.98%, Training: Epoch[148/182] Iteration[050/352] Loss: 0.0019 Acc:100.00%
Training: Epoch[148/182] Iteration[100/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[148/182] Iteration[150/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[148/182] Iteration[200/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[148/182] Iteration[250/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[148/182] Iteration[300/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[148/182] Iteration[350/352] Loss: 0.0023 Acc:99.96%
Training Progress:  81%|▊| 147/182 [1:49:10<29:47, 51.06s/it, Train Acc=99.96%, Epoch[148/182] Train Acc: 99.96% Valid Acc:93.76% Train loss:0.0023 Valid loss:0.2896 LR:0.0010000000000000002
Training Progress:  81%|▊| 148/182 [1:49:10<28:54, 51.00s/it, Train Acc=99.96%, Training: Epoch[149/182] Iteration[050/352] Loss: 0.0029 Acc:99.98%
Training: Epoch[149/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[149/182] Iteration[150/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[149/182] Iteration[200/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[149/182] Iteration[250/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[149/182] Iteration[300/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[149/182] Iteration[350/352] Loss: 0.0026 Acc:99.96%
Training Progress:  81%|▊| 148/182 [1:50:02<28:54, 51.00s/it, Train Acc=99.96%, Epoch[149/182] Train Acc: 99.96% Valid Acc:93.72% Train loss:0.0026 Valid loss:0.2941 LR:0.0010000000000000002
Training Progress:  82%|▊| 149/182 [1:50:02<28:13, 51.31s/it, Train Acc=99.96%, Training: Epoch[150/182] Iteration[050/352] Loss: 0.0025 Acc:99.95%
Training: Epoch[150/182] Iteration[100/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[150/182] Iteration[150/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[150/182] Iteration[200/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[150/182] Iteration[250/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[150/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[150/182] Iteration[350/352] Loss: 0.0025 Acc:99.97%
Training Progress:  82%|▊| 149/182 [1:50:55<28:13, 51.31s/it, Train Acc=99.97%, Epoch[150/182] Train Acc: 99.97% Valid Acc:93.66% Train loss:0.0025 Valid loss:0.2932 LR:0.0010000000000000002
Training Progress:  82%|▊| 150/182 [1:50:55<27:35, 51.75s/it, Train Acc=99.97%, Training: Epoch[151/182] Iteration[050/352] Loss: 0.0019 Acc:100.00%
Training: Epoch[151/182] Iteration[100/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[151/182] Iteration[150/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[151/182] Iteration[200/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[151/182] Iteration[250/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[151/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[151/182] Iteration[350/352] Loss: 0.0023 Acc:99.97%
Training Progress:  82%|▊| 150/182 [1:51:47<27:35, 51.75s/it, Train Acc=99.97%, Epoch[151/182] Train Acc: 99.97% Valid Acc:93.76% Train loss:0.0023 Valid loss:0.2914 LR:0.0010000000000000002
Training Progress:  83%|▊| 151/182 [1:51:47<26:52, 52.02s/it, Train Acc=99.97%, Training: Epoch[152/182] Iteration[050/352] Loss: 0.0019 Acc:100.00%
Training: Epoch[152/182] Iteration[100/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[152/182] Iteration[150/352] Loss: 0.0029 Acc:99.97%
Training: Epoch[152/182] Iteration[200/352] Loss: 0.0027 Acc:99.97%
Training: Epoch[152/182] Iteration[250/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[152/182] Iteration[300/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[152/182] Iteration[350/352] Loss: 0.0026 Acc:99.97%
Training Progress:  83%|▊| 151/182 [1:52:38<26:52, 52.02s/it, Train Acc=99.97%, Epoch[152/182] Train Acc: 99.97% Valid Acc:93.70% Train loss:0.0026 Valid loss:0.2882 LR:0.0010000000000000002
Training Progress:  84%|▊| 152/182 [1:52:38<25:47, 51.59s/it, Train Acc=99.97%, Training: Epoch[153/182] Iteration[050/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[153/182] Iteration[100/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[153/182] Iteration[150/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[153/182] Iteration[200/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[153/182] Iteration[250/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[153/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[153/182] Iteration[350/352] Loss: 0.0024 Acc:99.98%
Training Progress:  84%|▊| 152/182 [1:53:30<25:47, 51.59s/it, Train Acc=99.98%, Epoch[153/182] Train Acc: 99.98% Valid Acc:93.82% Train loss:0.0024 Valid loss:0.2923 LR:0.0010000000000000002
Training Progress:  84%|▊| 153/182 [1:53:30<24:56, 51.62s/it, Train Acc=99.98%, Training: Epoch[154/182] Iteration[050/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[154/182] Iteration[100/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[154/182] Iteration[150/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[154/182] Iteration[200/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[154/182] Iteration[250/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[154/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[154/182] Iteration[350/352] Loss: 0.0025 Acc:99.97%
Training Progress:  84%|▊| 153/182 [1:54:18<24:56, 51.62s/it, Train Acc=99.97%, Epoch[154/182] Train Acc: 99.97% Valid Acc:93.72% Train loss:0.0025 Valid loss:0.2918 LR:0.0010000000000000002
Training Progress:  85%|▊| 154/182 [1:54:18<23:42, 50.81s/it, Train Acc=99.97%, Training: Epoch[155/182] Iteration[050/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[155/182] Iteration[100/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[155/182] Iteration[150/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[155/182] Iteration[200/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[155/182] Iteration[250/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[155/182] Iteration[300/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[155/182] Iteration[350/352] Loss: 0.0023 Acc:99.97%
Training Progress:  85%|▊| 154/182 [1:55:11<23:42, 50.81s/it, Train Acc=99.97%, Epoch[155/182] Train Acc: 99.97% Valid Acc:93.64% Train loss:0.0023 Valid loss:0.2895 LR:0.0010000000000000002
Training Progress:  85%|▊| 155/182 [1:55:11<23:02, 51.22s/it, Train Acc=99.97%, Training: Epoch[156/182] Iteration[050/352] Loss: 0.0020 Acc:99.98%
Training: Epoch[156/182] Iteration[100/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[156/182] Iteration[150/352] Loss: 0.0027 Acc:99.94%
Training: Epoch[156/182] Iteration[200/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[156/182] Iteration[250/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[156/182] Iteration[300/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[156/182] Iteration[350/352] Loss: 0.0027 Acc:99.95%
Training Progress:  85%|▊| 155/182 [1:56:02<23:02, 51.22s/it, Train Acc=99.95%, Epoch[156/182] Train Acc: 99.95% Valid Acc:93.74% Train loss:0.0027 Valid loss:0.2926 LR:0.0010000000000000002
Training Progress:  86%|▊| 156/182 [1:56:02<22:15, 51.36s/it, Train Acc=99.95%, Training: Epoch[157/182] Iteration[050/352] Loss: 0.0030 Acc:99.94%
Training: Epoch[157/182] Iteration[100/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[157/182] Iteration[150/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[157/182] Iteration[200/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[157/182] Iteration[250/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[157/182] Iteration[300/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[157/182] Iteration[350/352] Loss: 0.0025 Acc:99.96%
Training Progress:  86%|▊| 156/182 [1:56:54<22:15, 51.36s/it, Train Acc=99.96%, Epoch[157/182] Train Acc: 99.96% Valid Acc:93.72% Train loss:0.0025 Valid loss:0.2942 LR:0.0010000000000000002
Training Progress:  86%|▊| 157/182 [1:56:54<21:29, 51.60s/it, Train Acc=99.96%, Training: Epoch[158/182] Iteration[050/352] Loss: 0.0019 Acc:99.98%
Training: Epoch[158/182] Iteration[100/352] Loss: 0.0019 Acc:99.98%
Training: Epoch[158/182] Iteration[150/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[158/182] Iteration[200/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[158/182] Iteration[250/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[158/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[158/182] Iteration[350/352] Loss: 0.0024 Acc:99.97%
Training Progress:  86%|▊| 157/182 [1:57:48<21:29, 51.60s/it, Train Acc=99.97%, Epoch[158/182] Train Acc: 99.97% Valid Acc:93.70% Train loss:0.0024 Valid loss:0.2913 LR:0.0010000000000000002
Training Progress:  87%|▊| 158/182 [1:57:48<20:48, 52.04s/it, Train Acc=99.97%, Training: Epoch[159/182] Iteration[050/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[159/182] Iteration[100/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[159/182] Iteration[150/352] Loss: 0.0023 Acc:99.96%
Training: Epoch[159/182] Iteration[200/352] Loss: 0.0026 Acc:99.95%
Training: Epoch[159/182] Iteration[250/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[159/182] Iteration[300/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[159/182] Iteration[350/352] Loss: 0.0024 Acc:99.97%
Training Progress:  87%|▊| 158/182 [1:58:40<20:48, 52.04s/it, Train Acc=99.97%, Epoch[159/182] Train Acc: 99.97% Valid Acc:93.80% Train loss:0.0025 Valid loss:0.2948 LR:0.0010000000000000002
Training Progress:  87%|▊| 159/182 [1:58:40<19:57, 52.08s/it, Train Acc=99.97%, Training: Epoch[160/182] Iteration[050/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[160/182] Iteration[100/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[160/182] Iteration[150/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[160/182] Iteration[200/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[160/182] Iteration[250/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[160/182] Iteration[300/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[160/182] Iteration[350/352] Loss: 0.0026 Acc:99.96%
Training Progress:  87%|▊| 159/182 [1:59:32<19:57, 52.08s/it, Train Acc=99.96%, Epoch[160/182] Train Acc: 99.96% Valid Acc:93.60% Train loss:0.0026 Valid loss:0.2928 LR:0.0010000000000000002
Training Progress:  88%|▉| 160/182 [1:59:32<19:08, 52.19s/it, Train Acc=99.96%, Training: Epoch[161/182] Iteration[050/352] Loss: 0.0020 Acc:99.97%
Training: Epoch[161/182] Iteration[100/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[161/182] Iteration[150/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[161/182] Iteration[200/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[161/182] Iteration[250/352] Loss: 0.0025 Acc:99.95%
Training: Epoch[161/182] Iteration[300/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[161/182] Iteration[350/352] Loss: 0.0024 Acc:99.96%
Training Progress:  88%|▉| 160/182 [2:00:25<19:08, 52.19s/it, Train Acc=99.96%, Epoch[161/182] Train Acc: 99.96% Valid Acc:93.74% Train loss:0.0024 Valid loss:0.2907 LR:0.0010000000000000002
Training Progress:  88%|▉| 161/182 [2:00:25<18:17, 52.28s/it, Train Acc=99.96%, Training: Epoch[162/182] Iteration[050/352] Loss: 0.0029 Acc:99.94%
Training: Epoch[162/182] Iteration[100/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[162/182] Iteration[150/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[162/182] Iteration[200/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[162/182] Iteration[250/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[162/182] Iteration[300/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[162/182] Iteration[350/352] Loss: 0.0025 Acc:99.96%
Training Progress:  88%|▉| 161/182 [2:01:18<18:17, 52.28s/it, Train Acc=99.96%, Epoch[162/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0025 Valid loss:0.2929 LR:0.0010000000000000002
Training Progress:  89%|▉| 162/182 [2:01:18<17:31, 52.58s/it, Train Acc=99.96%, Training: Epoch[163/182] Iteration[050/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[163/182] Iteration[100/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[163/182] Iteration[150/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[163/182] Iteration[200/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[163/182] Iteration[250/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[163/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[163/182] Iteration[350/352] Loss: 0.0025 Acc:99.97%
Training Progress:  89%|▉| 162/182 [2:02:10<17:31, 52.58s/it, Train Acc=99.97%, Epoch[163/182] Train Acc: 99.97% Valid Acc:93.72% Train loss:0.0025 Valid loss:0.2938 LR:0.0010000000000000002
Training Progress:  90%|▉| 163/182 [2:02:10<16:38, 52.57s/it, Train Acc=99.97%, Training: Epoch[164/182] Iteration[050/352] Loss: 0.0028 Acc:99.94%
Training: Epoch[164/182] Iteration[100/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[164/182] Iteration[150/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[164/182] Iteration[200/352] Loss: 0.0027 Acc:99.96%
Training: Epoch[164/182] Iteration[250/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[164/182] Iteration[300/352] Loss: 0.0026 Acc:99.96%
Training: Epoch[164/182] Iteration[350/352] Loss: 0.0026 Acc:99.96%
Training Progress:  90%|▉| 163/182 [2:03:03<16:38, 52.57s/it, Train Acc=99.96%, Epoch[164/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0026 Valid loss:0.2963 LR:0.0010000000000000002
Training Progress:  90%|▉| 164/182 [2:03:03<15:43, 52.42s/it, Train Acc=99.96%, Training: Epoch[165/182] Iteration[050/352] Loss: 0.0030 Acc:99.92%
Training: Epoch[165/182] Iteration[100/352] Loss: 0.0025 Acc:99.95%
Training: Epoch[165/182] Iteration[150/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[165/182] Iteration[200/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[165/182] Iteration[250/352] Loss: 0.0025 Acc:99.95%
Training: Epoch[165/182] Iteration[300/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[165/182] Iteration[350/352] Loss: 0.0025 Acc:99.96%
Training Progress:  90%|▉| 164/182 [2:03:55<15:43, 52.42s/it, Train Acc=99.96%, Epoch[165/182] Train Acc: 99.96% Valid Acc:93.68% Train loss:0.0025 Valid loss:0.2939 LR:0.0010000000000000002
Training Progress:  91%|▉| 165/182 [2:03:55<14:51, 52.47s/it, Train Acc=99.96%, Training: Epoch[166/182] Iteration[050/352] Loss: 0.0022 Acc:100.00%
Training: Epoch[166/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[166/182] Iteration[150/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[166/182] Iteration[200/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[166/182] Iteration[250/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[166/182] Iteration[300/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[166/182] Iteration[350/352] Loss: 0.0024 Acc:99.98%
Training Progress:  91%|▉| 165/182 [2:04:45<14:51, 52.47s/it, Train Acc=99.98%, Epoch[166/182] Train Acc: 99.98% Valid Acc:93.68% Train loss:0.0024 Valid loss:0.2918 LR:0.0010000000000000002
Training Progress:  91%|▉| 166/182 [2:04:45<13:48, 51.81s/it, Train Acc=99.98%, Training: Epoch[167/182] Iteration[050/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[167/182] Iteration[100/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[167/182] Iteration[150/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[167/182] Iteration[200/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[167/182] Iteration[250/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[167/182] Iteration[300/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[167/182] Iteration[350/352] Loss: 0.0023 Acc:99.98%
Training Progress:  91%|▉| 166/182 [2:05:38<13:48, 51.81s/it, Train Acc=99.98%, Epoch[167/182] Train Acc: 99.98% Valid Acc:93.74% Train loss:0.0023 Valid loss:0.2914 LR:0.0010000000000000002
Training Progress:  92%|▉| 167/182 [2:05:38<12:59, 51.99s/it, Train Acc=99.98%, Training: Epoch[168/182] Iteration[050/352] Loss: 0.0020 Acc:100.00%
Training: Epoch[168/182] Iteration[100/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[168/182] Iteration[150/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[168/182] Iteration[200/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[168/182] Iteration[250/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[168/182] Iteration[300/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[168/182] Iteration[350/352] Loss: 0.0023 Acc:99.98%
Training Progress:  92%|▉| 167/182 [2:06:31<12:59, 51.99s/it, Train Acc=99.98%, Epoch[168/182] Train Acc: 99.98% Valid Acc:93.78% Train loss:0.0023 Valid loss:0.2984 LR:0.0010000000000000002
Training Progress:  92%|▉| 168/182 [2:06:31<12:13, 52.37s/it, Train Acc=99.98%, Training: Epoch[169/182] Iteration[050/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[169/182] Iteration[100/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[169/182] Iteration[150/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[169/182] Iteration[200/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[169/182] Iteration[250/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[169/182] Iteration[300/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[169/182] Iteration[350/352] Loss: 0.0021 Acc:99.99%
Training Progress:  92%|▉| 168/182 [2:07:24<12:13, 52.37s/it, Train Acc=99.99%, Epoch[169/182] Train Acc: 99.99% Valid Acc:93.74% Train loss:0.0021 Valid loss:0.2896 LR:0.0010000000000000002
Training Progress:  93%|▉| 169/182 [2:07:24<11:23, 52.62s/it, Train Acc=99.99%, Training: Epoch[170/182] Iteration[050/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[170/182] Iteration[100/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[170/182] Iteration[150/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[170/182] Iteration[200/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[170/182] Iteration[250/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[170/182] Iteration[300/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[170/182] Iteration[350/352] Loss: 0.0024 Acc:99.98%
Training Progress:  93%|▉| 169/182 [2:08:19<11:23, 52.62s/it, Train Acc=99.98%, Epoch[170/182] Train Acc: 99.98% Valid Acc:93.76% Train loss:0.0024 Valid loss:0.2920 LR:0.0010000000000000002
Training Progress:  93%|▉| 170/182 [2:08:19<10:39, 53.29s/it, Train Acc=99.98%, Training: Epoch[171/182] Iteration[050/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[171/182] Iteration[100/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[171/182] Iteration[150/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[171/182] Iteration[200/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[171/182] Iteration[250/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[171/182] Iteration[300/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[171/182] Iteration[350/352] Loss: 0.0024 Acc:99.98%
Training Progress:  93%|▉| 170/182 [2:09:13<10:39, 53.29s/it, Train Acc=99.98%, Epoch[171/182] Train Acc: 99.98% Valid Acc:93.74% Train loss:0.0024 Valid loss:0.2945 LR:0.0010000000000000002
Training Progress:  94%|▉| 171/182 [2:09:13<09:48, 53.54s/it, Train Acc=99.98%, Training: Epoch[172/182] Iteration[050/352] Loss: 0.0021 Acc:100.00%
Training: Epoch[172/182] Iteration[100/352] Loss: 0.0020 Acc:99.99%
Training: Epoch[172/182] Iteration[150/352] Loss: 0.0022 Acc:99.99%
Training: Epoch[172/182] Iteration[200/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[172/182] Iteration[250/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[172/182] Iteration[300/352] Loss: 0.0020 Acc:99.99%
Training: Epoch[172/182] Iteration[350/352] Loss: 0.0021 Acc:99.99%
Training Progress:  94%|▉| 171/182 [2:10:07<09:48, 53.54s/it, Train Acc=99.99%, Epoch[172/182] Train Acc: 99.99% Valid Acc:93.80% Train loss:0.0021 Valid loss:0.2914 LR:0.0010000000000000002
Training Progress:  95%|▉| 172/182 [2:10:07<08:56, 53.61s/it, Train Acc=99.99%, Training: Epoch[173/182] Iteration[050/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[173/182] Iteration[100/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[173/182] Iteration[150/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[173/182] Iteration[200/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[173/182] Iteration[250/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[173/182] Iteration[300/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[173/182] Iteration[350/352] Loss: 0.0025 Acc:99.96%
Training Progress:  95%|▉| 172/182 [2:11:01<08:56, 53.61s/it, Train Acc=99.96%, Epoch[173/182] Train Acc: 99.96% Valid Acc:93.72% Train loss:0.0025 Valid loss:0.2917 LR:0.0010000000000000002
Training Progress:  95%|▉| 173/182 [2:11:01<08:03, 53.69s/it, Train Acc=99.96%, Training: Epoch[174/182] Iteration[050/352] Loss: 0.0026 Acc:99.95%
Training: Epoch[174/182] Iteration[100/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[174/182] Iteration[150/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[174/182] Iteration[200/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[174/182] Iteration[250/352] Loss: 0.0021 Acc:99.99%
Training: Epoch[174/182] Iteration[300/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[174/182] Iteration[350/352] Loss: 0.0022 Acc:99.98%
Training Progress:  95%|▉| 173/182 [2:11:53<08:03, 53.69s/it, Train Acc=99.98%, Epoch[174/182] Train Acc: 99.98% Valid Acc:93.56% Train loss:0.0022 Valid loss:0.2950 LR:0.0010000000000000002
Training Progress:  96%|▉| 174/182 [2:11:53<07:04, 53.07s/it, Train Acc=99.98%, Training: Epoch[175/182] Iteration[050/352] Loss: 0.0021 Acc:100.00%
Training: Epoch[175/182] Iteration[100/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[175/182] Iteration[150/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[175/182] Iteration[200/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[175/182] Iteration[250/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[175/182] Iteration[300/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[175/182] Iteration[350/352] Loss: 0.0025 Acc:99.95%
Training Progress:  96%|▉| 174/182 [2:12:44<07:04, 53.07s/it, Train Acc=99.95%, Epoch[175/182] Train Acc: 99.95% Valid Acc:93.74% Train loss:0.0025 Valid loss:0.2947 LR:0.0010000000000000002
Training Progress:  96%|▉| 175/182 [2:12:44<06:08, 52.59s/it, Train Acc=99.95%, Training: Epoch[176/182] Iteration[050/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[176/182] Iteration[100/352] Loss: 0.0026 Acc:99.98%
Training: Epoch[176/182] Iteration[150/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[176/182] Iteration[200/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[176/182] Iteration[250/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[176/182] Iteration[300/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[176/182] Iteration[350/352] Loss: 0.0022 Acc:99.98%
Training Progress:  96%|▉| 175/182 [2:13:37<06:08, 52.59s/it, Train Acc=99.98%, Epoch[176/182] Train Acc: 99.98% Valid Acc:93.80% Train loss:0.0022 Valid loss:0.2936 LR:0.0010000000000000002
Training Progress:  97%|▉| 176/182 [2:13:37<05:16, 52.79s/it, Train Acc=99.98%, Training: Epoch[177/182] Iteration[050/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[177/182] Iteration[100/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[177/182] Iteration[150/352] Loss: 0.0028 Acc:99.96%
Training: Epoch[177/182] Iteration[200/352] Loss: 0.0026 Acc:99.97%
Training: Epoch[177/182] Iteration[250/352] Loss: 0.0025 Acc:99.97%
Training: Epoch[177/182] Iteration[300/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[177/182] Iteration[350/352] Loss: 0.0023 Acc:99.98%
Training Progress:  97%|▉| 176/182 [2:14:28<05:16, 52.79s/it, Train Acc=99.98%, Epoch[177/182] Train Acc: 99.98% Valid Acc:93.80% Train loss:0.0023 Valid loss:0.2914 LR:0.0010000000000000002
Training Progress:  97%|▉| 177/182 [2:14:28<04:21, 52.24s/it, Train Acc=99.98%, Training: Epoch[178/182] Iteration[050/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[178/182] Iteration[100/352] Loss: 0.0025 Acc:99.98%
Training: Epoch[178/182] Iteration[150/352] Loss: 0.0024 Acc:99.98%
Training: Epoch[178/182] Iteration[200/352] Loss: 0.0022 Acc:99.99%
Training: Epoch[178/182] Iteration[250/352] Loss: 0.0022 Acc:99.99%
Training: Epoch[178/182] Iteration[300/352] Loss: 0.0022 Acc:99.98%
Training: Epoch[178/182] Iteration[350/352] Loss: 0.0022 Acc:99.98%
Training Progress:  97%|▉| 177/182 [2:15:22<04:21, 52.24s/it, Train Acc=99.98%, Epoch[178/182] Train Acc: 99.98% Valid Acc:93.80% Train loss:0.0022 Valid loss:0.2927 LR:0.0010000000000000002
Training Progress:  98%|▉| 178/182 [2:15:22<03:30, 52.71s/it, Train Acc=99.98%, Training: Epoch[179/182] Iteration[050/352] Loss: 0.0023 Acc:99.97%
Training: Epoch[179/182] Iteration[100/352] Loss: 0.0023 Acc:99.95%
Training: Epoch[179/182] Iteration[150/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[179/182] Iteration[200/352] Loss: 0.0023 Acc:99.96%
Training: Epoch[179/182] Iteration[250/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[179/182] Iteration[300/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[179/182] Iteration[350/352] Loss: 0.0023 Acc:99.97%
Training Progress:  98%|▉| 178/182 [2:16:16<03:30, 52.71s/it, Train Acc=99.97%, Epoch[179/182] Train Acc: 99.97% Valid Acc:93.82% Train loss:0.0023 Valid loss:0.2903 LR:0.0010000000000000002
Training Progress:  98%|▉| 179/182 [2:16:16<02:39, 53.12s/it, Train Acc=99.97%, Training: Epoch[180/182] Iteration[050/352] Loss: 0.0023 Acc:99.98%
Training: Epoch[180/182] Iteration[100/352] Loss: 0.0020 Acc:99.99%
Training: Epoch[180/182] Iteration[150/352] Loss: 0.0019 Acc:99.99%
Training: Epoch[180/182] Iteration[200/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[180/182] Iteration[250/352] Loss: 0.0021 Acc:99.98%
Training: Epoch[180/182] Iteration[300/352] Loss: 0.0022 Acc:99.97%
Training: Epoch[180/182] Iteration[350/352] Loss: 0.0023 Acc:99.97%
Training Progress:  98%|▉| 179/182 [2:17:08<02:39, 53.12s/it, Train Acc=99.97%, Epoch[180/182] Train Acc: 99.97% Valid Acc:93.86% Train loss:0.0024 Valid loss:0.2928 LR:0.0010000000000000002
Training Progress:  99%|▉| 180/182 [2:17:08<01:45, 52.87s/it, Train Acc=99.97%, Training: Epoch[181/182] Iteration[050/352] Loss: 0.0030 Acc:99.97%
Training: Epoch[181/182] Iteration[100/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[181/182] Iteration[150/352] Loss: 0.0030 Acc:99.94%
Training: Epoch[181/182] Iteration[200/352] Loss: 0.0029 Acc:99.95%
Training: Epoch[181/182] Iteration[250/352] Loss: 0.0028 Acc:99.95%
Training: Epoch[181/182] Iteration[300/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[181/182] Iteration[350/352] Loss: 0.0026 Acc:99.96%
Training Progress:  99%|▉| 180/182 [2:18:00<01:45, 52.87s/it, Train Acc=99.96%, Epoch[181/182] Train Acc: 99.96% Valid Acc:93.84% Train loss:0.0026 Valid loss:0.2938 LR:0.0010000000000000002
Training Progress:  99%|▉| 181/182 [2:18:00<00:52, 52.57s/it, Train Acc=99.96%, Training: Epoch[182/182] Iteration[050/352] Loss: 0.0025 Acc:99.95%
Training: Epoch[182/182] Iteration[100/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[182/182] Iteration[150/352] Loss: 0.0027 Acc:99.95%
Training: Epoch[182/182] Iteration[200/352] Loss: 0.0025 Acc:99.96%
Training: Epoch[182/182] Iteration[250/352] Loss: 0.0024 Acc:99.96%
Training: Epoch[182/182] Iteration[300/352] Loss: 0.0024 Acc:99.97%
Training: Epoch[182/182] Iteration[350/352] Loss: 0.0024 Acc:99.97%
Training Progress:  99%|▉| 181/182 [2:18:53<00:52, 52.57s/it, Train Acc=99.97%, Epoch[182/182] Train Acc: 99.97% Valid Acc:93.80% Train loss:0.0024 Valid loss:0.2905 LR:0.0010000000000000002
class:plane     , total num:4508.0, correct num:4507.0  Recall: 99.98% Precision: 100.00%
class:car       , total num:4520.0, correct num:4520.0  Recall: 100.00% Precision: 100.00%
class:bird      , total num:4534.0, correct num:4532.0  Recall: 99.95% Precision: 99.95%
class:cat       , total num:4494.0, correct num:4491.0  Recall: 99.93% Precision: 99.89%
class:deer      , total num:4480.0, correct num:4479.0  Recall: 99.98% Precision: 99.95%
class:dog       , total num:4514.0, correct num:4509.0  Recall: 99.89% Precision: 99.98%
class:frog      , total num:4490.0, correct num:4490.0  Recall: 100.00% Precision: 100.00%
class:horse     , total num:4459.0, correct num:4458.0  Recall: 99.98% Precision: 99.95%
class:ship      , total num:4519.0, correct num:4518.0  Recall: 99.98% Precision: 99.98%
class:truck     , total num:4482.0, correct num:4482.0  Recall: 100.00% Precision: 99.98%
class:plane     , total num:492.0 , correct num:461.0  Recall: 93.68% Precision: 94.84%
class:car       , total num:480.0 , correct num:469.0  Recall: 97.69% Precision: 97.28%
class:bird      , total num:466.0 , correct num:418.0  Recall: 89.68% Precision: 91.65%
class:cat       , total num:506.0 , correct num:442.0  Recall: 87.33% Precision: 86.65%
class:deer      , total num:520.0 , correct num:484.0  Recall: 93.06% Precision: 95.82%
class:dog       , total num:486.0 , correct num:441.0  Recall: 90.72% Precision: 88.36%
class:frog      , total num:510.0 , correct num:490.0  Recall: 96.06% Precision: 94.76%
class:horse     , total num:541.0 , correct num:523.0  Recall: 96.65% Precision: 95.07%
class:ship      , total num:481.0 , correct num:462.0  Recall: 96.03% Precision: 97.04%
class:truck     , total num:518.0 , correct num:500.0  Recall: 96.51% Precision: 96.32%
Training Progress: 100%|█| 182/182 [2:18:55<00:00, 45.80s/it, Train Acc=99.97%, 

================ Training Finished ================
Finished Time      : 05-15_14-38
Best Validation Acc: 0.9386
Best Epoch         : 179
Best Test Acc      : 0.9336
Total Training Time: 8335.65 sec (138.93 min)
===================================================

Acknowledgments and References

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

↪Back to the content⤴