2020-09-07 21:36:00,904 - algorithms.Algorithm - INFO   - Algorithm options {'data_train_opt': {'batch_size': 128, 'unsupervised': True, 'epoch_size': None, 'random_sized_crop': False, 'dataset_name': 'mnist', 'split': 'train'}, 'data_test_opt': {'batch_size': 128, 'unsupervised': True, 'epoch_size': None, 'random_sized_crop': False, 'dataset_name': 'mnist', 'split': 'test'}, 'max_num_epochs': 200, 'networks': {'model': {'def_file': 'architectures/NetworkInNetwork.py', 'pretrained': None, 'opt': {'num_classes': 4, 'num_inchannels': 1, 'num_stages': 4, 'use_avg_on_conv3': False}, 'optim_params': {'optim_type': 'sgd', 'lr': 0.1, 'momentum': 0.9, 'weight_decay': 0.0005, 'nesterov': True, 'LUT_lr': [(60, 0.1), (120, 0.02), (160, 0.004), (200, 0.0008)]}}}, 'criterions': {'loss': {'ctype': 'CrossEntropyLoss', 'opt': None}}, 'algorithm_type': 'ClassificationModel', 'exp_dir': './experiments/MNIST_RotNet_NIN4blocks', 'disp_step': 50}
2020-09-07 21:36:00,904 - algorithms.Algorithm - INFO   - Set network model
2020-09-07 21:36:00,904 - algorithms.Algorithm - INFO   - ==> Initiliaze network model from file architectures/NetworkInNetwork.py with opts: {'num_classes': 4, 'num_inchannels': 1, 'num_stages': 4, 'use_avg_on_conv3': False}
2020-09-07 21:36:00,920 - algorithms.Algorithm - INFO   - Initialize criterion[loss]: CrossEntropyLoss with options: None
2020-09-07 21:36:04,783 - algorithms.Algorithm - INFO   - Initialize optimizer: sgd with params: {'optim_type': 'sgd', 'lr': 0.1, 'momentum': 0.9, 'weight_decay': 0.0005, 'nesterov': True, 'LUT_lr': [(60, 0.1), (120, 0.02), (160, 0.004), (200, 0.0008)]} for netwotk: model
2020-09-07 21:36:04,784 - algorithms.Algorithm - INFO   - Training epoch [  1 / 200]
2020-09-07 21:36:04,784 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:36:04,784 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:36:10,963 - algorithms.Algorithm - INFO   - ==> Iteration [  1][  50 /  469]: {'prec1': 68.125, 'loss': 0.6797, 'load_time': 35.2013, 'process_time': 64.7987}
2020-09-07 21:36:16,372 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 100 /  469]: {'prec1': 75.3262, 'loss': 0.5385, 'load_time': 33.6704, 'process_time': 66.3296}
2020-09-07 21:36:21,727 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 150 /  469]: {'prec1': 78.8867, 'loss': 0.4643, 'load_time': 33.2838, 'process_time': 66.7162}
2020-09-07 21:36:27,082 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 200 /  469]: {'prec1': 81.1572, 'loss': 0.4182, 'load_time': 32.9463, 'process_time': 67.0537}
2020-09-07 21:36:32,557 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 250 /  469]: {'prec1': 82.8031, 'loss': 0.3841, 'load_time': 33.8775, 'process_time': 66.1225}
2020-09-07 21:36:37,976 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 300 /  469]: {'prec1': 83.9447, 'loss': 0.3593, 'load_time': 34.2384, 'process_time': 65.7616}
2020-09-07 21:36:43,497 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 350 /  469]: {'prec1': 84.8544, 'loss': 0.3407, 'load_time': 34.7566, 'process_time': 65.2434}
2020-09-07 21:36:49,007 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 400 /  469]: {'prec1': 85.563, 'loss': 0.3257, 'load_time': 34.7681, 'process_time': 65.2319}
2020-09-07 21:36:54,428 - algorithms.Algorithm - INFO   - ==> Iteration [  1][ 450 /  469]: {'prec1': 86.191, 'loss': 0.3129, 'load_time': 34.516, 'process_time': 65.484}
2020-09-07 21:36:56,532 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 86.3763, 'loss': 0.309, 'load_time': 34.6751, 'process_time': 65.3249}
2020-09-07 21:36:56,604 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:36:56,604 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:37:03,364 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 84.825, 'loss': 0.3665, 'load_time': 2.5782, 'process_time': 97.4218}
2020-09-07 21:37:03,365 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 84.825, 'loss': 0.3665, 'load_time': 2.5782, 'process_time': 97.4218}
2020-09-07 21:37:03,365 - algorithms.Algorithm - INFO   - Training epoch [  2 / 200]
2020-09-07 21:37:03,365 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:37:03,365 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:37:08,945 - algorithms.Algorithm - INFO   - ==> Iteration [  2][  50 /  469]: {'prec1': 91.1406, 'loss': 0.2052, 'load_time': 35.7837, 'process_time': 64.2163}
2020-09-07 21:37:14,456 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 100 /  469]: {'prec1': 91.4082, 'loss': 0.2014, 'load_time': 36.1314, 'process_time': 63.8686}
2020-09-07 21:37:19,938 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 150 /  469]: {'prec1': 91.444, 'loss': 0.2015, 'load_time': 35.3504, 'process_time': 64.6496}
2020-09-07 21:37:25,509 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 200 /  469]: {'prec1': 91.4326, 'loss': 0.202, 'load_time': 36.3112, 'process_time': 63.6888}
2020-09-07 21:37:31,032 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 250 /  469]: {'prec1': 91.3969, 'loss': 0.2023, 'load_time': 36.2069, 'process_time': 63.7931}
2020-09-07 21:37:36,513 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 300 /  469]: {'prec1': 91.4896, 'loss': 0.2003, 'load_time': 36.5683, 'process_time': 63.4317}
2020-09-07 21:37:42,087 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 350 /  469]: {'prec1': 91.4559, 'loss': 0.2005, 'load_time': 36.7366, 'process_time': 63.2634}
2020-09-07 21:37:47,669 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 400 /  469]: {'prec1': 91.5322, 'loss': 0.1991, 'load_time': 37.0294, 'process_time': 62.9706}
2020-09-07 21:37:53,234 - algorithms.Algorithm - INFO   - ==> Iteration [  2][ 450 /  469]: {'prec1': 91.6233, 'loss': 0.1973, 'load_time': 36.9974, 'process_time': 63.0026}
2020-09-07 21:37:55,332 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 91.6289, 'loss': 0.1973, 'load_time': 37.1876, 'process_time': 62.8124}
2020-09-07 21:37:55,411 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:37:55,411 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:38:02,159 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.9921, 'loss': 0.2341, 'load_time': 2.5435, 'process_time': 97.4565}
2020-09-07 21:38:02,159 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.9921, 'loss': 0.2341, 'load_time': 2.5435, 'process_time': 97.4565}
2020-09-07 21:38:02,159 - algorithms.Algorithm - INFO   - Training epoch [  3 / 200]
2020-09-07 21:38:02,159 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:38:02,159 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:38:07,794 - algorithms.Algorithm - INFO   - ==> Iteration [  3][  50 /  469]: {'prec1': 92.5859, 'loss': 0.1734, 'load_time': 37.6586, 'process_time': 62.3414}
2020-09-07 21:38:13,369 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 100 /  469]: {'prec1': 92.5098, 'loss': 0.1796, 'load_time': 38.2027, 'process_time': 61.7973}
2020-09-07 21:38:18,991 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 150 /  469]: {'prec1': 92.3164, 'loss': 0.1836, 'load_time': 39.312, 'process_time': 60.688}
2020-09-07 21:38:24,632 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 200 /  469]: {'prec1': 92.377, 'loss': 0.1824, 'load_time': 39.0407, 'process_time': 60.9593}
2020-09-07 21:38:30,215 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 250 /  469]: {'prec1': 92.3141, 'loss': 0.1837, 'load_time': 39.0172, 'process_time': 60.9828}
2020-09-07 21:38:35,753 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 300 /  469]: {'prec1': 92.3639, 'loss': 0.1834, 'load_time': 38.6925, 'process_time': 61.3075}
2020-09-07 21:38:41,478 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 350 /  469]: {'prec1': 92.356, 'loss': 0.1826, 'load_time': 39.1091, 'process_time': 60.8909}
2020-09-07 21:38:47,199 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 400 /  469]: {'prec1': 92.3418, 'loss': 0.1825, 'load_time': 39.3311, 'process_time': 60.6689}
2020-09-07 21:38:52,783 - algorithms.Algorithm - INFO   - ==> Iteration [  3][ 450 /  469]: {'prec1': 92.3268, 'loss': 0.1828, 'load_time': 39.2912, 'process_time': 60.7088}
2020-09-07 21:38:54,955 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 92.3413, 'loss': 0.1822, 'load_time': 39.4401, 'process_time': 60.5599}
2020-09-07 21:38:55,034 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:38:55,035 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:39:01,759 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.0699, 'loss': 0.2502, 'load_time': 2.6205, 'process_time': 97.3795}
2020-09-07 21:39:01,759 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.0699, 'loss': 0.2502, 'load_time': 2.6205, 'process_time': 97.3795}
2020-09-07 21:39:01,759 - algorithms.Algorithm - INFO   - Training epoch [  4 / 200]
2020-09-07 21:39:01,760 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:39:01,760 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:39:07,460 - algorithms.Algorithm - INFO   - ==> Iteration [  4][  50 /  469]: {'prec1': 92.6094, 'loss': 0.1737, 'load_time': 38.2911, 'process_time': 61.7089}
2020-09-07 21:39:13,103 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 100 /  469]: {'prec1': 92.8633, 'loss': 0.1685, 'load_time': 39.7155, 'process_time': 60.2845}
2020-09-07 21:39:18,653 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 150 /  469]: {'prec1': 92.6016, 'loss': 0.1723, 'load_time': 38.9232, 'process_time': 61.0768}
2020-09-07 21:39:24,348 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 200 /  469]: {'prec1': 92.6143, 'loss': 0.1737, 'load_time': 39.3025, 'process_time': 60.6975}
2020-09-07 21:39:30,133 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 250 /  469]: {'prec1': 92.6828, 'loss': 0.1727, 'load_time': 40.5157, 'process_time': 59.4843}
2020-09-07 21:39:35,789 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 300 /  469]: {'prec1': 92.7682, 'loss': 0.1713, 'load_time': 40.6416, 'process_time': 59.3584}
2020-09-07 21:39:41,507 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 350 /  469]: {'prec1': 92.7701, 'loss': 0.1714, 'load_time': 40.7758, 'process_time': 59.2242}
2020-09-07 21:39:47,192 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 400 /  469]: {'prec1': 92.8135, 'loss': 0.1705, 'load_time': 41.0149, 'process_time': 58.9851}
2020-09-07 21:39:52,936 - algorithms.Algorithm - INFO   - ==> Iteration [  4][ 450 /  469]: {'prec1': 92.773, 'loss': 0.1708, 'load_time': 41.1166, 'process_time': 58.8834}
2020-09-07 21:39:55,127 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 92.7521, 'loss': 0.1713, 'load_time': 41.2131, 'process_time': 58.7869}
2020-09-07 21:39:55,207 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:39:55,207 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:40:01,926 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.0378, 'loss': 0.2622, 'load_time': 2.5284, 'process_time': 97.4716}
2020-09-07 21:40:01,926 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.0378, 'loss': 0.2622, 'load_time': 2.5284, 'process_time': 97.4716}
2020-09-07 21:40:01,926 - algorithms.Algorithm - INFO   - Training epoch [  5 / 200]
2020-09-07 21:40:01,926 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:40:01,926 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:40:07,601 - algorithms.Algorithm - INFO   - ==> Iteration [  5][  50 /  469]: {'prec1': 92.957, 'loss': 0.1659, 'load_time': 39.8882, 'process_time': 60.1118}
2020-09-07 21:40:13,200 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 100 /  469]: {'prec1': 92.9219, 'loss': 0.1676, 'load_time': 39.571, 'process_time': 60.429}
2020-09-07 21:40:18,842 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 150 /  469]: {'prec1': 92.8685, 'loss': 0.1694, 'load_time': 40.0892, 'process_time': 59.9108}
2020-09-07 21:40:24,545 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 200 /  469]: {'prec1': 92.7969, 'loss': 0.1712, 'load_time': 40.344, 'process_time': 59.656}
2020-09-07 21:40:30,306 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 250 /  469]: {'prec1': 92.8125, 'loss': 0.1699, 'load_time': 41.2601, 'process_time': 58.7399}
2020-09-07 21:40:36,024 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 300 /  469]: {'prec1': 92.776, 'loss': 0.1705, 'load_time': 41.3728, 'process_time': 58.6272}
2020-09-07 21:40:41,778 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 350 /  469]: {'prec1': 92.8259, 'loss': 0.1693, 'load_time': 41.5855, 'process_time': 58.4145}
2020-09-07 21:40:47,612 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 400 /  469]: {'prec1': 92.8877, 'loss': 0.1683, 'load_time': 41.8739, 'process_time': 58.1261}
2020-09-07 21:40:53,385 - algorithms.Algorithm - INFO   - ==> Iteration [  5][ 450 /  469]: {'prec1': 92.9076, 'loss': 0.1681, 'load_time': 42.028, 'process_time': 57.972}
2020-09-07 21:40:55,577 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 92.9154, 'loss': 0.1677, 'load_time': 42.1928, 'process_time': 57.8072}
2020-09-07 21:40:55,662 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:40:55,662 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:41:02,400 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.5854, 'loss': 0.2201, 'load_time': 2.6367, 'process_time': 97.3633}
2020-09-07 21:41:02,400 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.5854, 'loss': 0.2201, 'load_time': 2.6367, 'process_time': 97.3633}
2020-09-07 21:41:02,400 - algorithms.Algorithm - INFO   - Training epoch [  6 / 200]
2020-09-07 21:41:02,400 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:41:02,400 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:41:08,054 - algorithms.Algorithm - INFO   - ==> Iteration [  6][  50 /  469]: {'prec1': 92.9609, 'loss': 0.164, 'load_time': 38.21, 'process_time': 61.79}
2020-09-07 21:41:13,726 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 100 /  469]: {'prec1': 92.9238, 'loss': 0.1659, 'load_time': 38.6652, 'process_time': 61.3348}
2020-09-07 21:41:19,450 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 150 /  469]: {'prec1': 93.0078, 'loss': 0.1659, 'load_time': 39.9462, 'process_time': 60.0538}
2020-09-07 21:41:25,187 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 200 /  469]: {'prec1': 93.0898, 'loss': 0.1645, 'load_time': 40.841, 'process_time': 59.159}
2020-09-07 21:41:30,985 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 250 /  469]: {'prec1': 93.1094, 'loss': 0.1639, 'load_time': 41.1293, 'process_time': 58.8707}
2020-09-07 21:41:36,749 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 300 /  469]: {'prec1': 93.0618, 'loss': 0.1649, 'load_time': 41.7396, 'process_time': 58.2604}
2020-09-07 21:41:42,549 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 350 /  469]: {'prec1': 93.0675, 'loss': 0.1649, 'load_time': 42.423, 'process_time': 57.577}
2020-09-07 21:41:48,396 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 400 /  469]: {'prec1': 93.0469, 'loss': 0.1651, 'load_time': 42.8153, 'process_time': 57.1847}
2020-09-07 21:41:54,225 - algorithms.Algorithm - INFO   - ==> Iteration [  6][ 450 /  469]: {'prec1': 93.0052, 'loss': 0.1654, 'load_time': 43.5061, 'process_time': 56.4939}
2020-09-07 21:41:56,387 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.0076, 'loss': 0.1655, 'load_time': 43.4509, 'process_time': 56.5491}
2020-09-07 21:41:56,469 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:41:56,470 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:42:03,175 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.8426, 'loss': 0.2123, 'load_time': 2.63, 'process_time': 97.37}
2020-09-07 21:42:03,175 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.8426, 'loss': 0.2123, 'load_time': 2.63, 'process_time': 97.37}
2020-09-07 21:42:03,175 - algorithms.Algorithm - INFO   - Training epoch [  7 / 200]
2020-09-07 21:42:03,175 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:42:03,175 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:42:08,771 - algorithms.Algorithm - INFO   - ==> Iteration [  7][  50 /  469]: {'prec1': 93.3477, 'loss': 0.1592, 'load_time': 36.1351, 'process_time': 63.8649}
2020-09-07 21:42:14,413 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 100 /  469]: {'prec1': 93.3672, 'loss': 0.1612, 'load_time': 38.5355, 'process_time': 61.4645}
2020-09-07 21:42:20,139 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 150 /  469]: {'prec1': 93.3021, 'loss': 0.1614, 'load_time': 39.5648, 'process_time': 60.4352}
2020-09-07 21:42:25,917 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 200 /  469]: {'prec1': 93.2227, 'loss': 0.1626, 'load_time': 40.6394, 'process_time': 59.3606}
2020-09-07 21:42:31,733 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 250 /  469]: {'prec1': 93.2539, 'loss': 0.1612, 'load_time': 41.8471, 'process_time': 58.1529}
2020-09-07 21:42:37,526 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 300 /  469]: {'prec1': 93.2487, 'loss': 0.1621, 'load_time': 42.2915, 'process_time': 57.7085}
2020-09-07 21:42:43,273 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 350 /  469]: {'prec1': 93.1975, 'loss': 0.1631, 'load_time': 42.4814, 'process_time': 57.5186}
2020-09-07 21:42:49,094 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 400 /  469]: {'prec1': 93.1772, 'loss': 0.1632, 'load_time': 42.7511, 'process_time': 57.2489}
2020-09-07 21:42:54,826 - algorithms.Algorithm - INFO   - ==> Iteration [  7][ 450 /  469]: {'prec1': 93.2079, 'loss': 0.1629, 'load_time': 42.7384, 'process_time': 57.2616}
2020-09-07 21:42:57,002 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.2089, 'loss': 0.1631, 'load_time': 42.9366, 'process_time': 57.0634}
2020-09-07 21:42:57,087 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:42:57,087 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:43:03,804 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.3259, 'loss': 0.228, 'load_time': 2.5675, 'process_time': 97.4325}
2020-09-07 21:43:03,805 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.3259, 'loss': 0.228, 'load_time': 2.5675, 'process_time': 97.4325}
2020-09-07 21:43:03,805 - algorithms.Algorithm - INFO   - Training epoch [  8 / 200]
2020-09-07 21:43:03,805 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:43:03,805 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:43:09,516 - algorithms.Algorithm - INFO   - ==> Iteration [  8][  50 /  469]: {'prec1': 93.1797, 'loss': 0.1599, 'load_time': 40.4661, 'process_time': 59.5339}
2020-09-07 21:43:15,208 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 100 /  469]: {'prec1': 93.168, 'loss': 0.1588, 'load_time': 41.5854, 'process_time': 58.4146}
2020-09-07 21:43:20,901 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 150 /  469]: {'prec1': 93.1263, 'loss': 0.1593, 'load_time': 41.2221, 'process_time': 58.7779}
2020-09-07 21:43:26,658 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 200 /  469]: {'prec1': 93.2217, 'loss': 0.1588, 'load_time': 40.9837, 'process_time': 59.0163}
2020-09-07 21:43:32,394 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 250 /  469]: {'prec1': 93.2289, 'loss': 0.1591, 'load_time': 42.5629, 'process_time': 57.4371}
2020-09-07 21:43:38,145 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 300 /  469]: {'prec1': 93.2324, 'loss': 0.1592, 'load_time': 42.6954, 'process_time': 57.3046}
2020-09-07 21:43:43,956 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 350 /  469]: {'prec1': 93.2093, 'loss': 0.1603, 'load_time': 42.9718, 'process_time': 57.0282}
2020-09-07 21:43:49,708 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 400 /  469]: {'prec1': 93.1626, 'loss': 0.162, 'load_time': 43.1497, 'process_time': 56.8503}
2020-09-07 21:43:55,495 - algorithms.Algorithm - INFO   - ==> Iteration [  8][ 450 /  469]: {'prec1': 93.1467, 'loss': 0.1622, 'load_time': 43.2412, 'process_time': 56.7588}
2020-09-07 21:43:57,662 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.15, 'loss': 0.1621, 'load_time': 43.4369, 'process_time': 56.5631}
2020-09-07 21:43:57,742 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:43:57,742 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:44:04,489 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.7882, 'loss': 0.213, 'load_time': 2.6079, 'process_time': 97.3921}
2020-09-07 21:44:04,489 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.7882, 'loss': 0.213, 'load_time': 2.6079, 'process_time': 97.3921}
2020-09-07 21:44:04,489 - algorithms.Algorithm - INFO   - Training epoch [  9 / 200]
2020-09-07 21:44:04,489 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:44:04,489 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:44:10,175 - algorithms.Algorithm - INFO   - ==> Iteration [  9][  50 /  469]: {'prec1': 93.1562, 'loss': 0.1643, 'load_time': 41.1168, 'process_time': 58.8832}
2020-09-07 21:44:15,793 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 100 /  469]: {'prec1': 93.2383, 'loss': 0.1622, 'load_time': 40.5529, 'process_time': 59.4471}
2020-09-07 21:44:21,570 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 150 /  469]: {'prec1': 93.2826, 'loss': 0.1613, 'load_time': 42.0131, 'process_time': 57.9869}
2020-09-07 21:44:27,376 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 200 /  469]: {'prec1': 93.3037, 'loss': 0.1611, 'load_time': 42.9505, 'process_time': 57.0495}
2020-09-07 21:44:33,131 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 250 /  469]: {'prec1': 93.2164, 'loss': 0.1613, 'load_time': 43.4298, 'process_time': 56.5702}
2020-09-07 21:44:38,915 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 300 /  469]: {'prec1': 93.1654, 'loss': 0.1622, 'load_time': 43.3273, 'process_time': 56.6727}
2020-09-07 21:44:44,726 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 350 /  469]: {'prec1': 93.1557, 'loss': 0.1621, 'load_time': 43.7482, 'process_time': 56.2518}
2020-09-07 21:44:50,550 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 400 /  469]: {'prec1': 93.2061, 'loss': 0.1616, 'load_time': 43.6966, 'process_time': 56.3034}
2020-09-07 21:44:56,302 - algorithms.Algorithm - INFO   - ==> Iteration [  9][ 450 /  469]: {'prec1': 93.2227, 'loss': 0.1613, 'load_time': 43.8156, 'process_time': 56.1844}
2020-09-07 21:44:58,506 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.1986, 'loss': 0.1618, 'load_time': 44.0322, 'process_time': 55.9678}
2020-09-07 21:44:58,586 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:44:58,586 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:45:05,336 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.3765, 'loss': 0.2556, 'load_time': 2.5461, 'process_time': 97.4539}
2020-09-07 21:45:05,336 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.3765, 'loss': 0.2556, 'load_time': 2.5461, 'process_time': 97.4539}
2020-09-07 21:45:05,336 - algorithms.Algorithm - INFO   - Training epoch [ 10 / 200]
2020-09-07 21:45:05,336 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:45:05,336 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:45:10,975 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][  50 /  469]: {'prec1': 93.1367, 'loss': 0.1596, 'load_time': 37.3698, 'process_time': 62.6302}
2020-09-07 21:45:16,622 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 100 /  469]: {'prec1': 93.1387, 'loss': 0.1604, 'load_time': 39.9929, 'process_time': 60.0071}
2020-09-07 21:45:22,292 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 150 /  469]: {'prec1': 93.2018, 'loss': 0.1604, 'load_time': 40.835, 'process_time': 59.165}
2020-09-07 21:45:28,080 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 200 /  469]: {'prec1': 93.209, 'loss': 0.1604, 'load_time': 41.0136, 'process_time': 58.9864}
2020-09-07 21:45:33,851 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 250 /  469]: {'prec1': 93.25, 'loss': 0.1598, 'load_time': 41.4707, 'process_time': 58.5293}
2020-09-07 21:45:39,665 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 300 /  469]: {'prec1': 93.2441, 'loss': 0.1598, 'load_time': 42.0764, 'process_time': 57.9236}
2020-09-07 21:45:45,428 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 350 /  469]: {'prec1': 93.2924, 'loss': 0.1596, 'load_time': 42.2381, 'process_time': 57.7619}
2020-09-07 21:45:51,192 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 400 /  469]: {'prec1': 93.2837, 'loss': 0.1603, 'load_time': 42.3796, 'process_time': 57.6204}
2020-09-07 21:45:56,972 - algorithms.Algorithm - INFO   - ==> Iteration [ 10][ 450 /  469]: {'prec1': 93.2791, 'loss': 0.1603, 'load_time': 42.5082, 'process_time': 57.4918}
2020-09-07 21:45:59,121 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.2572, 'loss': 0.1606, 'load_time': 42.5985, 'process_time': 57.4015}
2020-09-07 21:45:59,202 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:45:59,203 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:46:06,024 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.5966, 'loss': 0.2022, 'load_time': 2.6218, 'process_time': 97.3782}
2020-09-07 21:46:06,025 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.5966, 'loss': 0.2022, 'load_time': 2.6218, 'process_time': 97.3782}
2020-09-07 21:46:06,025 - algorithms.Algorithm - INFO   - Training epoch [ 11 / 200]
2020-09-07 21:46:06,025 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:46:06,025 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:46:11,672 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][  50 /  469]: {'prec1': 93.4141, 'loss': 0.1571, 'load_time': 36.5957, 'process_time': 63.4043}
2020-09-07 21:46:17,351 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 100 /  469]: {'prec1': 93.5625, 'loss': 0.1535, 'load_time': 38.834, 'process_time': 61.166}
2020-09-07 21:46:23,001 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 150 /  469]: {'prec1': 93.4661, 'loss': 0.1558, 'load_time': 39.7053, 'process_time': 60.2947}
2020-09-07 21:46:28,786 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 200 /  469]: {'prec1': 93.4189, 'loss': 0.1569, 'load_time': 40.7105, 'process_time': 59.2895}
2020-09-07 21:46:34,558 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 250 /  469]: {'prec1': 93.4305, 'loss': 0.1565, 'load_time': 41.8258, 'process_time': 58.1742}
2020-09-07 21:46:40,420 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 300 /  469]: {'prec1': 93.3711, 'loss': 0.1576, 'load_time': 42.0867, 'process_time': 57.9133}
2020-09-07 21:46:46,164 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 350 /  469]: {'prec1': 93.3638, 'loss': 0.1575, 'load_time': 42.4154, 'process_time': 57.5846}
2020-09-07 21:46:51,911 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 400 /  469]: {'prec1': 93.2881, 'loss': 0.1588, 'load_time': 42.1058, 'process_time': 57.8942}
2020-09-07 21:46:57,714 - algorithms.Algorithm - INFO   - ==> Iteration [ 11][ 450 /  469]: {'prec1': 93.2995, 'loss': 0.1587, 'load_time': 42.4493, 'process_time': 57.5507}
2020-09-07 21:46:59,947 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.3123, 'loss': 0.1585, 'load_time': 42.5583, 'process_time': 57.4417}
2020-09-07 21:47:00,027 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:47:00,028 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:47:06,814 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4211, 'loss': 0.2014, 'load_time': 2.5438, 'process_time': 97.4562}
2020-09-07 21:47:06,815 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4211, 'loss': 0.2014, 'load_time': 2.5438, 'process_time': 97.4562}
2020-09-07 21:47:06,815 - algorithms.Algorithm - INFO   - Training epoch [ 12 / 200]
2020-09-07 21:47:06,815 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:47:06,815 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:47:12,516 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][  50 /  469]: {'prec1': 93.4766, 'loss': 0.1529, 'load_time': 35.5916, 'process_time': 64.4084}
2020-09-07 21:47:18,147 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 100 /  469]: {'prec1': 93.5684, 'loss': 0.1536, 'load_time': 38.0731, 'process_time': 61.9269}
2020-09-07 21:47:23,934 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 150 /  469]: {'prec1': 93.4414, 'loss': 0.1569, 'load_time': 40.1742, 'process_time': 59.8258}
2020-09-07 21:47:29,575 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 200 /  469]: {'prec1': 93.3867, 'loss': 0.1578, 'load_time': 41.2052, 'process_time': 58.7948}
2020-09-07 21:47:35,312 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 250 /  469]: {'prec1': 93.3586, 'loss': 0.1582, 'load_time': 41.1434, 'process_time': 58.8566}
2020-09-07 21:47:41,153 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 300 /  469]: {'prec1': 93.2949, 'loss': 0.159, 'load_time': 41.8346, 'process_time': 58.1654}
2020-09-07 21:47:46,985 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 350 /  469]: {'prec1': 93.2913, 'loss': 0.1592, 'load_time': 42.0765, 'process_time': 57.9235}
2020-09-07 21:47:52,832 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 400 /  469]: {'prec1': 93.2188, 'loss': 0.1608, 'load_time': 42.2731, 'process_time': 57.7269}
2020-09-07 21:47:58,512 - algorithms.Algorithm - INFO   - ==> Iteration [ 12][ 450 /  469]: {'prec1': 93.309, 'loss': 0.1597, 'load_time': 41.7046, 'process_time': 58.2954}
2020-09-07 21:48:00,731 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.3101, 'loss': 0.1593, 'load_time': 41.9202, 'process_time': 58.0798}
2020-09-07 21:48:00,813 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:48:00,814 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:48:07,633 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.6609, 'loss': 0.2043, 'load_time': 2.6195, 'process_time': 97.3805}
2020-09-07 21:48:07,633 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.6609, 'loss': 0.2043, 'load_time': 2.6195, 'process_time': 97.3805}
2020-09-07 21:48:07,633 - algorithms.Algorithm - INFO   - Training epoch [ 13 / 200]
2020-09-07 21:48:07,633 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:48:07,633 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:48:13,251 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][  50 /  469]: {'prec1': 93.7188, 'loss': 0.1537, 'load_time': 37.8575, 'process_time': 62.1425}
2020-09-07 21:48:18,943 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 100 /  469]: {'prec1': 93.7852, 'loss': 0.1519, 'load_time': 39.8351, 'process_time': 60.1649}
2020-09-07 21:48:24,655 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 150 /  469]: {'prec1': 93.6237, 'loss': 0.1542, 'load_time': 39.7374, 'process_time': 60.2626}
2020-09-07 21:48:30,390 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 200 /  469]: {'prec1': 93.5166, 'loss': 0.155, 'load_time': 40.7596, 'process_time': 59.2404}
2020-09-07 21:48:36,257 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 250 /  469]: {'prec1': 93.4688, 'loss': 0.1562, 'load_time': 41.8062, 'process_time': 58.1938}
2020-09-07 21:48:42,041 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 300 /  469]: {'prec1': 93.4629, 'loss': 0.1561, 'load_time': 41.8399, 'process_time': 58.1601}
2020-09-07 21:48:47,767 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 350 /  469]: {'prec1': 93.4224, 'loss': 0.1565, 'load_time': 41.8868, 'process_time': 58.1132}
2020-09-07 21:48:53,515 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 400 /  469]: {'prec1': 93.4297, 'loss': 0.1563, 'load_time': 41.9596, 'process_time': 58.0404}
2020-09-07 21:48:59,294 - algorithms.Algorithm - INFO   - ==> Iteration [ 13][ 450 /  469]: {'prec1': 93.421, 'loss': 0.1563, 'load_time': 42.1032, 'process_time': 57.8968}
2020-09-07 21:49:01,546 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.4198, 'loss': 0.156, 'load_time': 42.3932, 'process_time': 57.6068}
2020-09-07 21:49:01,630 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:49:01,630 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:49:08,447 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.3085, 'loss': 0.2349, 'load_time': 2.8125, 'process_time': 97.1875}
2020-09-07 21:49:08,447 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.3085, 'loss': 0.2349, 'load_time': 2.8125, 'process_time': 97.1875}
2020-09-07 21:49:08,447 - algorithms.Algorithm - INFO   - Training epoch [ 14 / 200]
2020-09-07 21:49:08,447 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:49:08,447 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:49:14,166 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][  50 /  469]: {'prec1': 93.3711, 'loss': 0.154, 'load_time': 38.5945, 'process_time': 61.4055}
2020-09-07 21:49:19,825 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 100 /  469]: {'prec1': 93.7363, 'loss': 0.1475, 'load_time': 38.7549, 'process_time': 61.2451}
2020-09-07 21:49:25,542 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 150 /  469]: {'prec1': 93.6185, 'loss': 0.1506, 'load_time': 39.2985, 'process_time': 60.7015}
2020-09-07 21:49:31,265 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 200 /  469]: {'prec1': 93.4893, 'loss': 0.1537, 'load_time': 40.2248, 'process_time': 59.7752}
2020-09-07 21:49:37,120 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 250 /  469]: {'prec1': 93.4172, 'loss': 0.1556, 'load_time': 41.2426, 'process_time': 58.7574}
2020-09-07 21:49:42,923 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 300 /  469]: {'prec1': 93.3737, 'loss': 0.1555, 'load_time': 41.5919, 'process_time': 58.4081}
2020-09-07 21:49:48,693 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 350 /  469]: {'prec1': 93.3064, 'loss': 0.1573, 'load_time': 41.7872, 'process_time': 58.2128}
2020-09-07 21:49:54,490 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 400 /  469]: {'prec1': 93.3286, 'loss': 0.1574, 'load_time': 42.0548, 'process_time': 57.9452}
2020-09-07 21:50:00,397 - algorithms.Algorithm - INFO   - ==> Iteration [ 14][ 450 /  469]: {'prec1': 93.3381, 'loss': 0.1563, 'load_time': 42.6071, 'process_time': 57.3929}
2020-09-07 21:50:02,613 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.362, 'loss': 0.1561, 'load_time': 42.7055, 'process_time': 57.2945}
2020-09-07 21:50:02,699 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:50:02,700 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:50:09,537 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.3692, 'loss': 0.2097, 'load_time': 2.536, 'process_time': 97.464}
2020-09-07 21:50:09,538 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.3692, 'loss': 0.2097, 'load_time': 2.536, 'process_time': 97.464}
2020-09-07 21:50:09,538 - algorithms.Algorithm - INFO   - Training epoch [ 15 / 200]
2020-09-07 21:50:09,538 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:50:09,538 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:50:15,179 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][  50 /  469]: {'prec1': 93.0586, 'loss': 0.1602, 'load_time': 36.762, 'process_time': 63.238}
2020-09-07 21:50:20,900 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 100 /  469]: {'prec1': 93.3027, 'loss': 0.1571, 'load_time': 38.4505, 'process_time': 61.5495}
2020-09-07 21:50:26,560 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 150 /  469]: {'prec1': 93.3633, 'loss': 0.157, 'load_time': 39.435, 'process_time': 60.565}
2020-09-07 21:50:32,243 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 200 /  469]: {'prec1': 93.4932, 'loss': 0.1541, 'load_time': 39.848, 'process_time': 60.152}
2020-09-07 21:50:38,000 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 250 /  469]: {'prec1': 93.5148, 'loss': 0.1543, 'load_time': 40.4041, 'process_time': 59.5959}
2020-09-07 21:50:43,838 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 300 /  469]: {'prec1': 93.5182, 'loss': 0.1545, 'load_time': 41.4095, 'process_time': 58.5905}
2020-09-07 21:50:49,515 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 350 /  469]: {'prec1': 93.4715, 'loss': 0.1558, 'load_time': 41.1871, 'process_time': 58.8129}
2020-09-07 21:50:55,353 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 400 /  469]: {'prec1': 93.4683, 'loss': 0.1565, 'load_time': 41.4347, 'process_time': 58.5653}
2020-09-07 21:51:01,064 - algorithms.Algorithm - INFO   - ==> Iteration [ 15][ 450 /  469]: {'prec1': 93.5356, 'loss': 0.1554, 'load_time': 41.7988, 'process_time': 58.2012}
2020-09-07 21:51:03,271 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.5051, 'loss': 0.1559, 'load_time': 41.8564, 'process_time': 58.1436}
2020-09-07 21:51:03,354 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:51:03,354 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:51:10,189 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.2518, 'loss': 0.1862, 'load_time': 2.5536, 'process_time': 97.4464}
2020-09-07 21:51:10,189 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.2518, 'loss': 0.1862, 'load_time': 2.5536, 'process_time': 97.4464}
2020-09-07 21:51:10,189 - algorithms.Algorithm - INFO   - Training epoch [ 16 / 200]
2020-09-07 21:51:10,189 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:51:10,189 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:51:15,865 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][  50 /  469]: {'prec1': 93.8984, 'loss': 0.1429, 'load_time': 38.1746, 'process_time': 61.8254}
2020-09-07 21:51:21,585 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 100 /  469]: {'prec1': 93.6133, 'loss': 0.1508, 'load_time': 39.8167, 'process_time': 60.1833}
2020-09-07 21:51:27,257 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 150 /  469]: {'prec1': 93.5052, 'loss': 0.1539, 'load_time': 39.6778, 'process_time': 60.3222}
2020-09-07 21:51:33,003 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 200 /  469]: {'prec1': 93.499, 'loss': 0.1545, 'load_time': 40.7513, 'process_time': 59.2487}
2020-09-07 21:51:38,752 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 250 /  469]: {'prec1': 93.5102, 'loss': 0.1543, 'load_time': 41.0107, 'process_time': 58.9893}
2020-09-07 21:51:44,465 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 300 /  469]: {'prec1': 93.502, 'loss': 0.1549, 'load_time': 41.3775, 'process_time': 58.6225}
2020-09-07 21:51:50,237 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 350 /  469]: {'prec1': 93.5, 'loss': 0.1546, 'load_time': 41.3953, 'process_time': 58.6047}
2020-09-07 21:51:56,120 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 400 /  469]: {'prec1': 93.4678, 'loss': 0.1558, 'load_time': 41.9852, 'process_time': 58.0148}
2020-09-07 21:52:01,865 - algorithms.Algorithm - INFO   - ==> Iteration [ 16][ 450 /  469]: {'prec1': 93.4913, 'loss': 0.1553, 'load_time': 42.3969, 'process_time': 57.6031}
2020-09-07 21:52:04,095 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.4772, 'loss': 0.1552, 'load_time': 42.5322, 'process_time': 57.4678}
2020-09-07 21:52:04,173 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:52:04,173 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:52:10,934 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4681, 'loss': 0.2084, 'load_time': 2.6328, 'process_time': 97.3672}
2020-09-07 21:52:10,935 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4681, 'loss': 0.2084, 'load_time': 2.6328, 'process_time': 97.3672}
2020-09-07 21:52:10,935 - algorithms.Algorithm - INFO   - Training epoch [ 17 / 200]
2020-09-07 21:52:10,935 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:52:10,935 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:52:16,661 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][  50 /  469]: {'prec1': 93.7266, 'loss': 0.1484, 'load_time': 39.5424, 'process_time': 60.4576}
2020-09-07 21:52:22,308 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 100 /  469]: {'prec1': 93.6172, 'loss': 0.1514, 'load_time': 39.522, 'process_time': 60.478}
2020-09-07 21:52:27,946 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 150 /  469]: {'prec1': 93.6484, 'loss': 0.1517, 'load_time': 38.9875, 'process_time': 61.0125}
2020-09-07 21:52:33,691 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 200 /  469]: {'prec1': 93.6006, 'loss': 0.1528, 'load_time': 39.6395, 'process_time': 60.3605}
2020-09-07 21:52:39,399 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 250 /  469]: {'prec1': 93.7352, 'loss': 0.1498, 'load_time': 40.0915, 'process_time': 59.9085}
2020-09-07 21:52:45,164 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 300 /  469]: {'prec1': 93.6934, 'loss': 0.1503, 'load_time': 40.3738, 'process_time': 59.6262}
2020-09-07 21:52:50,971 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 350 /  469]: {'prec1': 93.6295, 'loss': 0.1515, 'load_time': 41.0535, 'process_time': 58.9465}
2020-09-07 21:52:56,667 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 400 /  469]: {'prec1': 93.5576, 'loss': 0.1528, 'load_time': 40.9988, 'process_time': 59.0012}
2020-09-07 21:53:02,415 - algorithms.Algorithm - INFO   - ==> Iteration [ 17][ 450 /  469]: {'prec1': 93.5564, 'loss': 0.1531, 'load_time': 41.0023, 'process_time': 58.9977}
2020-09-07 21:53:04,624 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.5455, 'loss': 0.1534, 'load_time': 41.1665, 'process_time': 58.8335}
2020-09-07 21:53:04,708 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:53:04,708 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:53:11,489 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.3197, 'loss': 0.2019, 'load_time': 2.6365, 'process_time': 97.3635}
2020-09-07 21:53:11,489 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.3197, 'loss': 0.2019, 'load_time': 2.6365, 'process_time': 97.3635}
2020-09-07 21:53:11,489 - algorithms.Algorithm - INFO   - Training epoch [ 18 / 200]
2020-09-07 21:53:11,489 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:53:11,489 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:53:17,337 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][  50 /  469]: {'prec1': 93.5, 'loss': 0.1543, 'load_time': 41.2641, 'process_time': 58.7359}
2020-09-07 21:53:23,011 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 100 /  469]: {'prec1': 93.709, 'loss': 0.1503, 'load_time': 40.4911, 'process_time': 59.5089}
2020-09-07 21:53:28,682 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 150 /  469]: {'prec1': 93.5273, 'loss': 0.1548, 'load_time': 40.1942, 'process_time': 59.8058}
2020-09-07 21:53:34,459 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 200 /  469]: {'prec1': 93.5684, 'loss': 0.1537, 'load_time': 41.0767, 'process_time': 58.9233}
2020-09-07 21:53:40,208 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 250 /  469]: {'prec1': 93.5609, 'loss': 0.1541, 'load_time': 41.1471, 'process_time': 58.8529}
2020-09-07 21:53:45,974 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 300 /  469]: {'prec1': 93.5234, 'loss': 0.1542, 'load_time': 41.6342, 'process_time': 58.3658}
2020-09-07 21:53:51,748 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 350 /  469]: {'prec1': 93.4827, 'loss': 0.1551, 'load_time': 41.9658, 'process_time': 58.0342}
2020-09-07 21:53:57,516 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 400 /  469]: {'prec1': 93.4829, 'loss': 0.1555, 'load_time': 42.0167, 'process_time': 57.9833}
2020-09-07 21:54:03,361 - algorithms.Algorithm - INFO   - ==> Iteration [ 18][ 450 /  469]: {'prec1': 93.4939, 'loss': 0.1547, 'load_time': 42.342, 'process_time': 57.658}
2020-09-07 21:54:05,571 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.4838, 'loss': 0.1547, 'load_time': 42.4642, 'process_time': 57.5358}
2020-09-07 21:54:05,654 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:54:05,655 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:54:12,381 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9489, 'loss': 0.2277, 'load_time': 2.6414, 'process_time': 97.3586}
2020-09-07 21:54:12,381 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9489, 'loss': 0.2277, 'load_time': 2.6414, 'process_time': 97.3586}
2020-09-07 21:54:12,381 - algorithms.Algorithm - INFO   - Training epoch [ 19 / 200]
2020-09-07 21:54:12,381 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:54:12,381 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:54:18,067 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][  50 /  469]: {'prec1': 93.7773, 'loss': 0.1471, 'load_time': 36.4351, 'process_time': 63.5649}
2020-09-07 21:54:23,769 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 100 /  469]: {'prec1': 93.7969, 'loss': 0.1471, 'load_time': 38.075, 'process_time': 61.925}
2020-09-07 21:54:29,471 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 150 /  469]: {'prec1': 93.5247, 'loss': 0.1522, 'load_time': 39.4494, 'process_time': 60.5506}
2020-09-07 21:54:35,268 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 200 /  469]: {'prec1': 93.3877, 'loss': 0.1558, 'load_time': 40.8939, 'process_time': 59.1061}
2020-09-07 21:54:41,084 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 250 /  469]: {'prec1': 93.418, 'loss': 0.1552, 'load_time': 41.4382, 'process_time': 58.5618}
2020-09-07 21:54:46,902 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 300 /  469]: {'prec1': 93.4824, 'loss': 0.1544, 'load_time': 41.6636, 'process_time': 58.3364}
2020-09-07 21:54:52,604 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 350 /  469]: {'prec1': 93.5067, 'loss': 0.154, 'load_time': 41.7754, 'process_time': 58.2246}
2020-09-07 21:54:58,337 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 400 /  469]: {'prec1': 93.4604, 'loss': 0.1545, 'load_time': 41.9125, 'process_time': 58.0875}
2020-09-07 21:55:04,177 - algorithms.Algorithm - INFO   - ==> Iteration [ 19][ 450 /  469]: {'prec1': 93.467, 'loss': 0.1539, 'load_time': 42.0374, 'process_time': 57.9626}
2020-09-07 21:55:06,381 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.4889, 'loss': 0.1535, 'load_time': 42.1344, 'process_time': 57.8656}
2020-09-07 21:55:06,462 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:55:06,463 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:55:13,199 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.0588, 'loss': 0.2386, 'load_time': 2.6427, 'process_time': 97.3573}
2020-09-07 21:55:13,200 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.0588, 'loss': 0.2386, 'load_time': 2.6427, 'process_time': 97.3573}
2020-09-07 21:55:13,200 - algorithms.Algorithm - INFO   - Training epoch [ 20 / 200]
2020-09-07 21:55:13,200 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:55:13,200 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:55:18,848 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][  50 /  469]: {'prec1': 93.8281, 'loss': 0.1449, 'load_time': 37.6744, 'process_time': 62.3256}
2020-09-07 21:55:24,515 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 100 /  469]: {'prec1': 93.8027, 'loss': 0.1459, 'load_time': 39.8331, 'process_time': 60.1669}
2020-09-07 21:55:30,216 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 150 /  469]: {'prec1': 93.7539, 'loss': 0.1488, 'load_time': 40.4281, 'process_time': 59.5719}
2020-09-07 21:55:36,015 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 200 /  469]: {'prec1': 93.7393, 'loss': 0.1494, 'load_time': 41.065, 'process_time': 58.935}
2020-09-07 21:55:41,800 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 250 /  469]: {'prec1': 93.6664, 'loss': 0.1509, 'load_time': 41.8323, 'process_time': 58.1677}
2020-09-07 21:55:47,612 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 300 /  469]: {'prec1': 93.6471, 'loss': 0.1512, 'load_time': 42.1469, 'process_time': 57.8531}
2020-09-07 21:55:53,384 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 350 /  469]: {'prec1': 93.6323, 'loss': 0.1513, 'load_time': 42.415, 'process_time': 57.585}
2020-09-07 21:55:59,149 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 400 /  469]: {'prec1': 93.5791, 'loss': 0.1519, 'load_time': 42.647, 'process_time': 57.353}
2020-09-07 21:56:04,937 - algorithms.Algorithm - INFO   - ==> Iteration [ 20][ 450 /  469]: {'prec1': 93.5469, 'loss': 0.1523, 'load_time': 42.628, 'process_time': 57.372}
2020-09-07 21:56:07,145 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.5763, 'loss': 0.1516, 'load_time': 42.8166, 'process_time': 57.1834}
2020-09-07 21:56:07,225 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:56:07,226 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:56:13,941 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.8895, 'loss': 0.2161, 'load_time': 2.6792, 'process_time': 97.3208}
2020-09-07 21:56:13,941 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.8895, 'loss': 0.2161, 'load_time': 2.6792, 'process_time': 97.3208}
2020-09-07 21:56:13,941 - algorithms.Algorithm - INFO   - Training epoch [ 21 / 200]
2020-09-07 21:56:13,941 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:56:13,941 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:56:19,585 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][  50 /  469]: {'prec1': 93.6953, 'loss': 0.148, 'load_time': 38.865, 'process_time': 61.135}
2020-09-07 21:56:25,282 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 100 /  469]: {'prec1': 93.6641, 'loss': 0.1494, 'load_time': 40.4173, 'process_time': 59.5827}
2020-09-07 21:56:30,905 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 150 /  469]: {'prec1': 93.5677, 'loss': 0.151, 'load_time': 40.5721, 'process_time': 59.4279}
2020-09-07 21:56:36,689 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 200 /  469]: {'prec1': 93.5713, 'loss': 0.1526, 'load_time': 41.2445, 'process_time': 58.7555}
2020-09-07 21:56:42,475 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 250 /  469]: {'prec1': 93.6047, 'loss': 0.1521, 'load_time': 41.993, 'process_time': 58.007}
2020-09-07 21:56:48,185 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 300 /  469]: {'prec1': 93.6159, 'loss': 0.1514, 'load_time': 42.3484, 'process_time': 57.6516}
2020-09-07 21:56:54,029 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 350 /  469]: {'prec1': 93.591, 'loss': 0.1523, 'load_time': 42.797, 'process_time': 57.203}
2020-09-07 21:56:59,827 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 400 /  469]: {'prec1': 93.605, 'loss': 0.1518, 'load_time': 42.8612, 'process_time': 57.1388}
2020-09-07 21:57:05,547 - algorithms.Algorithm - INFO   - ==> Iteration [ 21][ 450 /  469]: {'prec1': 93.6233, 'loss': 0.1516, 'load_time': 43.1358, 'process_time': 56.8642}
2020-09-07 21:57:07,733 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6245, 'loss': 0.1516, 'load_time': 43.1004, 'process_time': 56.8996}
2020-09-07 21:57:07,814 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:57:07,814 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:57:14,579 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.201, 'loss': 0.2022, 'load_time': 2.7145, 'process_time': 97.2855}
2020-09-07 21:57:14,579 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.201, 'loss': 0.2022, 'load_time': 2.7145, 'process_time': 97.2855}
2020-09-07 21:57:14,579 - algorithms.Algorithm - INFO   - Training epoch [ 22 / 200]
2020-09-07 21:57:14,580 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:57:14,580 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:57:20,265 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][  50 /  469]: {'prec1': 93.3984, 'loss': 0.1531, 'load_time': 37.5488, 'process_time': 62.4512}
2020-09-07 21:57:25,982 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 100 /  469]: {'prec1': 93.6953, 'loss': 0.1502, 'load_time': 38.9512, 'process_time': 61.0488}
2020-09-07 21:57:31,710 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 150 /  469]: {'prec1': 93.6549, 'loss': 0.1522, 'load_time': 40.0133, 'process_time': 59.9867}
2020-09-07 21:57:37,380 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 200 /  469]: {'prec1': 93.6572, 'loss': 0.1531, 'load_time': 40.7755, 'process_time': 59.2245}
2020-09-07 21:57:43,263 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 250 /  469]: {'prec1': 93.6305, 'loss': 0.1531, 'load_time': 41.6315, 'process_time': 58.3685}
2020-09-07 21:57:49,016 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 300 /  469]: {'prec1': 93.7031, 'loss': 0.1516, 'load_time': 42.0892, 'process_time': 57.9108}
2020-09-07 21:57:54,754 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 350 /  469]: {'prec1': 93.6741, 'loss': 0.1521, 'load_time': 42.3024, 'process_time': 57.6976}
2020-09-07 21:58:00,600 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 400 /  469]: {'prec1': 93.6123, 'loss': 0.1533, 'load_time': 43.0274, 'process_time': 56.9726}
2020-09-07 21:58:06,378 - algorithms.Algorithm - INFO   - ==> Iteration [ 22][ 450 /  469]: {'prec1': 93.6688, 'loss': 0.152, 'load_time': 43.1183, 'process_time': 56.8817}
2020-09-07 21:58:08,579 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.682, 'loss': 0.152, 'load_time': 43.2128, 'process_time': 56.7872}
2020-09-07 21:58:08,660 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:58:08,661 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:58:15,418 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.8957, 'loss': 0.2553, 'load_time': 2.6854, 'process_time': 97.3146}
2020-09-07 21:58:15,418 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.8957, 'loss': 0.2553, 'load_time': 2.6854, 'process_time': 97.3146}
2020-09-07 21:58:15,418 - algorithms.Algorithm - INFO   - Training epoch [ 23 / 200]
2020-09-07 21:58:15,418 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:58:15,418 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:58:21,082 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][  50 /  469]: {'prec1': 93.9023, 'loss': 0.1441, 'load_time': 39.7798, 'process_time': 60.2202}
2020-09-07 21:58:26,684 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 100 /  469]: {'prec1': 93.7285, 'loss': 0.1485, 'load_time': 40.631, 'process_time': 59.369}
2020-09-07 21:58:32,452 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 150 /  469]: {'prec1': 93.6419, 'loss': 0.1495, 'load_time': 41.384, 'process_time': 58.616}
2020-09-07 21:58:38,205 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 200 /  469]: {'prec1': 93.6475, 'loss': 0.1498, 'load_time': 41.4739, 'process_time': 58.5261}
2020-09-07 21:58:43,899 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 250 /  469]: {'prec1': 93.5727, 'loss': 0.1507, 'load_time': 41.7025, 'process_time': 58.2975}
2020-09-07 21:58:49,680 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 300 /  469]: {'prec1': 93.64, 'loss': 0.1501, 'load_time': 41.8246, 'process_time': 58.1754}
2020-09-07 21:58:55,395 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 350 /  469]: {'prec1': 93.6138, 'loss': 0.1509, 'load_time': 42.0133, 'process_time': 57.9867}
2020-09-07 21:59:01,168 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 400 /  469]: {'prec1': 93.6699, 'loss': 0.1495, 'load_time': 42.071, 'process_time': 57.929}
2020-09-07 21:59:07,015 - algorithms.Algorithm - INFO   - ==> Iteration [ 23][ 450 /  469]: {'prec1': 93.6814, 'loss': 0.1495, 'load_time': 42.3047, 'process_time': 57.6953}
2020-09-07 21:59:09,249 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6836, 'loss': 0.1497, 'load_time': 42.2342, 'process_time': 57.7658}
2020-09-07 21:59:09,330 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 21:59:09,331 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 21:59:16,113 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.5348, 'loss': 0.2029, 'load_time': 2.6777, 'process_time': 97.3223}
2020-09-07 21:59:16,113 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.5348, 'loss': 0.2029, 'load_time': 2.6777, 'process_time': 97.3223}
2020-09-07 21:59:16,113 - algorithms.Algorithm - INFO   - Training epoch [ 24 / 200]
2020-09-07 21:59:16,113 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 21:59:16,113 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 21:59:21,875 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][  50 /  469]: {'prec1': 93.8008, 'loss': 0.1507, 'load_time': 39.6064, 'process_time': 60.3936}
2020-09-07 21:59:27,592 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 100 /  469]: {'prec1': 93.7793, 'loss': 0.1495, 'load_time': 40.6061, 'process_time': 59.3939}
2020-09-07 21:59:33,219 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 150 /  469]: {'prec1': 93.5703, 'loss': 0.1524, 'load_time': 40.9824, 'process_time': 59.0176}
2020-09-07 21:59:39,045 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 200 /  469]: {'prec1': 93.5898, 'loss': 0.1506, 'load_time': 41.934, 'process_time': 58.066}
2020-09-07 21:59:44,813 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 250 /  469]: {'prec1': 93.557, 'loss': 0.152, 'load_time': 41.9827, 'process_time': 58.0173}
2020-09-07 21:59:50,579 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 300 /  469]: {'prec1': 93.61, 'loss': 0.1508, 'load_time': 42.5617, 'process_time': 57.4383}
2020-09-07 21:59:56,328 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 350 /  469]: {'prec1': 93.6205, 'loss': 0.1504, 'load_time': 42.5955, 'process_time': 57.4045}
2020-09-07 22:00:02,011 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 400 /  469]: {'prec1': 93.6582, 'loss': 0.1497, 'load_time': 42.4181, 'process_time': 57.5819}
2020-09-07 22:00:07,806 - algorithms.Algorithm - INFO   - ==> Iteration [ 24][ 450 /  469]: {'prec1': 93.6619, 'loss': 0.1499, 'load_time': 42.8238, 'process_time': 57.1762}
2020-09-07 22:00:10,029 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.656, 'loss': 0.1499, 'load_time': 43.1144, 'process_time': 56.8856}
2020-09-07 22:00:10,111 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:00:10,111 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:00:16,805 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.3605, 'loss': 0.22, 'load_time': 2.6524, 'process_time': 97.3476}
2020-09-07 22:00:16,805 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.3605, 'loss': 0.22, 'load_time': 2.6524, 'process_time': 97.3476}
2020-09-07 22:00:16,805 - algorithms.Algorithm - INFO   - Training epoch [ 25 / 200]
2020-09-07 22:00:16,805 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:00:16,805 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:00:22,468 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][  50 /  469]: {'prec1': 93.6758, 'loss': 0.1537, 'load_time': 40.1753, 'process_time': 59.8247}
2020-09-07 22:00:28,193 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 100 /  469]: {'prec1': 93.8359, 'loss': 0.1478, 'load_time': 40.8666, 'process_time': 59.1334}
2020-09-07 22:00:33,887 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 150 /  469]: {'prec1': 93.7852, 'loss': 0.1476, 'load_time': 41.2701, 'process_time': 58.7299}
2020-09-07 22:00:39,586 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 200 /  469]: {'prec1': 93.7041, 'loss': 0.15, 'load_time': 41.6331, 'process_time': 58.3669}
2020-09-07 22:00:45,344 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 250 /  469]: {'prec1': 93.6359, 'loss': 0.1529, 'load_time': 42.2661, 'process_time': 57.7339}
2020-09-07 22:00:51,147 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 300 /  469]: {'prec1': 93.6439, 'loss': 0.1526, 'load_time': 42.6709, 'process_time': 57.3291}
2020-09-07 22:00:56,935 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 350 /  469]: {'prec1': 93.6557, 'loss': 0.1517, 'load_time': 43.1009, 'process_time': 56.8991}
2020-09-07 22:01:02,723 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 400 /  469]: {'prec1': 93.6489, 'loss': 0.1518, 'load_time': 43.0139, 'process_time': 56.9861}
2020-09-07 22:01:08,552 - algorithms.Algorithm - INFO   - ==> Iteration [ 25][ 450 /  469]: {'prec1': 93.6649, 'loss': 0.1516, 'load_time': 42.8742, 'process_time': 57.1258}
2020-09-07 22:01:10,716 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6692, 'loss': 0.1515, 'load_time': 42.8395, 'process_time': 57.1605}
2020-09-07 22:01:10,795 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:01:10,796 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:01:17,507 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.8846, 'loss': 0.2159, 'load_time': 2.6878, 'process_time': 97.3122}
2020-09-07 22:01:17,508 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.8846, 'loss': 0.2159, 'load_time': 2.6878, 'process_time': 97.3122}
2020-09-07 22:01:17,508 - algorithms.Algorithm - INFO   - Training epoch [ 26 / 200]
2020-09-07 22:01:17,508 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:01:17,508 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:01:23,242 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][  50 /  469]: {'prec1': 94.1133, 'loss': 0.1402, 'load_time': 38.8529, 'process_time': 61.1471}
2020-09-07 22:01:28,951 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 100 /  469]: {'prec1': 94.0625, 'loss': 0.1405, 'load_time': 39.7174, 'process_time': 60.2826}
2020-09-07 22:01:34,702 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 150 /  469]: {'prec1': 93.9336, 'loss': 0.1424, 'load_time': 41.1066, 'process_time': 58.8934}
2020-09-07 22:01:40,485 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 200 /  469]: {'prec1': 93.6797, 'loss': 0.1473, 'load_time': 41.4537, 'process_time': 58.5463}
2020-09-07 22:01:46,213 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 250 /  469]: {'prec1': 93.6859, 'loss': 0.1481, 'load_time': 41.3992, 'process_time': 58.6008}
2020-09-07 22:01:51,960 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 300 /  469]: {'prec1': 93.5918, 'loss': 0.1493, 'load_time': 41.401, 'process_time': 58.599}
2020-09-07 22:01:57,738 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 350 /  469]: {'prec1': 93.6133, 'loss': 0.1497, 'load_time': 41.5121, 'process_time': 58.4879}
2020-09-07 22:02:03,626 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 400 /  469]: {'prec1': 93.6196, 'loss': 0.1493, 'load_time': 42.0024, 'process_time': 57.9976}
2020-09-07 22:02:09,346 - algorithms.Algorithm - INFO   - ==> Iteration [ 26][ 450 /  469]: {'prec1': 93.6068, 'loss': 0.1499, 'load_time': 42.2042, 'process_time': 57.7958}
2020-09-07 22:02:11,549 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.612, 'loss': 0.1497, 'load_time': 42.2613, 'process_time': 57.7387}
2020-09-07 22:02:11,632 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:02:11,632 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:02:18,301 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.6955, 'loss': 0.1958, 'load_time': 2.6425, 'process_time': 97.3575}
2020-09-07 22:02:18,301 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.6955, 'loss': 0.1958, 'load_time': 2.6425, 'process_time': 97.3575}
2020-09-07 22:02:18,301 - algorithms.Algorithm - INFO   - Training epoch [ 27 / 200]
2020-09-07 22:02:18,301 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:02:18,301 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:02:23,920 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][  50 /  469]: {'prec1': 93.918, 'loss': 0.1439, 'load_time': 37.5897, 'process_time': 62.4103}
2020-09-07 22:02:29,513 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 100 /  469]: {'prec1': 93.8105, 'loss': 0.1467, 'load_time': 38.9499, 'process_time': 61.0501}
2020-09-07 22:02:35,158 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 150 /  469]: {'prec1': 93.6758, 'loss': 0.1486, 'load_time': 38.8351, 'process_time': 61.1649}
2020-09-07 22:02:41,058 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 200 /  469]: {'prec1': 93.7627, 'loss': 0.1465, 'load_time': 40.6593, 'process_time': 59.3407}
2020-09-07 22:02:46,770 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 250 /  469]: {'prec1': 93.6711, 'loss': 0.1482, 'load_time': 41.3045, 'process_time': 58.6955}
2020-09-07 22:02:52,562 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 300 /  469]: {'prec1': 93.6204, 'loss': 0.1502, 'load_time': 41.9455, 'process_time': 58.0545}
2020-09-07 22:02:58,332 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 350 /  469]: {'prec1': 93.6546, 'loss': 0.1497, 'load_time': 42.0759, 'process_time': 57.9241}
2020-09-07 22:03:04,106 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 400 /  469]: {'prec1': 93.7192, 'loss': 0.1483, 'load_time': 42.2278, 'process_time': 57.7722}
2020-09-07 22:03:09,950 - algorithms.Algorithm - INFO   - ==> Iteration [ 27][ 450 /  469]: {'prec1': 93.6766, 'loss': 0.1495, 'load_time': 42.6695, 'process_time': 57.3305}
2020-09-07 22:03:12,125 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6637, 'loss': 0.1501, 'load_time': 42.689, 'process_time': 57.311}
2020-09-07 22:03:12,207 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:03:12,207 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:03:18,904 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.1554, 'loss': 0.1901, 'load_time': 2.59, 'process_time': 97.41}
2020-09-07 22:03:18,904 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.1554, 'loss': 0.1901, 'load_time': 2.59, 'process_time': 97.41}
2020-09-07 22:03:18,904 - algorithms.Algorithm - INFO   - Training epoch [ 28 / 200]
2020-09-07 22:03:18,905 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:03:18,905 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:03:24,600 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][  50 /  469]: {'prec1': 93.8359, 'loss': 0.1447, 'load_time': 40.0954, 'process_time': 59.9046}
2020-09-07 22:03:30,292 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 100 /  469]: {'prec1': 93.6133, 'loss': 0.1473, 'load_time': 40.9527, 'process_time': 59.0473}
2020-09-07 22:03:35,960 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 150 /  469]: {'prec1': 93.4909, 'loss': 0.1502, 'load_time': 40.9451, 'process_time': 59.0549}
2020-09-07 22:03:41,766 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 200 /  469]: {'prec1': 93.5596, 'loss': 0.15, 'load_time': 41.2417, 'process_time': 58.7583}
2020-09-07 22:03:47,479 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 250 /  469]: {'prec1': 93.6273, 'loss': 0.149, 'load_time': 41.62, 'process_time': 58.38}
2020-09-07 22:03:53,244 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 300 /  469]: {'prec1': 93.638, 'loss': 0.1494, 'load_time': 41.992, 'process_time': 58.008}
2020-09-07 22:03:59,066 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 350 /  469]: {'prec1': 93.6602, 'loss': 0.1489, 'load_time': 42.2511, 'process_time': 57.7489}
2020-09-07 22:04:04,834 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 400 /  469]: {'prec1': 93.6436, 'loss': 0.1491, 'load_time': 42.4968, 'process_time': 57.5032}
2020-09-07 22:04:10,558 - algorithms.Algorithm - INFO   - ==> Iteration [ 28][ 450 /  469]: {'prec1': 93.6363, 'loss': 0.1494, 'load_time': 42.3396, 'process_time': 57.6604}
2020-09-07 22:04:12,761 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6553, 'loss': 0.1494, 'load_time': 42.6002, 'process_time': 57.3998}
2020-09-07 22:04:12,843 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:04:12,843 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:04:19,606 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.7647, 'loss': 0.208, 'load_time': 2.588, 'process_time': 97.412}
2020-09-07 22:04:19,606 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.7647, 'loss': 0.208, 'load_time': 2.588, 'process_time': 97.412}
2020-09-07 22:04:19,606 - algorithms.Algorithm - INFO   - Training epoch [ 29 / 200]
2020-09-07 22:04:19,606 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:04:19,606 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:04:25,283 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][  50 /  469]: {'prec1': 93.9922, 'loss': 0.1452, 'load_time': 39.5763, 'process_time': 60.4237}
2020-09-07 22:04:30,947 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 100 /  469]: {'prec1': 93.8711, 'loss': 0.1473, 'load_time': 38.9952, 'process_time': 61.0048}
2020-09-07 22:04:36,677 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 150 /  469]: {'prec1': 93.957, 'loss': 0.1439, 'load_time': 39.9785, 'process_time': 60.0215}
2020-09-07 22:04:42,452 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 200 /  469]: {'prec1': 93.8008, 'loss': 0.1462, 'load_time': 41.3938, 'process_time': 58.6062}
2020-09-07 22:04:48,221 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 250 /  469]: {'prec1': 93.7703, 'loss': 0.1467, 'load_time': 41.8065, 'process_time': 58.1935}
2020-09-07 22:04:53,998 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 300 /  469]: {'prec1': 93.7253, 'loss': 0.1478, 'load_time': 42.0353, 'process_time': 57.9647}
2020-09-07 22:04:59,879 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 350 /  469]: {'prec1': 93.7238, 'loss': 0.1484, 'load_time': 42.6487, 'process_time': 57.3513}
2020-09-07 22:05:05,663 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 400 /  469]: {'prec1': 93.7114, 'loss': 0.1494, 'load_time': 42.8934, 'process_time': 57.1066}
2020-09-07 22:05:11,417 - algorithms.Algorithm - INFO   - ==> Iteration [ 29][ 450 /  469]: {'prec1': 93.704, 'loss': 0.1491, 'load_time': 42.742, 'process_time': 57.258}
2020-09-07 22:05:13,604 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6846, 'loss': 0.1496, 'load_time': 42.7768, 'process_time': 57.2232}
2020-09-07 22:05:13,686 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:05:13,686 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:05:20,424 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.0886, 'loss': 0.1936, 'load_time': 2.6568, 'process_time': 97.3432}
2020-09-07 22:05:20,424 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.0886, 'loss': 0.1936, 'load_time': 2.6568, 'process_time': 97.3432}
2020-09-07 22:05:20,424 - algorithms.Algorithm - INFO   - Training epoch [ 30 / 200]
2020-09-07 22:05:20,424 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:05:20,424 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:05:26,120 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][  50 /  469]: {'prec1': 93.9805, 'loss': 0.1421, 'load_time': 38.5663, 'process_time': 61.4337}
2020-09-07 22:05:31,789 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 100 /  469]: {'prec1': 93.9355, 'loss': 0.1437, 'load_time': 39.6513, 'process_time': 60.3487}
2020-09-07 22:05:37,504 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 150 /  469]: {'prec1': 93.8307, 'loss': 0.1479, 'load_time': 40.2901, 'process_time': 59.7099}
2020-09-07 22:05:43,269 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 200 /  469]: {'prec1': 93.7744, 'loss': 0.1483, 'load_time': 41.2063, 'process_time': 58.7937}
2020-09-07 22:05:49,026 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 250 /  469]: {'prec1': 93.7461, 'loss': 0.1495, 'load_time': 41.7644, 'process_time': 58.2356}
2020-09-07 22:05:54,858 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 300 /  469]: {'prec1': 93.7259, 'loss': 0.1495, 'load_time': 42.2983, 'process_time': 57.7017}
2020-09-07 22:06:00,738 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 350 /  469]: {'prec1': 93.7188, 'loss': 0.1491, 'load_time': 42.8563, 'process_time': 57.1437}
2020-09-07 22:06:06,417 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 400 /  469]: {'prec1': 93.6523, 'loss': 0.1505, 'load_time': 42.5899, 'process_time': 57.4101}
2020-09-07 22:06:12,187 - algorithms.Algorithm - INFO   - ==> Iteration [ 30][ 450 /  469]: {'prec1': 93.6684, 'loss': 0.1503, 'load_time': 42.5434, 'process_time': 57.4566}
2020-09-07 22:06:14,402 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6775, 'loss': 0.1499, 'load_time': 42.6207, 'process_time': 57.3793}
2020-09-07 22:06:14,485 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:06:14,486 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:06:21,291 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.5855, 'loss': 0.189, 'load_time': 2.6285, 'process_time': 97.3715}
2020-09-07 22:06:21,292 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.5855, 'loss': 0.189, 'load_time': 2.6285, 'process_time': 97.3715}
2020-09-07 22:06:21,292 - algorithms.Algorithm - INFO   - Training epoch [ 31 / 200]
2020-09-07 22:06:21,292 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:06:21,292 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:06:26,969 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][  50 /  469]: {'prec1': 93.9453, 'loss': 0.1408, 'load_time': 36.9105, 'process_time': 63.0895}
2020-09-07 22:06:32,644 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 100 /  469]: {'prec1': 93.9707, 'loss': 0.143, 'load_time': 37.6517, 'process_time': 62.3483}
2020-09-07 22:06:38,298 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 150 /  469]: {'prec1': 93.9648, 'loss': 0.1436, 'load_time': 38.1336, 'process_time': 61.8664}
2020-09-07 22:06:44,048 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 200 /  469]: {'prec1': 93.9863, 'loss': 0.143, 'load_time': 39.3272, 'process_time': 60.6728}
2020-09-07 22:06:49,795 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 250 /  469]: {'prec1': 93.9211, 'loss': 0.1443, 'load_time': 39.6503, 'process_time': 60.3497}
2020-09-07 22:06:55,604 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 300 /  469]: {'prec1': 93.7975, 'loss': 0.1467, 'load_time': 40.5689, 'process_time': 59.4311}
2020-09-07 22:07:01,335 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 350 /  469]: {'prec1': 93.7846, 'loss': 0.1467, 'load_time': 40.6363, 'process_time': 59.3637}
2020-09-07 22:07:07,065 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 400 /  469]: {'prec1': 93.8242, 'loss': 0.1465, 'load_time': 40.7679, 'process_time': 59.2321}
2020-09-07 22:07:12,867 - algorithms.Algorithm - INFO   - ==> Iteration [ 31][ 450 /  469]: {'prec1': 93.7678, 'loss': 0.1476, 'load_time': 40.9475, 'process_time': 59.0525}
2020-09-07 22:07:15,044 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7267, 'loss': 0.1483, 'load_time': 41.1357, 'process_time': 58.8643}
2020-09-07 22:07:15,124 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:07:15,125 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:07:21,810 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.8426, 'loss': 0.2164, 'load_time': 2.5849, 'process_time': 97.4151}
2020-09-07 22:07:21,810 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.8426, 'loss': 0.2164, 'load_time': 2.5849, 'process_time': 97.4151}
2020-09-07 22:07:21,810 - algorithms.Algorithm - INFO   - Training epoch [ 32 / 200]
2020-09-07 22:07:21,810 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:07:21,810 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:07:27,450 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][  50 /  469]: {'prec1': 93.4805, 'loss': 0.1527, 'load_time': 38.3177, 'process_time': 61.6823}
2020-09-07 22:07:33,041 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 100 /  469]: {'prec1': 93.6484, 'loss': 0.1498, 'load_time': 38.101, 'process_time': 61.899}
2020-09-07 22:07:38,737 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 150 /  469]: {'prec1': 93.6523, 'loss': 0.149, 'load_time': 39.0002, 'process_time': 60.9998}
2020-09-07 22:07:44,409 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 200 /  469]: {'prec1': 93.6016, 'loss': 0.1504, 'load_time': 39.5295, 'process_time': 60.4705}
2020-09-07 22:07:50,194 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 250 /  469]: {'prec1': 93.6617, 'loss': 0.1489, 'load_time': 39.9995, 'process_time': 60.0005}
2020-09-07 22:07:55,893 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 300 /  469]: {'prec1': 93.6543, 'loss': 0.1491, 'load_time': 40.6602, 'process_time': 59.3398}
2020-09-07 22:08:01,657 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 350 /  469]: {'prec1': 93.7266, 'loss': 0.1477, 'load_time': 41.0226, 'process_time': 58.9774}
2020-09-07 22:08:07,459 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 400 /  469]: {'prec1': 93.6895, 'loss': 0.1491, 'load_time': 40.96, 'process_time': 59.04}
2020-09-07 22:08:13,250 - algorithms.Algorithm - INFO   - ==> Iteration [ 32][ 450 /  469]: {'prec1': 93.6849, 'loss': 0.1495, 'load_time': 41.2392, 'process_time': 58.7608}
2020-09-07 22:08:15,475 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.6927, 'loss': 0.1491, 'load_time': 41.4604, 'process_time': 58.5396}
2020-09-07 22:08:15,558 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:08:15,558 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:08:22,296 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9316, 'loss': 0.2066, 'load_time': 2.6258, 'process_time': 97.3742}
2020-09-07 22:08:22,296 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9316, 'loss': 0.2066, 'load_time': 2.6258, 'process_time': 97.3742}
2020-09-07 22:08:22,296 - algorithms.Algorithm - INFO   - Training epoch [ 33 / 200]
2020-09-07 22:08:22,296 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:08:22,296 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:08:27,992 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][  50 /  469]: {'prec1': 93.9219, 'loss': 0.1427, 'load_time': 37.878, 'process_time': 62.122}
2020-09-07 22:08:33,627 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 100 /  469]: {'prec1': 93.9824, 'loss': 0.1419, 'load_time': 39.4483, 'process_time': 60.5517}
2020-09-07 22:08:39,241 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 150 /  469]: {'prec1': 93.9258, 'loss': 0.143, 'load_time': 39.3418, 'process_time': 60.6582}
2020-09-07 22:08:44,984 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 200 /  469]: {'prec1': 93.9023, 'loss': 0.1438, 'load_time': 39.856, 'process_time': 60.144}
2020-09-07 22:08:50,798 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 250 /  469]: {'prec1': 93.8398, 'loss': 0.1461, 'load_time': 40.982, 'process_time': 59.018}
2020-09-07 22:08:56,516 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 300 /  469]: {'prec1': 93.8457, 'loss': 0.1459, 'load_time': 41.24, 'process_time': 58.76}
2020-09-07 22:09:02,390 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 350 /  469]: {'prec1': 93.8767, 'loss': 0.145, 'load_time': 41.7362, 'process_time': 58.2638}
2020-09-07 22:09:08,210 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 400 /  469]: {'prec1': 93.8096, 'loss': 0.1462, 'load_time': 42.1149, 'process_time': 57.8851}
2020-09-07 22:09:14,042 - algorithms.Algorithm - INFO   - ==> Iteration [ 33][ 450 /  469]: {'prec1': 93.7626, 'loss': 0.1476, 'load_time': 42.4258, 'process_time': 57.5742}
2020-09-07 22:09:16,244 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7526, 'loss': 0.1479, 'load_time': 42.6402, 'process_time': 57.3598}
2020-09-07 22:09:16,326 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:09:16,326 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:09:23,075 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4779, 'loss': 0.1996, 'load_time': 2.6989, 'process_time': 97.3011}
2020-09-07 22:09:23,076 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4779, 'loss': 0.1996, 'load_time': 2.6989, 'process_time': 97.3011}
2020-09-07 22:09:23,076 - algorithms.Algorithm - INFO   - Training epoch [ 34 / 200]
2020-09-07 22:09:23,076 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:09:23,076 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:09:28,715 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][  50 /  469]: {'prec1': 94.1523, 'loss': 0.1405, 'load_time': 38.3274, 'process_time': 61.6726}
2020-09-07 22:09:34,296 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 100 /  469]: {'prec1': 94.0996, 'loss': 0.1423, 'load_time': 37.5509, 'process_time': 62.4491}
2020-09-07 22:09:40,013 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 150 /  469]: {'prec1': 94.043, 'loss': 0.1431, 'load_time': 38.8516, 'process_time': 61.1484}
2020-09-07 22:09:45,720 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 200 /  469]: {'prec1': 93.9111, 'loss': 0.1454, 'load_time': 39.9516, 'process_time': 60.0484}
2020-09-07 22:09:51,521 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 250 /  469]: {'prec1': 93.9008, 'loss': 0.1465, 'load_time': 40.5947, 'process_time': 59.4053}
2020-09-07 22:09:57,294 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 300 /  469]: {'prec1': 93.8125, 'loss': 0.1481, 'load_time': 41.1267, 'process_time': 58.8733}
2020-09-07 22:10:03,091 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 350 /  469]: {'prec1': 93.7852, 'loss': 0.1485, 'load_time': 41.6995, 'process_time': 58.3005}
2020-09-07 22:10:08,892 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 400 /  469]: {'prec1': 93.7881, 'loss': 0.1485, 'load_time': 42.1349, 'process_time': 57.8651}
2020-09-07 22:10:14,768 - algorithms.Algorithm - INFO   - ==> Iteration [ 34][ 450 /  469]: {'prec1': 93.7569, 'loss': 0.1488, 'load_time': 42.6084, 'process_time': 57.3916}
2020-09-07 22:10:16,955 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7222, 'loss': 0.1494, 'load_time': 42.7025, 'process_time': 57.2975}
2020-09-07 22:10:17,033 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:10:17,033 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:10:23,812 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9464, 'loss': 0.2058, 'load_time': 2.633, 'process_time': 97.367}
2020-09-07 22:10:23,812 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9464, 'loss': 0.2058, 'load_time': 2.633, 'process_time': 97.367}
2020-09-07 22:10:23,812 - algorithms.Algorithm - INFO   - Training epoch [ 35 / 200]
2020-09-07 22:10:23,812 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:10:23,812 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:10:29,500 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][  50 /  469]: {'prec1': 94.3711, 'loss': 0.1357, 'load_time': 38.7434, 'process_time': 61.2566}
2020-09-07 22:10:35,166 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 100 /  469]: {'prec1': 94.3125, 'loss': 0.1373, 'load_time': 39.5562, 'process_time': 60.4438}
2020-09-07 22:10:40,826 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 150 /  469]: {'prec1': 94.0677, 'loss': 0.141, 'load_time': 41.1121, 'process_time': 58.8879}
2020-09-07 22:10:46,587 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 200 /  469]: {'prec1': 93.8643, 'loss': 0.1446, 'load_time': 41.6603, 'process_time': 58.3397}
2020-09-07 22:10:52,353 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 250 /  469]: {'prec1': 93.8773, 'loss': 0.1441, 'load_time': 41.723, 'process_time': 58.277}
2020-09-07 22:10:58,163 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 300 /  469]: {'prec1': 93.8014, 'loss': 0.1455, 'load_time': 42.3219, 'process_time': 57.6781}
2020-09-07 22:11:03,941 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 350 /  469]: {'prec1': 93.7444, 'loss': 0.1468, 'load_time': 42.3396, 'process_time': 57.6604}
2020-09-07 22:11:09,756 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 400 /  469]: {'prec1': 93.7358, 'loss': 0.1471, 'load_time': 42.5037, 'process_time': 57.4963}
2020-09-07 22:11:15,520 - algorithms.Algorithm - INFO   - ==> Iteration [ 35][ 450 /  469]: {'prec1': 93.674, 'loss': 0.1479, 'load_time': 42.5837, 'process_time': 57.4163}
2020-09-07 22:11:17,732 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.69, 'loss': 0.1478, 'load_time': 42.595, 'process_time': 57.405}
2020-09-07 22:11:17,809 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:11:17,810 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:11:24,520 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.2381, 'loss': 0.2161, 'load_time': 2.6466, 'process_time': 97.3534}
2020-09-07 22:11:24,520 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.2381, 'loss': 0.2161, 'load_time': 2.6466, 'process_time': 97.3534}
2020-09-07 22:11:24,520 - algorithms.Algorithm - INFO   - Training epoch [ 36 / 200]
2020-09-07 22:11:24,520 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:11:24,520 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:11:30,208 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][  50 /  469]: {'prec1': 93.8906, 'loss': 0.1468, 'load_time': 41.7005, 'process_time': 58.2995}
2020-09-07 22:11:35,887 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 100 /  469]: {'prec1': 93.7949, 'loss': 0.1456, 'load_time': 41.7945, 'process_time': 58.2055}
2020-09-07 22:11:41,655 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 150 /  469]: {'prec1': 93.8242, 'loss': 0.1462, 'load_time': 42.6162, 'process_time': 57.3838}
2020-09-07 22:11:47,350 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 200 /  469]: {'prec1': 93.8418, 'loss': 0.1459, 'load_time': 42.5198, 'process_time': 57.4802}
2020-09-07 22:11:53,075 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 250 /  469]: {'prec1': 93.7672, 'loss': 0.1474, 'load_time': 43.0081, 'process_time': 56.9919}
2020-09-07 22:11:58,866 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 300 /  469]: {'prec1': 93.7109, 'loss': 0.1488, 'load_time': 43.1208, 'process_time': 56.8792}
2020-09-07 22:12:04,680 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 350 /  469]: {'prec1': 93.7321, 'loss': 0.148, 'load_time': 43.2393, 'process_time': 56.7607}
2020-09-07 22:12:10,456 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 400 /  469]: {'prec1': 93.7515, 'loss': 0.148, 'load_time': 43.6014, 'process_time': 56.3986}
2020-09-07 22:12:16,279 - algorithms.Algorithm - INFO   - ==> Iteration [ 36][ 450 /  469]: {'prec1': 93.7365, 'loss': 0.148, 'load_time': 43.7115, 'process_time': 56.2885}
2020-09-07 22:12:18,491 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7425, 'loss': 0.1479, 'load_time': 43.8587, 'process_time': 56.1413}
2020-09-07 22:12:18,573 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:12:18,573 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:12:25,319 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.939, 'loss': 0.2245, 'load_time': 2.5878, 'process_time': 97.4122}
2020-09-07 22:12:25,319 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.939, 'loss': 0.2245, 'load_time': 2.5878, 'process_time': 97.4122}
2020-09-07 22:12:25,319 - algorithms.Algorithm - INFO   - Training epoch [ 37 / 200]
2020-09-07 22:12:25,319 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:12:25,320 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:12:30,890 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][  50 /  469]: {'prec1': 94.3398, 'loss': 0.1334, 'load_time': 34.279, 'process_time': 65.721}
2020-09-07 22:12:36,602 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 100 /  469]: {'prec1': 93.7695, 'loss': 0.1449, 'load_time': 39.2311, 'process_time': 60.7689}
2020-09-07 22:12:42,266 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 150 /  469]: {'prec1': 93.8346, 'loss': 0.1461, 'load_time': 39.6941, 'process_time': 60.3059}
2020-09-07 22:12:47,956 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 200 /  469]: {'prec1': 93.8027, 'loss': 0.1476, 'load_time': 40.6169, 'process_time': 59.3831}
2020-09-07 22:12:53,660 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 250 /  469]: {'prec1': 93.793, 'loss': 0.148, 'load_time': 41.4263, 'process_time': 58.5737}
2020-09-07 22:12:59,498 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 300 /  469]: {'prec1': 93.748, 'loss': 0.1487, 'load_time': 41.5985, 'process_time': 58.4015}
2020-09-07 22:13:05,232 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 350 /  469]: {'prec1': 93.7595, 'loss': 0.1487, 'load_time': 41.9859, 'process_time': 58.0141}
2020-09-07 22:13:11,018 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 400 /  469]: {'prec1': 93.7646, 'loss': 0.1485, 'load_time': 42.0913, 'process_time': 57.9087}
2020-09-07 22:13:16,788 - algorithms.Algorithm - INFO   - ==> Iteration [ 37][ 450 /  469]: {'prec1': 93.7947, 'loss': 0.1481, 'load_time': 42.5921, 'process_time': 57.4079}
2020-09-07 22:13:19,015 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7896, 'loss': 0.1479, 'load_time': 42.8235, 'process_time': 57.1765}
2020-09-07 22:13:19,094 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:13:19,094 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:13:25,817 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 89.6781, 'loss': 0.2512, 'load_time': 2.6172, 'process_time': 97.3828}
2020-09-07 22:13:25,817 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 89.6781, 'loss': 0.2512, 'load_time': 2.6172, 'process_time': 97.3828}
2020-09-07 22:13:25,817 - algorithms.Algorithm - INFO   - Training epoch [ 38 / 200]
2020-09-07 22:13:25,817 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:13:25,817 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:13:31,524 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][  50 /  469]: {'prec1': 93.625, 'loss': 0.1486, 'load_time': 41.3936, 'process_time': 58.6064}
2020-09-07 22:13:37,194 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 100 /  469]: {'prec1': 93.6973, 'loss': 0.1479, 'load_time': 41.9022, 'process_time': 58.0978}
2020-09-07 22:13:42,883 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 150 /  469]: {'prec1': 93.8346, 'loss': 0.1453, 'load_time': 42.1263, 'process_time': 57.8737}
2020-09-07 22:13:48,681 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 200 /  469]: {'prec1': 93.7568, 'loss': 0.1458, 'load_time': 42.6934, 'process_time': 57.3066}
2020-09-07 22:13:54,520 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 250 /  469]: {'prec1': 93.7289, 'loss': 0.1474, 'load_time': 43.4391, 'process_time': 56.5609}
2020-09-07 22:14:00,288 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 300 /  469]: {'prec1': 93.7487, 'loss': 0.1475, 'load_time': 43.2282, 'process_time': 56.7718}
2020-09-07 22:14:06,014 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 350 /  469]: {'prec1': 93.7288, 'loss': 0.1481, 'load_time': 43.2776, 'process_time': 56.7224}
2020-09-07 22:14:11,857 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 400 /  469]: {'prec1': 93.7803, 'loss': 0.1467, 'load_time': 43.5687, 'process_time': 56.4313}
2020-09-07 22:14:17,700 - algorithms.Algorithm - INFO   - ==> Iteration [ 38][ 450 /  469]: {'prec1': 93.783, 'loss': 0.147, 'load_time': 43.3676, 'process_time': 56.6324}
2020-09-07 22:14:19,882 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7846, 'loss': 0.1471, 'load_time': 43.4474, 'process_time': 56.5526}
2020-09-07 22:14:19,963 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:14:19,963 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:14:26,707 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9637, 'loss': 0.2237, 'load_time': 2.5958, 'process_time': 97.4042}
2020-09-07 22:14:26,707 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9637, 'loss': 0.2237, 'load_time': 2.5958, 'process_time': 97.4042}
2020-09-07 22:14:26,707 - algorithms.Algorithm - INFO   - Training epoch [ 39 / 200]
2020-09-07 22:14:26,707 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:14:26,707 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:14:32,352 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][  50 /  469]: {'prec1': 94.0508, 'loss': 0.1478, 'load_time': 37.4694, 'process_time': 62.5306}
2020-09-07 22:14:38,095 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 100 /  469]: {'prec1': 93.8945, 'loss': 0.1451, 'load_time': 38.6123, 'process_time': 61.3877}
2020-09-07 22:14:43,845 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 150 /  469]: {'prec1': 93.8763, 'loss': 0.1455, 'load_time': 40.0975, 'process_time': 59.9025}
2020-09-07 22:14:49,576 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 200 /  469]: {'prec1': 93.792, 'loss': 0.1479, 'load_time': 40.9011, 'process_time': 59.0989}
2020-09-07 22:14:55,327 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 250 /  469]: {'prec1': 93.7672, 'loss': 0.1478, 'load_time': 41.4428, 'process_time': 58.5572}
2020-09-07 22:15:01,148 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 300 /  469]: {'prec1': 93.8294, 'loss': 0.1467, 'load_time': 41.9442, 'process_time': 58.0558}
2020-09-07 22:15:06,958 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 350 /  469]: {'prec1': 93.8242, 'loss': 0.1471, 'load_time': 41.9367, 'process_time': 58.0633}
2020-09-07 22:15:12,699 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 400 /  469]: {'prec1': 93.8687, 'loss': 0.1461, 'load_time': 42.0687, 'process_time': 57.9313}
2020-09-07 22:15:18,451 - algorithms.Algorithm - INFO   - ==> Iteration [ 39][ 450 /  469]: {'prec1': 93.8581, 'loss': 0.1464, 'load_time': 42.1059, 'process_time': 57.8941}
2020-09-07 22:15:20,673 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8145, 'loss': 0.1473, 'load_time': 42.3868, 'process_time': 57.6132}
2020-09-07 22:15:20,754 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:15:20,754 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:15:27,446 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.3568, 'loss': 0.2031, 'load_time': 2.637, 'process_time': 97.363}
2020-09-07 22:15:27,447 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.3568, 'loss': 0.2031, 'load_time': 2.637, 'process_time': 97.363}
2020-09-07 22:15:27,447 - algorithms.Algorithm - INFO   - Training epoch [ 40 / 200]
2020-09-07 22:15:27,447 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:15:27,447 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:15:33,123 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][  50 /  469]: {'prec1': 93.7344, 'loss': 0.1456, 'load_time': 36.4707, 'process_time': 63.5293}
2020-09-07 22:15:38,827 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 100 /  469]: {'prec1': 93.7734, 'loss': 0.1445, 'load_time': 37.9072, 'process_time': 62.0928}
2020-09-07 22:15:44,461 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 150 /  469]: {'prec1': 93.7279, 'loss': 0.1461, 'load_time': 39.4612, 'process_time': 60.5388}
2020-09-07 22:15:50,202 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 200 /  469]: {'prec1': 93.791, 'loss': 0.1457, 'load_time': 40.4887, 'process_time': 59.5113}
2020-09-07 22:15:55,984 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 250 /  469]: {'prec1': 93.7594, 'loss': 0.1473, 'load_time': 40.9423, 'process_time': 59.0577}
2020-09-07 22:16:01,752 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 300 /  469]: {'prec1': 93.7865, 'loss': 0.1473, 'load_time': 41.4144, 'process_time': 58.5856}
2020-09-07 22:16:07,558 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 350 /  469]: {'prec1': 93.7919, 'loss': 0.1469, 'load_time': 42.2802, 'process_time': 57.7198}
2020-09-07 22:16:13,360 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 400 /  469]: {'prec1': 93.7397, 'loss': 0.1477, 'load_time': 42.6677, 'process_time': 57.3323}
2020-09-07 22:16:19,206 - algorithms.Algorithm - INFO   - ==> Iteration [ 40][ 450 /  469]: {'prec1': 93.7847, 'loss': 0.1473, 'load_time': 43.1081, 'process_time': 56.8919}
2020-09-07 22:16:21,402 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7708, 'loss': 0.1478, 'load_time': 43.3623, 'process_time': 56.6377}
2020-09-07 22:16:21,484 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:16:21,484 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:16:28,230 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.8142, 'loss': 0.1929, 'load_time': 2.6211, 'process_time': 97.3789}
2020-09-07 22:16:28,231 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.8142, 'loss': 0.1929, 'load_time': 2.6211, 'process_time': 97.3789}
2020-09-07 22:16:28,231 - algorithms.Algorithm - INFO   - Training epoch [ 41 / 200]
2020-09-07 22:16:28,231 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:16:28,231 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:16:34,001 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][  50 /  469]: {'prec1': 94.1172, 'loss': 0.1377, 'load_time': 41.1848, 'process_time': 58.8152}
2020-09-07 22:16:39,630 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 100 /  469]: {'prec1': 94.1289, 'loss': 0.1384, 'load_time': 40.873, 'process_time': 59.127}
2020-09-07 22:16:45,297 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 150 /  469]: {'prec1': 93.8919, 'loss': 0.143, 'load_time': 40.5695, 'process_time': 59.4305}
2020-09-07 22:16:51,079 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 200 /  469]: {'prec1': 93.8447, 'loss': 0.145, 'load_time': 41.5067, 'process_time': 58.4933}
2020-09-07 22:16:56,862 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 250 /  469]: {'prec1': 93.8148, 'loss': 0.1461, 'load_time': 41.7707, 'process_time': 58.2293}
2020-09-07 22:17:02,662 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 300 /  469]: {'prec1': 93.7689, 'loss': 0.147, 'load_time': 42.3343, 'process_time': 57.6657}
2020-09-07 22:17:08,478 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 350 /  469]: {'prec1': 93.7612, 'loss': 0.1474, 'load_time': 42.7015, 'process_time': 57.2985}
2020-09-07 22:17:14,280 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 400 /  469]: {'prec1': 93.7754, 'loss': 0.1472, 'load_time': 42.8827, 'process_time': 57.1173}
2020-09-07 22:17:20,076 - algorithms.Algorithm - INFO   - ==> Iteration [ 41][ 450 /  469]: {'prec1': 93.7934, 'loss': 0.1473, 'load_time': 43.2405, 'process_time': 56.7595}
2020-09-07 22:17:22,237 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7939, 'loss': 0.1474, 'load_time': 43.3251, 'process_time': 56.6749}
2020-09-07 22:17:22,320 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:17:22,320 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:17:29,041 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.0552, 'loss': 0.2104, 'load_time': 2.6966, 'process_time': 97.3034}
2020-09-07 22:17:29,041 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.0552, 'loss': 0.2104, 'load_time': 2.6966, 'process_time': 97.3034}
2020-09-07 22:17:29,042 - algorithms.Algorithm - INFO   - Training epoch [ 42 / 200]
2020-09-07 22:17:29,042 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:17:29,042 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:17:34,614 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][  50 /  469]: {'prec1': 94.0859, 'loss': 0.1391, 'load_time': 33.8484, 'process_time': 66.1516}
2020-09-07 22:17:40,278 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 100 /  469]: {'prec1': 94.0352, 'loss': 0.1414, 'load_time': 37.0735, 'process_time': 62.9265}
2020-09-07 22:17:46,026 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 150 /  469]: {'prec1': 93.957, 'loss': 0.143, 'load_time': 38.1444, 'process_time': 61.8556}
2020-09-07 22:17:51,725 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 200 /  469]: {'prec1': 93.9941, 'loss': 0.1434, 'load_time': 39.7172, 'process_time': 60.2828}
2020-09-07 22:17:57,453 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 250 /  469]: {'prec1': 93.8602, 'loss': 0.1455, 'load_time': 40.0296, 'process_time': 59.9704}
2020-09-07 22:18:03,258 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 300 /  469]: {'prec1': 93.8861, 'loss': 0.1446, 'load_time': 40.5648, 'process_time': 59.4352}
2020-09-07 22:18:09,010 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 350 /  469]: {'prec1': 93.8694, 'loss': 0.1453, 'load_time': 40.6908, 'process_time': 59.3092}
2020-09-07 22:18:14,758 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 400 /  469]: {'prec1': 93.8687, 'loss': 0.1455, 'load_time': 41.0968, 'process_time': 58.9032}
2020-09-07 22:18:20,493 - algorithms.Algorithm - INFO   - ==> Iteration [ 42][ 450 /  469]: {'prec1': 93.8568, 'loss': 0.1462, 'load_time': 41.3219, 'process_time': 58.6781}
2020-09-07 22:18:22,725 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8499, 'loss': 0.1464, 'load_time': 41.539, 'process_time': 58.461}
2020-09-07 22:18:22,804 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:18:22,805 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:18:29,564 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.5459, 'loss': 0.2178, 'load_time': 2.6116, 'process_time': 97.3884}
2020-09-07 22:18:29,564 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.5459, 'loss': 0.2178, 'load_time': 2.6116, 'process_time': 97.3884}
2020-09-07 22:18:29,564 - algorithms.Algorithm - INFO   - Training epoch [ 43 / 200]
2020-09-07 22:18:29,564 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:18:29,564 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:18:35,175 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][  50 /  469]: {'prec1': 93.8047, 'loss': 0.1488, 'load_time': 35.6915, 'process_time': 64.3085}
2020-09-07 22:18:40,897 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 100 /  469]: {'prec1': 93.8809, 'loss': 0.1457, 'load_time': 37.2299, 'process_time': 62.7701}
2020-09-07 22:18:46,541 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 150 /  469]: {'prec1': 94.0247, 'loss': 0.1442, 'load_time': 37.9537, 'process_time': 62.0463}
2020-09-07 22:18:52,281 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 200 /  469]: {'prec1': 93.9326, 'loss': 0.1451, 'load_time': 38.984, 'process_time': 61.016}
2020-09-07 22:18:58,048 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 250 /  469]: {'prec1': 93.8773, 'loss': 0.146, 'load_time': 39.7563, 'process_time': 60.2437}
2020-09-07 22:19:03,827 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 300 /  469]: {'prec1': 93.8333, 'loss': 0.1466, 'load_time': 40.2479, 'process_time': 59.7521}
2020-09-07 22:19:09,666 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 350 /  469]: {'prec1': 93.8069, 'loss': 0.1472, 'load_time': 40.7832, 'process_time': 59.2168}
2020-09-07 22:19:15,458 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 400 /  469]: {'prec1': 93.8008, 'loss': 0.1469, 'load_time': 41.2133, 'process_time': 58.7867}
2020-09-07 22:19:21,232 - algorithms.Algorithm - INFO   - ==> Iteration [ 43][ 450 /  469]: {'prec1': 93.8012, 'loss': 0.147, 'load_time': 41.5317, 'process_time': 58.4683}
2020-09-07 22:19:23,408 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7937, 'loss': 0.1474, 'load_time': 41.6357, 'process_time': 58.3643}
2020-09-07 22:19:23,488 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:19:23,488 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:19:30,250 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9044, 'loss': 0.2171, 'load_time': 2.6763, 'process_time': 97.3237}
2020-09-07 22:19:30,250 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9044, 'loss': 0.2171, 'load_time': 2.6763, 'process_time': 97.3237}
2020-09-07 22:19:30,250 - algorithms.Algorithm - INFO   - Training epoch [ 44 / 200]
2020-09-07 22:19:30,250 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:19:30,250 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:19:35,946 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][  50 /  469]: {'prec1': 93.9141, 'loss': 0.1426, 'load_time': 38.2846, 'process_time': 61.7154}
2020-09-07 22:19:41,618 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 100 /  469]: {'prec1': 93.8242, 'loss': 0.1444, 'load_time': 38.9471, 'process_time': 61.0529}
2020-09-07 22:19:47,351 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 150 /  469]: {'prec1': 93.8346, 'loss': 0.1453, 'load_time': 40.4422, 'process_time': 59.5578}
2020-09-07 22:19:53,149 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 200 /  469]: {'prec1': 93.7148, 'loss': 0.1466, 'load_time': 41.4469, 'process_time': 58.5531}
2020-09-07 22:19:58,883 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 250 /  469]: {'prec1': 93.7594, 'loss': 0.1459, 'load_time': 41.6474, 'process_time': 58.3526}
2020-09-07 22:20:04,656 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 300 /  469]: {'prec1': 93.8164, 'loss': 0.1451, 'load_time': 41.9088, 'process_time': 58.0912}
2020-09-07 22:20:10,454 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 350 /  469]: {'prec1': 93.8153, 'loss': 0.1451, 'load_time': 42.0555, 'process_time': 57.9445}
2020-09-07 22:20:16,239 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 400 /  469]: {'prec1': 93.7686, 'loss': 0.1462, 'load_time': 42.5487, 'process_time': 57.4513}
2020-09-07 22:20:22,006 - algorithms.Algorithm - INFO   - ==> Iteration [ 44][ 450 /  469]: {'prec1': 93.8012, 'loss': 0.1466, 'load_time': 42.9003, 'process_time': 57.0997}
2020-09-07 22:20:24,155 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8219, 'loss': 0.1462, 'load_time': 42.6867, 'process_time': 57.3133}
2020-09-07 22:20:24,237 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:20:24,238 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:20:30,951 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.6658, 'loss': 0.1976, 'load_time': 2.6739, 'process_time': 97.3261}
2020-09-07 22:20:30,951 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.6658, 'loss': 0.1976, 'load_time': 2.6739, 'process_time': 97.3261}
2020-09-07 22:20:30,951 - algorithms.Algorithm - INFO   - Training epoch [ 45 / 200]
2020-09-07 22:20:30,951 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:20:30,951 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:20:36,640 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][  50 /  469]: {'prec1': 93.5117, 'loss': 0.1498, 'load_time': 38.0552, 'process_time': 61.9448}
2020-09-07 22:20:42,353 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 100 /  469]: {'prec1': 93.6172, 'loss': 0.1485, 'load_time': 41.0269, 'process_time': 58.9731}
2020-09-07 22:20:48,092 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 150 /  469]: {'prec1': 93.7357, 'loss': 0.1478, 'load_time': 41.9565, 'process_time': 58.0435}
2020-09-07 22:20:53,853 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 200 /  469]: {'prec1': 93.7109, 'loss': 0.147, 'load_time': 41.9831, 'process_time': 58.0169}
2020-09-07 22:20:59,661 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 250 /  469]: {'prec1': 93.7586, 'loss': 0.1468, 'load_time': 41.9302, 'process_time': 58.0698}
2020-09-07 22:21:05,460 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 300 /  469]: {'prec1': 93.7448, 'loss': 0.1466, 'load_time': 41.9568, 'process_time': 58.0432}
2020-09-07 22:21:11,270 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 350 /  469]: {'prec1': 93.8231, 'loss': 0.146, 'load_time': 42.3181, 'process_time': 57.6819}
2020-09-07 22:21:17,117 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 400 /  469]: {'prec1': 93.8022, 'loss': 0.1468, 'load_time': 42.7274, 'process_time': 57.2726}
2020-09-07 22:21:22,961 - algorithms.Algorithm - INFO   - ==> Iteration [ 45][ 450 /  469]: {'prec1': 93.7474, 'loss': 0.1482, 'load_time': 42.7599, 'process_time': 57.2401}
2020-09-07 22:21:25,126 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.7719, 'loss': 0.1475, 'load_time': 42.6341, 'process_time': 57.3659}
2020-09-07 22:21:25,208 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:21:25,209 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:21:31,954 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.5373, 'loss': 0.2009, 'load_time': 2.6261, 'process_time': 97.3739}
2020-09-07 22:21:31,955 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.5373, 'loss': 0.2009, 'load_time': 2.6261, 'process_time': 97.3739}
2020-09-07 22:21:31,955 - algorithms.Algorithm - INFO   - Training epoch [ 46 / 200]
2020-09-07 22:21:31,955 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:21:31,955 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:21:37,586 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][  50 /  469]: {'prec1': 93.9648, 'loss': 0.1397, 'load_time': 35.8541, 'process_time': 64.1459}
2020-09-07 22:21:43,320 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 100 /  469]: {'prec1': 94.1484, 'loss': 0.14, 'load_time': 39.3806, 'process_time': 60.6194}
2020-09-07 22:21:48,909 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 150 /  469]: {'prec1': 94.0326, 'loss': 0.143, 'load_time': 39.3153, 'process_time': 60.6847}
2020-09-07 22:21:54,629 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 200 /  469]: {'prec1': 93.7949, 'loss': 0.1478, 'load_time': 39.9282, 'process_time': 60.0718}
2020-09-07 22:22:00,424 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 250 /  469]: {'prec1': 93.8656, 'loss': 0.1469, 'load_time': 40.9224, 'process_time': 59.0776}
2020-09-07 22:22:06,157 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 300 /  469]: {'prec1': 93.8678, 'loss': 0.1471, 'load_time': 41.3902, 'process_time': 58.6098}
2020-09-07 22:22:11,949 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 350 /  469]: {'prec1': 93.8315, 'loss': 0.1475, 'load_time': 41.9867, 'process_time': 58.0133}
2020-09-07 22:22:17,760 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 400 /  469]: {'prec1': 93.8687, 'loss': 0.1466, 'load_time': 42.0044, 'process_time': 57.9956}
2020-09-07 22:22:23,513 - algorithms.Algorithm - INFO   - ==> Iteration [ 46][ 450 /  469]: {'prec1': 93.8533, 'loss': 0.1464, 'load_time': 41.9683, 'process_time': 58.0317}
2020-09-07 22:22:25,740 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8444, 'loss': 0.1466, 'load_time': 42.105, 'process_time': 57.895}
2020-09-07 22:22:25,823 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:22:25,823 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:22:32,591 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.3012, 'loss': 0.1814, 'load_time': 2.6703, 'process_time': 97.3297}
2020-09-07 22:22:32,591 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.3012, 'loss': 0.1814, 'load_time': 2.6703, 'process_time': 97.3297}
2020-09-07 22:22:32,591 - algorithms.Algorithm - INFO   - Training epoch [ 47 / 200]
2020-09-07 22:22:32,591 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:22:32,591 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:22:38,219 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][  50 /  469]: {'prec1': 94.3633, 'loss': 0.1346, 'load_time': 35.9833, 'process_time': 64.0167}
2020-09-07 22:22:43,902 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 100 /  469]: {'prec1': 94.125, 'loss': 0.1403, 'load_time': 37.5832, 'process_time': 62.4168}
2020-09-07 22:22:49,558 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 150 /  469]: {'prec1': 94.1068, 'loss': 0.1402, 'load_time': 38.5601, 'process_time': 61.4399}
2020-09-07 22:22:55,323 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 200 /  469]: {'prec1': 93.9248, 'loss': 0.1438, 'load_time': 39.683, 'process_time': 60.317}
2020-09-07 22:23:01,106 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 250 /  469]: {'prec1': 93.9203, 'loss': 0.1442, 'load_time': 40.2936, 'process_time': 59.7064}
2020-09-07 22:23:06,848 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 300 /  469]: {'prec1': 93.8991, 'loss': 0.1452, 'load_time': 40.9013, 'process_time': 59.0987}
2020-09-07 22:23:12,652 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 350 /  469]: {'prec1': 93.9202, 'loss': 0.1448, 'load_time': 41.32, 'process_time': 58.68}
2020-09-07 22:23:18,482 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 400 /  469]: {'prec1': 93.8716, 'loss': 0.146, 'load_time': 41.8036, 'process_time': 58.1964}
2020-09-07 22:23:24,251 - algorithms.Algorithm - INFO   - ==> Iteration [ 47][ 450 /  469]: {'prec1': 93.9102, 'loss': 0.145, 'load_time': 42.043, 'process_time': 57.957}
2020-09-07 22:23:26,447 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.889, 'loss': 0.1454, 'load_time': 42.0655, 'process_time': 57.9345}
2020-09-07 22:23:26,531 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:23:26,531 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:23:33,313 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4977, 'loss': 0.1957, 'load_time': 2.6888, 'process_time': 97.3112}
2020-09-07 22:23:33,313 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4977, 'loss': 0.1957, 'load_time': 2.6888, 'process_time': 97.3112}
2020-09-07 22:23:33,313 - algorithms.Algorithm - INFO   - Training epoch [ 48 / 200]
2020-09-07 22:23:33,313 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:23:33,313 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:23:38,978 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][  50 /  469]: {'prec1': 93.8438, 'loss': 0.1461, 'load_time': 39.5294, 'process_time': 60.4706}
2020-09-07 22:23:44,686 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 100 /  469]: {'prec1': 94.0938, 'loss': 0.142, 'load_time': 40.1336, 'process_time': 59.8664}
2020-09-07 22:23:50,378 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 150 /  469]: {'prec1': 94.0078, 'loss': 0.1427, 'load_time': 40.8081, 'process_time': 59.1919}
2020-09-07 22:23:56,066 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 200 /  469]: {'prec1': 93.8906, 'loss': 0.1461, 'load_time': 40.746, 'process_time': 59.254}
2020-09-07 22:24:01,762 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 250 /  469]: {'prec1': 93.9289, 'loss': 0.1453, 'load_time': 41.3034, 'process_time': 58.6966}
2020-09-07 22:24:07,514 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 300 /  469]: {'prec1': 93.8535, 'loss': 0.1462, 'load_time': 41.4375, 'process_time': 58.5625}
2020-09-07 22:24:13,188 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 350 /  469]: {'prec1': 93.8237, 'loss': 0.1469, 'load_time': 41.5182, 'process_time': 58.4818}
2020-09-07 22:24:19,037 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 400 /  469]: {'prec1': 93.8477, 'loss': 0.1471, 'load_time': 42.0618, 'process_time': 57.9382}
2020-09-07 22:24:24,769 - algorithms.Algorithm - INFO   - ==> Iteration [ 48][ 450 /  469]: {'prec1': 93.8494, 'loss': 0.1468, 'load_time': 42.1736, 'process_time': 57.8264}
2020-09-07 22:24:27,040 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.848, 'loss': 0.1468, 'load_time': 42.3715, 'process_time': 57.6285}
2020-09-07 22:24:27,122 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:24:27,123 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:24:33,967 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.5312, 'loss': 0.1866, 'load_time': 2.6882, 'process_time': 97.3118}
2020-09-07 22:24:33,967 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.5312, 'loss': 0.1866, 'load_time': 2.6882, 'process_time': 97.3118}
2020-09-07 22:24:33,967 - algorithms.Algorithm - INFO   - Training epoch [ 49 / 200]
2020-09-07 22:24:33,967 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:24:33,967 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:24:39,589 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][  50 /  469]: {'prec1': 94.125, 'loss': 0.1423, 'load_time': 36.6228, 'process_time': 63.3772}
2020-09-07 22:24:45,281 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 100 /  469]: {'prec1': 94.0605, 'loss': 0.1428, 'load_time': 40.1894, 'process_time': 59.8106}
2020-09-07 22:24:51,009 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 150 /  469]: {'prec1': 94.1029, 'loss': 0.1422, 'load_time': 40.641, 'process_time': 59.359}
2020-09-07 22:24:56,684 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 200 /  469]: {'prec1': 94.0312, 'loss': 0.1431, 'load_time': 41.2449, 'process_time': 58.7551}
2020-09-07 22:25:02,395 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 250 /  469]: {'prec1': 93.9797, 'loss': 0.1441, 'load_time': 41.7213, 'process_time': 58.2787}
2020-09-07 22:25:08,130 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 300 /  469]: {'prec1': 93.9603, 'loss': 0.1446, 'load_time': 41.2923, 'process_time': 58.7077}
2020-09-07 22:25:13,931 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 350 /  469]: {'prec1': 93.9537, 'loss': 0.1451, 'load_time': 41.4453, 'process_time': 58.5547}
2020-09-07 22:25:19,703 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 400 /  469]: {'prec1': 93.9199, 'loss': 0.1455, 'load_time': 41.4917, 'process_time': 58.5083}
2020-09-07 22:25:25,498 - algorithms.Algorithm - INFO   - ==> Iteration [ 49][ 450 /  469]: {'prec1': 93.8811, 'loss': 0.1462, 'load_time': 41.6013, 'process_time': 58.3987}
2020-09-07 22:25:27,703 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8413, 'loss': 0.1469, 'load_time': 41.826, 'process_time': 58.174}
2020-09-07 22:25:27,784 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:25:27,784 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:25:34,497 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.0885, 'loss': 0.2355, 'load_time': 2.6407, 'process_time': 97.3593}
2020-09-07 22:25:34,497 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.0885, 'loss': 0.2355, 'load_time': 2.6407, 'process_time': 97.3593}
2020-09-07 22:25:34,497 - algorithms.Algorithm - INFO   - Training epoch [ 50 / 200]
2020-09-07 22:25:34,497 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:25:34,497 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:25:40,161 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][  50 /  469]: {'prec1': 93.8164, 'loss': 0.1505, 'load_time': 37.8101, 'process_time': 62.1899}
2020-09-07 22:25:45,795 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 100 /  469]: {'prec1': 93.8438, 'loss': 0.1472, 'load_time': 39.3468, 'process_time': 60.6532}
2020-09-07 22:25:51,604 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 150 /  469]: {'prec1': 93.7891, 'loss': 0.1488, 'load_time': 40.4318, 'process_time': 59.5682}
2020-09-07 22:25:57,360 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 200 /  469]: {'prec1': 93.7881, 'loss': 0.1479, 'load_time': 41.8042, 'process_time': 58.1958}
2020-09-07 22:26:03,040 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 250 /  469]: {'prec1': 93.8289, 'loss': 0.1472, 'load_time': 42.1403, 'process_time': 57.8597}
2020-09-07 22:26:08,727 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 300 /  469]: {'prec1': 93.8424, 'loss': 0.147, 'load_time': 41.713, 'process_time': 58.287}
2020-09-07 22:26:14,443 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 350 /  469]: {'prec1': 93.8962, 'loss': 0.1463, 'load_time': 41.9566, 'process_time': 58.0434}
2020-09-07 22:26:20,154 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 400 /  469]: {'prec1': 93.8535, 'loss': 0.1464, 'load_time': 42.0979, 'process_time': 57.9021}
2020-09-07 22:26:25,875 - algorithms.Algorithm - INFO   - ==> Iteration [ 50][ 450 /  469]: {'prec1': 93.8581, 'loss': 0.147, 'load_time': 41.8504, 'process_time': 58.1496}
2020-09-07 22:26:28,107 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8402, 'loss': 0.1472, 'load_time': 42.0044, 'process_time': 57.9956}
2020-09-07 22:26:28,195 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:26:28,195 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:26:35,008 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.321, 'loss': 0.1878, 'load_time': 2.6263, 'process_time': 97.3737}
2020-09-07 22:26:35,008 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.321, 'loss': 0.1878, 'load_time': 2.6263, 'process_time': 97.3737}
2020-09-07 22:26:35,008 - algorithms.Algorithm - INFO   - Training epoch [ 51 / 200]
2020-09-07 22:26:35,008 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:26:35,008 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:26:40,768 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][  50 /  469]: {'prec1': 94.3672, 'loss': 0.1385, 'load_time': 39.2145, 'process_time': 60.7855}
2020-09-07 22:26:46,456 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 100 /  469]: {'prec1': 94.1016, 'loss': 0.1401, 'load_time': 39.6466, 'process_time': 60.3534}
2020-09-07 22:26:52,208 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 150 /  469]: {'prec1': 94.1406, 'loss': 0.1399, 'load_time': 40.5545, 'process_time': 59.4455}
2020-09-07 22:26:57,965 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 200 /  469]: {'prec1': 94.1748, 'loss': 0.139, 'load_time': 40.7283, 'process_time': 59.2717}
2020-09-07 22:27:03,787 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 250 /  469]: {'prec1': 94.1063, 'loss': 0.1405, 'load_time': 41.3804, 'process_time': 58.6196}
2020-09-07 22:27:09,514 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 300 /  469]: {'prec1': 93.9635, 'loss': 0.1435, 'load_time': 41.3119, 'process_time': 58.6881}
2020-09-07 22:27:15,315 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 350 /  469]: {'prec1': 93.9414, 'loss': 0.144, 'load_time': 41.9179, 'process_time': 58.0821}
2020-09-07 22:27:21,062 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 400 /  469]: {'prec1': 93.8687, 'loss': 0.1452, 'load_time': 41.8868, 'process_time': 58.1132}
2020-09-07 22:27:26,902 - algorithms.Algorithm - INFO   - ==> Iteration [ 51][ 450 /  469]: {'prec1': 93.9102, 'loss': 0.145, 'load_time': 41.868, 'process_time': 58.132}
2020-09-07 22:27:29,089 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.9034, 'loss': 0.1453, 'load_time': 42.0498, 'process_time': 57.9502}
2020-09-07 22:27:29,171 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:27:29,172 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:27:35,936 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.871, 'loss': 0.1914, 'load_time': 2.6383, 'process_time': 97.3617}
2020-09-07 22:27:35,936 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.871, 'loss': 0.1914, 'load_time': 2.6383, 'process_time': 97.3617}
2020-09-07 22:27:35,936 - algorithms.Algorithm - INFO   - Training epoch [ 52 / 200]
2020-09-07 22:27:35,936 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:27:35,936 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:27:41,606 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][  50 /  469]: {'prec1': 93.6875, 'loss': 0.1451, 'load_time': 36.5355, 'process_time': 63.4645}
2020-09-07 22:27:47,305 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 100 /  469]: {'prec1': 93.6875, 'loss': 0.1457, 'load_time': 38.1258, 'process_time': 61.8742}
2020-09-07 22:27:53,022 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 150 /  469]: {'prec1': 93.7357, 'loss': 0.1453, 'load_time': 38.3266, 'process_time': 61.6734}
2020-09-07 22:27:58,810 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 200 /  469]: {'prec1': 93.8008, 'loss': 0.1456, 'load_time': 40.0588, 'process_time': 59.9412}
2020-09-07 22:28:04,507 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 250 /  469]: {'prec1': 93.807, 'loss': 0.1471, 'load_time': 40.6866, 'process_time': 59.3134}
2020-09-07 22:28:10,374 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 300 /  469]: {'prec1': 93.9062, 'loss': 0.1459, 'load_time': 41.134, 'process_time': 58.866}
2020-09-07 22:28:16,158 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 350 /  469]: {'prec1': 93.8465, 'loss': 0.1465, 'load_time': 41.1386, 'process_time': 58.8614}
2020-09-07 22:28:21,988 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 400 /  469]: {'prec1': 93.8691, 'loss': 0.1461, 'load_time': 41.2232, 'process_time': 58.7768}
2020-09-07 22:28:27,772 - algorithms.Algorithm - INFO   - ==> Iteration [ 52][ 450 /  469]: {'prec1': 93.8446, 'loss': 0.1465, 'load_time': 41.4618, 'process_time': 58.5382}
2020-09-07 22:28:30,031 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8436, 'loss': 0.1466, 'load_time': 41.7804, 'process_time': 58.2196}
2020-09-07 22:28:30,114 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:28:30,114 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:28:36,882 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.352, 'loss': 0.1632, 'load_time': 2.5314, 'process_time': 97.4686}
2020-09-07 22:28:36,882 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.352, 'loss': 0.1632, 'load_time': 2.5314, 'process_time': 97.4686}
2020-09-07 22:28:36,882 - algorithms.Algorithm - INFO   - Training epoch [ 53 / 200]
2020-09-07 22:28:36,882 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:28:36,882 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:28:42,635 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][  50 /  469]: {'prec1': 94.0469, 'loss': 0.1448, 'load_time': 39.3519, 'process_time': 60.6481}
2020-09-07 22:28:48,300 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 100 /  469]: {'prec1': 94.0254, 'loss': 0.1433, 'load_time': 38.5879, 'process_time': 61.4121}
2020-09-07 22:28:54,026 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 150 /  469]: {'prec1': 93.9818, 'loss': 0.1442, 'load_time': 39.5453, 'process_time': 60.4547}
2020-09-07 22:28:59,785 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 200 /  469]: {'prec1': 94.0156, 'loss': 0.1441, 'load_time': 40.6321, 'process_time': 59.3679}
2020-09-07 22:29:05,606 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 250 /  469]: {'prec1': 94.0617, 'loss': 0.1439, 'load_time': 41.3161, 'process_time': 58.6839}
2020-09-07 22:29:11,417 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 300 /  469]: {'prec1': 94.0911, 'loss': 0.1437, 'load_time': 41.6105, 'process_time': 58.3895}
2020-09-07 22:29:17,230 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 350 /  469]: {'prec1': 94.0363, 'loss': 0.1441, 'load_time': 41.5315, 'process_time': 58.4685}
2020-09-07 22:29:22,974 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 400 /  469]: {'prec1': 94.0273, 'loss': 0.1446, 'load_time': 41.8943, 'process_time': 58.1057}
2020-09-07 22:29:28,767 - algorithms.Algorithm - INFO   - ==> Iteration [ 53][ 450 /  469]: {'prec1': 93.9583, 'loss': 0.1454, 'load_time': 41.8602, 'process_time': 58.1398}
2020-09-07 22:29:30,985 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.923, 'loss': 0.1458, 'load_time': 42.0289, 'process_time': 57.9711}
2020-09-07 22:29:31,067 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:29:31,067 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:29:37,860 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.7128, 'loss': 0.2, 'load_time': 2.6585, 'process_time': 97.3415}
2020-09-07 22:29:37,860 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.7128, 'loss': 0.2, 'load_time': 2.6585, 'process_time': 97.3415}
2020-09-07 22:29:37,860 - algorithms.Algorithm - INFO   - Training epoch [ 54 / 200]
2020-09-07 22:29:37,860 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:29:37,860 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:29:43,507 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][  50 /  469]: {'prec1': 94.1172, 'loss': 0.1424, 'load_time': 37.8725, 'process_time': 62.1275}
2020-09-07 22:29:49,168 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 100 /  469]: {'prec1': 94.1094, 'loss': 0.1413, 'load_time': 39.2581, 'process_time': 60.7419}
2020-09-07 22:29:54,942 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 150 /  469]: {'prec1': 94.0482, 'loss': 0.1435, 'load_time': 39.7528, 'process_time': 60.2472}
2020-09-07 22:30:00,749 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 200 /  469]: {'prec1': 94.0566, 'loss': 0.1433, 'load_time': 41.0026, 'process_time': 58.9974}
2020-09-07 22:30:06,586 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 250 /  469]: {'prec1': 93.9305, 'loss': 0.1452, 'load_time': 41.3948, 'process_time': 58.6052}
2020-09-07 22:30:12,371 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 300 /  469]: {'prec1': 93.9753, 'loss': 0.1442, 'load_time': 41.3143, 'process_time': 58.6857}
2020-09-07 22:30:18,268 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 350 /  469]: {'prec1': 93.9263, 'loss': 0.145, 'load_time': 41.7051, 'process_time': 58.2949}
2020-09-07 22:30:24,059 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 400 /  469]: {'prec1': 93.9102, 'loss': 0.1457, 'load_time': 41.9132, 'process_time': 58.0868}
2020-09-07 22:30:29,889 - algorithms.Algorithm - INFO   - ==> Iteration [ 54][ 450 /  469]: {'prec1': 93.875, 'loss': 0.1462, 'load_time': 42.1583, 'process_time': 57.8417}
2020-09-07 22:30:32,150 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8988, 'loss': 0.1453, 'load_time': 42.3115, 'process_time': 57.6885}
2020-09-07 22:30:32,231 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:30:32,232 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:30:39,083 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.8994, 'loss': 0.2167, 'load_time': 2.6177, 'process_time': 97.3823}
2020-09-07 22:30:39,083 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.8994, 'loss': 0.2167, 'load_time': 2.6177, 'process_time': 97.3823}
2020-09-07 22:30:39,083 - algorithms.Algorithm - INFO   - Training epoch [ 55 / 200]
2020-09-07 22:30:39,083 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:30:39,083 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:30:44,790 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][  50 /  469]: {'prec1': 93.7969, 'loss': 0.1451, 'load_time': 39.8398, 'process_time': 60.1602}
2020-09-07 22:30:50,500 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 100 /  469]: {'prec1': 94.1445, 'loss': 0.1373, 'load_time': 40.3352, 'process_time': 59.6648}
2020-09-07 22:30:56,156 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 150 /  469]: {'prec1': 94.0339, 'loss': 0.1403, 'load_time': 40.2367, 'process_time': 59.7633}
2020-09-07 22:31:01,836 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 200 /  469]: {'prec1': 94.0234, 'loss': 0.1414, 'load_time': 40.8358, 'process_time': 59.1642}
2020-09-07 22:31:07,605 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 250 /  469]: {'prec1': 93.9891, 'loss': 0.1416, 'load_time': 41.7065, 'process_time': 58.2935}
2020-09-07 22:31:13,374 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 300 /  469]: {'prec1': 93.9915, 'loss': 0.1424, 'load_time': 41.9054, 'process_time': 58.0946}
2020-09-07 22:31:19,101 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 350 /  469]: {'prec1': 93.9743, 'loss': 0.1434, 'load_time': 42.141, 'process_time': 57.859}
2020-09-07 22:31:24,847 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 400 /  469]: {'prec1': 93.9326, 'loss': 0.1444, 'load_time': 42.3161, 'process_time': 57.6839}
2020-09-07 22:31:30,665 - algorithms.Algorithm - INFO   - ==> Iteration [ 55][ 450 /  469]: {'prec1': 93.9388, 'loss': 0.1442, 'load_time': 42.4118, 'process_time': 57.5882}
2020-09-07 22:31:32,842 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.9346, 'loss': 0.1444, 'load_time': 42.5285, 'process_time': 57.4715}
2020-09-07 22:31:32,924 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:31:32,925 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:31:39,692 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.2703, 'loss': 0.2002, 'load_time': 2.5663, 'process_time': 97.4337}
2020-09-07 22:31:39,693 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.2703, 'loss': 0.2002, 'load_time': 2.5663, 'process_time': 97.4337}
2020-09-07 22:31:39,693 - algorithms.Algorithm - INFO   - Training epoch [ 56 / 200]
2020-09-07 22:31:39,693 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:31:39,693 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:31:45,367 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][  50 /  469]: {'prec1': 94.1992, 'loss': 0.1382, 'load_time': 40.1061, 'process_time': 59.8939}
2020-09-07 22:31:51,011 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 100 /  469]: {'prec1': 94.1602, 'loss': 0.1395, 'load_time': 38.9432, 'process_time': 61.0568}
2020-09-07 22:31:56,771 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 150 /  469]: {'prec1': 93.9779, 'loss': 0.1412, 'load_time': 40.6248, 'process_time': 59.3752}
2020-09-07 22:32:02,523 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 200 /  469]: {'prec1': 93.9307, 'loss': 0.1417, 'load_time': 41.4942, 'process_time': 58.5058}
2020-09-07 22:32:08,272 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 250 /  469]: {'prec1': 93.9281, 'loss': 0.1433, 'load_time': 41.5342, 'process_time': 58.4658}
2020-09-07 22:32:13,989 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 300 /  469]: {'prec1': 93.9095, 'loss': 0.1442, 'load_time': 41.9361, 'process_time': 58.0639}
2020-09-07 22:32:19,747 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 350 /  469]: {'prec1': 93.8806, 'loss': 0.1449, 'load_time': 42.3641, 'process_time': 57.6359}
2020-09-07 22:32:25,420 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 400 /  469]: {'prec1': 93.9121, 'loss': 0.1443, 'load_time': 42.9306, 'process_time': 57.0694}
2020-09-07 22:32:31,174 - algorithms.Algorithm - INFO   - ==> Iteration [ 56][ 450 /  469]: {'prec1': 93.872, 'loss': 0.1454, 'load_time': 42.7732, 'process_time': 57.2268}
2020-09-07 22:32:33,392 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8983, 'loss': 0.1447, 'load_time': 42.8055, 'process_time': 57.1945}
2020-09-07 22:32:33,474 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:32:33,474 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:32:40,186 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4977, 'loss': 0.192, 'load_time': 2.5977, 'process_time': 97.4023}
2020-09-07 22:32:40,187 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4977, 'loss': 0.192, 'load_time': 2.5977, 'process_time': 97.4023}
2020-09-07 22:32:40,187 - algorithms.Algorithm - INFO   - Training epoch [ 57 / 200]
2020-09-07 22:32:40,187 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:32:40,187 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:32:45,842 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][  50 /  469]: {'prec1': 94.1641, 'loss': 0.1414, 'load_time': 38.1464, 'process_time': 61.8536}
2020-09-07 22:32:51,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 100 /  469]: {'prec1': 94.0879, 'loss': 0.1434, 'load_time': 39.4981, 'process_time': 60.5019}
2020-09-07 22:32:57,295 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 150 /  469]: {'prec1': 94.0026, 'loss': 0.1438, 'load_time': 40.4436, 'process_time': 59.5564}
2020-09-07 22:33:03,050 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 200 /  469]: {'prec1': 94.0166, 'loss': 0.1437, 'load_time': 41.1872, 'process_time': 58.8128}
2020-09-07 22:33:08,915 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 250 /  469]: {'prec1': 93.9508, 'loss': 0.1441, 'load_time': 41.8963, 'process_time': 58.1037}
2020-09-07 22:33:14,603 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 300 /  469]: {'prec1': 93.9727, 'loss': 0.1437, 'load_time': 41.853, 'process_time': 58.147}
2020-09-07 22:33:20,318 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 350 /  469]: {'prec1': 93.8811, 'loss': 0.1455, 'load_time': 42.1697, 'process_time': 57.8303}
2020-09-07 22:33:26,044 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 400 /  469]: {'prec1': 93.8931, 'loss': 0.145, 'load_time': 42.0715, 'process_time': 57.9285}
2020-09-07 22:33:31,835 - algorithms.Algorithm - INFO   - ==> Iteration [ 57][ 450 /  469]: {'prec1': 93.8559, 'loss': 0.1459, 'load_time': 42.3098, 'process_time': 57.6902}
2020-09-07 22:33:34,018 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8869, 'loss': 0.1455, 'load_time': 42.4664, 'process_time': 57.5336}
2020-09-07 22:33:34,101 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:33:34,101 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:33:40,844 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 90.9687, 'loss': 0.2175, 'load_time': 2.6778, 'process_time': 97.3222}
2020-09-07 22:33:40,844 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 90.9687, 'loss': 0.2175, 'load_time': 2.6778, 'process_time': 97.3222}
2020-09-07 22:33:40,844 - algorithms.Algorithm - INFO   - Training epoch [ 58 / 200]
2020-09-07 22:33:40,844 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:33:40,844 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:33:46,564 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][  50 /  469]: {'prec1': 93.9766, 'loss': 0.1463, 'load_time': 39.7137, 'process_time': 60.2863}
2020-09-07 22:33:52,193 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 100 /  469]: {'prec1': 94.0215, 'loss': 0.1438, 'load_time': 40.5151, 'process_time': 59.4849}
2020-09-07 22:33:57,904 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 150 /  469]: {'prec1': 93.9401, 'loss': 0.145, 'load_time': 41.7035, 'process_time': 58.2965}
2020-09-07 22:34:03,733 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 200 /  469]: {'prec1': 93.8877, 'loss': 0.1468, 'load_time': 42.5, 'process_time': 57.5}
2020-09-07 22:34:09,455 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 250 /  469]: {'prec1': 93.9172, 'loss': 0.1462, 'load_time': 42.9504, 'process_time': 57.0496}
2020-09-07 22:34:15,243 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 300 /  469]: {'prec1': 93.972, 'loss': 0.1451, 'load_time': 43.2792, 'process_time': 56.7208}
2020-09-07 22:34:21,032 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 350 /  469]: {'prec1': 93.971, 'loss': 0.1459, 'load_time': 43.5059, 'process_time': 56.4941}
2020-09-07 22:34:26,816 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 400 /  469]: {'prec1': 94.0249, 'loss': 0.1446, 'load_time': 44.0057, 'process_time': 55.9943}
2020-09-07 22:34:32,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 58][ 450 /  469]: {'prec1': 94.0122, 'loss': 0.1446, 'load_time': 44.0152, 'process_time': 55.9848}
2020-09-07 22:34:34,814 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 94.0151, 'loss': 0.1445, 'load_time': 44.0611, 'process_time': 55.9389}
2020-09-07 22:34:34,897 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:34:34,897 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:34:41,552 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.0416, 'loss': 0.1846, 'load_time': 2.6262, 'process_time': 97.3738}
2020-09-07 22:34:41,552 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.0416, 'loss': 0.1846, 'load_time': 2.6262, 'process_time': 97.3738}
2020-09-07 22:34:41,552 - algorithms.Algorithm - INFO   - Training epoch [ 59 / 200]
2020-09-07 22:34:41,552 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:34:41,552 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:34:47,220 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][  50 /  469]: {'prec1': 94.0117, 'loss': 0.1434, 'load_time': 40.3516, 'process_time': 59.6484}
2020-09-07 22:34:52,867 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 100 /  469]: {'prec1': 93.8027, 'loss': 0.1439, 'load_time': 41.3271, 'process_time': 58.6729}
2020-09-07 22:34:58,617 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 150 /  469]: {'prec1': 93.901, 'loss': 0.1449, 'load_time': 42.2098, 'process_time': 57.7902}
2020-09-07 22:35:04,420 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 200 /  469]: {'prec1': 94.0078, 'loss': 0.1432, 'load_time': 42.3691, 'process_time': 57.6309}
2020-09-07 22:35:10,267 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 250 /  469]: {'prec1': 93.9203, 'loss': 0.1445, 'load_time': 42.8203, 'process_time': 57.1797}
2020-09-07 22:35:16,051 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 300 /  469]: {'prec1': 93.9603, 'loss': 0.1448, 'load_time': 43.4893, 'process_time': 56.5107}
2020-09-07 22:35:21,819 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 350 /  469]: {'prec1': 94.0073, 'loss': 0.1438, 'load_time': 43.4659, 'process_time': 56.5341}
2020-09-07 22:35:27,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 400 /  469]: {'prec1': 93.9688, 'loss': 0.1439, 'load_time': 43.4631, 'process_time': 56.5369}
2020-09-07 22:35:33,379 - algorithms.Algorithm - INFO   - ==> Iteration [ 59][ 450 /  469]: {'prec1': 93.941, 'loss': 0.1452, 'load_time': 43.6804, 'process_time': 56.3196}
2020-09-07 22:35:35,596 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.9445, 'loss': 0.145, 'load_time': 43.812, 'process_time': 56.188}
2020-09-07 22:35:35,677 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:35:35,678 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:35:42,239 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.4606, 'loss': 0.2096, 'load_time': 2.5694, 'process_time': 97.4306}
2020-09-07 22:35:42,239 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.4606, 'loss': 0.2096, 'load_time': 2.5694, 'process_time': 97.4306}
2020-09-07 22:35:42,239 - algorithms.Algorithm - INFO   - Training epoch [ 60 / 200]
2020-09-07 22:35:42,239 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.1000000000
2020-09-07 22:35:42,239 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:35:47,886 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][  50 /  469]: {'prec1': 94.3047, 'loss': 0.1381, 'load_time': 42.1538, 'process_time': 57.8462}
2020-09-07 22:35:53,590 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 100 /  469]: {'prec1': 94.2305, 'loss': 0.14, 'load_time': 41.924, 'process_time': 58.076}
2020-09-07 22:35:59,279 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 150 /  469]: {'prec1': 94.237, 'loss': 0.1399, 'load_time': 42.854, 'process_time': 57.146}
2020-09-07 22:36:05,067 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 200 /  469]: {'prec1': 94.0625, 'loss': 0.1431, 'load_time': 43.4862, 'process_time': 56.5138}
2020-09-07 22:36:10,818 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 250 /  469]: {'prec1': 94.0125, 'loss': 0.1436, 'load_time': 44.0146, 'process_time': 55.9854}
2020-09-07 22:36:16,617 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 300 /  469]: {'prec1': 93.9382, 'loss': 0.1447, 'load_time': 44.5065, 'process_time': 55.4935}
2020-09-07 22:36:22,426 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 350 /  469]: {'prec1': 93.9096, 'loss': 0.1449, 'load_time': 45.067, 'process_time': 54.933}
2020-09-07 22:36:28,236 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 400 /  469]: {'prec1': 93.9209, 'loss': 0.1447, 'load_time': 45.5505, 'process_time': 54.4495}
2020-09-07 22:36:34,019 - algorithms.Algorithm - INFO   - ==> Iteration [ 60][ 450 /  469]: {'prec1': 93.9006, 'loss': 0.1453, 'load_time': 45.8838, 'process_time': 54.1162}
2020-09-07 22:36:36,208 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 93.8637, 'loss': 0.1461, 'load_time': 45.9474, 'process_time': 54.0526}
2020-09-07 22:36:36,292 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:36:36,293 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:36:42,956 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 91.2159, 'loss': 0.2038, 'load_time': 2.5654, 'process_time': 97.4346}
2020-09-07 22:36:42,956 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 91.2159, 'loss': 0.2038, 'load_time': 2.5654, 'process_time': 97.4346}
2020-09-07 22:36:42,956 - algorithms.Algorithm - INFO   - Training epoch [ 61 / 200]
2020-09-07 22:36:42,956 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:36:42,956 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:36:48,477 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][  50 /  469]: {'prec1': 94.5742, 'loss': 0.1299, 'load_time': 39.5219, 'process_time': 60.4781}
2020-09-07 22:36:54,107 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 100 /  469]: {'prec1': 95.0625, 'loss': 0.1186, 'load_time': 41.0493, 'process_time': 58.9507}
2020-09-07 22:36:59,864 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 150 /  469]: {'prec1': 95.1146, 'loss': 0.1165, 'load_time': 42.0589, 'process_time': 57.9411}
2020-09-07 22:37:05,605 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 200 /  469]: {'prec1': 95.1484, 'loss': 0.1154, 'load_time': 42.7811, 'process_time': 57.2189}
2020-09-07 22:37:11,357 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 250 /  469]: {'prec1': 95.1594, 'loss': 0.1154, 'load_time': 43.9026, 'process_time': 56.0974}
2020-09-07 22:37:17,171 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 300 /  469]: {'prec1': 95.2038, 'loss': 0.1141, 'load_time': 44.1185, 'process_time': 55.8815}
2020-09-07 22:37:22,978 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 350 /  469]: {'prec1': 95.2701, 'loss': 0.1126, 'load_time': 44.5207, 'process_time': 55.4793}
2020-09-07 22:37:28,706 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 400 /  469]: {'prec1': 95.2896, 'loss': 0.1119, 'load_time': 44.5815, 'process_time': 55.4185}
2020-09-07 22:37:34,507 - algorithms.Algorithm - INFO   - ==> Iteration [ 61][ 450 /  469]: {'prec1': 95.3203, 'loss': 0.1109, 'load_time': 44.7101, 'process_time': 55.2899}
2020-09-07 22:37:36,703 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.3289, 'loss': 0.1105, 'load_time': 44.7586, 'process_time': 55.2414}
2020-09-07 22:37:36,786 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:37:36,786 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:37:43,413 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.9206, 'loss': 0.1489, 'load_time': 2.5339, 'process_time': 97.4661}
2020-09-07 22:37:43,413 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.9206, 'loss': 0.1489, 'load_time': 2.5339, 'process_time': 97.4661}
2020-09-07 22:37:43,413 - algorithms.Algorithm - INFO   - Training epoch [ 62 / 200]
2020-09-07 22:37:43,413 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:37:43,414 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:37:49,114 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][  50 /  469]: {'prec1': 95.4805, 'loss': 0.1049, 'load_time': 40.3042, 'process_time': 59.6958}
2020-09-07 22:37:54,823 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 100 /  469]: {'prec1': 95.6562, 'loss': 0.0994, 'load_time': 42.9829, 'process_time': 57.0171}
2020-09-07 22:38:00,507 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 150 /  469]: {'prec1': 95.7461, 'loss': 0.0992, 'load_time': 43.7703, 'process_time': 56.2297}
2020-09-07 22:38:06,224 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 200 /  469]: {'prec1': 95.6689, 'loss': 0.1013, 'load_time': 43.806, 'process_time': 56.194}
2020-09-07 22:38:12,015 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 250 /  469]: {'prec1': 95.5906, 'loss': 0.1036, 'load_time': 44.3764, 'process_time': 55.6236}
2020-09-07 22:38:17,692 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 300 /  469]: {'prec1': 95.5495, 'loss': 0.1041, 'load_time': 44.6089, 'process_time': 55.3911}
2020-09-07 22:38:23,429 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 350 /  469]: {'prec1': 95.5926, 'loss': 0.1034, 'load_time': 44.8014, 'process_time': 55.1986}
2020-09-07 22:38:29,268 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 400 /  469]: {'prec1': 95.6562, 'loss': 0.1026, 'load_time': 45.3372, 'process_time': 54.6628}
2020-09-07 22:38:35,131 - algorithms.Algorithm - INFO   - ==> Iteration [ 62][ 450 /  469]: {'prec1': 95.6701, 'loss': 0.1024, 'load_time': 45.6557, 'process_time': 54.3443}
2020-09-07 22:38:37,276 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.6656, 'loss': 0.1024, 'load_time': 45.6725, 'process_time': 54.3275}
2020-09-07 22:38:37,356 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:38:37,356 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:38:44,043 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.8217, 'loss': 0.149, 'load_time': 2.5276, 'process_time': 97.4724}
2020-09-07 22:38:44,043 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.8217, 'loss': 0.149, 'load_time': 2.5276, 'process_time': 97.4724}
2020-09-07 22:38:44,043 - algorithms.Algorithm - INFO   - Training epoch [ 63 / 200]
2020-09-07 22:38:44,043 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:38:44,043 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:38:49,666 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][  50 /  469]: {'prec1': 95.75, 'loss': 0.1033, 'load_time': 38.7008, 'process_time': 61.2992}
2020-09-07 22:38:55,261 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 100 /  469]: {'prec1': 95.6758, 'loss': 0.102, 'load_time': 39.4298, 'process_time': 60.5702}
2020-09-07 22:39:00,952 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 150 /  469]: {'prec1': 95.7044, 'loss': 0.1009, 'load_time': 40.5551, 'process_time': 59.4449}
2020-09-07 22:39:06,774 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 200 /  469]: {'prec1': 95.6816, 'loss': 0.1005, 'load_time': 41.2346, 'process_time': 58.7654}
2020-09-07 22:39:12,588 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 250 /  469]: {'prec1': 95.7977, 'loss': 0.0984, 'load_time': 41.6097, 'process_time': 58.3903}
2020-09-07 22:39:18,309 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 300 /  469]: {'prec1': 95.7318, 'loss': 0.0992, 'load_time': 41.5889, 'process_time': 58.4111}
2020-09-07 22:39:24,110 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 350 /  469]: {'prec1': 95.7199, 'loss': 0.0994, 'load_time': 41.9633, 'process_time': 58.0367}
2020-09-07 22:39:29,878 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 400 /  469]: {'prec1': 95.7554, 'loss': 0.099, 'load_time': 42.3792, 'process_time': 57.6208}
2020-09-07 22:39:35,727 - algorithms.Algorithm - INFO   - ==> Iteration [ 63][ 450 /  469]: {'prec1': 95.7548, 'loss': 0.0993, 'load_time': 42.7434, 'process_time': 57.2566}
2020-09-07 22:39:37,950 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.7228, 'loss': 0.1, 'load_time': 42.7975, 'process_time': 57.2025}
2020-09-07 22:39:38,034 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:39:38,034 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:39:44,822 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.6808, 'loss': 0.1539, 'load_time': 2.6466, 'process_time': 97.3534}
2020-09-07 22:39:44,822 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.6808, 'loss': 0.1539, 'load_time': 2.6466, 'process_time': 97.3534}
2020-09-07 22:39:44,823 - algorithms.Algorithm - INFO   - Training epoch [ 64 / 200]
2020-09-07 22:39:44,823 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:39:44,823 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:39:50,577 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][  50 /  469]: {'prec1': 95.7695, 'loss': 0.0985, 'load_time': 40.8167, 'process_time': 59.1833}
2020-09-07 22:39:56,168 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 100 /  469]: {'prec1': 95.9102, 'loss': 0.0959, 'load_time': 40.8612, 'process_time': 59.1388}
2020-09-07 22:40:01,899 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 150 /  469]: {'prec1': 95.9128, 'loss': 0.0953, 'load_time': 40.7623, 'process_time': 59.2377}
2020-09-07 22:40:07,612 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 200 /  469]: {'prec1': 95.8896, 'loss': 0.0947, 'load_time': 41.3433, 'process_time': 58.6567}
2020-09-07 22:40:13,317 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 250 /  469]: {'prec1': 95.8508, 'loss': 0.0963, 'load_time': 42.4843, 'process_time': 57.5157}
2020-09-07 22:40:19,097 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 300 /  469]: {'prec1': 95.819, 'loss': 0.0966, 'load_time': 42.6909, 'process_time': 57.3091}
2020-09-07 22:40:24,828 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 350 /  469]: {'prec1': 95.7924, 'loss': 0.0978, 'load_time': 42.9454, 'process_time': 57.0546}
2020-09-07 22:40:30,505 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 400 /  469]: {'prec1': 95.7822, 'loss': 0.0981, 'load_time': 43.111, 'process_time': 56.889}
2020-09-07 22:40:36,260 - algorithms.Algorithm - INFO   - ==> Iteration [ 64][ 450 /  469]: {'prec1': 95.7982, 'loss': 0.098, 'load_time': 43.4248, 'process_time': 56.5752}
2020-09-07 22:40:38,435 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.7985, 'loss': 0.0979, 'load_time': 43.4895, 'process_time': 56.5105}
2020-09-07 22:40:38,519 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:40:38,520 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:40:45,157 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.8093, 'loss': 0.1526, 'load_time': 2.5031, 'process_time': 97.4969}
2020-09-07 22:40:45,157 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.8093, 'loss': 0.1526, 'load_time': 2.5031, 'process_time': 97.4969}
2020-09-07 22:40:45,157 - algorithms.Algorithm - INFO   - Training epoch [ 65 / 200]
2020-09-07 22:40:45,157 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:40:45,157 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:40:50,869 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][  50 /  469]: {'prec1': 96.0, 'loss': 0.0974, 'load_time': 42.7011, 'process_time': 57.2989}
2020-09-07 22:40:56,643 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 100 /  469]: {'prec1': 96.0078, 'loss': 0.0966, 'load_time': 43.7572, 'process_time': 56.2428}
2020-09-07 22:41:02,320 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 150 /  469]: {'prec1': 95.9727, 'loss': 0.0964, 'load_time': 42.7405, 'process_time': 57.2595}
2020-09-07 22:41:08,055 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 200 /  469]: {'prec1': 96.001, 'loss': 0.0948, 'load_time': 42.9238, 'process_time': 57.0762}
2020-09-07 22:41:13,810 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 250 /  469]: {'prec1': 95.907, 'loss': 0.0962, 'load_time': 42.9002, 'process_time': 57.0998}
2020-09-07 22:41:19,616 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 300 /  469]: {'prec1': 95.849, 'loss': 0.0972, 'load_time': 43.4999, 'process_time': 56.5001}
2020-09-07 22:41:25,383 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 350 /  469]: {'prec1': 95.8577, 'loss': 0.0967, 'load_time': 43.8378, 'process_time': 56.1622}
2020-09-07 22:41:31,106 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 400 /  469]: {'prec1': 95.8672, 'loss': 0.0964, 'load_time': 43.9444, 'process_time': 56.0556}
2020-09-07 22:41:36,884 - algorithms.Algorithm - INFO   - ==> Iteration [ 65][ 450 /  469]: {'prec1': 95.8615, 'loss': 0.0964, 'load_time': 44.5163, 'process_time': 55.4837}
2020-09-07 22:41:39,104 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.859, 'loss': 0.0965, 'load_time': 44.8027, 'process_time': 55.1973}
2020-09-07 22:41:39,184 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:41:39,184 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:41:45,758 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.9786, 'loss': 0.1716, 'load_time': 2.5513, 'process_time': 97.4487}
2020-09-07 22:41:45,759 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.9786, 'loss': 0.1716, 'load_time': 2.5513, 'process_time': 97.4487}
2020-09-07 22:41:45,759 - algorithms.Algorithm - INFO   - Training epoch [ 66 / 200]
2020-09-07 22:41:45,759 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:41:45,759 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:41:51,409 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][  50 /  469]: {'prec1': 95.8672, 'loss': 0.0959, 'load_time': 43.1918, 'process_time': 56.8082}
2020-09-07 22:41:57,047 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 100 /  469]: {'prec1': 95.9043, 'loss': 0.0959, 'load_time': 41.7006, 'process_time': 58.2994}
2020-09-07 22:42:02,771 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 150 /  469]: {'prec1': 95.8333, 'loss': 0.0972, 'load_time': 42.8191, 'process_time': 57.1809}
2020-09-07 22:42:08,535 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 200 /  469]: {'prec1': 95.9316, 'loss': 0.0959, 'load_time': 44.3942, 'process_time': 55.6058}
2020-09-07 22:42:14,143 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 250 /  469]: {'prec1': 95.9547, 'loss': 0.0955, 'load_time': 44.3856, 'process_time': 55.6144}
2020-09-07 22:42:19,858 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 300 /  469]: {'prec1': 95.9577, 'loss': 0.0949, 'load_time': 44.7054, 'process_time': 55.2946}
2020-09-07 22:42:25,572 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 350 /  469]: {'prec1': 95.9632, 'loss': 0.0952, 'load_time': 45.3609, 'process_time': 54.6391}
2020-09-07 22:42:31,288 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 400 /  469]: {'prec1': 95.9443, 'loss': 0.0953, 'load_time': 45.7704, 'process_time': 54.2296}
2020-09-07 22:42:36,984 - algorithms.Algorithm - INFO   - ==> Iteration [ 66][ 450 /  469]: {'prec1': 95.9032, 'loss': 0.096, 'load_time': 45.5219, 'process_time': 54.4781}
2020-09-07 22:42:39,185 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8843, 'loss': 0.0964, 'load_time': 45.9695, 'process_time': 54.0305}
2020-09-07 22:42:39,264 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:42:39,264 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:42:45,698 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0825, 'loss': 0.1653, 'load_time': 2.531, 'process_time': 97.469}
2020-09-07 22:42:45,698 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0825, 'loss': 0.1653, 'load_time': 2.531, 'process_time': 97.469}
2020-09-07 22:42:45,698 - algorithms.Algorithm - INFO   - Training epoch [ 67 / 200]
2020-09-07 22:42:45,698 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:42:45,699 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:42:51,232 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][  50 /  469]: {'prec1': 95.918, 'loss': 0.0905, 'load_time': 41.3188, 'process_time': 58.6812}
2020-09-07 22:42:56,829 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 100 /  469]: {'prec1': 96.0742, 'loss': 0.0921, 'load_time': 42.2522, 'process_time': 57.7478}
2020-09-07 22:43:02,579 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 150 /  469]: {'prec1': 96.069, 'loss': 0.0916, 'load_time': 43.939, 'process_time': 56.061}
2020-09-07 22:43:08,221 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 200 /  469]: {'prec1': 95.9307, 'loss': 0.0942, 'load_time': 44.6117, 'process_time': 55.3883}
2020-09-07 22:43:13,990 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 250 /  469]: {'prec1': 95.9078, 'loss': 0.095, 'load_time': 45.7426, 'process_time': 54.2574}
2020-09-07 22:43:19,735 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 300 /  469]: {'prec1': 95.9056, 'loss': 0.0953, 'load_time': 46.6856, 'process_time': 53.3144}
2020-09-07 22:43:25,425 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 350 /  469]: {'prec1': 95.8661, 'loss': 0.0964, 'load_time': 47.0366, 'process_time': 52.9634}
2020-09-07 22:43:31,146 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 400 /  469]: {'prec1': 95.8457, 'loss': 0.0971, 'load_time': 47.1209, 'process_time': 52.8791}
2020-09-07 22:43:36,934 - algorithms.Algorithm - INFO   - ==> Iteration [ 67][ 450 /  469]: {'prec1': 95.8511, 'loss': 0.0972, 'load_time': 47.6384, 'process_time': 52.3616}
2020-09-07 22:43:39,123 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8622, 'loss': 0.0972, 'load_time': 47.8456, 'process_time': 52.1544}
2020-09-07 22:43:39,206 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:43:39,206 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:43:45,769 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.7896, 'loss': 0.1521, 'load_time': 2.5196, 'process_time': 97.4804}
2020-09-07 22:43:45,769 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.7896, 'loss': 0.1521, 'load_time': 2.5196, 'process_time': 97.4804}
2020-09-07 22:43:45,769 - algorithms.Algorithm - INFO   - Training epoch [ 68 / 200]
2020-09-07 22:43:45,769 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:43:45,769 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:43:51,414 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][  50 /  469]: {'prec1': 96.1875, 'loss': 0.0929, 'load_time': 42.839, 'process_time': 57.161}
2020-09-07 22:43:57,113 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 100 /  469]: {'prec1': 96.1641, 'loss': 0.09, 'load_time': 44.0224, 'process_time': 55.9776}
2020-09-07 22:44:02,749 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 150 /  469]: {'prec1': 96.0885, 'loss': 0.0938, 'load_time': 44.3056, 'process_time': 55.6944}
2020-09-07 22:44:08,360 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 200 /  469]: {'prec1': 96.0029, 'loss': 0.0949, 'load_time': 44.457, 'process_time': 55.543}
2020-09-07 22:44:14,053 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 250 /  469]: {'prec1': 95.925, 'loss': 0.096, 'load_time': 44.7384, 'process_time': 55.2616}
2020-09-07 22:44:19,707 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 300 /  469]: {'prec1': 95.9362, 'loss': 0.0957, 'load_time': 45.0567, 'process_time': 54.9433}
2020-09-07 22:44:25,382 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 350 /  469]: {'prec1': 95.8733, 'loss': 0.0969, 'load_time': 45.5041, 'process_time': 54.4959}
2020-09-07 22:44:31,144 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 400 /  469]: {'prec1': 95.8813, 'loss': 0.0969, 'load_time': 45.5699, 'process_time': 54.4301}
2020-09-07 22:44:36,910 - algorithms.Algorithm - INFO   - ==> Iteration [ 68][ 450 /  469]: {'prec1': 95.8694, 'loss': 0.0975, 'load_time': 45.7309, 'process_time': 54.2691}
2020-09-07 22:44:39,130 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8798, 'loss': 0.0972, 'load_time': 45.9208, 'process_time': 54.0792}
2020-09-07 22:44:39,214 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:44:39,214 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:44:45,817 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2951, 'loss': 0.1687, 'load_time': 2.5552, 'process_time': 97.4448}
2020-09-07 22:44:45,817 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2951, 'loss': 0.1687, 'load_time': 2.5552, 'process_time': 97.4448}
2020-09-07 22:44:45,817 - algorithms.Algorithm - INFO   - Training epoch [ 69 / 200]
2020-09-07 22:44:45,817 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:44:45,818 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:44:51,469 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][  50 /  469]: {'prec1': 95.7656, 'loss': 0.0955, 'load_time': 44.638, 'process_time': 55.362}
2020-09-07 22:44:57,085 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 100 /  469]: {'prec1': 95.8496, 'loss': 0.096, 'load_time': 44.8079, 'process_time': 55.1921}
2020-09-07 22:45:02,747 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 150 /  469]: {'prec1': 95.9701, 'loss': 0.0945, 'load_time': 44.602, 'process_time': 55.398}
2020-09-07 22:45:08,453 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 200 /  469]: {'prec1': 96.0244, 'loss': 0.0934, 'load_time': 45.6588, 'process_time': 54.3412}
2020-09-07 22:45:14,157 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 250 /  469]: {'prec1': 95.982, 'loss': 0.0944, 'load_time': 45.901, 'process_time': 54.099}
2020-09-07 22:45:19,894 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 300 /  469]: {'prec1': 95.9134, 'loss': 0.0958, 'load_time': 46.2894, 'process_time': 53.7106}
2020-09-07 22:45:25,634 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 350 /  469]: {'prec1': 95.9124, 'loss': 0.0954, 'load_time': 46.5679, 'process_time': 53.4321}
2020-09-07 22:45:31,355 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 400 /  469]: {'prec1': 95.9341, 'loss': 0.0951, 'load_time': 46.1702, 'process_time': 53.8298}
2020-09-07 22:45:37,080 - algorithms.Algorithm - INFO   - ==> Iteration [ 69][ 450 /  469]: {'prec1': 95.9167, 'loss': 0.0953, 'load_time': 46.6802, 'process_time': 53.3198}
2020-09-07 22:45:39,269 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9076, 'loss': 0.0957, 'load_time': 46.8076, 'process_time': 53.1924}
2020-09-07 22:45:39,350 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:45:39,350 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:45:45,883 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.8588, 'loss': 0.1543, 'load_time': 2.5187, 'process_time': 97.4813}
2020-09-07 22:45:45,884 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.8588, 'loss': 0.1543, 'load_time': 2.5187, 'process_time': 97.4813}
2020-09-07 22:45:45,884 - algorithms.Algorithm - INFO   - Training epoch [ 70 / 200]
2020-09-07 22:45:45,884 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:45:45,884 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:45:51,504 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][  50 /  469]: {'prec1': 95.9141, 'loss': 0.0947, 'load_time': 40.2577, 'process_time': 59.7423}
2020-09-07 22:45:57,124 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 100 /  469]: {'prec1': 95.9512, 'loss': 0.0944, 'load_time': 44.2743, 'process_time': 55.7257}
2020-09-07 22:46:02,774 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 150 /  469]: {'prec1': 95.9219, 'loss': 0.0955, 'load_time': 44.8482, 'process_time': 55.1518}
2020-09-07 22:46:08,496 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 200 /  469]: {'prec1': 95.8438, 'loss': 0.0971, 'load_time': 44.6762, 'process_time': 55.3238}
2020-09-07 22:46:14,273 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 250 /  469]: {'prec1': 95.9172, 'loss': 0.0951, 'load_time': 45.6405, 'process_time': 54.3595}
2020-09-07 22:46:20,102 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 300 /  469]: {'prec1': 95.8574, 'loss': 0.0969, 'load_time': 46.0266, 'process_time': 53.9734}
2020-09-07 22:46:25,849 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 350 /  469]: {'prec1': 95.846, 'loss': 0.097, 'load_time': 46.4037, 'process_time': 53.5963}
2020-09-07 22:46:31,591 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 400 /  469]: {'prec1': 95.8481, 'loss': 0.0971, 'load_time': 46.6118, 'process_time': 53.3882}
2020-09-07 22:46:37,312 - algorithms.Algorithm - INFO   - ==> Iteration [ 70][ 450 /  469]: {'prec1': 95.8238, 'loss': 0.0976, 'load_time': 46.5147, 'process_time': 53.4853}
2020-09-07 22:46:39,518 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8311, 'loss': 0.0975, 'load_time': 46.584, 'process_time': 53.416}
2020-09-07 22:46:39,599 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:46:39,599 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:46:46,088 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.944, 'loss': 0.1808, 'load_time': 2.4708, 'process_time': 97.5292}
2020-09-07 22:46:46,088 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.944, 'loss': 0.1808, 'load_time': 2.4708, 'process_time': 97.5292}
2020-09-07 22:46:46,088 - algorithms.Algorithm - INFO   - Training epoch [ 71 / 200]
2020-09-07 22:46:46,088 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:46:46,088 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:46:51,643 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][  50 /  469]: {'prec1': 96.3125, 'loss': 0.0858, 'load_time': 41.0293, 'process_time': 58.9707}
2020-09-07 22:46:57,273 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 100 /  469]: {'prec1': 96.2617, 'loss': 0.0884, 'load_time': 44.1004, 'process_time': 55.8996}
2020-09-07 22:47:03,021 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 150 /  469]: {'prec1': 96.2474, 'loss': 0.0886, 'load_time': 45.6676, 'process_time': 54.3324}
2020-09-07 22:47:08,703 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 200 /  469]: {'prec1': 96.2031, 'loss': 0.0902, 'load_time': 45.429, 'process_time': 54.571}
2020-09-07 22:47:14,371 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 250 /  469]: {'prec1': 96.0687, 'loss': 0.0935, 'load_time': 46.2437, 'process_time': 53.7563}
2020-09-07 22:47:20,094 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 300 /  469]: {'prec1': 96.0456, 'loss': 0.0931, 'load_time': 46.3894, 'process_time': 53.6106}
2020-09-07 22:47:25,895 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 350 /  469]: {'prec1': 95.9537, 'loss': 0.0946, 'load_time': 46.6336, 'process_time': 53.3664}
2020-09-07 22:47:31,654 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 400 /  469]: {'prec1': 95.9175, 'loss': 0.0956, 'load_time': 46.3292, 'process_time': 53.6708}
2020-09-07 22:47:37,412 - algorithms.Algorithm - INFO   - ==> Iteration [ 71][ 450 /  469]: {'prec1': 95.8628, 'loss': 0.0962, 'load_time': 46.0994, 'process_time': 53.9006}
2020-09-07 22:47:39,608 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8547, 'loss': 0.0964, 'load_time': 46.4507, 'process_time': 53.5493}
2020-09-07 22:47:39,691 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:47:39,692 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:47:46,222 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4484, 'loss': 0.1656, 'load_time': 2.4813, 'process_time': 97.5187}
2020-09-07 22:47:46,222 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4484, 'loss': 0.1656, 'load_time': 2.4813, 'process_time': 97.5187}
2020-09-07 22:47:46,222 - algorithms.Algorithm - INFO   - Training epoch [ 72 / 200]
2020-09-07 22:47:46,222 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:47:46,222 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:47:51,851 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][  50 /  469]: {'prec1': 96.1016, 'loss': 0.0905, 'load_time': 42.1793, 'process_time': 57.8207}
2020-09-07 22:47:57,466 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 100 /  469]: {'prec1': 95.9473, 'loss': 0.0925, 'load_time': 43.8755, 'process_time': 56.1245}
2020-09-07 22:48:03,143 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 150 /  469]: {'prec1': 95.9414, 'loss': 0.0928, 'load_time': 43.4784, 'process_time': 56.5216}
2020-09-07 22:48:08,923 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 200 /  469]: {'prec1': 95.9902, 'loss': 0.0924, 'load_time': 44.8098, 'process_time': 55.1902}
2020-09-07 22:48:14,672 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 250 /  469]: {'prec1': 95.9539, 'loss': 0.0935, 'load_time': 45.6545, 'process_time': 54.3455}
2020-09-07 22:48:20,451 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 300 /  469]: {'prec1': 95.9082, 'loss': 0.0948, 'load_time': 46.1989, 'process_time': 53.8011}
2020-09-07 22:48:26,194 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 350 /  469]: {'prec1': 95.8901, 'loss': 0.0958, 'load_time': 46.5668, 'process_time': 53.4332}
2020-09-07 22:48:31,909 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 400 /  469]: {'prec1': 95.8589, 'loss': 0.0966, 'load_time': 46.4031, 'process_time': 53.5969}
2020-09-07 22:48:37,657 - algorithms.Algorithm - INFO   - ==> Iteration [ 72][ 450 /  469]: {'prec1': 95.8715, 'loss': 0.0968, 'load_time': 46.634, 'process_time': 53.366}
2020-09-07 22:48:39,836 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8499, 'loss': 0.0971, 'load_time': 46.7403, 'process_time': 53.2597}
2020-09-07 22:48:39,919 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:48:39,919 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:48:46,471 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3075, 'loss': 0.1646, 'load_time': 2.5292, 'process_time': 97.4708}
2020-09-07 22:48:46,471 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3075, 'loss': 0.1646, 'load_time': 2.5292, 'process_time': 97.4708}
2020-09-07 22:48:46,471 - algorithms.Algorithm - INFO   - Training epoch [ 73 / 200]
2020-09-07 22:48:46,471 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:48:46,471 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:48:52,192 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][  50 /  469]: {'prec1': 95.9141, 'loss': 0.0942, 'load_time': 42.6464, 'process_time': 57.3536}
2020-09-07 22:48:57,722 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 100 /  469]: {'prec1': 96.1035, 'loss': 0.09, 'load_time': 43.1668, 'process_time': 56.8332}
2020-09-07 22:49:03,389 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 150 /  469]: {'prec1': 95.9492, 'loss': 0.0927, 'load_time': 43.6655, 'process_time': 56.3345}
2020-09-07 22:49:09,098 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 200 /  469]: {'prec1': 96.0078, 'loss': 0.0918, 'load_time': 44.4073, 'process_time': 55.5927}
2020-09-07 22:49:14,819 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 250 /  469]: {'prec1': 96.0266, 'loss': 0.0919, 'load_time': 45.4561, 'process_time': 54.5439}
2020-09-07 22:49:20,671 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 300 /  469]: {'prec1': 95.9922, 'loss': 0.0928, 'load_time': 45.6806, 'process_time': 54.3194}
2020-09-07 22:49:26,314 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 350 /  469]: {'prec1': 96.0073, 'loss': 0.0927, 'load_time': 45.349, 'process_time': 54.651}
2020-09-07 22:49:32,063 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 400 /  469]: {'prec1': 95.9194, 'loss': 0.0945, 'load_time': 45.5805, 'process_time': 54.4195}
2020-09-07 22:49:37,778 - algorithms.Algorithm - INFO   - ==> Iteration [ 73][ 450 /  469]: {'prec1': 95.9106, 'loss': 0.0954, 'load_time': 45.4365, 'process_time': 54.5635}
2020-09-07 22:49:40,008 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9022, 'loss': 0.0958, 'load_time': 45.5493, 'process_time': 54.4507}
2020-09-07 22:49:40,091 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:49:40,091 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:49:46,553 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.5534, 'loss': 0.1764, 'load_time': 2.5197, 'process_time': 97.4803}
2020-09-07 22:49:46,553 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.5534, 'loss': 0.1764, 'load_time': 2.5197, 'process_time': 97.4803}
2020-09-07 22:49:46,553 - algorithms.Algorithm - INFO   - Training epoch [ 74 / 200]
2020-09-07 22:49:46,553 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:49:46,553 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:49:52,213 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][  50 /  469]: {'prec1': 96.0742, 'loss': 0.0922, 'load_time': 40.3327, 'process_time': 59.6673}
2020-09-07 22:49:57,759 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 100 /  469]: {'prec1': 95.9688, 'loss': 0.0941, 'load_time': 42.7543, 'process_time': 57.2457}
2020-09-07 22:50:03,488 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 150 /  469]: {'prec1': 96.0013, 'loss': 0.0936, 'load_time': 44.8674, 'process_time': 55.1326}
2020-09-07 22:50:09,210 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 200 /  469]: {'prec1': 95.8584, 'loss': 0.0963, 'load_time': 45.4491, 'process_time': 54.5509}
2020-09-07 22:50:14,957 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 250 /  469]: {'prec1': 95.85, 'loss': 0.0961, 'load_time': 45.9878, 'process_time': 54.0122}
2020-09-07 22:50:20,650 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 300 /  469]: {'prec1': 95.847, 'loss': 0.0962, 'load_time': 46.1945, 'process_time': 53.8055}
2020-09-07 22:50:26,460 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 350 /  469]: {'prec1': 95.8131, 'loss': 0.0973, 'load_time': 46.5302, 'process_time': 53.4698}
2020-09-07 22:50:32,228 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 400 /  469]: {'prec1': 95.8105, 'loss': 0.0979, 'load_time': 46.8352, 'process_time': 53.1648}
2020-09-07 22:50:37,984 - algorithms.Algorithm - INFO   - ==> Iteration [ 74][ 450 /  469]: {'prec1': 95.8129, 'loss': 0.0977, 'load_time': 47.0123, 'process_time': 52.9877}
2020-09-07 22:50:40,165 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8307, 'loss': 0.0975, 'load_time': 47.1382, 'process_time': 52.8618}
2020-09-07 22:50:40,245 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:50:40,246 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:50:46,757 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.8624, 'loss': 0.177, 'load_time': 2.4881, 'process_time': 97.5119}
2020-09-07 22:50:46,758 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.8624, 'loss': 0.177, 'load_time': 2.4881, 'process_time': 97.5119}
2020-09-07 22:50:46,758 - algorithms.Algorithm - INFO   - Training epoch [ 75 / 200]
2020-09-07 22:50:46,758 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:50:46,758 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:50:52,378 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][  50 /  469]: {'prec1': 96.0703, 'loss': 0.0946, 'load_time': 42.1745, 'process_time': 57.8255}
2020-09-07 22:50:58,051 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 100 /  469]: {'prec1': 96.1074, 'loss': 0.0925, 'load_time': 44.3122, 'process_time': 55.6878}
2020-09-07 22:51:03,754 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 150 /  469]: {'prec1': 96.1107, 'loss': 0.0927, 'load_time': 46.2207, 'process_time': 53.7793}
2020-09-07 22:51:09,477 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 200 /  469]: {'prec1': 95.9863, 'loss': 0.0951, 'load_time': 46.1469, 'process_time': 53.8531}
2020-09-07 22:51:15,242 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 250 /  469]: {'prec1': 95.9695, 'loss': 0.0952, 'load_time': 46.505, 'process_time': 53.495}
2020-09-07 22:51:20,964 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 300 /  469]: {'prec1': 95.8919, 'loss': 0.0968, 'load_time': 46.7001, 'process_time': 53.2999}
2020-09-07 22:51:26,755 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 350 /  469]: {'prec1': 95.8856, 'loss': 0.0969, 'load_time': 47.1177, 'process_time': 52.8823}
2020-09-07 22:51:32,490 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 400 /  469]: {'prec1': 95.8643, 'loss': 0.0967, 'load_time': 47.3068, 'process_time': 52.6932}
2020-09-07 22:51:38,284 - algorithms.Algorithm - INFO   - ==> Iteration [ 75][ 450 /  469]: {'prec1': 95.8659, 'loss': 0.0965, 'load_time': 47.498, 'process_time': 52.502}
2020-09-07 22:51:40,469 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8718, 'loss': 0.0965, 'load_time': 47.6164, 'process_time': 52.3836}
2020-09-07 22:51:40,551 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:51:40,552 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:51:46,976 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1987, 'loss': 0.1688, 'load_time': 2.505, 'process_time': 97.495}
2020-09-07 22:51:46,976 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1987, 'loss': 0.1688, 'load_time': 2.505, 'process_time': 97.495}
2020-09-07 22:51:46,976 - algorithms.Algorithm - INFO   - Training epoch [ 76 / 200]
2020-09-07 22:51:46,976 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:51:46,976 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:51:52,606 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][  50 /  469]: {'prec1': 95.6289, 'loss': 0.0982, 'load_time': 42.9552, 'process_time': 57.0448}
2020-09-07 22:51:58,280 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 100 /  469]: {'prec1': 96.0645, 'loss': 0.0914, 'load_time': 44.2063, 'process_time': 55.7937}
2020-09-07 22:52:03,973 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 150 /  469]: {'prec1': 96.0195, 'loss': 0.0926, 'load_time': 44.8703, 'process_time': 55.1297}
2020-09-07 22:52:09,631 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 200 /  469]: {'prec1': 95.9375, 'loss': 0.0941, 'load_time': 45.2472, 'process_time': 54.7528}
2020-09-07 22:52:15,351 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 250 /  469]: {'prec1': 95.8812, 'loss': 0.0962, 'load_time': 46.1126, 'process_time': 53.8874}
2020-09-07 22:52:21,122 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 300 /  469]: {'prec1': 95.8587, 'loss': 0.0964, 'load_time': 46.4706, 'process_time': 53.5294}
2020-09-07 22:52:26,784 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 350 /  469]: {'prec1': 95.8968, 'loss': 0.0958, 'load_time': 46.3682, 'process_time': 53.6318}
2020-09-07 22:52:32,484 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 400 /  469]: {'prec1': 95.9033, 'loss': 0.0962, 'load_time': 46.5024, 'process_time': 53.4976}
2020-09-07 22:52:38,200 - algorithms.Algorithm - INFO   - ==> Iteration [ 76][ 450 /  469]: {'prec1': 95.9175, 'loss': 0.0957, 'load_time': 46.6228, 'process_time': 53.3772}
2020-09-07 22:52:40,403 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9243, 'loss': 0.0955, 'load_time': 46.803, 'process_time': 53.197}
2020-09-07 22:52:40,485 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:52:40,485 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:52:46,918 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4212, 'loss': 0.1685, 'load_time': 2.5179, 'process_time': 97.4821}
2020-09-07 22:52:46,918 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4212, 'loss': 0.1685, 'load_time': 2.5179, 'process_time': 97.4821}
2020-09-07 22:52:46,918 - algorithms.Algorithm - INFO   - Training epoch [ 77 / 200]
2020-09-07 22:52:46,918 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:52:46,918 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:52:52,604 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][  50 /  469]: {'prec1': 95.8398, 'loss': 0.0958, 'load_time': 43.9883, 'process_time': 56.0117}
2020-09-07 22:52:58,135 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 100 /  469]: {'prec1': 95.873, 'loss': 0.0955, 'load_time': 42.0779, 'process_time': 57.9221}
2020-09-07 22:53:03,824 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 150 /  469]: {'prec1': 95.862, 'loss': 0.0959, 'load_time': 43.5089, 'process_time': 56.4911}
2020-09-07 22:53:09,455 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 200 /  469]: {'prec1': 95.8867, 'loss': 0.0953, 'load_time': 44.2093, 'process_time': 55.7907}
2020-09-07 22:53:15,208 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 250 /  469]: {'prec1': 95.7906, 'loss': 0.0975, 'load_time': 45.2464, 'process_time': 54.7536}
2020-09-07 22:53:20,971 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 300 /  469]: {'prec1': 95.7962, 'loss': 0.097, 'load_time': 45.4833, 'process_time': 54.5167}
2020-09-07 22:53:26,718 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 350 /  469]: {'prec1': 95.8097, 'loss': 0.0971, 'load_time': 46.0632, 'process_time': 53.9368}
2020-09-07 22:53:32,408 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 400 /  469]: {'prec1': 95.7959, 'loss': 0.0976, 'load_time': 46.3181, 'process_time': 53.6819}
2020-09-07 22:53:38,218 - algorithms.Algorithm - INFO   - ==> Iteration [ 77][ 450 /  469]: {'prec1': 95.7982, 'loss': 0.0974, 'load_time': 46.2675, 'process_time': 53.7325}
2020-09-07 22:53:40,434 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.8138, 'loss': 0.0972, 'load_time': 46.3421, 'process_time': 53.6579}
2020-09-07 22:53:40,519 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:53:40,519 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:53:47,036 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.5522, 'loss': 0.1606, 'load_time': 2.4766, 'process_time': 97.5234}
2020-09-07 22:53:47,036 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.5522, 'loss': 0.1606, 'load_time': 2.4766, 'process_time': 97.5234}
2020-09-07 22:53:47,036 - algorithms.Algorithm - INFO   - Training epoch [ 78 / 200]
2020-09-07 22:53:47,036 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:53:47,036 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:53:52,663 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][  50 /  469]: {'prec1': 96.2578, 'loss': 0.0908, 'load_time': 39.8798, 'process_time': 60.1202}
2020-09-07 22:53:58,236 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 100 /  469]: {'prec1': 96.0586, 'loss': 0.0935, 'load_time': 41.5601, 'process_time': 58.4399}
2020-09-07 22:54:03,870 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 150 /  469]: {'prec1': 96.0273, 'loss': 0.0935, 'load_time': 42.3095, 'process_time': 57.6905}
2020-09-07 22:54:09,616 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 200 /  469]: {'prec1': 96.0625, 'loss': 0.0929, 'load_time': 43.5267, 'process_time': 56.4733}
2020-09-07 22:54:15,388 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 250 /  469]: {'prec1': 96.0563, 'loss': 0.0932, 'load_time': 44.8745, 'process_time': 55.1255}
2020-09-07 22:54:21,160 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 300 /  469]: {'prec1': 96.0475, 'loss': 0.0936, 'load_time': 44.943, 'process_time': 55.057}
2020-09-07 22:54:26,920 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 350 /  469]: {'prec1': 96.0552, 'loss': 0.0935, 'load_time': 45.1513, 'process_time': 54.8487}
2020-09-07 22:54:32,697 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 400 /  469]: {'prec1': 95.9927, 'loss': 0.0948, 'load_time': 45.6933, 'process_time': 54.3067}
2020-09-07 22:54:38,484 - algorithms.Algorithm - INFO   - ==> Iteration [ 78][ 450 /  469]: {'prec1': 95.9718, 'loss': 0.0948, 'load_time': 45.9848, 'process_time': 54.0152}
2020-09-07 22:54:40,714 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9681, 'loss': 0.0949, 'load_time': 46.2529, 'process_time': 53.7471}
2020-09-07 22:54:40,795 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:54:40,795 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:54:47,327 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0256, 'loss': 0.1675, 'load_time': 2.4844, 'process_time': 97.5156}
2020-09-07 22:54:47,328 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0256, 'loss': 0.1675, 'load_time': 2.4844, 'process_time': 97.5156}
2020-09-07 22:54:47,328 - algorithms.Algorithm - INFO   - Training epoch [ 79 / 200]
2020-09-07 22:54:47,328 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:54:47,328 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:54:52,914 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][  50 /  469]: {'prec1': 95.8789, 'loss': 0.0949, 'load_time': 37.6577, 'process_time': 62.3423}
2020-09-07 22:54:58,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 100 /  469]: {'prec1': 95.8535, 'loss': 0.0968, 'load_time': 42.221, 'process_time': 57.779}
2020-09-07 22:55:04,159 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 150 /  469]: {'prec1': 95.9388, 'loss': 0.0957, 'load_time': 44.0325, 'process_time': 55.9675}
2020-09-07 22:55:09,845 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 200 /  469]: {'prec1': 95.9209, 'loss': 0.0956, 'load_time': 44.8374, 'process_time': 55.1626}
2020-09-07 22:55:15,546 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 250 /  469]: {'prec1': 95.957, 'loss': 0.0943, 'load_time': 45.2664, 'process_time': 54.7336}
2020-09-07 22:55:21,220 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 300 /  469]: {'prec1': 95.9766, 'loss': 0.0944, 'load_time': 45.1944, 'process_time': 54.8056}
2020-09-07 22:55:27,065 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 350 /  469]: {'prec1': 95.9364, 'loss': 0.0951, 'load_time': 45.9128, 'process_time': 54.0872}
2020-09-07 22:55:32,778 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 400 /  469]: {'prec1': 95.9214, 'loss': 0.0953, 'load_time': 45.85, 'process_time': 54.15}
2020-09-07 22:55:38,577 - algorithms.Algorithm - INFO   - ==> Iteration [ 79][ 450 /  469]: {'prec1': 95.9115, 'loss': 0.0951, 'load_time': 46.3214, 'process_time': 53.6786}
2020-09-07 22:55:40,791 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.903, 'loss': 0.0953, 'load_time': 46.5974, 'process_time': 53.4026}
2020-09-07 22:55:40,869 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:55:40,869 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:55:47,324 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1616, 'loss': 0.166, 'load_time': 2.5161, 'process_time': 97.4839}
2020-09-07 22:55:47,324 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1616, 'loss': 0.166, 'load_time': 2.5161, 'process_time': 97.4839}
2020-09-07 22:55:47,324 - algorithms.Algorithm - INFO   - Training epoch [ 80 / 200]
2020-09-07 22:55:47,324 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:55:47,324 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:55:53,048 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][  50 /  469]: {'prec1': 96.2383, 'loss': 0.0869, 'load_time': 43.9904, 'process_time': 56.0096}
2020-09-07 22:55:58,639 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 100 /  469]: {'prec1': 96.2031, 'loss': 0.0904, 'load_time': 44.6937, 'process_time': 55.3063}
2020-09-07 22:56:04,399 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 150 /  469]: {'prec1': 96.1667, 'loss': 0.0907, 'load_time': 46.6478, 'process_time': 53.3522}
2020-09-07 22:56:10,079 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 200 /  469]: {'prec1': 96.123, 'loss': 0.0911, 'load_time': 46.4208, 'process_time': 53.5792}
2020-09-07 22:56:15,784 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 250 /  469]: {'prec1': 96.1148, 'loss': 0.0912, 'load_time': 46.3617, 'process_time': 53.6383}
2020-09-07 22:56:21,562 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 300 /  469]: {'prec1': 96.0573, 'loss': 0.0924, 'load_time': 46.9566, 'process_time': 53.0434}
2020-09-07 22:56:27,280 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 350 /  469]: {'prec1': 95.9955, 'loss': 0.0937, 'load_time': 47.4419, 'process_time': 52.5581}
2020-09-07 22:56:33,055 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 400 /  469]: {'prec1': 95.8955, 'loss': 0.0955, 'load_time': 47.4697, 'process_time': 52.5303}
2020-09-07 22:56:38,833 - algorithms.Algorithm - INFO   - ==> Iteration [ 80][ 450 /  469]: {'prec1': 95.9358, 'loss': 0.095, 'load_time': 47.4133, 'process_time': 52.5867}
2020-09-07 22:56:41,031 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9111, 'loss': 0.0954, 'load_time': 47.5398, 'process_time': 52.4602}
2020-09-07 22:56:41,115 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:56:41,115 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:56:47,585 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.394, 'loss': 0.165, 'load_time': 2.4529, 'process_time': 97.5471}
2020-09-07 22:56:47,585 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.394, 'loss': 0.165, 'load_time': 2.4529, 'process_time': 97.5471}
2020-09-07 22:56:47,585 - algorithms.Algorithm - INFO   - Training epoch [ 81 / 200]
2020-09-07 22:56:47,585 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:56:47,585 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:56:53,182 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][  50 /  469]: {'prec1': 96.2422, 'loss': 0.0886, 'load_time': 42.82, 'process_time': 57.18}
2020-09-07 22:56:58,829 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 100 /  469]: {'prec1': 96.1426, 'loss': 0.0917, 'load_time': 43.0617, 'process_time': 56.9383}
2020-09-07 22:57:04,409 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 150 /  469]: {'prec1': 96.1654, 'loss': 0.0913, 'load_time': 43.0032, 'process_time': 56.9968}
2020-09-07 22:57:10,195 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 200 /  469]: {'prec1': 96.0371, 'loss': 0.0933, 'load_time': 44.2498, 'process_time': 55.7502}
2020-09-07 22:57:15,876 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 250 /  469]: {'prec1': 96.0969, 'loss': 0.0922, 'load_time': 44.3905, 'process_time': 55.6095}
2020-09-07 22:57:21,644 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 300 /  469]: {'prec1': 96.0508, 'loss': 0.0931, 'load_time': 44.5619, 'process_time': 55.4381}
2020-09-07 22:57:27,329 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 350 /  469]: {'prec1': 96.0162, 'loss': 0.094, 'load_time': 45.0703, 'process_time': 54.9297}
2020-09-07 22:57:33,098 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 400 /  469]: {'prec1': 96.0083, 'loss': 0.0941, 'load_time': 45.1787, 'process_time': 54.8213}
2020-09-07 22:57:38,839 - algorithms.Algorithm - INFO   - ==> Iteration [ 81][ 450 /  469]: {'prec1': 96.0091, 'loss': 0.0943, 'load_time': 45.4747, 'process_time': 54.5253}
2020-09-07 22:57:41,038 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0113, 'loss': 0.094, 'load_time': 45.6729, 'process_time': 54.3271}
2020-09-07 22:57:41,118 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:57:41,119 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:57:47,601 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.7388, 'loss': 0.1829, 'load_time': 2.4604, 'process_time': 97.5396}
2020-09-07 22:57:47,602 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.7388, 'loss': 0.1829, 'load_time': 2.4604, 'process_time': 97.5396}
2020-09-07 22:57:47,602 - algorithms.Algorithm - INFO   - Training epoch [ 82 / 200]
2020-09-07 22:57:47,602 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:57:47,602 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:57:53,098 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][  50 /  469]: {'prec1': 96.207, 'loss': 0.0877, 'load_time': 40.0848, 'process_time': 59.9152}
2020-09-07 22:57:58,778 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 100 /  469]: {'prec1': 96.0527, 'loss': 0.0903, 'load_time': 42.4564, 'process_time': 57.5436}
2020-09-07 22:58:04,461 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 150 /  469]: {'prec1': 95.9766, 'loss': 0.0921, 'load_time': 44.2922, 'process_time': 55.7078}
2020-09-07 22:58:10,194 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 200 /  469]: {'prec1': 95.9023, 'loss': 0.094, 'load_time': 45.4855, 'process_time': 54.5145}
2020-09-07 22:58:15,984 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 250 /  469]: {'prec1': 95.9422, 'loss': 0.0938, 'load_time': 46.4198, 'process_time': 53.5802}
2020-09-07 22:58:21,637 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 300 /  469]: {'prec1': 95.9525, 'loss': 0.0936, 'load_time': 46.489, 'process_time': 53.511}
2020-09-07 22:58:27,373 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 350 /  469]: {'prec1': 95.9297, 'loss': 0.0938, 'load_time': 46.7725, 'process_time': 53.2275}
2020-09-07 22:58:33,074 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 400 /  469]: {'prec1': 95.9023, 'loss': 0.0944, 'load_time': 46.7785, 'process_time': 53.2215}
2020-09-07 22:58:38,871 - algorithms.Algorithm - INFO   - ==> Iteration [ 82][ 450 /  469]: {'prec1': 95.9184, 'loss': 0.0946, 'load_time': 47.06, 'process_time': 52.94}
2020-09-07 22:58:41,121 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9138, 'loss': 0.0948, 'load_time': 47.3103, 'process_time': 52.6897}
2020-09-07 22:58:41,202 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:58:41,202 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:58:47,662 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.949, 'loss': 0.1672, 'load_time': 2.4113, 'process_time': 97.5887}
2020-09-07 22:58:47,662 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.949, 'loss': 0.1672, 'load_time': 2.4113, 'process_time': 97.5887}
2020-09-07 22:58:47,662 - algorithms.Algorithm - INFO   - Training epoch [ 83 / 200]
2020-09-07 22:58:47,662 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:58:47,662 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:58:53,258 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][  50 /  469]: {'prec1': 96.2539, 'loss': 0.0891, 'load_time': 41.2491, 'process_time': 58.7509}
2020-09-07 22:58:58,864 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 100 /  469]: {'prec1': 96.2832, 'loss': 0.0872, 'load_time': 43.4774, 'process_time': 56.5226}
2020-09-07 22:59:04,486 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 150 /  469]: {'prec1': 96.2109, 'loss': 0.0884, 'load_time': 43.8841, 'process_time': 56.1159}
2020-09-07 22:59:10,205 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 200 /  469]: {'prec1': 96.1904, 'loss': 0.0892, 'load_time': 44.7678, 'process_time': 55.2322}
2020-09-07 22:59:15,871 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 250 /  469]: {'prec1': 96.1461, 'loss': 0.09, 'load_time': 45.5232, 'process_time': 54.4768}
2020-09-07 22:59:21,578 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 300 /  469]: {'prec1': 96.0625, 'loss': 0.0918, 'load_time': 45.8247, 'process_time': 54.1753}
2020-09-07 22:59:27,345 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 350 /  469]: {'prec1': 96.0502, 'loss': 0.0919, 'load_time': 46.2203, 'process_time': 53.7797}
2020-09-07 22:59:33,091 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 400 /  469]: {'prec1': 96.0161, 'loss': 0.0929, 'load_time': 46.8795, 'process_time': 53.1205}
2020-09-07 22:59:38,847 - algorithms.Algorithm - INFO   - ==> Iteration [ 83][ 450 /  469]: {'prec1': 95.9661, 'loss': 0.0941, 'load_time': 47.2013, 'process_time': 52.7987}
2020-09-07 22:59:41,019 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9705, 'loss': 0.094, 'load_time': 47.2682, 'process_time': 52.7318}
2020-09-07 22:59:41,102 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 22:59:41,102 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 22:59:47,589 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.7685, 'loss': 0.1706, 'load_time': 2.472, 'process_time': 97.528}
2020-09-07 22:59:47,589 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.7685, 'loss': 0.1706, 'load_time': 2.472, 'process_time': 97.528}
2020-09-07 22:59:47,589 - algorithms.Algorithm - INFO   - Training epoch [ 84 / 200]
2020-09-07 22:59:47,589 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 22:59:47,589 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 22:59:53,225 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][  50 /  469]: {'prec1': 95.9258, 'loss': 0.091, 'load_time': 43.5053, 'process_time': 56.4947}
2020-09-07 22:59:58,794 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 100 /  469]: {'prec1': 95.9883, 'loss': 0.0906, 'load_time': 44.7096, 'process_time': 55.2904}
2020-09-07 23:00:04,358 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 150 /  469]: {'prec1': 96.1068, 'loss': 0.0892, 'load_time': 44.3498, 'process_time': 55.6502}
2020-09-07 23:00:10,036 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 200 /  469]: {'prec1': 96.0381, 'loss': 0.0906, 'load_time': 45.0878, 'process_time': 54.9122}
2020-09-07 23:00:15,774 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 250 /  469]: {'prec1': 95.957, 'loss': 0.0928, 'load_time': 46.4055, 'process_time': 53.5945}
2020-09-07 23:00:21,571 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 300 /  469]: {'prec1': 95.9017, 'loss': 0.0943, 'load_time': 47.1598, 'process_time': 52.8402}
2020-09-07 23:00:27,379 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 350 /  469]: {'prec1': 95.9129, 'loss': 0.0943, 'load_time': 47.6565, 'process_time': 52.3435}
2020-09-07 23:00:33,161 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 400 /  469]: {'prec1': 95.9082, 'loss': 0.0945, 'load_time': 48.2279, 'process_time': 51.7721}
2020-09-07 23:00:38,917 - algorithms.Algorithm - INFO   - ==> Iteration [ 84][ 450 /  469]: {'prec1': 95.9531, 'loss': 0.0941, 'load_time': 48.2026, 'process_time': 51.7974}
2020-09-07 23:00:41,081 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9558, 'loss': 0.0942, 'load_time': 48.3088, 'process_time': 51.6912}
2020-09-07 23:00:41,163 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:00:41,163 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:00:47,751 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1344, 'loss': 0.1693, 'load_time': 2.4969, 'process_time': 97.5031}
2020-09-07 23:00:47,751 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1344, 'loss': 0.1693, 'load_time': 2.4969, 'process_time': 97.5031}
2020-09-07 23:00:47,752 - algorithms.Algorithm - INFO   - Training epoch [ 85 / 200]
2020-09-07 23:00:47,752 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:00:47,752 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:00:53,423 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][  50 /  469]: {'prec1': 96.2969, 'loss': 0.0865, 'load_time': 44.3606, 'process_time': 55.6394}
2020-09-07 23:00:59,074 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 100 /  469]: {'prec1': 96.0684, 'loss': 0.0924, 'load_time': 44.9182, 'process_time': 55.0818}
2020-09-07 23:01:04,751 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 150 /  469]: {'prec1': 96.0911, 'loss': 0.0924, 'load_time': 45.4051, 'process_time': 54.5949}
2020-09-07 23:01:10,491 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 200 /  469]: {'prec1': 96.125, 'loss': 0.0916, 'load_time': 45.8607, 'process_time': 54.1393}
2020-09-07 23:01:16,237 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 250 /  469]: {'prec1': 96.1391, 'loss': 0.0919, 'load_time': 46.4227, 'process_time': 53.5773}
2020-09-07 23:01:21,990 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 300 /  469]: {'prec1': 96.1107, 'loss': 0.0926, 'load_time': 46.9612, 'process_time': 53.0388}
2020-09-07 23:01:27,750 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 350 /  469]: {'prec1': 96.072, 'loss': 0.093, 'load_time': 47.0519, 'process_time': 52.9481}
2020-09-07 23:01:33,476 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 400 /  469]: {'prec1': 96.1064, 'loss': 0.0922, 'load_time': 47.0938, 'process_time': 52.9062}
2020-09-07 23:01:39,248 - algorithms.Algorithm - INFO   - ==> Iteration [ 85][ 450 /  469]: {'prec1': 96.0734, 'loss': 0.0928, 'load_time': 47.3262, 'process_time': 52.6738}
2020-09-07 23:01:41,439 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0754, 'loss': 0.0927, 'load_time': 47.3984, 'process_time': 52.6016}
2020-09-07 23:01:41,519 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:01:41,519 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:01:48,084 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.86, 'loss': 0.1835, 'load_time': 2.516, 'process_time': 97.484}
2020-09-07 23:01:48,084 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.86, 'loss': 0.1835, 'load_time': 2.516, 'process_time': 97.484}
2020-09-07 23:01:48,085 - algorithms.Algorithm - INFO   - Training epoch [ 86 / 200]
2020-09-07 23:01:48,085 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:01:48,085 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:01:53,711 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][  50 /  469]: {'prec1': 96.2266, 'loss': 0.091, 'load_time': 42.947, 'process_time': 57.053}
2020-09-07 23:01:59,370 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 100 /  469]: {'prec1': 96.1934, 'loss': 0.0906, 'load_time': 43.7323, 'process_time': 56.2677}
2020-09-07 23:02:04,956 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 150 /  469]: {'prec1': 96.1328, 'loss': 0.091, 'load_time': 45.0937, 'process_time': 54.9063}
2020-09-07 23:02:10,733 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 200 /  469]: {'prec1': 96.0576, 'loss': 0.0924, 'load_time': 46.2464, 'process_time': 53.7536}
2020-09-07 23:02:16,491 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 250 /  469]: {'prec1': 96.0367, 'loss': 0.0925, 'load_time': 46.7854, 'process_time': 53.2146}
2020-09-07 23:02:22,171 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 300 /  469]: {'prec1': 96.0254, 'loss': 0.0929, 'load_time': 46.7044, 'process_time': 53.2956}
2020-09-07 23:02:27,932 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 350 /  469]: {'prec1': 96.0273, 'loss': 0.0929, 'load_time': 46.9537, 'process_time': 53.0463}
2020-09-07 23:02:33,657 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 400 /  469]: {'prec1': 96.0171, 'loss': 0.0932, 'load_time': 46.9262, 'process_time': 53.0738}
2020-09-07 23:02:39,379 - algorithms.Algorithm - INFO   - ==> Iteration [ 86][ 450 /  469]: {'prec1': 95.9865, 'loss': 0.0938, 'load_time': 46.9227, 'process_time': 53.0773}
2020-09-07 23:02:41,545 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.9726, 'loss': 0.0942, 'load_time': 46.8935, 'process_time': 53.1065}
2020-09-07 23:02:41,627 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:02:41,627 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:02:48,154 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3124, 'loss': 0.1728, 'load_time': 2.4872, 'process_time': 97.5128}
2020-09-07 23:02:48,154 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3124, 'loss': 0.1728, 'load_time': 2.4872, 'process_time': 97.5128}
2020-09-07 23:02:48,154 - algorithms.Algorithm - INFO   - Training epoch [ 87 / 200]
2020-09-07 23:02:48,154 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:02:48,154 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:02:53,867 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][  50 /  469]: {'prec1': 96.3438, 'loss': 0.0849, 'load_time': 44.8645, 'process_time': 55.1355}
2020-09-07 23:02:59,550 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 100 /  469]: {'prec1': 96.2695, 'loss': 0.0858, 'load_time': 45.0234, 'process_time': 54.9766}
2020-09-07 23:03:05,209 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 150 /  469]: {'prec1': 96.237, 'loss': 0.0874, 'load_time': 44.8825, 'process_time': 55.1175}
2020-09-07 23:03:10,904 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 200 /  469]: {'prec1': 96.1533, 'loss': 0.0893, 'load_time': 44.8473, 'process_time': 55.1527}
2020-09-07 23:03:16,613 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 250 /  469]: {'prec1': 96.1086, 'loss': 0.0899, 'load_time': 45.4151, 'process_time': 54.5849}
2020-09-07 23:03:22,384 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 300 /  469]: {'prec1': 96.0801, 'loss': 0.0903, 'load_time': 45.6193, 'process_time': 54.3807}
2020-09-07 23:03:28,242 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 350 /  469]: {'prec1': 96.072, 'loss': 0.0906, 'load_time': 46.1702, 'process_time': 53.8298}
2020-09-07 23:03:33,961 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 400 /  469]: {'prec1': 96.0703, 'loss': 0.0905, 'load_time': 46.1163, 'process_time': 53.8837}
2020-09-07 23:03:39,697 - algorithms.Algorithm - INFO   - ==> Iteration [ 87][ 450 /  469]: {'prec1': 96.0252, 'loss': 0.0916, 'load_time': 46.0175, 'process_time': 53.9825}
2020-09-07 23:03:41,823 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0413, 'loss': 0.0914, 'load_time': 45.9768, 'process_time': 54.0232}
2020-09-07 23:03:41,903 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:03:41,903 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:03:48,387 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4509, 'loss': 0.1709, 'load_time': 2.5152, 'process_time': 97.4848}
2020-09-07 23:03:48,387 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4509, 'loss': 0.1709, 'load_time': 2.5152, 'process_time': 97.4848}
2020-09-07 23:03:48,387 - algorithms.Algorithm - INFO   - Training epoch [ 88 / 200]
2020-09-07 23:03:48,387 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:03:48,387 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:03:54,065 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][  50 /  469]: {'prec1': 95.8438, 'loss': 0.0955, 'load_time': 45.4185, 'process_time': 54.5815}
2020-09-07 23:03:59,611 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 100 /  469]: {'prec1': 96.1016, 'loss': 0.0905, 'load_time': 44.5128, 'process_time': 55.4872}
2020-09-07 23:04:05,371 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 150 /  469]: {'prec1': 96.0312, 'loss': 0.0922, 'load_time': 45.5146, 'process_time': 54.4854}
2020-09-07 23:04:11,039 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 200 /  469]: {'prec1': 96.0547, 'loss': 0.0919, 'load_time': 45.2987, 'process_time': 54.7013}
2020-09-07 23:04:16,751 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 250 /  469]: {'prec1': 96.0234, 'loss': 0.0921, 'load_time': 45.9532, 'process_time': 54.0468}
2020-09-07 23:04:22,531 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 300 /  469]: {'prec1': 95.9954, 'loss': 0.0927, 'load_time': 46.4078, 'process_time': 53.5922}
2020-09-07 23:04:28,241 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 350 /  469]: {'prec1': 95.9325, 'loss': 0.0939, 'load_time': 46.7723, 'process_time': 53.2277}
2020-09-07 23:04:33,973 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 400 /  469]: {'prec1': 95.918, 'loss': 0.0941, 'load_time': 46.8847, 'process_time': 53.1153}
2020-09-07 23:04:39,723 - algorithms.Algorithm - INFO   - ==> Iteration [ 88][ 450 /  469]: {'prec1': 95.9327, 'loss': 0.0938, 'load_time': 47.0725, 'process_time': 52.9275}
2020-09-07 23:04:41,891 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 95.963, 'loss': 0.0935, 'load_time': 47.0224, 'process_time': 52.9776}
2020-09-07 23:04:41,970 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:04:41,970 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:04:48,521 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0652, 'loss': 0.1788, 'load_time': 2.4945, 'process_time': 97.5055}
2020-09-07 23:04:48,521 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0652, 'loss': 0.1788, 'load_time': 2.4945, 'process_time': 97.5055}
2020-09-07 23:04:48,521 - algorithms.Algorithm - INFO   - Training epoch [ 89 / 200]
2020-09-07 23:04:48,521 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:04:48,521 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:04:54,131 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][  50 /  469]: {'prec1': 96.0703, 'loss': 0.0941, 'load_time': 44.6859, 'process_time': 55.3141}
2020-09-07 23:04:59,730 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 100 /  469]: {'prec1': 96.127, 'loss': 0.0914, 'load_time': 45.5699, 'process_time': 54.4301}
2020-09-07 23:05:05,409 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 150 /  469]: {'prec1': 96.2109, 'loss': 0.0905, 'load_time': 45.5391, 'process_time': 54.4609}
2020-09-07 23:05:11,164 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 200 /  469]: {'prec1': 96.2373, 'loss': 0.0903, 'load_time': 45.6816, 'process_time': 54.3184}
2020-09-07 23:05:16,919 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 250 /  469]: {'prec1': 96.2305, 'loss': 0.0901, 'load_time': 46.2961, 'process_time': 53.7039}
2020-09-07 23:05:22,676 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 300 /  469]: {'prec1': 96.1953, 'loss': 0.0903, 'load_time': 46.5318, 'process_time': 53.4682}
2020-09-07 23:05:28,437 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 350 /  469]: {'prec1': 96.1568, 'loss': 0.0908, 'load_time': 46.9227, 'process_time': 53.0773}
2020-09-07 23:05:34,180 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 400 /  469]: {'prec1': 96.1064, 'loss': 0.0917, 'load_time': 47.0374, 'process_time': 52.9626}
2020-09-07 23:05:39,895 - algorithms.Algorithm - INFO   - ==> Iteration [ 89][ 450 /  469]: {'prec1': 96.0773, 'loss': 0.0923, 'load_time': 47.2276, 'process_time': 52.7724}
2020-09-07 23:05:42,058 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0833, 'loss': 0.0922, 'load_time': 47.2197, 'process_time': 52.7803}
2020-09-07 23:05:42,140 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:05:42,140 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:05:48,613 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.6177, 'loss': 0.1902, 'load_time': 2.4768, 'process_time': 97.5232}
2020-09-07 23:05:48,613 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.6177, 'loss': 0.1902, 'load_time': 2.4768, 'process_time': 97.5232}
2020-09-07 23:05:48,613 - algorithms.Algorithm - INFO   - Training epoch [ 90 / 200]
2020-09-07 23:05:48,613 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:05:48,614 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:05:54,300 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][  50 /  469]: {'prec1': 96.3398, 'loss': 0.0857, 'load_time': 47.3325, 'process_time': 52.6675}
2020-09-07 23:05:59,868 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 100 /  469]: {'prec1': 96.2852, 'loss': 0.0872, 'load_time': 44.7587, 'process_time': 55.2413}
2020-09-07 23:06:05,543 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 150 /  469]: {'prec1': 96.2357, 'loss': 0.0887, 'load_time': 46.7815, 'process_time': 53.2185}
2020-09-07 23:06:11,194 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 200 /  469]: {'prec1': 96.1514, 'loss': 0.0911, 'load_time': 47.162, 'process_time': 52.838}
2020-09-07 23:06:16,930 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 250 /  469]: {'prec1': 96.1242, 'loss': 0.0916, 'load_time': 47.5087, 'process_time': 52.4913}
2020-09-07 23:06:22,741 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 300 /  469]: {'prec1': 96.071, 'loss': 0.0923, 'load_time': 47.5877, 'process_time': 52.4123}
2020-09-07 23:06:28,434 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 350 /  469]: {'prec1': 96.0915, 'loss': 0.0921, 'load_time': 47.6976, 'process_time': 52.3024}
2020-09-07 23:06:34,230 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 400 /  469]: {'prec1': 96.0898, 'loss': 0.0919, 'load_time': 48.0712, 'process_time': 51.9288}
2020-09-07 23:06:39,987 - algorithms.Algorithm - INFO   - ==> Iteration [ 90][ 450 /  469]: {'prec1': 96.0686, 'loss': 0.0925, 'load_time': 48.3876, 'process_time': 51.6124}
2020-09-07 23:06:42,143 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0479, 'loss': 0.0929, 'load_time': 48.4441, 'process_time': 51.5559}
2020-09-07 23:06:42,225 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:06:42,225 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:06:48,720 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4459, 'loss': 0.1616, 'load_time': 2.4907, 'process_time': 97.5093}
2020-09-07 23:06:48,720 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4459, 'loss': 0.1616, 'load_time': 2.4907, 'process_time': 97.5093}
2020-09-07 23:06:48,720 - algorithms.Algorithm - INFO   - Training epoch [ 91 / 200]
2020-09-07 23:06:48,720 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:06:48,720 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:06:54,376 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][  50 /  469]: {'prec1': 96.5469, 'loss': 0.0812, 'load_time': 43.6533, 'process_time': 56.3467}
2020-09-07 23:07:00,068 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 100 /  469]: {'prec1': 96.377, 'loss': 0.0849, 'load_time': 45.6415, 'process_time': 54.3585}
2020-09-07 23:07:05,742 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 150 /  469]: {'prec1': 96.1927, 'loss': 0.0887, 'load_time': 45.5795, 'process_time': 54.4205}
2020-09-07 23:07:11,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 200 /  469]: {'prec1': 96.1699, 'loss': 0.0894, 'load_time': 46.809, 'process_time': 53.191}
2020-09-07 23:07:17,244 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 250 /  469]: {'prec1': 96.1711, 'loss': 0.0893, 'load_time': 46.8275, 'process_time': 53.1725}
2020-09-07 23:07:23,016 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 300 /  469]: {'prec1': 96.0573, 'loss': 0.0919, 'load_time': 47.3767, 'process_time': 52.6233}
2020-09-07 23:07:28,685 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 350 /  469]: {'prec1': 96.0636, 'loss': 0.0919, 'load_time': 47.1672, 'process_time': 52.8328}
2020-09-07 23:07:34,455 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 400 /  469]: {'prec1': 96.0405, 'loss': 0.0924, 'load_time': 47.2639, 'process_time': 52.7361}
2020-09-07 23:07:40,257 - algorithms.Algorithm - INFO   - ==> Iteration [ 91][ 450 /  469]: {'prec1': 96.0486, 'loss': 0.0922, 'load_time': 47.7994, 'process_time': 52.2006}
2020-09-07 23:07:42,391 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0373, 'loss': 0.0926, 'load_time': 47.5904, 'process_time': 52.4096}
2020-09-07 23:07:42,474 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:07:42,474 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:07:48,942 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1937, 'loss': 0.1655, 'load_time': 2.4983, 'process_time': 97.5017}
2020-09-07 23:07:48,942 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1937, 'loss': 0.1655, 'load_time': 2.4983, 'process_time': 97.5017}
2020-09-07 23:07:48,942 - algorithms.Algorithm - INFO   - Training epoch [ 92 / 200]
2020-09-07 23:07:48,942 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:07:48,942 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:07:54,567 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][  50 /  469]: {'prec1': 95.957, 'loss': 0.0896, 'load_time': 40.8603, 'process_time': 59.1397}
2020-09-07 23:08:00,184 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 100 /  469]: {'prec1': 95.9121, 'loss': 0.091, 'load_time': 43.4477, 'process_time': 56.5523}
2020-09-07 23:08:05,860 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 150 /  469]: {'prec1': 95.8711, 'loss': 0.0931, 'load_time': 43.8645, 'process_time': 56.1355}
2020-09-07 23:08:11,577 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 200 /  469]: {'prec1': 95.9385, 'loss': 0.0926, 'load_time': 45.3789, 'process_time': 54.6211}
2020-09-07 23:08:17,320 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 250 /  469]: {'prec1': 95.9844, 'loss': 0.0916, 'load_time': 46.1185, 'process_time': 53.8815}
2020-09-07 23:08:23,124 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 300 /  469]: {'prec1': 96.026, 'loss': 0.0912, 'load_time': 46.7591, 'process_time': 53.2409}
2020-09-07 23:08:28,921 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 350 /  469]: {'prec1': 96.0435, 'loss': 0.0912, 'load_time': 46.9676, 'process_time': 53.0324}
2020-09-07 23:08:34,779 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 400 /  469]: {'prec1': 96.0371, 'loss': 0.0917, 'load_time': 48.0141, 'process_time': 51.9859}
2020-09-07 23:08:40,540 - algorithms.Algorithm - INFO   - ==> Iteration [ 92][ 450 /  469]: {'prec1': 96.0169, 'loss': 0.0919, 'load_time': 48.3808, 'process_time': 51.6192}
2020-09-07 23:08:42,713 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0224, 'loss': 0.0918, 'load_time': 48.4298, 'process_time': 51.5702}
2020-09-07 23:08:42,794 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:08:42,795 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:08:49,291 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2259, 'loss': 0.1774, 'load_time': 2.5596, 'process_time': 97.4404}
2020-09-07 23:08:49,291 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2259, 'loss': 0.1774, 'load_time': 2.5596, 'process_time': 97.4404}
2020-09-07 23:08:49,291 - algorithms.Algorithm - INFO   - Training epoch [ 93 / 200]
2020-09-07 23:08:49,291 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:08:49,291 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:08:54,914 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][  50 /  469]: {'prec1': 96.2422, 'loss': 0.085, 'load_time': 41.3934, 'process_time': 58.6066}
2020-09-07 23:09:00,480 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 100 /  469]: {'prec1': 96.2305, 'loss': 0.0865, 'load_time': 42.8333, 'process_time': 57.1667}
2020-09-07 23:09:06,243 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 150 /  469]: {'prec1': 96.1888, 'loss': 0.0882, 'load_time': 44.5737, 'process_time': 55.4263}
2020-09-07 23:09:11,926 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 200 /  469]: {'prec1': 96.2178, 'loss': 0.0882, 'load_time': 45.2216, 'process_time': 54.7784}
2020-09-07 23:09:17,626 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 250 /  469]: {'prec1': 96.2672, 'loss': 0.0874, 'load_time': 45.5067, 'process_time': 54.4933}
2020-09-07 23:09:23,370 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 300 /  469]: {'prec1': 96.2285, 'loss': 0.0884, 'load_time': 46.0136, 'process_time': 53.9864}
2020-09-07 23:09:29,092 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 350 /  469]: {'prec1': 96.1975, 'loss': 0.0894, 'load_time': 46.4481, 'process_time': 53.5519}
2020-09-07 23:09:34,876 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 400 /  469]: {'prec1': 96.21, 'loss': 0.0892, 'load_time': 46.5489, 'process_time': 53.4511}
2020-09-07 23:09:40,540 - algorithms.Algorithm - INFO   - ==> Iteration [ 93][ 450 /  469]: {'prec1': 96.1619, 'loss': 0.09, 'load_time': 46.7789, 'process_time': 53.2211}
2020-09-07 23:09:42,747 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1391, 'loss': 0.0902, 'load_time': 46.8808, 'process_time': 53.1192}
2020-09-07 23:09:42,831 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:09:42,831 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:09:49,247 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.6523, 'loss': 0.1809, 'load_time': 2.4795, 'process_time': 97.5205}
2020-09-07 23:09:49,247 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.6523, 'loss': 0.1809, 'load_time': 2.4795, 'process_time': 97.5205}
2020-09-07 23:09:49,247 - algorithms.Algorithm - INFO   - Training epoch [ 94 / 200]
2020-09-07 23:09:49,247 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:09:49,247 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:09:54,912 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][  50 /  469]: {'prec1': 96.1523, 'loss': 0.0902, 'load_time': 44.377, 'process_time': 55.623}
2020-09-07 23:10:00,629 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 100 /  469]: {'prec1': 96.2188, 'loss': 0.0887, 'load_time': 44.4956, 'process_time': 55.5044}
2020-09-07 23:10:06,314 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 150 /  469]: {'prec1': 96.2396, 'loss': 0.0886, 'load_time': 45.1592, 'process_time': 54.8408}
2020-09-07 23:10:12,057 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 200 /  469]: {'prec1': 96.2363, 'loss': 0.0878, 'load_time': 46.3553, 'process_time': 53.6447}
2020-09-07 23:10:17,791 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 250 /  469]: {'prec1': 96.2328, 'loss': 0.0878, 'load_time': 46.4301, 'process_time': 53.5699}
2020-09-07 23:10:23,494 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 300 /  469]: {'prec1': 96.1771, 'loss': 0.0891, 'load_time': 46.5892, 'process_time': 53.4108}
2020-09-07 23:10:29,199 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 350 /  469]: {'prec1': 96.1451, 'loss': 0.0901, 'load_time': 46.8022, 'process_time': 53.1978}
2020-09-07 23:10:34,891 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 400 /  469]: {'prec1': 96.0942, 'loss': 0.0909, 'load_time': 46.9076, 'process_time': 53.0924}
2020-09-07 23:10:40,661 - algorithms.Algorithm - INFO   - ==> Iteration [ 94][ 450 /  469]: {'prec1': 96.0933, 'loss': 0.0911, 'load_time': 46.9279, 'process_time': 53.0721}
2020-09-07 23:10:42,817 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.091, 'loss': 0.091, 'load_time': 47.0463, 'process_time': 52.9537}
2020-09-07 23:10:42,899 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:10:42,899 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:10:49,331 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.6424, 'loss': 0.1965, 'load_time': 2.4805, 'process_time': 97.5195}
2020-09-07 23:10:49,331 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.6424, 'loss': 0.1965, 'load_time': 2.4805, 'process_time': 97.5195}
2020-09-07 23:10:49,331 - algorithms.Algorithm - INFO   - Training epoch [ 95 / 200]
2020-09-07 23:10:49,331 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:10:49,331 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:10:54,940 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][  50 /  469]: {'prec1': 96.3672, 'loss': 0.0849, 'load_time': 42.8662, 'process_time': 57.1338}
2020-09-07 23:11:00,615 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 100 /  469]: {'prec1': 96.5703, 'loss': 0.0824, 'load_time': 45.3967, 'process_time': 54.6033}
2020-09-07 23:11:06,316 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 150 /  469]: {'prec1': 96.388, 'loss': 0.0854, 'load_time': 46.305, 'process_time': 53.695}
2020-09-07 23:11:12,066 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 200 /  469]: {'prec1': 96.3516, 'loss': 0.0864, 'load_time': 46.9018, 'process_time': 53.0982}
2020-09-07 23:11:17,745 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 250 /  469]: {'prec1': 96.3187, 'loss': 0.0866, 'load_time': 47.0931, 'process_time': 52.9069}
2020-09-07 23:11:23,536 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 300 /  469]: {'prec1': 96.2572, 'loss': 0.0881, 'load_time': 47.3955, 'process_time': 52.6045}
2020-09-07 23:11:29,339 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 350 /  469]: {'prec1': 96.2472, 'loss': 0.0882, 'load_time': 47.5287, 'process_time': 52.4713}
2020-09-07 23:11:35,109 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 400 /  469]: {'prec1': 96.1875, 'loss': 0.0891, 'load_time': 47.7575, 'process_time': 52.2425}
2020-09-07 23:11:40,882 - algorithms.Algorithm - INFO   - ==> Iteration [ 95][ 450 /  469]: {'prec1': 96.1267, 'loss': 0.0905, 'load_time': 48.0215, 'process_time': 51.9785}
2020-09-07 23:11:43,074 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1198, 'loss': 0.0906, 'load_time': 48.083, 'process_time': 51.917}
2020-09-07 23:11:43,156 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:11:43,156 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:11:49,693 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1295, 'loss': 0.1726, 'load_time': 2.5026, 'process_time': 97.4974}
2020-09-07 23:11:49,693 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1295, 'loss': 0.1726, 'load_time': 2.5026, 'process_time': 97.4974}
2020-09-07 23:11:49,693 - algorithms.Algorithm - INFO   - Training epoch [ 96 / 200]
2020-09-07 23:11:49,694 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:11:49,694 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:11:55,276 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][  50 /  469]: {'prec1': 96.1992, 'loss': 0.0926, 'load_time': 44.4613, 'process_time': 55.5387}
2020-09-07 23:12:00,951 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 100 /  469]: {'prec1': 96.2539, 'loss': 0.0891, 'load_time': 45.3024, 'process_time': 54.6976}
2020-09-07 23:12:06,531 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 150 /  469]: {'prec1': 96.2227, 'loss': 0.089, 'load_time': 44.9397, 'process_time': 55.0603}
2020-09-07 23:12:12,220 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 200 /  469]: {'prec1': 96.2354, 'loss': 0.0889, 'load_time': 45.7898, 'process_time': 54.2102}
2020-09-07 23:12:17,979 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 250 /  469]: {'prec1': 96.2406, 'loss': 0.0888, 'load_time': 46.7066, 'process_time': 53.2934}
2020-09-07 23:12:23,691 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 300 /  469]: {'prec1': 96.1771, 'loss': 0.0898, 'load_time': 47.1028, 'process_time': 52.8972}
2020-09-07 23:12:29,469 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 350 /  469]: {'prec1': 96.1317, 'loss': 0.0907, 'load_time': 47.3562, 'process_time': 52.6438}
2020-09-07 23:12:35,284 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 400 /  469]: {'prec1': 96.1304, 'loss': 0.0903, 'load_time': 47.5199, 'process_time': 52.4801}
2020-09-07 23:12:41,031 - algorithms.Algorithm - INFO   - ==> Iteration [ 96][ 450 /  469]: {'prec1': 96.1202, 'loss': 0.0907, 'load_time': 47.6533, 'process_time': 52.3467}
2020-09-07 23:12:43,203 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1085, 'loss': 0.0909, 'load_time': 47.8054, 'process_time': 52.1946}
2020-09-07 23:12:43,282 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:12:43,282 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:12:49,772 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.9317, 'loss': 0.176, 'load_time': 2.9205, 'process_time': 97.0795}
2020-09-07 23:12:49,772 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.9317, 'loss': 0.176, 'load_time': 2.9205, 'process_time': 97.0795}
2020-09-07 23:12:49,772 - algorithms.Algorithm - INFO   - Training epoch [ 97 / 200]
2020-09-07 23:12:49,772 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:12:49,772 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:12:55,403 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][  50 /  469]: {'prec1': 96.2461, 'loss': 0.0888, 'load_time': 43.2185, 'process_time': 56.7815}
2020-09-07 23:13:01,039 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 100 /  469]: {'prec1': 96.4004, 'loss': 0.0843, 'load_time': 43.9471, 'process_time': 56.0529}
2020-09-07 23:13:06,785 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 150 /  469]: {'prec1': 96.2513, 'loss': 0.087, 'load_time': 44.8743, 'process_time': 55.1257}
2020-09-07 23:13:12,533 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 200 /  469]: {'prec1': 96.1162, 'loss': 0.0887, 'load_time': 45.9905, 'process_time': 54.0095}
2020-09-07 23:13:18,222 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 250 /  469]: {'prec1': 96.1219, 'loss': 0.0895, 'load_time': 46.0799, 'process_time': 53.9201}
2020-09-07 23:13:23,970 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 300 /  469]: {'prec1': 96.0729, 'loss': 0.0909, 'load_time': 46.1091, 'process_time': 53.8909}
2020-09-07 23:13:29,786 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 350 /  469]: {'prec1': 96.0765, 'loss': 0.091, 'load_time': 47.0777, 'process_time': 52.9223}
2020-09-07 23:13:35,614 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 400 /  469]: {'prec1': 96.1211, 'loss': 0.09, 'load_time': 47.3521, 'process_time': 52.6479}
2020-09-07 23:13:41,347 - algorithms.Algorithm - INFO   - ==> Iteration [ 97][ 450 /  469]: {'prec1': 96.1094, 'loss': 0.0905, 'load_time': 47.2442, 'process_time': 52.7558}
2020-09-07 23:13:43,508 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.0922, 'loss': 0.0908, 'load_time': 47.2951, 'process_time': 52.7049}
2020-09-07 23:13:43,590 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:13:43,590 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:13:50,145 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.6734, 'loss': 0.1608, 'load_time': 2.4823, 'process_time': 97.5177}
2020-09-07 23:13:50,145 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.6734, 'loss': 0.1608, 'load_time': 2.4823, 'process_time': 97.5177}
2020-09-07 23:13:50,145 - algorithms.Algorithm - INFO   - Training epoch [ 98 / 200]
2020-09-07 23:13:50,145 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:13:50,145 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:13:55,772 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][  50 /  469]: {'prec1': 96.4453, 'loss': 0.0844, 'load_time': 43.6359, 'process_time': 56.3641}
2020-09-07 23:14:01,350 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 100 /  469]: {'prec1': 96.4219, 'loss': 0.0848, 'load_time': 43.0104, 'process_time': 56.9896}
2020-09-07 23:14:07,054 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 150 /  469]: {'prec1': 96.4336, 'loss': 0.0845, 'load_time': 44.7375, 'process_time': 55.2625}
2020-09-07 23:14:12,735 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 200 /  469]: {'prec1': 96.4141, 'loss': 0.0853, 'load_time': 45.7069, 'process_time': 54.2931}
2020-09-07 23:14:18,563 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 250 /  469]: {'prec1': 96.3312, 'loss': 0.0871, 'load_time': 46.7884, 'process_time': 53.2116}
2020-09-07 23:14:24,279 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 300 /  469]: {'prec1': 96.2656, 'loss': 0.0876, 'load_time': 47.6143, 'process_time': 52.3857}
2020-09-07 23:14:29,956 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 350 /  469]: {'prec1': 96.2093, 'loss': 0.0886, 'load_time': 47.5931, 'process_time': 52.4069}
2020-09-07 23:14:35,674 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 400 /  469]: {'prec1': 96.1826, 'loss': 0.089, 'load_time': 47.7005, 'process_time': 52.2995}
2020-09-07 23:14:41,385 - algorithms.Algorithm - INFO   - ==> Iteration [ 98][ 450 /  469]: {'prec1': 96.1753, 'loss': 0.0894, 'load_time': 47.5256, 'process_time': 52.4744}
2020-09-07 23:14:43,582 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1844, 'loss': 0.0892, 'load_time': 47.6122, 'process_time': 52.3878}
2020-09-07 23:14:43,665 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:14:43,665 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:14:50,212 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.813, 'loss': 0.1836, 'load_time': 2.526, 'process_time': 97.474}
2020-09-07 23:14:50,212 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.813, 'loss': 0.1836, 'load_time': 2.526, 'process_time': 97.474}
2020-09-07 23:14:50,212 - algorithms.Algorithm - INFO   - Training epoch [ 99 / 200]
2020-09-07 23:14:50,212 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:14:50,212 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:14:55,792 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][  50 /  469]: {'prec1': 96.5938, 'loss': 0.0813, 'load_time': 42.0327, 'process_time': 57.9673}
2020-09-07 23:15:01,373 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 100 /  469]: {'prec1': 96.375, 'loss': 0.0842, 'load_time': 42.2934, 'process_time': 57.7066}
2020-09-07 23:15:07,027 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 150 /  469]: {'prec1': 96.3503, 'loss': 0.0853, 'load_time': 43.0192, 'process_time': 56.9808}
2020-09-07 23:15:12,752 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 200 /  469]: {'prec1': 96.2402, 'loss': 0.0873, 'load_time': 43.454, 'process_time': 56.546}
2020-09-07 23:15:18,549 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 250 /  469]: {'prec1': 96.2508, 'loss': 0.0881, 'load_time': 44.2639, 'process_time': 55.7361}
2020-09-07 23:15:24,304 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 300 /  469]: {'prec1': 96.2435, 'loss': 0.0884, 'load_time': 44.792, 'process_time': 55.208}
2020-09-07 23:15:30,030 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 350 /  469]: {'prec1': 96.2165, 'loss': 0.0887, 'load_time': 45.241, 'process_time': 54.759}
2020-09-07 23:15:35,820 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 400 /  469]: {'prec1': 96.2559, 'loss': 0.088, 'load_time': 45.8606, 'process_time': 54.1394}
2020-09-07 23:15:41,570 - algorithms.Algorithm - INFO   - ==> Iteration [ 99][ 450 /  469]: {'prec1': 96.2283, 'loss': 0.0889, 'load_time': 46.1274, 'process_time': 53.8726}
2020-09-07 23:15:43,748 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.197, 'loss': 0.0893, 'load_time': 46.2129, 'process_time': 53.7871}
2020-09-07 23:15:43,834 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:15:43,834 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:15:50,295 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1715, 'loss': 0.171, 'load_time': 2.539, 'process_time': 97.461}
2020-09-07 23:15:50,295 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1715, 'loss': 0.171, 'load_time': 2.539, 'process_time': 97.461}
2020-09-07 23:15:50,295 - algorithms.Algorithm - INFO   - Training epoch [100 / 200]
2020-09-07 23:15:50,295 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:15:50,295 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:15:55,848 - algorithms.Algorithm - INFO   - ==> Iteration [100][  50 /  469]: {'prec1': 96.5703, 'loss': 0.0796, 'load_time': 40.1084, 'process_time': 59.8916}
2020-09-07 23:16:01,528 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 100 /  469]: {'prec1': 96.3379, 'loss': 0.0832, 'load_time': 42.6906, 'process_time': 57.3094}
2020-09-07 23:16:07,212 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 150 /  469]: {'prec1': 96.2409, 'loss': 0.0861, 'load_time': 44.1011, 'process_time': 55.8989}
2020-09-07 23:16:13,024 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 200 /  469]: {'prec1': 96.2363, 'loss': 0.0863, 'load_time': 45.0961, 'process_time': 54.9039}
2020-09-07 23:16:18,787 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 250 /  469]: {'prec1': 96.1523, 'loss': 0.0882, 'load_time': 46.0517, 'process_time': 53.9483}
2020-09-07 23:16:24,519 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 300 /  469]: {'prec1': 96.181, 'loss': 0.0883, 'load_time': 46.008, 'process_time': 53.992}
2020-09-07 23:16:30,313 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 350 /  469]: {'prec1': 96.202, 'loss': 0.0881, 'load_time': 46.7702, 'process_time': 53.2298}
2020-09-07 23:16:35,986 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 400 /  469]: {'prec1': 96.1968, 'loss': 0.0883, 'load_time': 46.7439, 'process_time': 53.2561}
2020-09-07 23:16:41,695 - algorithms.Algorithm - INFO   - ==> Iteration [100][ 450 /  469]: {'prec1': 96.1918, 'loss': 0.0886, 'load_time': 46.7266, 'process_time': 53.2734}
2020-09-07 23:16:43,863 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1931, 'loss': 0.0887, 'load_time': 46.7075, 'process_time': 53.2925}
2020-09-07 23:16:43,943 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:16:43,944 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:16:50,431 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1838, 'loss': 0.1704, 'load_time': 2.5149, 'process_time': 97.4851}
2020-09-07 23:16:50,431 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1838, 'loss': 0.1704, 'load_time': 2.5149, 'process_time': 97.4851}
2020-09-07 23:16:50,431 - algorithms.Algorithm - INFO   - Training epoch [101 / 200]
2020-09-07 23:16:50,431 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:16:50,432 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:16:56,110 - algorithms.Algorithm - INFO   - ==> Iteration [101][  50 /  469]: {'prec1': 96.0977, 'loss': 0.0885, 'load_time': 43.4565, 'process_time': 56.5435}
2020-09-07 23:17:01,770 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 100 /  469]: {'prec1': 96.0527, 'loss': 0.0902, 'load_time': 44.4014, 'process_time': 55.5986}
2020-09-07 23:17:07,452 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 150 /  469]: {'prec1': 96.0898, 'loss': 0.0899, 'load_time': 44.6669, 'process_time': 55.3331}
2020-09-07 23:17:13,113 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 200 /  469]: {'prec1': 96.123, 'loss': 0.0899, 'load_time': 44.8231, 'process_time': 55.1769}
2020-09-07 23:17:18,864 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 250 /  469]: {'prec1': 96.0922, 'loss': 0.0901, 'load_time': 45.632, 'process_time': 54.368}
2020-09-07 23:17:24,599 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 300 /  469]: {'prec1': 96.0651, 'loss': 0.0904, 'load_time': 46.2992, 'process_time': 53.7008}
2020-09-07 23:17:30,356 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 350 /  469]: {'prec1': 96.0647, 'loss': 0.0908, 'load_time': 46.4061, 'process_time': 53.5939}
2020-09-07 23:17:36,085 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 400 /  469]: {'prec1': 96.1118, 'loss': 0.0897, 'load_time': 46.4715, 'process_time': 53.5285}
2020-09-07 23:17:41,885 - algorithms.Algorithm - INFO   - ==> Iteration [101][ 450 /  469]: {'prec1': 96.1506, 'loss': 0.0893, 'load_time': 47.092, 'process_time': 52.908}
2020-09-07 23:17:44,012 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1644, 'loss': 0.089, 'load_time': 47.1833, 'process_time': 52.8167}
2020-09-07 23:17:44,094 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:17:44,095 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:17:50,550 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.8971, 'loss': 0.1828, 'load_time': 2.4572, 'process_time': 97.5428}
2020-09-07 23:17:50,551 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.8971, 'loss': 0.1828, 'load_time': 2.4572, 'process_time': 97.5428}
2020-09-07 23:17:50,551 - algorithms.Algorithm - INFO   - Training epoch [102 / 200]
2020-09-07 23:17:50,551 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:17:50,551 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:17:56,099 - algorithms.Algorithm - INFO   - ==> Iteration [102][  50 /  469]: {'prec1': 96.4883, 'loss': 0.0824, 'load_time': 41.3248, 'process_time': 58.6752}
2020-09-07 23:18:01,721 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 100 /  469]: {'prec1': 96.5039, 'loss': 0.0828, 'load_time': 42.5746, 'process_time': 57.4254}
2020-09-07 23:18:07,407 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 150 /  469]: {'prec1': 96.3464, 'loss': 0.0859, 'load_time': 43.2033, 'process_time': 56.7967}
2020-09-07 23:18:13,094 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 200 /  469]: {'prec1': 96.3721, 'loss': 0.0852, 'load_time': 44.0981, 'process_time': 55.9019}
2020-09-07 23:18:18,758 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 250 /  469]: {'prec1': 96.3758, 'loss': 0.0855, 'load_time': 44.2473, 'process_time': 55.7527}
2020-09-07 23:18:24,516 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 300 /  469]: {'prec1': 96.2988, 'loss': 0.0864, 'load_time': 44.7488, 'process_time': 55.2512}
2020-09-07 23:18:30,350 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 350 /  469]: {'prec1': 96.2701, 'loss': 0.0867, 'load_time': 45.5502, 'process_time': 54.4498}
2020-09-07 23:18:36,093 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 400 /  469]: {'prec1': 96.2266, 'loss': 0.0881, 'load_time': 45.704, 'process_time': 54.296}
2020-09-07 23:18:41,900 - algorithms.Algorithm - INFO   - ==> Iteration [102][ 450 /  469]: {'prec1': 96.1979, 'loss': 0.0889, 'load_time': 46.1848, 'process_time': 53.8152}
2020-09-07 23:18:44,004 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2122, 'loss': 0.0887, 'load_time': 46.2838, 'process_time': 53.7162}
2020-09-07 23:18:44,086 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:18:44,087 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:18:50,570 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1937, 'loss': 0.1742, 'load_time': 2.4604, 'process_time': 97.5396}
2020-09-07 23:18:50,570 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1937, 'loss': 0.1742, 'load_time': 2.4604, 'process_time': 97.5396}
2020-09-07 23:18:50,570 - algorithms.Algorithm - INFO   - Training epoch [103 / 200]
2020-09-07 23:18:50,570 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:18:50,570 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:18:56,170 - algorithms.Algorithm - INFO   - ==> Iteration [103][  50 /  469]: {'prec1': 96.5586, 'loss': 0.0824, 'load_time': 41.7666, 'process_time': 58.2334}
2020-09-07 23:19:01,849 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 100 /  469]: {'prec1': 96.5996, 'loss': 0.0827, 'load_time': 43.5889, 'process_time': 56.4111}
2020-09-07 23:19:07,536 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 150 /  469]: {'prec1': 96.3958, 'loss': 0.0867, 'load_time': 43.5021, 'process_time': 56.4979}
2020-09-07 23:19:13,191 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 200 /  469]: {'prec1': 96.3135, 'loss': 0.0867, 'load_time': 44.5205, 'process_time': 55.4795}
2020-09-07 23:19:18,882 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 250 /  469]: {'prec1': 96.1977, 'loss': 0.0888, 'load_time': 45.3312, 'process_time': 54.6688}
2020-09-07 23:19:24,721 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 300 /  469]: {'prec1': 96.1908, 'loss': 0.0892, 'load_time': 45.8614, 'process_time': 54.1386}
2020-09-07 23:19:30,493 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 350 /  469]: {'prec1': 96.1886, 'loss': 0.0894, 'load_time': 45.657, 'process_time': 54.343}
2020-09-07 23:19:36,193 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 400 /  469]: {'prec1': 96.1772, 'loss': 0.0891, 'load_time': 45.7722, 'process_time': 54.2278}
2020-09-07 23:19:41,923 - algorithms.Algorithm - INFO   - ==> Iteration [103][ 450 /  469]: {'prec1': 96.1966, 'loss': 0.0887, 'load_time': 45.9298, 'process_time': 54.0702}
2020-09-07 23:19:44,129 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.1979, 'loss': 0.0885, 'load_time': 46.1596, 'process_time': 53.8404}
2020-09-07 23:19:44,211 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:19:44,211 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:19:50,748 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0899, 'loss': 0.1716, 'load_time': 2.4578, 'process_time': 97.5422}
2020-09-07 23:19:50,749 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0899, 'loss': 0.1716, 'load_time': 2.4578, 'process_time': 97.5422}
2020-09-07 23:19:50,749 - algorithms.Algorithm - INFO   - Training epoch [104 / 200]
2020-09-07 23:19:50,749 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:19:50,749 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:19:56,371 - algorithms.Algorithm - INFO   - ==> Iteration [104][  50 /  469]: {'prec1': 96.2031, 'loss': 0.089, 'load_time': 43.6217, 'process_time': 56.3783}
2020-09-07 23:20:01,957 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 100 /  469]: {'prec1': 96.0781, 'loss': 0.091, 'load_time': 43.6456, 'process_time': 56.3544}
2020-09-07 23:20:07,565 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 150 /  469]: {'prec1': 96.1133, 'loss': 0.0901, 'load_time': 43.0171, 'process_time': 56.9829}
2020-09-07 23:20:13,273 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 200 /  469]: {'prec1': 96.2529, 'loss': 0.088, 'load_time': 44.1635, 'process_time': 55.8365}
2020-09-07 23:20:18,980 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 250 /  469]: {'prec1': 96.2047, 'loss': 0.0891, 'load_time': 45.131, 'process_time': 54.869}
2020-09-07 23:20:24,694 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 300 /  469]: {'prec1': 96.1979, 'loss': 0.09, 'load_time': 45.7523, 'process_time': 54.2477}
2020-09-07 23:20:30,439 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 350 /  469]: {'prec1': 96.2199, 'loss': 0.09, 'load_time': 45.701, 'process_time': 54.299}
2020-09-07 23:20:36,194 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 400 /  469]: {'prec1': 96.2471, 'loss': 0.0892, 'load_time': 45.8796, 'process_time': 54.1204}
2020-09-07 23:20:41,905 - algorithms.Algorithm - INFO   - ==> Iteration [104][ 450 /  469]: {'prec1': 96.2287, 'loss': 0.0892, 'load_time': 46.117, 'process_time': 53.883}
2020-09-07 23:20:44,066 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2287, 'loss': 0.089, 'load_time': 46.1932, 'process_time': 53.8068}
2020-09-07 23:20:44,147 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:20:44,148 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:20:50,662 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0775, 'loss': 0.1832, 'load_time': 2.5178, 'process_time': 97.4822}
2020-09-07 23:20:50,662 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0775, 'loss': 0.1832, 'load_time': 2.5178, 'process_time': 97.4822}
2020-09-07 23:20:50,663 - algorithms.Algorithm - INFO   - Training epoch [105 / 200]
2020-09-07 23:20:50,663 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:20:50,663 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:20:56,312 - algorithms.Algorithm - INFO   - ==> Iteration [105][  50 /  469]: {'prec1': 96.4727, 'loss': 0.0807, 'load_time': 44.0173, 'process_time': 55.9827}
2020-09-07 23:21:01,864 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 100 /  469]: {'prec1': 96.4512, 'loss': 0.0814, 'load_time': 43.852, 'process_time': 56.148}
2020-09-07 23:21:07,564 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 150 /  469]: {'prec1': 96.4232, 'loss': 0.0835, 'load_time': 45.0919, 'process_time': 54.9081}
2020-09-07 23:21:13,238 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 200 /  469]: {'prec1': 96.3623, 'loss': 0.0846, 'load_time': 46.113, 'process_time': 53.887}
2020-09-07 23:21:18,991 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 250 /  469]: {'prec1': 96.3219, 'loss': 0.0858, 'load_time': 47.358, 'process_time': 52.642}
2020-09-07 23:21:24,750 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 300 /  469]: {'prec1': 96.3457, 'loss': 0.086, 'load_time': 47.8621, 'process_time': 52.1379}
2020-09-07 23:21:30,458 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 350 /  469]: {'prec1': 96.3672, 'loss': 0.0856, 'load_time': 47.4674, 'process_time': 52.5326}
2020-09-07 23:21:36,217 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 400 /  469]: {'prec1': 96.3291, 'loss': 0.0865, 'load_time': 47.2558, 'process_time': 52.7442}
2020-09-07 23:21:41,952 - algorithms.Algorithm - INFO   - ==> Iteration [105][ 450 /  469]: {'prec1': 96.2344, 'loss': 0.0884, 'load_time': 47.1779, 'process_time': 52.8221}
2020-09-07 23:21:44,162 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2398, 'loss': 0.0882, 'load_time': 47.345, 'process_time': 52.655}
2020-09-07 23:21:44,242 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:21:44,242 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:21:50,691 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2926, 'loss': 0.1735, 'load_time': 2.8904, 'process_time': 97.1096}
2020-09-07 23:21:50,691 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2926, 'loss': 0.1735, 'load_time': 2.8904, 'process_time': 97.1096}
2020-09-07 23:21:50,691 - algorithms.Algorithm - INFO   - Training epoch [106 / 200]
2020-09-07 23:21:50,691 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:21:50,691 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:21:56,451 - algorithms.Algorithm - INFO   - ==> Iteration [106][  50 /  469]: {'prec1': 96.625, 'loss': 0.0798, 'load_time': 47.9209, 'process_time': 52.0791}
2020-09-07 23:22:02,046 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 100 /  469]: {'prec1': 96.4473, 'loss': 0.0822, 'load_time': 45.3417, 'process_time': 54.6583}
2020-09-07 23:22:07,677 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 150 /  469]: {'prec1': 96.4805, 'loss': 0.0828, 'load_time': 44.6993, 'process_time': 55.3007}
2020-09-07 23:22:13,477 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 200 /  469]: {'prec1': 96.4062, 'loss': 0.0842, 'load_time': 46.7612, 'process_time': 53.2388}
2020-09-07 23:22:19,156 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 250 /  469]: {'prec1': 96.3516, 'loss': 0.0847, 'load_time': 46.5554, 'process_time': 53.4446}
2020-09-07 23:22:24,902 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 300 /  469]: {'prec1': 96.3535, 'loss': 0.0854, 'load_time': 47.1251, 'process_time': 52.8749}
2020-09-07 23:22:30,670 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 350 /  469]: {'prec1': 96.3337, 'loss': 0.0857, 'load_time': 47.5486, 'process_time': 52.4514}
2020-09-07 23:22:36,448 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 400 /  469]: {'prec1': 96.2939, 'loss': 0.0872, 'load_time': 47.6422, 'process_time': 52.3578}
2020-09-07 23:22:42,160 - algorithms.Algorithm - INFO   - ==> Iteration [106][ 450 /  469]: {'prec1': 96.2865, 'loss': 0.0874, 'load_time': 47.4546, 'process_time': 52.5454}
2020-09-07 23:22:44,331 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2798, 'loss': 0.0876, 'load_time': 47.4123, 'process_time': 52.5877}
2020-09-07 23:22:44,411 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:22:44,412 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:22:50,866 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2902, 'loss': 0.1704, 'load_time': 2.4846, 'process_time': 97.5154}
2020-09-07 23:22:50,866 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2902, 'loss': 0.1704, 'load_time': 2.4846, 'process_time': 97.5154}
2020-09-07 23:22:50,866 - algorithms.Algorithm - INFO   - Training epoch [107 / 200]
2020-09-07 23:22:50,866 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:22:50,866 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:22:56,495 - algorithms.Algorithm - INFO   - ==> Iteration [107][  50 /  469]: {'prec1': 96.3086, 'loss': 0.0875, 'load_time': 39.1506, 'process_time': 60.8494}
2020-09-07 23:23:02,160 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 100 /  469]: {'prec1': 96.4648, 'loss': 0.082, 'load_time': 42.2889, 'process_time': 57.7111}
2020-09-07 23:23:07,810 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 150 /  469]: {'prec1': 96.3698, 'loss': 0.0834, 'load_time': 42.637, 'process_time': 57.363}
2020-09-07 23:23:13,449 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 200 /  469]: {'prec1': 96.3789, 'loss': 0.0838, 'load_time': 42.9343, 'process_time': 57.0657}
2020-09-07 23:23:19,201 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 250 /  469]: {'prec1': 96.3391, 'loss': 0.0845, 'load_time': 44.197, 'process_time': 55.803}
2020-09-07 23:23:24,944 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 300 /  469]: {'prec1': 96.3171, 'loss': 0.0853, 'load_time': 44.6634, 'process_time': 55.3366}
2020-09-07 23:23:30,663 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 350 /  469]: {'prec1': 96.2985, 'loss': 0.0857, 'load_time': 45.1816, 'process_time': 54.8184}
2020-09-07 23:23:36,478 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 400 /  469]: {'prec1': 96.2974, 'loss': 0.0862, 'load_time': 45.4521, 'process_time': 54.5479}
2020-09-07 23:23:42,200 - algorithms.Algorithm - INFO   - ==> Iteration [107][ 450 /  469]: {'prec1': 96.3025, 'loss': 0.0862, 'load_time': 45.47, 'process_time': 54.53}
2020-09-07 23:23:44,361 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2828, 'loss': 0.0864, 'load_time': 45.7025, 'process_time': 54.2975}
2020-09-07 23:23:44,442 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:23:44,443 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:23:50,915 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1369, 'loss': 0.178, 'load_time': 2.4999, 'process_time': 97.5001}
2020-09-07 23:23:50,915 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1369, 'loss': 0.178, 'load_time': 2.4999, 'process_time': 97.5001}
2020-09-07 23:23:50,915 - algorithms.Algorithm - INFO   - Training epoch [108 / 200]
2020-09-07 23:23:50,915 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:23:50,915 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:23:56,488 - algorithms.Algorithm - INFO   - ==> Iteration [108][  50 /  469]: {'prec1': 96.7578, 'loss': 0.0778, 'load_time': 39.7424, 'process_time': 60.2576}
2020-09-07 23:24:02,044 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 100 /  469]: {'prec1': 96.6641, 'loss': 0.079, 'load_time': 40.3327, 'process_time': 59.6673}
2020-09-07 23:24:07,781 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 150 /  469]: {'prec1': 96.4909, 'loss': 0.0826, 'load_time': 42.0105, 'process_time': 57.9895}
2020-09-07 23:24:13,441 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 200 /  469]: {'prec1': 96.5, 'loss': 0.0831, 'load_time': 43.1839, 'process_time': 56.8161}
2020-09-07 23:24:19,192 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 250 /  469]: {'prec1': 96.4672, 'loss': 0.0838, 'load_time': 44.4066, 'process_time': 55.5934}
2020-09-07 23:24:24,883 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 300 /  469]: {'prec1': 96.3919, 'loss': 0.0852, 'load_time': 45.0246, 'process_time': 54.9754}
2020-09-07 23:24:30,656 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 350 /  469]: {'prec1': 96.3705, 'loss': 0.0855, 'load_time': 45.6843, 'process_time': 54.3157}
2020-09-07 23:24:36,474 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 400 /  469]: {'prec1': 96.3403, 'loss': 0.0862, 'load_time': 45.7396, 'process_time': 54.2604}
2020-09-07 23:24:42,264 - algorithms.Algorithm - INFO   - ==> Iteration [108][ 450 /  469]: {'prec1': 96.3177, 'loss': 0.0866, 'load_time': 46.0397, 'process_time': 53.9603}
2020-09-07 23:24:44,440 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2984, 'loss': 0.0869, 'load_time': 46.2833, 'process_time': 53.7167}
2020-09-07 23:24:44,520 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:24:44,521 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:24:50,983 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.9861, 'loss': 0.1817, 'load_time': 2.4979, 'process_time': 97.5021}
2020-09-07 23:24:50,983 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.9861, 'loss': 0.1817, 'load_time': 2.4979, 'process_time': 97.5021}
2020-09-07 23:24:50,983 - algorithms.Algorithm - INFO   - Training epoch [109 / 200]
2020-09-07 23:24:50,984 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:24:50,984 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:24:56,598 - algorithms.Algorithm - INFO   - ==> Iteration [109][  50 /  469]: {'prec1': 96.457, 'loss': 0.0824, 'load_time': 42.0907, 'process_time': 57.9093}
2020-09-07 23:25:02,318 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 100 /  469]: {'prec1': 96.4668, 'loss': 0.0816, 'load_time': 42.7558, 'process_time': 57.2442}
2020-09-07 23:25:07,978 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 150 /  469]: {'prec1': 96.5781, 'loss': 0.0794, 'load_time': 44.1345, 'process_time': 55.8655}
2020-09-07 23:25:13,675 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 200 /  469]: {'prec1': 96.5635, 'loss': 0.0799, 'load_time': 44.4564, 'process_time': 55.5436}
2020-09-07 23:25:19,410 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 250 /  469]: {'prec1': 96.4945, 'loss': 0.0821, 'load_time': 44.7957, 'process_time': 55.2043}
2020-09-07 23:25:25,134 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 300 /  469]: {'prec1': 96.4453, 'loss': 0.0834, 'load_time': 45.2398, 'process_time': 54.7602}
2020-09-07 23:25:30,897 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 350 /  469]: {'prec1': 96.3627, 'loss': 0.085, 'load_time': 45.8849, 'process_time': 54.1151}
2020-09-07 23:25:36,630 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 400 /  469]: {'prec1': 96.3135, 'loss': 0.0862, 'load_time': 45.7781, 'process_time': 54.2219}
2020-09-07 23:25:42,344 - algorithms.Algorithm - INFO   - ==> Iteration [109][ 450 /  469]: {'prec1': 96.2639, 'loss': 0.0872, 'load_time': 45.9227, 'process_time': 54.0773}
2020-09-07 23:25:44,567 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2581, 'loss': 0.0872, 'load_time': 45.9968, 'process_time': 54.0032}
2020-09-07 23:25:44,649 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:25:44,649 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:25:51,145 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.7129, 'loss': 0.1591, 'load_time': 2.8596, 'process_time': 97.1404}
2020-09-07 23:25:51,145 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.7129, 'loss': 0.1591, 'load_time': 2.8596, 'process_time': 97.1404}
2020-09-07 23:25:51,146 - algorithms.Algorithm - INFO   - Training epoch [110 / 200]
2020-09-07 23:25:51,146 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:25:51,146 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:25:56,717 - algorithms.Algorithm - INFO   - ==> Iteration [110][  50 /  469]: {'prec1': 96.6562, 'loss': 0.0774, 'load_time': 42.8015, 'process_time': 57.1985}
2020-09-07 23:26:02,286 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 100 /  469]: {'prec1': 96.4199, 'loss': 0.0841, 'load_time': 41.9245, 'process_time': 58.0755}
2020-09-07 23:26:08,034 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 150 /  469]: {'prec1': 96.2604, 'loss': 0.0859, 'load_time': 42.5955, 'process_time': 57.4045}
2020-09-07 23:26:13,687 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 200 /  469]: {'prec1': 96.3428, 'loss': 0.0841, 'load_time': 43.3789, 'process_time': 56.6211}
2020-09-07 23:26:19,473 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 250 /  469]: {'prec1': 96.3695, 'loss': 0.0845, 'load_time': 44.3125, 'process_time': 55.6875}
2020-09-07 23:26:25,149 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 300 /  469]: {'prec1': 96.3952, 'loss': 0.0842, 'load_time': 44.594, 'process_time': 55.406}
2020-09-07 23:26:30,925 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 350 /  469]: {'prec1': 96.3778, 'loss': 0.0846, 'load_time': 45.0825, 'process_time': 54.9175}
2020-09-07 23:26:36,584 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 400 /  469]: {'prec1': 96.3345, 'loss': 0.0849, 'load_time': 45.2285, 'process_time': 54.7715}
2020-09-07 23:26:42,319 - algorithms.Algorithm - INFO   - ==> Iteration [110][ 450 /  469]: {'prec1': 96.2852, 'loss': 0.0858, 'load_time': 45.5351, 'process_time': 54.4649}
2020-09-07 23:26:44,504 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.275, 'loss': 0.0861, 'load_time': 45.737, 'process_time': 54.263}
2020-09-07 23:26:44,584 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:26:44,584 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:26:51,030 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.9984, 'loss': 0.1777, 'load_time': 2.5254, 'process_time': 97.4746}
2020-09-07 23:26:51,030 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.9984, 'loss': 0.1777, 'load_time': 2.5254, 'process_time': 97.4746}
2020-09-07 23:26:51,030 - algorithms.Algorithm - INFO   - Training epoch [111 / 200]
2020-09-07 23:26:51,030 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:26:51,030 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:26:56,771 - algorithms.Algorithm - INFO   - ==> Iteration [111][  50 /  469]: {'prec1': 96.668, 'loss': 0.0795, 'load_time': 43.7501, 'process_time': 56.2499}
2020-09-07 23:27:02,377 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 100 /  469]: {'prec1': 96.5469, 'loss': 0.0822, 'load_time': 42.7426, 'process_time': 57.2574}
2020-09-07 23:27:08,073 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 150 /  469]: {'prec1': 96.4792, 'loss': 0.0833, 'load_time': 44.71, 'process_time': 55.29}
2020-09-07 23:27:13,793 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 200 /  469]: {'prec1': 96.374, 'loss': 0.0847, 'load_time': 46.4999, 'process_time': 53.5001}
2020-09-07 23:27:19,437 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 250 /  469]: {'prec1': 96.4125, 'loss': 0.0841, 'load_time': 46.5018, 'process_time': 53.4982}
2020-09-07 23:27:25,284 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 300 /  469]: {'prec1': 96.3418, 'loss': 0.0853, 'load_time': 47.4357, 'process_time': 52.5643}
2020-09-07 23:27:31,056 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 350 /  469]: {'prec1': 96.3158, 'loss': 0.0864, 'load_time': 47.9043, 'process_time': 52.0957}
2020-09-07 23:27:36,889 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 400 /  469]: {'prec1': 96.3105, 'loss': 0.0864, 'load_time': 47.7371, 'process_time': 52.2629}
2020-09-07 23:27:42,624 - algorithms.Algorithm - INFO   - ==> Iteration [111][ 450 /  469]: {'prec1': 96.237, 'loss': 0.0879, 'load_time': 48.064, 'process_time': 51.936}
2020-09-07 23:27:44,819 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2048, 'loss': 0.0884, 'load_time': 48.1296, 'process_time': 51.8704}
2020-09-07 23:27:44,898 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:27:44,898 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:27:51,331 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.7017, 'loss': 0.1865, 'load_time': 2.5044, 'process_time': 97.4956}
2020-09-07 23:27:51,331 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.7017, 'loss': 0.1865, 'load_time': 2.5044, 'process_time': 97.4956}
2020-09-07 23:27:51,331 - algorithms.Algorithm - INFO   - Training epoch [112 / 200]
2020-09-07 23:27:51,331 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:27:51,331 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:27:56,971 - algorithms.Algorithm - INFO   - ==> Iteration [112][  50 /  469]: {'prec1': 96.4648, 'loss': 0.0837, 'load_time': 43.536, 'process_time': 56.464}
2020-09-07 23:28:02,608 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 100 /  469]: {'prec1': 96.5254, 'loss': 0.0833, 'load_time': 43.6468, 'process_time': 56.3532}
2020-09-07 23:28:08,269 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 150 /  469]: {'prec1': 96.5208, 'loss': 0.0831, 'load_time': 45.4107, 'process_time': 54.5893}
2020-09-07 23:28:13,972 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 200 /  469]: {'prec1': 96.4658, 'loss': 0.0838, 'load_time': 45.9673, 'process_time': 54.0327}
2020-09-07 23:28:19,699 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 250 /  469]: {'prec1': 96.4141, 'loss': 0.0846, 'load_time': 45.9303, 'process_time': 54.0697}
2020-09-07 23:28:25,430 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 300 /  469]: {'prec1': 96.3275, 'loss': 0.0855, 'load_time': 46.3527, 'process_time': 53.6473}
2020-09-07 23:28:31,144 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 350 /  469]: {'prec1': 96.3343, 'loss': 0.0859, 'load_time': 46.2501, 'process_time': 53.7499}
2020-09-07 23:28:36,935 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 400 /  469]: {'prec1': 96.311, 'loss': 0.0863, 'load_time': 46.3346, 'process_time': 53.6654}
2020-09-07 23:28:42,659 - algorithms.Algorithm - INFO   - ==> Iteration [112][ 450 /  469]: {'prec1': 96.2704, 'loss': 0.0872, 'load_time': 46.3825, 'process_time': 53.6175}
2020-09-07 23:28:44,818 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2646, 'loss': 0.0871, 'load_time': 46.2894, 'process_time': 53.7106}
2020-09-07 23:28:44,900 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:28:44,900 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:28:51,381 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1764, 'loss': 0.1786, 'load_time': 2.4929, 'process_time': 97.5071}
2020-09-07 23:28:51,381 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1764, 'loss': 0.1786, 'load_time': 2.4929, 'process_time': 97.5071}
2020-09-07 23:28:51,381 - algorithms.Algorithm - INFO   - Training epoch [113 / 200]
2020-09-07 23:28:51,381 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:28:51,381 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:28:57,072 - algorithms.Algorithm - INFO   - ==> Iteration [113][  50 /  469]: {'prec1': 96.7578, 'loss': 0.0764, 'load_time': 40.9847, 'process_time': 59.0153}
2020-09-07 23:29:02,698 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 100 /  469]: {'prec1': 96.6289, 'loss': 0.079, 'load_time': 42.2068, 'process_time': 57.7932}
2020-09-07 23:29:08,409 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 150 /  469]: {'prec1': 96.5299, 'loss': 0.0814, 'load_time': 43.6114, 'process_time': 56.3886}
2020-09-07 23:29:14,144 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 200 /  469]: {'prec1': 96.4277, 'loss': 0.0831, 'load_time': 44.8664, 'process_time': 55.1336}
2020-09-07 23:29:19,917 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 250 /  469]: {'prec1': 96.4391, 'loss': 0.0825, 'load_time': 45.7603, 'process_time': 54.2397}
2020-09-07 23:29:25,620 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 300 /  469]: {'prec1': 96.4069, 'loss': 0.0835, 'load_time': 45.8389, 'process_time': 54.1611}
2020-09-07 23:29:31,347 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 350 /  469]: {'prec1': 96.3225, 'loss': 0.0848, 'load_time': 45.9255, 'process_time': 54.0745}
2020-09-07 23:29:37,157 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 400 /  469]: {'prec1': 96.2944, 'loss': 0.0859, 'load_time': 46.249, 'process_time': 53.751}
2020-09-07 23:29:42,946 - algorithms.Algorithm - INFO   - ==> Iteration [113][ 450 /  469]: {'prec1': 96.3016, 'loss': 0.086, 'load_time': 46.5312, 'process_time': 53.4688}
2020-09-07 23:29:45,060 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2981, 'loss': 0.0863, 'load_time': 46.343, 'process_time': 53.657}
2020-09-07 23:29:45,140 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:29:45,141 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:29:51,638 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1369, 'loss': 0.1747, 'load_time': 2.5101, 'process_time': 97.4899}
2020-09-07 23:29:51,639 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1369, 'loss': 0.1747, 'load_time': 2.5101, 'process_time': 97.4899}
2020-09-07 23:29:51,639 - algorithms.Algorithm - INFO   - Training epoch [114 / 200]
2020-09-07 23:29:51,639 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:29:51,639 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:29:57,201 - algorithms.Algorithm - INFO   - ==> Iteration [114][  50 /  469]: {'prec1': 96.5625, 'loss': 0.0821, 'load_time': 41.7191, 'process_time': 58.2809}
2020-09-07 23:30:02,834 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 100 /  469]: {'prec1': 96.5508, 'loss': 0.0808, 'load_time': 41.7995, 'process_time': 58.2005}
2020-09-07 23:30:08,479 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 150 /  469]: {'prec1': 96.6094, 'loss': 0.0794, 'load_time': 42.5655, 'process_time': 57.4345}
2020-09-07 23:30:14,129 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 200 /  469]: {'prec1': 96.5732, 'loss': 0.0807, 'load_time': 42.9228, 'process_time': 57.0772}
2020-09-07 23:30:19,811 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 250 /  469]: {'prec1': 96.5227, 'loss': 0.082, 'load_time': 43.1585, 'process_time': 56.8415}
2020-09-07 23:30:25,512 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 300 /  469]: {'prec1': 96.4225, 'loss': 0.0836, 'load_time': 43.8682, 'process_time': 56.1318}
2020-09-07 23:30:31,222 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 350 /  469]: {'prec1': 96.4029, 'loss': 0.0845, 'load_time': 43.8468, 'process_time': 56.1532}
2020-09-07 23:30:36,954 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 400 /  469]: {'prec1': 96.3618, 'loss': 0.0855, 'load_time': 44.2888, 'process_time': 55.7112}
2020-09-07 23:30:42,681 - algorithms.Algorithm - INFO   - ==> Iteration [114][ 450 /  469]: {'prec1': 96.3273, 'loss': 0.086, 'load_time': 44.9411, 'process_time': 55.0589}
2020-09-07 23:30:44,844 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3206, 'loss': 0.0861, 'load_time': 45.0018, 'process_time': 54.9982}
2020-09-07 23:30:44,926 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:30:44,927 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:30:51,371 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1097, 'loss': 0.1795, 'load_time': 2.4444, 'process_time': 97.5556}
2020-09-07 23:30:51,372 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1097, 'loss': 0.1795, 'load_time': 2.4444, 'process_time': 97.5556}
2020-09-07 23:30:51,372 - algorithms.Algorithm - INFO   - Training epoch [115 / 200]
2020-09-07 23:30:51,372 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:30:51,372 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:30:56,984 - algorithms.Algorithm - INFO   - ==> Iteration [115][  50 /  469]: {'prec1': 96.5977, 'loss': 0.0801, 'load_time': 42.1847, 'process_time': 57.8153}
2020-09-07 23:31:02,537 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 100 /  469]: {'prec1': 96.6035, 'loss': 0.0816, 'load_time': 43.7546, 'process_time': 56.2454}
2020-09-07 23:31:08,271 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 150 /  469]: {'prec1': 96.4753, 'loss': 0.0832, 'load_time': 44.9456, 'process_time': 55.0544}
2020-09-07 23:31:14,069 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 200 /  469]: {'prec1': 96.4805, 'loss': 0.0825, 'load_time': 45.9763, 'process_time': 54.0237}
2020-09-07 23:31:19,843 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 250 /  469]: {'prec1': 96.3984, 'loss': 0.0843, 'load_time': 46.7882, 'process_time': 53.2118}
2020-09-07 23:31:25,604 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 300 /  469]: {'prec1': 96.4121, 'loss': 0.0846, 'load_time': 47.2398, 'process_time': 52.7602}
2020-09-07 23:31:31,384 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 350 /  469]: {'prec1': 96.4146, 'loss': 0.0845, 'load_time': 47.399, 'process_time': 52.601}
2020-09-07 23:31:37,051 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 400 /  469]: {'prec1': 96.3755, 'loss': 0.085, 'load_time': 47.3492, 'process_time': 52.6508}
2020-09-07 23:31:42,850 - algorithms.Algorithm - INFO   - ==> Iteration [115][ 450 /  469]: {'prec1': 96.3381, 'loss': 0.0854, 'load_time': 47.7837, 'process_time': 52.2163}
2020-09-07 23:31:45,014 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3364, 'loss': 0.0854, 'load_time': 47.9515, 'process_time': 52.0485}
2020-09-07 23:31:45,096 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:31:45,096 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:31:51,618 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1641, 'loss': 0.1829, 'load_time': 2.4231, 'process_time': 97.5769}
2020-09-07 23:31:51,618 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1641, 'loss': 0.1829, 'load_time': 2.4231, 'process_time': 97.5769}
2020-09-07 23:31:51,618 - algorithms.Algorithm - INFO   - Training epoch [116 / 200]
2020-09-07 23:31:51,618 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:31:51,618 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:31:57,263 - algorithms.Algorithm - INFO   - ==> Iteration [116][  50 /  469]: {'prec1': 96.3086, 'loss': 0.0867, 'load_time': 40.8108, 'process_time': 59.1892}
2020-09-07 23:32:02,910 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 100 /  469]: {'prec1': 96.125, 'loss': 0.0901, 'load_time': 41.356, 'process_time': 58.644}
2020-09-07 23:32:08,600 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 150 /  469]: {'prec1': 96.1862, 'loss': 0.0878, 'load_time': 43.3847, 'process_time': 56.6153}
2020-09-07 23:32:14,320 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 200 /  469]: {'prec1': 96.25, 'loss': 0.0862, 'load_time': 44.1601, 'process_time': 55.8399}
2020-09-07 23:32:20,022 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 250 /  469]: {'prec1': 96.2547, 'loss': 0.0862, 'load_time': 44.8802, 'process_time': 55.1198}
2020-09-07 23:32:25,759 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 300 /  469]: {'prec1': 96.2786, 'loss': 0.0864, 'load_time': 45.1028, 'process_time': 54.8972}
2020-09-07 23:32:31,419 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 350 /  469]: {'prec1': 96.2584, 'loss': 0.0865, 'load_time': 44.9406, 'process_time': 55.0594}
2020-09-07 23:32:37,183 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 400 /  469]: {'prec1': 96.2461, 'loss': 0.087, 'load_time': 45.1147, 'process_time': 54.8853}
2020-09-07 23:32:42,858 - algorithms.Algorithm - INFO   - ==> Iteration [116][ 450 /  469]: {'prec1': 96.2444, 'loss': 0.0869, 'load_time': 45.4161, 'process_time': 54.5839}
2020-09-07 23:32:45,027 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.2524, 'loss': 0.0869, 'load_time': 45.554, 'process_time': 54.446}
2020-09-07 23:32:45,109 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:32:45,109 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:32:51,622 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0231, 'loss': 0.1792, 'load_time': 2.4994, 'process_time': 97.5006}
2020-09-07 23:32:51,622 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0231, 'loss': 0.1792, 'load_time': 2.4994, 'process_time': 97.5006}
2020-09-07 23:32:51,622 - algorithms.Algorithm - INFO   - Training epoch [117 / 200]
2020-09-07 23:32:51,622 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:32:51,622 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:32:57,182 - algorithms.Algorithm - INFO   - ==> Iteration [117][  50 /  469]: {'prec1': 96.3594, 'loss': 0.084, 'load_time': 40.7867, 'process_time': 59.2133}
2020-09-07 23:33:02,768 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 100 /  469]: {'prec1': 96.4824, 'loss': 0.0813, 'load_time': 42.153, 'process_time': 57.847}
2020-09-07 23:33:08,386 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 150 /  469]: {'prec1': 96.4844, 'loss': 0.0808, 'load_time': 42.2345, 'process_time': 57.7655}
2020-09-07 23:33:14,060 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 200 /  469]: {'prec1': 96.4648, 'loss': 0.0823, 'load_time': 42.8988, 'process_time': 57.1012}
2020-09-07 23:33:19,804 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 250 /  469]: {'prec1': 96.4719, 'loss': 0.0829, 'load_time': 43.9379, 'process_time': 56.0621}
2020-09-07 23:33:25,453 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 300 /  469]: {'prec1': 96.5104, 'loss': 0.0827, 'load_time': 44.1117, 'process_time': 55.8883}
2020-09-07 23:33:31,166 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 350 /  469]: {'prec1': 96.4704, 'loss': 0.0838, 'load_time': 44.4898, 'process_time': 55.5102}
2020-09-07 23:33:36,979 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 400 /  469]: {'prec1': 96.4336, 'loss': 0.0846, 'load_time': 44.7813, 'process_time': 55.2187}
2020-09-07 23:33:42,677 - algorithms.Algorithm - INFO   - ==> Iteration [117][ 450 /  469]: {'prec1': 96.3659, 'loss': 0.0856, 'load_time': 44.934, 'process_time': 55.066}
2020-09-07 23:33:44,847 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3661, 'loss': 0.0856, 'load_time': 45.1175, 'process_time': 54.8825}
2020-09-07 23:33:44,928 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:33:44,928 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:33:51,403 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.5064, 'loss': 0.1888, 'load_time': 2.4864, 'process_time': 97.5136}
2020-09-07 23:33:51,403 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.5064, 'loss': 0.1888, 'load_time': 2.4864, 'process_time': 97.5136}
2020-09-07 23:33:51,403 - algorithms.Algorithm - INFO   - Training epoch [118 / 200]
2020-09-07 23:33:51,403 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:33:51,403 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:33:56,974 - algorithms.Algorithm - INFO   - ==> Iteration [118][  50 /  469]: {'prec1': 96.7617, 'loss': 0.0797, 'load_time': 39.3418, 'process_time': 60.6582}
2020-09-07 23:34:02,651 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 100 /  469]: {'prec1': 96.6387, 'loss': 0.0816, 'load_time': 42.7895, 'process_time': 57.2105}
2020-09-07 23:34:08,326 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 150 /  469]: {'prec1': 96.543, 'loss': 0.0827, 'load_time': 43.493, 'process_time': 56.507}
2020-09-07 23:34:14,011 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 200 /  469]: {'prec1': 96.5273, 'loss': 0.0822, 'load_time': 44.2195, 'process_time': 55.7805}
2020-09-07 23:34:19,657 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 250 /  469]: {'prec1': 96.5422, 'loss': 0.0817, 'load_time': 44.7995, 'process_time': 55.2005}
2020-09-07 23:34:25,401 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 300 /  469]: {'prec1': 96.5312, 'loss': 0.082, 'load_time': 45.2085, 'process_time': 54.7915}
2020-09-07 23:34:31,193 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 350 /  469]: {'prec1': 96.471, 'loss': 0.0832, 'load_time': 45.9632, 'process_time': 54.0368}
2020-09-07 23:34:36,914 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 400 /  469]: {'prec1': 96.415, 'loss': 0.0841, 'load_time': 46.2934, 'process_time': 53.7066}
2020-09-07 23:34:42,570 - algorithms.Algorithm - INFO   - ==> Iteration [118][ 450 /  469]: {'prec1': 96.3737, 'loss': 0.085, 'load_time': 46.185, 'process_time': 53.815}
2020-09-07 23:34:44,772 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3687, 'loss': 0.0851, 'load_time': 46.3369, 'process_time': 53.6631}
2020-09-07 23:34:44,853 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:34:44,853 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:34:51,284 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.5831, 'loss': 0.2009, 'load_time': 2.4887, 'process_time': 97.5113}
2020-09-07 23:34:51,284 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.5831, 'loss': 0.2009, 'load_time': 2.4887, 'process_time': 97.5113}
2020-09-07 23:34:51,284 - algorithms.Algorithm - INFO   - Training epoch [119 / 200]
2020-09-07 23:34:51,284 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:34:51,284 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:34:56,943 - algorithms.Algorithm - INFO   - ==> Iteration [119][  50 /  469]: {'prec1': 96.7773, 'loss': 0.0769, 'load_time': 42.4341, 'process_time': 57.5659}
2020-09-07 23:35:02,610 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 100 /  469]: {'prec1': 96.6055, 'loss': 0.0799, 'load_time': 42.9846, 'process_time': 57.0154}
2020-09-07 23:35:08,391 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 150 /  469]: {'prec1': 96.4544, 'loss': 0.0822, 'load_time': 45.0553, 'process_time': 54.9447}
2020-09-07 23:35:14,216 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 200 /  469]: {'prec1': 96.4922, 'loss': 0.082, 'load_time': 46.6311, 'process_time': 53.3689}
2020-09-07 23:35:20,009 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 250 /  469]: {'prec1': 96.5227, 'loss': 0.0819, 'load_time': 46.9108, 'process_time': 53.0892}
2020-09-07 23:35:25,774 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 300 /  469]: {'prec1': 96.4727, 'loss': 0.0828, 'load_time': 47.043, 'process_time': 52.957}
2020-09-07 23:35:31,616 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 350 /  469]: {'prec1': 96.4308, 'loss': 0.0841, 'load_time': 47.2125, 'process_time': 52.7875}
2020-09-07 23:35:37,344 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 400 /  469]: {'prec1': 96.4116, 'loss': 0.0843, 'load_time': 47.3358, 'process_time': 52.6642}
2020-09-07 23:35:43,047 - algorithms.Algorithm - INFO   - ==> Iteration [119][ 450 /  469]: {'prec1': 96.3859, 'loss': 0.0843, 'load_time': 47.5306, 'process_time': 52.4694}
2020-09-07 23:35:45,218 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3757, 'loss': 0.0847, 'load_time': 47.6308, 'process_time': 52.3692}
2020-09-07 23:35:45,294 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:35:45,295 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:35:51,752 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1665, 'loss': 0.1705, 'load_time': 2.515, 'process_time': 97.485}
2020-09-07 23:35:51,752 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1665, 'loss': 0.1705, 'load_time': 2.515, 'process_time': 97.485}
2020-09-07 23:35:51,752 - algorithms.Algorithm - INFO   - Training epoch [120 / 200]
2020-09-07 23:35:51,752 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0200000000
2020-09-07 23:35:51,752 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:35:57,368 - algorithms.Algorithm - INFO   - ==> Iteration [120][  50 /  469]: {'prec1': 96.6445, 'loss': 0.0814, 'load_time': 43.31, 'process_time': 56.69}
2020-09-07 23:36:03,104 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 100 /  469]: {'prec1': 96.4141, 'loss': 0.0833, 'load_time': 44.1546, 'process_time': 55.8454}
2020-09-07 23:36:08,839 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 150 /  469]: {'prec1': 96.4219, 'loss': 0.0843, 'load_time': 45.5212, 'process_time': 54.4788}
2020-09-07 23:36:14,521 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 200 /  469]: {'prec1': 96.4629, 'loss': 0.0837, 'load_time': 46.1139, 'process_time': 53.8861}
2020-09-07 23:36:20,246 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 250 /  469]: {'prec1': 96.4039, 'loss': 0.0848, 'load_time': 46.6461, 'process_time': 53.3539}
2020-09-07 23:36:26,019 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 300 /  469]: {'prec1': 96.3672, 'loss': 0.0854, 'load_time': 46.9516, 'process_time': 53.0484}
2020-09-07 23:36:31,774 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 350 /  469]: {'prec1': 96.3471, 'loss': 0.086, 'load_time': 47.5045, 'process_time': 52.4955}
2020-09-07 23:36:37,506 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 400 /  469]: {'prec1': 96.3379, 'loss': 0.086, 'load_time': 47.8322, 'process_time': 52.1678}
2020-09-07 23:36:43,210 - algorithms.Algorithm - INFO   - ==> Iteration [120][ 450 /  469]: {'prec1': 96.3234, 'loss': 0.0863, 'load_time': 47.7571, 'process_time': 52.2429}
2020-09-07 23:36:45,368 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 96.3175, 'loss': 0.0864, 'load_time': 47.6111, 'process_time': 52.3889}
2020-09-07 23:36:45,452 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:36:45,452 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:36:51,898 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0429, 'loss': 0.1764, 'load_time': 2.5902, 'process_time': 97.4098}
2020-09-07 23:36:51,898 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0429, 'loss': 0.1764, 'load_time': 2.5902, 'process_time': 97.4098}
2020-09-07 23:36:51,898 - algorithms.Algorithm - INFO   - Training epoch [121 / 200]
2020-09-07 23:36:51,898 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:36:51,898 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:36:57,614 - algorithms.Algorithm - INFO   - ==> Iteration [121][  50 /  469]: {'prec1': 97.1953, 'loss': 0.0672, 'load_time': 46.9399, 'process_time': 53.0601}
2020-09-07 23:37:03,235 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 100 /  469]: {'prec1': 97.3066, 'loss': 0.0637, 'load_time': 45.5727, 'process_time': 54.4273}
2020-09-07 23:37:08,875 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 150 /  469]: {'prec1': 97.3073, 'loss': 0.0637, 'load_time': 45.7841, 'process_time': 54.2159}
2020-09-07 23:37:14,556 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 200 /  469]: {'prec1': 97.3613, 'loss': 0.0622, 'load_time': 45.7944, 'process_time': 54.2056}
2020-09-07 23:37:20,323 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 250 /  469]: {'prec1': 97.3477, 'loss': 0.0621, 'load_time': 46.0719, 'process_time': 53.9281}
2020-09-07 23:37:26,111 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 300 /  469]: {'prec1': 97.3906, 'loss': 0.0616, 'load_time': 46.7253, 'process_time': 53.2747}
2020-09-07 23:37:31,787 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 350 /  469]: {'prec1': 97.4336, 'loss': 0.0609, 'load_time': 46.3929, 'process_time': 53.6071}
2020-09-07 23:37:37,558 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 400 /  469]: {'prec1': 97.457, 'loss': 0.0603, 'load_time': 46.6853, 'process_time': 53.3147}
2020-09-07 23:37:43,261 - algorithms.Algorithm - INFO   - ==> Iteration [121][ 450 /  469]: {'prec1': 97.4562, 'loss': 0.0603, 'load_time': 46.5472, 'process_time': 53.4528}
2020-09-07 23:37:45,405 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 97.4539, 'loss': 0.0604, 'load_time': 46.469, 'process_time': 53.531}
2020-09-07 23:37:45,489 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:37:45,490 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:37:52,007 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.8489, 'loss': 0.1706, 'load_time': 2.5335, 'process_time': 97.4665}
2020-09-07 23:37:52,007 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.8489, 'loss': 0.1706, 'load_time': 2.5335, 'process_time': 97.4665}
2020-09-07 23:37:52,007 - algorithms.Algorithm - INFO   - Training epoch [122 / 200]
2020-09-07 23:37:52,007 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:37:52,007 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:37:57,645 - algorithms.Algorithm - INFO   - ==> Iteration [122][  50 /  469]: {'prec1': 98.0703, 'loss': 0.0492, 'load_time': 43.7815, 'process_time': 56.2185}
2020-09-07 23:38:03,257 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 100 /  469]: {'prec1': 97.998, 'loss': 0.0512, 'load_time': 44.1453, 'process_time': 55.8547}
2020-09-07 23:38:09,033 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 150 /  469]: {'prec1': 97.8789, 'loss': 0.0524, 'load_time': 45.0278, 'process_time': 54.9722}
2020-09-07 23:38:14,706 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 200 /  469]: {'prec1': 97.8896, 'loss': 0.0521, 'load_time': 45.588, 'process_time': 54.412}
2020-09-07 23:38:20,506 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 250 /  469]: {'prec1': 97.8328, 'loss': 0.0527, 'load_time': 46.5769, 'process_time': 53.4231}
2020-09-07 23:38:26,226 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 300 /  469]: {'prec1': 97.8177, 'loss': 0.0528, 'load_time': 47.2243, 'process_time': 52.7757}
2020-09-07 23:38:31,953 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 350 /  469]: {'prec1': 97.8231, 'loss': 0.0527, 'load_time': 47.4811, 'process_time': 52.5189}
2020-09-07 23:38:37,671 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 400 /  469]: {'prec1': 97.8042, 'loss': 0.053, 'load_time': 47.4937, 'process_time': 52.5063}
2020-09-07 23:38:43,476 - algorithms.Algorithm - INFO   - ==> Iteration [122][ 450 /  469]: {'prec1': 97.793, 'loss': 0.0531, 'load_time': 47.5951, 'process_time': 52.4049}
2020-09-07 23:38:45,637 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 97.781, 'loss': 0.0533, 'load_time': 47.7048, 'process_time': 52.2952}
2020-09-07 23:38:45,718 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:38:45,718 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:38:52,159 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.525, 'loss': 0.1828, 'load_time': 2.5557, 'process_time': 97.4443}
2020-09-07 23:38:52,159 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.525, 'loss': 0.1828, 'load_time': 2.5557, 'process_time': 97.4443}
2020-09-07 23:38:52,159 - algorithms.Algorithm - INFO   - Training epoch [123 / 200]
2020-09-07 23:38:52,159 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:38:52,159 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:38:57,777 - algorithms.Algorithm - INFO   - ==> Iteration [123][  50 /  469]: {'prec1': 97.7266, 'loss': 0.0527, 'load_time': 41.737, 'process_time': 58.263}
2020-09-07 23:39:03,385 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 100 /  469]: {'prec1': 97.9023, 'loss': 0.05, 'load_time': 42.1211, 'process_time': 57.8789}
2020-09-07 23:39:09,112 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 150 /  469]: {'prec1': 97.8919, 'loss': 0.0504, 'load_time': 44.736, 'process_time': 55.264}
2020-09-07 23:39:14,886 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 200 /  469]: {'prec1': 97.8975, 'loss': 0.0503, 'load_time': 45.6822, 'process_time': 54.3178}
2020-09-07 23:39:20,662 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 250 /  469]: {'prec1': 97.8578, 'loss': 0.0507, 'load_time': 46.926, 'process_time': 53.074}
2020-09-07 23:39:26,401 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 300 /  469]: {'prec1': 97.8926, 'loss': 0.0501, 'load_time': 46.9172, 'process_time': 53.0828}
2020-09-07 23:39:32,115 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 350 /  469]: {'prec1': 97.861, 'loss': 0.0506, 'load_time': 46.8643, 'process_time': 53.1357}
2020-09-07 23:39:37,827 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 400 /  469]: {'prec1': 97.8301, 'loss': 0.0511, 'load_time': 47.0788, 'process_time': 52.9212}
2020-09-07 23:39:43,561 - algorithms.Algorithm - INFO   - ==> Iteration [123][ 450 /  469]: {'prec1': 97.842, 'loss': 0.0508, 'load_time': 47.1522, 'process_time': 52.8478}
2020-09-07 23:39:45,677 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 97.8449, 'loss': 0.0508, 'load_time': 47.1621, 'process_time': 52.8379}
2020-09-07 23:39:45,760 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:39:45,760 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:39:52,244 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 94.0071, 'loss': 0.1795, 'load_time': 2.5545, 'process_time': 97.4455}
2020-09-07 23:39:52,245 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 94.0071, 'loss': 0.1795, 'load_time': 2.5545, 'process_time': 97.4455}
2020-09-07 23:39:52,245 - algorithms.Algorithm - INFO   - Training epoch [124 / 200]
2020-09-07 23:39:52,245 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:39:52,245 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:39:57,838 - algorithms.Algorithm - INFO   - ==> Iteration [124][  50 /  469]: {'prec1': 97.8633, 'loss': 0.05, 'load_time': 40.3133, 'process_time': 59.6867}
2020-09-07 23:40:03,457 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 100 /  469]: {'prec1': 97.8652, 'loss': 0.0494, 'load_time': 42.5212, 'process_time': 57.4788}
2020-09-07 23:40:09,223 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 150 /  469]: {'prec1': 97.9193, 'loss': 0.0484, 'load_time': 43.7295, 'process_time': 56.2705}
2020-09-07 23:40:14,963 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 200 /  469]: {'prec1': 97.9229, 'loss': 0.0484, 'load_time': 45.0343, 'process_time': 54.9657}
2020-09-07 23:40:20,655 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 250 /  469]: {'prec1': 97.9102, 'loss': 0.0486, 'load_time': 45.7498, 'process_time': 54.2502}
2020-09-07 23:40:26,317 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 300 /  469]: {'prec1': 97.8809, 'loss': 0.049, 'load_time': 46.1638, 'process_time': 53.8362}
2020-09-07 23:40:32,183 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 350 /  469]: {'prec1': 97.8683, 'loss': 0.0494, 'load_time': 46.6967, 'process_time': 53.3033}
2020-09-07 23:40:37,957 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 400 /  469]: {'prec1': 97.8682, 'loss': 0.0495, 'load_time': 46.8348, 'process_time': 53.1652}
2020-09-07 23:40:43,748 - algorithms.Algorithm - INFO   - ==> Iteration [124][ 450 /  469]: {'prec1': 97.8924, 'loss': 0.0491, 'load_time': 47.0428, 'process_time': 52.9572}
2020-09-07 23:40:45,919 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 97.9104, 'loss': 0.0488, 'load_time': 47.1001, 'process_time': 52.8999}
2020-09-07 23:40:46,000 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:40:46,001 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:40:52,532 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.6116, 'loss': 0.187, 'load_time': 2.5002, 'process_time': 97.4998}
2020-09-07 23:40:52,532 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.6116, 'loss': 0.187, 'load_time': 2.5002, 'process_time': 97.4998}
2020-09-07 23:40:52,532 - algorithms.Algorithm - INFO   - Training epoch [125 / 200]
2020-09-07 23:40:52,532 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:40:52,532 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:40:58,157 - algorithms.Algorithm - INFO   - ==> Iteration [125][  50 /  469]: {'prec1': 98.0039, 'loss': 0.0475, 'load_time': 43.2048, 'process_time': 56.7952}
2020-09-07 23:41:03,839 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 100 /  469]: {'prec1': 98.0723, 'loss': 0.046, 'load_time': 44.2227, 'process_time': 55.7773}
2020-09-07 23:41:09,605 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 150 /  469]: {'prec1': 98.0625, 'loss': 0.0463, 'load_time': 45.0461, 'process_time': 54.9539}
2020-09-07 23:41:15,347 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 200 /  469]: {'prec1': 98.0352, 'loss': 0.0467, 'load_time': 45.5739, 'process_time': 54.4261}
2020-09-07 23:41:21,080 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 250 /  469]: {'prec1': 98.0125, 'loss': 0.0471, 'load_time': 45.4821, 'process_time': 54.5179}
2020-09-07 23:41:26,759 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 300 /  469]: {'prec1': 98.0234, 'loss': 0.0472, 'load_time': 45.5383, 'process_time': 54.4617}
2020-09-07 23:41:32,494 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 350 /  469]: {'prec1': 97.986, 'loss': 0.0478, 'load_time': 46.0041, 'process_time': 53.9959}
2020-09-07 23:41:38,197 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 400 /  469]: {'prec1': 97.9502, 'loss': 0.0482, 'load_time': 45.8222, 'process_time': 54.1778}
2020-09-07 23:41:43,988 - algorithms.Algorithm - INFO   - ==> Iteration [125][ 450 /  469]: {'prec1': 97.967, 'loss': 0.048, 'load_time': 46.5703, 'process_time': 53.4297}
2020-09-07 23:41:46,227 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 97.9632, 'loss': 0.0481, 'load_time': 46.7272, 'process_time': 53.2728}
2020-09-07 23:41:46,310 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:41:46,310 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:41:52,791 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.7846, 'loss': 0.1887, 'load_time': 2.5933, 'process_time': 97.4067}
2020-09-07 23:41:52,791 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.7846, 'loss': 0.1887, 'load_time': 2.5933, 'process_time': 97.4067}
2020-09-07 23:41:52,792 - algorithms.Algorithm - INFO   - Training epoch [126 / 200]
2020-09-07 23:41:52,792 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:41:52,792 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:41:58,453 - algorithms.Algorithm - INFO   - ==> Iteration [126][  50 /  469]: {'prec1': 98.1133, 'loss': 0.0456, 'load_time': 44.2585, 'process_time': 55.7415}
2020-09-07 23:42:04,091 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 100 /  469]: {'prec1': 98.0723, 'loss': 0.0454, 'load_time': 42.9179, 'process_time': 57.0821}
2020-09-07 23:42:09,734 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 150 /  469]: {'prec1': 98.0247, 'loss': 0.0463, 'load_time': 43.2632, 'process_time': 56.7368}
2020-09-07 23:42:15,448 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 200 /  469]: {'prec1': 98.1035, 'loss': 0.045, 'load_time': 44.6556, 'process_time': 55.3444}
2020-09-07 23:42:21,218 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 250 /  469]: {'prec1': 98.0469, 'loss': 0.0463, 'load_time': 45.1734, 'process_time': 54.8266}
2020-09-07 23:42:26,983 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 300 /  469]: {'prec1': 98.056, 'loss': 0.046, 'load_time': 45.5851, 'process_time': 54.4149}
2020-09-07 23:42:32,706 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 350 /  469]: {'prec1': 98.0575, 'loss': 0.0462, 'load_time': 45.1951, 'process_time': 54.8049}
2020-09-07 23:42:38,497 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 400 /  469]: {'prec1': 98.0508, 'loss': 0.0461, 'load_time': 45.4853, 'process_time': 54.5147}
2020-09-07 23:42:44,267 - algorithms.Algorithm - INFO   - ==> Iteration [126][ 450 /  469]: {'prec1': 98.0382, 'loss': 0.0463, 'load_time': 46.0541, 'process_time': 53.9459}
2020-09-07 23:42:46,463 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.0621, 'loss': 0.0458, 'load_time': 46.1659, 'process_time': 53.8341}
2020-09-07 23:42:46,543 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:42:46,543 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:42:53,121 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.8959, 'loss': 0.1889, 'load_time': 2.4573, 'process_time': 97.5427}
2020-09-07 23:42:53,122 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.8959, 'loss': 0.1889, 'load_time': 2.4573, 'process_time': 97.5427}
2020-09-07 23:42:53,122 - algorithms.Algorithm - INFO   - Training epoch [127 / 200]
2020-09-07 23:42:53,122 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:42:53,122 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:42:58,706 - algorithms.Algorithm - INFO   - ==> Iteration [127][  50 /  469]: {'prec1': 98.2422, 'loss': 0.0405, 'load_time': 39.3087, 'process_time': 60.6913}
2020-09-07 23:43:04,317 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 100 /  469]: {'prec1': 98.1641, 'loss': 0.0423, 'load_time': 39.52, 'process_time': 60.48}
2020-09-07 23:43:09,942 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 150 /  469]: {'prec1': 98.1237, 'loss': 0.0437, 'load_time': 42.1845, 'process_time': 57.8155}
2020-09-07 23:43:15,559 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 200 /  469]: {'prec1': 98.1191, 'loss': 0.0448, 'load_time': 42.8289, 'process_time': 57.1711}
2020-09-07 23:43:21,314 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 250 /  469]: {'prec1': 98.1023, 'loss': 0.0449, 'load_time': 43.3347, 'process_time': 56.6653}
2020-09-07 23:43:27,064 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 300 /  469]: {'prec1': 98.099, 'loss': 0.0451, 'load_time': 44.1528, 'process_time': 55.8472}
2020-09-07 23:43:32,793 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 350 /  469]: {'prec1': 98.0804, 'loss': 0.0453, 'load_time': 44.405, 'process_time': 55.595}
2020-09-07 23:43:38,524 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 400 /  469]: {'prec1': 98.0684, 'loss': 0.0454, 'load_time': 44.647, 'process_time': 55.353}
2020-09-07 23:43:44,315 - algorithms.Algorithm - INFO   - ==> Iteration [127][ 450 /  469]: {'prec1': 98.0625, 'loss': 0.0455, 'load_time': 45.1107, 'process_time': 54.8893}
2020-09-07 23:43:46,511 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.046, 'loss': 0.0459, 'load_time': 45.4253, 'process_time': 54.5747}
2020-09-07 23:43:46,594 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:43:46,594 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:43:53,128 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.5324, 'loss': 0.1954, 'load_time': 2.5232, 'process_time': 97.4768}
2020-09-07 23:43:53,128 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.5324, 'loss': 0.1954, 'load_time': 2.5232, 'process_time': 97.4768}
2020-09-07 23:43:53,128 - algorithms.Algorithm - INFO   - Training epoch [128 / 200]
2020-09-07 23:43:53,128 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:43:53,128 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:43:58,786 - algorithms.Algorithm - INFO   - ==> Iteration [128][  50 /  469]: {'prec1': 98.2539, 'loss': 0.0411, 'load_time': 42.9075, 'process_time': 57.0925}
2020-09-07 23:44:04,464 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 100 /  469]: {'prec1': 98.2207, 'loss': 0.042, 'load_time': 43.3909, 'process_time': 56.6091}
2020-09-07 23:44:10,169 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 150 /  469]: {'prec1': 98.1836, 'loss': 0.0433, 'load_time': 45.1853, 'process_time': 54.8147}
2020-09-07 23:44:15,843 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 200 /  469]: {'prec1': 98.1152, 'loss': 0.0444, 'load_time': 45.517, 'process_time': 54.483}
2020-09-07 23:44:21,613 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 250 /  469]: {'prec1': 98.1188, 'loss': 0.0445, 'load_time': 46.3908, 'process_time': 53.6092}
2020-09-07 23:44:27,341 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 300 /  469]: {'prec1': 98.1237, 'loss': 0.0444, 'load_time': 46.9794, 'process_time': 53.0206}
2020-09-07 23:44:33,084 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 350 /  469]: {'prec1': 98.1049, 'loss': 0.0449, 'load_time': 46.8045, 'process_time': 53.1955}
2020-09-07 23:44:38,851 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 400 /  469]: {'prec1': 98.0913, 'loss': 0.0452, 'load_time': 47.4768, 'process_time': 52.5232}
2020-09-07 23:44:44,589 - algorithms.Algorithm - INFO   - ==> Iteration [128][ 450 /  469]: {'prec1': 98.1029, 'loss': 0.0451, 'load_time': 47.4138, 'process_time': 52.5862}
2020-09-07 23:44:46,748 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.106, 'loss': 0.0449, 'load_time': 47.4572, 'process_time': 52.5428}
2020-09-07 23:44:46,828 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:44:46,828 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:44:53,314 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.572, 'loss': 0.2003, 'load_time': 2.438, 'process_time': 97.562}
2020-09-07 23:44:53,315 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.572, 'loss': 0.2003, 'load_time': 2.438, 'process_time': 97.562}
2020-09-07 23:44:53,315 - algorithms.Algorithm - INFO   - Training epoch [129 / 200]
2020-09-07 23:44:53,315 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:44:53,315 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:44:59,094 - algorithms.Algorithm - INFO   - ==> Iteration [129][  50 /  469]: {'prec1': 98.2148, 'loss': 0.042, 'load_time': 44.7904, 'process_time': 55.2096}
2020-09-07 23:45:04,697 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 100 /  469]: {'prec1': 98.1914, 'loss': 0.0431, 'load_time': 45.9784, 'process_time': 54.0216}
2020-09-07 23:45:10,360 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 150 /  469]: {'prec1': 98.2526, 'loss': 0.0421, 'load_time': 45.3675, 'process_time': 54.6325}
2020-09-07 23:45:16,050 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 200 /  469]: {'prec1': 98.2217, 'loss': 0.043, 'load_time': 46.0659, 'process_time': 53.9341}
2020-09-07 23:45:21,749 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 250 /  469]: {'prec1': 98.1805, 'loss': 0.0436, 'load_time': 46.633, 'process_time': 53.367}
2020-09-07 23:45:27,421 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 300 /  469]: {'prec1': 98.1901, 'loss': 0.0438, 'load_time': 46.684, 'process_time': 53.316}
2020-09-07 23:45:33,156 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 350 /  469]: {'prec1': 98.1864, 'loss': 0.0437, 'load_time': 46.8165, 'process_time': 53.1835}
2020-09-07 23:45:38,856 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 400 /  469]: {'prec1': 98.1851, 'loss': 0.0436, 'load_time': 46.9614, 'process_time': 53.0386}
2020-09-07 23:45:44,584 - algorithms.Algorithm - INFO   - ==> Iteration [129][ 450 /  469]: {'prec1': 98.1667, 'loss': 0.0437, 'load_time': 46.8283, 'process_time': 53.1717}
2020-09-07 23:45:46,762 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.1642, 'loss': 0.0437, 'load_time': 46.9651, 'process_time': 53.0349}
2020-09-07 23:45:46,843 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:45:46,843 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:45:53,366 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.7352, 'loss': 0.1971, 'load_time': 2.504, 'process_time': 97.496}
2020-09-07 23:45:53,366 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.7352, 'loss': 0.1971, 'load_time': 2.504, 'process_time': 97.496}
2020-09-07 23:45:53,366 - algorithms.Algorithm - INFO   - Training epoch [130 / 200]
2020-09-07 23:45:53,366 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:45:53,366 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:45:59,010 - algorithms.Algorithm - INFO   - ==> Iteration [130][  50 /  469]: {'prec1': 98.3086, 'loss': 0.0409, 'load_time': 42.7866, 'process_time': 57.2134}
2020-09-07 23:46:04,606 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 100 /  469]: {'prec1': 98.252, 'loss': 0.0415, 'load_time': 42.472, 'process_time': 57.528}
2020-09-07 23:46:10,243 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 150 /  469]: {'prec1': 98.2956, 'loss': 0.0413, 'load_time': 44.1783, 'process_time': 55.8217}
2020-09-07 23:46:15,966 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 200 /  469]: {'prec1': 98.2832, 'loss': 0.0416, 'load_time': 45.5219, 'process_time': 54.4781}
2020-09-07 23:46:21,721 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 250 /  469]: {'prec1': 98.2344, 'loss': 0.0427, 'load_time': 46.0529, 'process_time': 53.9471}
2020-09-07 23:46:27,461 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 300 /  469]: {'prec1': 98.207, 'loss': 0.043, 'load_time': 46.4386, 'process_time': 53.5614}
2020-09-07 23:46:33,197 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 350 /  469]: {'prec1': 98.2059, 'loss': 0.043, 'load_time': 46.4385, 'process_time': 53.5615}
2020-09-07 23:46:38,912 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 400 /  469]: {'prec1': 98.2119, 'loss': 0.043, 'load_time': 46.8136, 'process_time': 53.1864}
2020-09-07 23:46:44,645 - algorithms.Algorithm - INFO   - ==> Iteration [130][ 450 /  469]: {'prec1': 98.197, 'loss': 0.0434, 'load_time': 46.9938, 'process_time': 53.0062}
2020-09-07 23:46:46,873 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.1951, 'loss': 0.0433, 'load_time': 47.0851, 'process_time': 52.9149}
2020-09-07 23:46:46,954 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:46:46,954 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:46:53,483 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.7154, 'loss': 0.2043, 'load_time': 2.5052, 'process_time': 97.4948}
2020-09-07 23:46:53,483 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.7154, 'loss': 0.2043, 'load_time': 2.5052, 'process_time': 97.4948}
2020-09-07 23:46:53,483 - algorithms.Algorithm - INFO   - Training epoch [131 / 200]
2020-09-07 23:46:53,483 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:46:53,484 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:46:59,161 - algorithms.Algorithm - INFO   - ==> Iteration [131][  50 /  469]: {'prec1': 98.2656, 'loss': 0.0406, 'load_time': 43.3686, 'process_time': 56.6314}
2020-09-07 23:47:04,796 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 100 /  469]: {'prec1': 98.3672, 'loss': 0.04, 'load_time': 43.5382, 'process_time': 56.4618}
2020-09-07 23:47:10,496 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 150 /  469]: {'prec1': 98.3255, 'loss': 0.0401, 'load_time': 44.2264, 'process_time': 55.7736}
2020-09-07 23:47:16,201 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 200 /  469]: {'prec1': 98.3154, 'loss': 0.0406, 'load_time': 44.6228, 'process_time': 55.3772}
2020-09-07 23:47:22,021 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 250 /  469]: {'prec1': 98.3086, 'loss': 0.041, 'load_time': 45.6892, 'process_time': 54.3108}
2020-09-07 23:47:27,832 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 300 /  469]: {'prec1': 98.2767, 'loss': 0.0416, 'load_time': 45.327, 'process_time': 54.673}
2020-09-07 23:47:33,694 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 350 /  469]: {'prec1': 98.2054, 'loss': 0.0432, 'load_time': 45.3161, 'process_time': 54.6839}
2020-09-07 23:47:39,440 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 400 /  469]: {'prec1': 98.1934, 'loss': 0.0434, 'load_time': 45.6395, 'process_time': 54.3605}
2020-09-07 23:47:45,246 - algorithms.Algorithm - INFO   - ==> Iteration [131][ 450 /  469]: {'prec1': 98.1884, 'loss': 0.0435, 'load_time': 45.5687, 'process_time': 54.4313}
2020-09-07 23:47:47,442 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.1893, 'loss': 0.0435, 'load_time': 45.691, 'process_time': 54.309}
2020-09-07 23:47:47,522 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:47:47,522 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:47:54,175 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.5844, 'loss': 0.2026, 'load_time': 2.7107, 'process_time': 97.2893}
2020-09-07 23:47:54,175 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.5844, 'loss': 0.2026, 'load_time': 2.7107, 'process_time': 97.2893}
2020-09-07 23:47:54,175 - algorithms.Algorithm - INFO   - Training epoch [132 / 200]
2020-09-07 23:47:54,175 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:47:54,175 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:47:59,862 - algorithms.Algorithm - INFO   - ==> Iteration [132][  50 /  469]: {'prec1': 98.1992, 'loss': 0.0449, 'load_time': 40.6167, 'process_time': 59.3833}
2020-09-07 23:48:05,544 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 100 /  469]: {'prec1': 98.2188, 'loss': 0.0431, 'load_time': 41.7302, 'process_time': 58.2698}
2020-09-07 23:48:11,195 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 150 /  469]: {'prec1': 98.3112, 'loss': 0.0409, 'load_time': 41.8117, 'process_time': 58.1883}
2020-09-07 23:48:16,967 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 200 /  469]: {'prec1': 98.2432, 'loss': 0.0418, 'load_time': 42.062, 'process_time': 57.938}
2020-09-07 23:48:22,723 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 250 /  469]: {'prec1': 98.2438, 'loss': 0.0414, 'load_time': 42.8836, 'process_time': 57.1164}
2020-09-07 23:48:28,453 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 300 /  469]: {'prec1': 98.2539, 'loss': 0.0414, 'load_time': 43.0906, 'process_time': 56.9094}
2020-09-07 23:48:34,234 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 350 /  469]: {'prec1': 98.2467, 'loss': 0.0417, 'load_time': 43.3444, 'process_time': 56.6556}
2020-09-07 23:48:39,991 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 400 /  469]: {'prec1': 98.2261, 'loss': 0.0423, 'load_time': 43.678, 'process_time': 56.322}
2020-09-07 23:48:45,750 - algorithms.Algorithm - INFO   - ==> Iteration [132][ 450 /  469]: {'prec1': 98.214, 'loss': 0.0425, 'load_time': 43.8837, 'process_time': 56.1163}
2020-09-07 23:48:47,939 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2015, 'loss': 0.0428, 'load_time': 43.8587, 'process_time': 56.1413}
2020-09-07 23:48:48,023 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:48:48,023 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:48:54,657 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4978, 'loss': 0.2044, 'load_time': 2.5482, 'process_time': 97.4518}
2020-09-07 23:48:54,657 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4978, 'loss': 0.2044, 'load_time': 2.5482, 'process_time': 97.4518}
2020-09-07 23:48:54,657 - algorithms.Algorithm - INFO   - Training epoch [133 / 200]
2020-09-07 23:48:54,657 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:48:54,657 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:49:00,398 - algorithms.Algorithm - INFO   - ==> Iteration [133][  50 /  469]: {'prec1': 98.2734, 'loss': 0.042, 'load_time': 43.4617, 'process_time': 56.5383}
2020-09-07 23:49:06,015 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 100 /  469]: {'prec1': 98.2949, 'loss': 0.0408, 'load_time': 42.2147, 'process_time': 57.7853}
2020-09-07 23:49:11,666 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 150 /  469]: {'prec1': 98.2852, 'loss': 0.0416, 'load_time': 41.941, 'process_time': 58.059}
2020-09-07 23:49:17,391 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 200 /  469]: {'prec1': 98.2451, 'loss': 0.0423, 'load_time': 42.7048, 'process_time': 57.2952}
2020-09-07 23:49:23,167 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 250 /  469]: {'prec1': 98.2031, 'loss': 0.0429, 'load_time': 43.1322, 'process_time': 56.8678}
2020-09-07 23:49:28,982 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 300 /  469]: {'prec1': 98.2057, 'loss': 0.0427, 'load_time': 44.178, 'process_time': 55.822}
2020-09-07 23:49:34,766 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 350 /  469]: {'prec1': 98.2238, 'loss': 0.0423, 'load_time': 44.3784, 'process_time': 55.6216}
2020-09-07 23:49:40,559 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 400 /  469]: {'prec1': 98.2129, 'loss': 0.0427, 'load_time': 44.82, 'process_time': 55.18}
2020-09-07 23:49:46,348 - algorithms.Algorithm - INFO   - ==> Iteration [133][ 450 /  469]: {'prec1': 98.2079, 'loss': 0.0427, 'load_time': 45.1163, 'process_time': 54.8837}
2020-09-07 23:49:48,571 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2061, 'loss': 0.0428, 'load_time': 45.2214, 'process_time': 54.7786}
2020-09-07 23:49:48,654 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:49:48,654 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:49:55,251 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.567, 'loss': 0.2067, 'load_time': 2.7105, 'process_time': 97.2895}
2020-09-07 23:49:55,251 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.567, 'loss': 0.2067, 'load_time': 2.7105, 'process_time': 97.2895}
2020-09-07 23:49:55,251 - algorithms.Algorithm - INFO   - Training epoch [134 / 200]
2020-09-07 23:49:55,251 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:49:55,251 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:50:00,983 - algorithms.Algorithm - INFO   - ==> Iteration [134][  50 /  469]: {'prec1': 98.3125, 'loss': 0.0411, 'load_time': 41.0233, 'process_time': 58.9767}
2020-09-07 23:50:06,769 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 100 /  469]: {'prec1': 98.2812, 'loss': 0.041, 'load_time': 44.5542, 'process_time': 55.4458}
2020-09-07 23:50:12,528 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 150 /  469]: {'prec1': 98.2174, 'loss': 0.0428, 'load_time': 45.1376, 'process_time': 54.8624}
2020-09-07 23:50:18,228 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 200 /  469]: {'prec1': 98.1738, 'loss': 0.0433, 'load_time': 45.5055, 'process_time': 54.4945}
2020-09-07 23:50:24,032 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 250 /  469]: {'prec1': 98.1516, 'loss': 0.0436, 'load_time': 45.92, 'process_time': 54.08}
2020-09-07 23:50:29,806 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 300 /  469]: {'prec1': 98.1426, 'loss': 0.0439, 'load_time': 46.1467, 'process_time': 53.8533}
2020-09-07 23:50:35,566 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 350 /  469]: {'prec1': 98.1708, 'loss': 0.0432, 'load_time': 46.0575, 'process_time': 53.9425}
2020-09-07 23:50:41,287 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 400 /  469]: {'prec1': 98.1387, 'loss': 0.0439, 'load_time': 46.1555, 'process_time': 53.8445}
2020-09-07 23:50:47,027 - algorithms.Algorithm - INFO   - ==> Iteration [134][ 450 /  469]: {'prec1': 98.1862, 'loss': 0.0429, 'load_time': 46.0859, 'process_time': 53.9141}
2020-09-07 23:50:49,195 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.195, 'loss': 0.0428, 'load_time': 46.2241, 'process_time': 53.7759}
2020-09-07 23:50:49,277 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:50:49,277 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:50:55,863 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3223, 'loss': 0.2146, 'load_time': 2.6219, 'process_time': 97.3781}
2020-09-07 23:50:55,863 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3223, 'loss': 0.2146, 'load_time': 2.6219, 'process_time': 97.3781}
2020-09-07 23:50:55,863 - algorithms.Algorithm - INFO   - Training epoch [135 / 200]
2020-09-07 23:50:55,863 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:50:55,863 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:51:01,491 - algorithms.Algorithm - INFO   - ==> Iteration [135][  50 /  469]: {'prec1': 98.3906, 'loss': 0.0393, 'load_time': 39.2027, 'process_time': 60.7973}
2020-09-07 23:51:07,286 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 100 /  469]: {'prec1': 98.3457, 'loss': 0.0404, 'load_time': 41.5076, 'process_time': 58.4924}
2020-09-07 23:51:13,082 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 150 /  469]: {'prec1': 98.2682, 'loss': 0.0414, 'load_time': 42.8236, 'process_time': 57.1764}
2020-09-07 23:51:18,783 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 200 /  469]: {'prec1': 98.2559, 'loss': 0.0416, 'load_time': 44.189, 'process_time': 55.811}
2020-09-07 23:51:24,576 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 250 /  469]: {'prec1': 98.2516, 'loss': 0.0418, 'load_time': 44.4151, 'process_time': 55.5849}
2020-09-07 23:51:30,371 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 300 /  469]: {'prec1': 98.2357, 'loss': 0.0419, 'load_time': 44.2226, 'process_time': 55.7774}
2020-09-07 23:51:36,138 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 350 /  469]: {'prec1': 98.2366, 'loss': 0.0419, 'load_time': 44.5888, 'process_time': 55.4112}
2020-09-07 23:51:41,879 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 400 /  469]: {'prec1': 98.23, 'loss': 0.0421, 'load_time': 44.922, 'process_time': 55.078}
2020-09-07 23:51:47,658 - algorithms.Algorithm - INFO   - ==> Iteration [135][ 450 /  469]: {'prec1': 98.2322, 'loss': 0.0419, 'load_time': 44.8084, 'process_time': 55.1916}
2020-09-07 23:51:49,877 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2183, 'loss': 0.0421, 'load_time': 45.1043, 'process_time': 54.8957}
2020-09-07 23:51:49,958 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:51:49,958 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:51:56,626 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.305, 'loss': 0.2126, 'load_time': 2.5568, 'process_time': 97.4432}
2020-09-07 23:51:56,626 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.305, 'loss': 0.2126, 'load_time': 2.5568, 'process_time': 97.4432}
2020-09-07 23:51:56,626 - algorithms.Algorithm - INFO   - Training epoch [136 / 200]
2020-09-07 23:51:56,626 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:51:56,626 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:52:02,323 - algorithms.Algorithm - INFO   - ==> Iteration [136][  50 /  469]: {'prec1': 98.3281, 'loss': 0.0403, 'load_time': 40.9826, 'process_time': 59.0174}
2020-09-07 23:52:08,098 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 100 /  469]: {'prec1': 98.3574, 'loss': 0.0397, 'load_time': 42.7385, 'process_time': 57.2615}
2020-09-07 23:52:13,840 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 150 /  469]: {'prec1': 98.2721, 'loss': 0.0412, 'load_time': 44.0124, 'process_time': 55.9876}
2020-09-07 23:52:19,570 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 200 /  469]: {'prec1': 98.2754, 'loss': 0.0408, 'load_time': 44.3647, 'process_time': 55.6353}
2020-09-07 23:52:25,313 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 250 /  469]: {'prec1': 98.2828, 'loss': 0.0411, 'load_time': 44.531, 'process_time': 55.469}
2020-09-07 23:52:31,089 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 300 /  469]: {'prec1': 98.2467, 'loss': 0.0418, 'load_time': 44.8917, 'process_time': 55.1083}
2020-09-07 23:52:36,873 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 350 /  469]: {'prec1': 98.2427, 'loss': 0.0419, 'load_time': 45.2305, 'process_time': 54.7695}
2020-09-07 23:52:42,595 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 400 /  469]: {'prec1': 98.2593, 'loss': 0.0417, 'load_time': 45.3393, 'process_time': 54.6607}
2020-09-07 23:52:48,361 - algorithms.Algorithm - INFO   - ==> Iteration [136][ 450 /  469]: {'prec1': 98.2548, 'loss': 0.0417, 'load_time': 45.4373, 'process_time': 54.5627}
2020-09-07 23:52:50,514 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2373, 'loss': 0.0419, 'load_time': 45.3978, 'process_time': 54.6022}
2020-09-07 23:52:50,594 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:52:50,594 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:52:57,227 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4162, 'loss': 0.2106, 'load_time': 2.5874, 'process_time': 97.4126}
2020-09-07 23:52:57,227 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4162, 'loss': 0.2106, 'load_time': 2.5874, 'process_time': 97.4126}
2020-09-07 23:52:57,227 - algorithms.Algorithm - INFO   - Training epoch [137 / 200]
2020-09-07 23:52:57,227 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:52:57,227 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:53:02,860 - algorithms.Algorithm - INFO   - ==> Iteration [137][  50 /  469]: {'prec1': 98.4062, 'loss': 0.0374, 'load_time': 38.3371, 'process_time': 61.6629}
2020-09-07 23:53:08,446 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 100 /  469]: {'prec1': 98.3672, 'loss': 0.0383, 'load_time': 39.8415, 'process_time': 60.1585}
2020-09-07 23:53:14,235 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 150 /  469]: {'prec1': 98.3659, 'loss': 0.039, 'load_time': 41.291, 'process_time': 58.709}
2020-09-07 23:53:20,010 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 200 /  469]: {'prec1': 98.3213, 'loss': 0.0399, 'load_time': 42.0951, 'process_time': 57.9049}
2020-09-07 23:53:25,871 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 250 /  469]: {'prec1': 98.3344, 'loss': 0.0399, 'load_time': 43.0228, 'process_time': 56.9772}
2020-09-07 23:53:31,605 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 300 /  469]: {'prec1': 98.3379, 'loss': 0.0398, 'load_time': 43.3328, 'process_time': 56.6672}
2020-09-07 23:53:37,402 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 350 /  469]: {'prec1': 98.3583, 'loss': 0.0395, 'load_time': 43.3917, 'process_time': 56.6083}
2020-09-07 23:53:43,174 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 400 /  469]: {'prec1': 98.334, 'loss': 0.0402, 'load_time': 43.7212, 'process_time': 56.2788}
2020-09-07 23:53:48,916 - algorithms.Algorithm - INFO   - ==> Iteration [137][ 450 /  469]: {'prec1': 98.3207, 'loss': 0.0403, 'load_time': 43.765, 'process_time': 56.235}
2020-09-07 23:53:51,134 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3063, 'loss': 0.0405, 'load_time': 44.0392, 'process_time': 55.9608}
2020-09-07 23:53:51,216 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:53:51,216 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:53:57,845 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4805, 'loss': 0.2113, 'load_time': 2.627, 'process_time': 97.373}
2020-09-07 23:53:57,845 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4805, 'loss': 0.2113, 'load_time': 2.627, 'process_time': 97.373}
2020-09-07 23:53:57,845 - algorithms.Algorithm - INFO   - Training epoch [138 / 200]
2020-09-07 23:53:57,845 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:53:57,845 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:54:03,476 - algorithms.Algorithm - INFO   - ==> Iteration [138][  50 /  469]: {'prec1': 98.2539, 'loss': 0.0421, 'load_time': 40.1486, 'process_time': 59.8514}
2020-09-07 23:54:09,130 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 100 /  469]: {'prec1': 98.3008, 'loss': 0.0408, 'load_time': 40.3895, 'process_time': 59.6105}
2020-09-07 23:54:14,917 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 150 /  469]: {'prec1': 98.349, 'loss': 0.0398, 'load_time': 42.2915, 'process_time': 57.7085}
2020-09-07 23:54:20,653 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 200 /  469]: {'prec1': 98.3418, 'loss': 0.0399, 'load_time': 42.9495, 'process_time': 57.0505}
2020-09-07 23:54:26,368 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 250 /  469]: {'prec1': 98.35, 'loss': 0.0396, 'load_time': 43.7935, 'process_time': 56.2065}
2020-09-07 23:54:32,186 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 300 /  469]: {'prec1': 98.2754, 'loss': 0.0409, 'load_time': 44.4687, 'process_time': 55.5313}
2020-09-07 23:54:37,945 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 350 /  469]: {'prec1': 98.2706, 'loss': 0.041, 'load_time': 44.2906, 'process_time': 55.7094}
2020-09-07 23:54:43,777 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 400 /  469]: {'prec1': 98.2568, 'loss': 0.0412, 'load_time': 44.311, 'process_time': 55.689}
2020-09-07 23:54:49,545 - algorithms.Algorithm - INFO   - ==> Iteration [138][ 450 /  469]: {'prec1': 98.2543, 'loss': 0.0413, 'load_time': 44.5048, 'process_time': 55.4952}
2020-09-07 23:54:51,781 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2651, 'loss': 0.0412, 'load_time': 44.7009, 'process_time': 55.2991}
2020-09-07 23:54:51,861 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:54:51,861 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:54:58,554 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.352, 'loss': 0.2227, 'load_time': 2.5846, 'process_time': 97.4154}
2020-09-07 23:54:58,554 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.352, 'loss': 0.2227, 'load_time': 2.5846, 'process_time': 97.4154}
2020-09-07 23:54:58,554 - algorithms.Algorithm - INFO   - Training epoch [139 / 200]
2020-09-07 23:54:58,554 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:54:58,554 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:55:04,350 - algorithms.Algorithm - INFO   - ==> Iteration [139][  50 /  469]: {'prec1': 98.4297, 'loss': 0.0382, 'load_time': 42.8123, 'process_time': 57.1877}
2020-09-07 23:55:10,125 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 100 /  469]: {'prec1': 98.2793, 'loss': 0.0406, 'load_time': 42.8173, 'process_time': 57.1827}
2020-09-07 23:55:15,803 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 150 /  469]: {'prec1': 98.2526, 'loss': 0.0415, 'load_time': 43.308, 'process_time': 56.692}
2020-09-07 23:55:21,595 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 200 /  469]: {'prec1': 98.2773, 'loss': 0.0412, 'load_time': 43.5617, 'process_time': 56.4383}
2020-09-07 23:55:27,419 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 250 /  469]: {'prec1': 98.2578, 'loss': 0.0417, 'load_time': 44.225, 'process_time': 55.775}
2020-09-07 23:55:33,242 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 300 /  469]: {'prec1': 98.3118, 'loss': 0.0406, 'load_time': 44.3761, 'process_time': 55.6239}
2020-09-07 23:55:39,025 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 350 /  469]: {'prec1': 98.3013, 'loss': 0.0411, 'load_time': 44.2969, 'process_time': 55.7031}
2020-09-07 23:55:44,818 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 400 /  469]: {'prec1': 98.2993, 'loss': 0.0411, 'load_time': 44.0872, 'process_time': 55.9128}
2020-09-07 23:55:50,658 - algorithms.Algorithm - INFO   - ==> Iteration [139][ 450 /  469]: {'prec1': 98.3047, 'loss': 0.0411, 'load_time': 44.0311, 'process_time': 55.9689}
2020-09-07 23:55:52,859 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.2855, 'loss': 0.0415, 'load_time': 44.1254, 'process_time': 55.8746}
2020-09-07 23:55:52,941 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:55:52,941 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:55:59,551 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4855, 'loss': 0.2073, 'load_time': 2.6905, 'process_time': 97.3095}
2020-09-07 23:55:59,551 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4855, 'loss': 0.2073, 'load_time': 2.6905, 'process_time': 97.3095}
2020-09-07 23:55:59,551 - algorithms.Algorithm - INFO   - Training epoch [140 / 200]
2020-09-07 23:55:59,551 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:55:59,551 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:56:05,255 - algorithms.Algorithm - INFO   - ==> Iteration [140][  50 /  469]: {'prec1': 98.1406, 'loss': 0.0435, 'load_time': 41.846, 'process_time': 58.154}
2020-09-07 23:56:11,026 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 100 /  469]: {'prec1': 98.1504, 'loss': 0.0423, 'load_time': 43.2195, 'process_time': 56.7805}
2020-09-07 23:56:16,821 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 150 /  469]: {'prec1': 98.2591, 'loss': 0.0406, 'load_time': 43.4808, 'process_time': 56.5192}
2020-09-07 23:56:22,526 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 200 /  469]: {'prec1': 98.3135, 'loss': 0.04, 'load_time': 42.9497, 'process_time': 57.0503}
2020-09-07 23:56:28,362 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 250 /  469]: {'prec1': 98.2859, 'loss': 0.0406, 'load_time': 43.7167, 'process_time': 56.2833}
2020-09-07 23:56:34,146 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 300 /  469]: {'prec1': 98.3118, 'loss': 0.0403, 'load_time': 44.0537, 'process_time': 55.9463}
2020-09-07 23:56:39,920 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 350 /  469]: {'prec1': 98.3337, 'loss': 0.0401, 'load_time': 44.6496, 'process_time': 55.3504}
2020-09-07 23:56:45,650 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 400 /  469]: {'prec1': 98.3101, 'loss': 0.0405, 'load_time': 44.9355, 'process_time': 55.0645}
2020-09-07 23:56:51,338 - algorithms.Algorithm - INFO   - ==> Iteration [140][ 450 /  469]: {'prec1': 98.3038, 'loss': 0.0404, 'load_time': 45.3128, 'process_time': 54.6872}
2020-09-07 23:56:53,548 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3131, 'loss': 0.0403, 'load_time': 45.6118, 'process_time': 54.3882}
2020-09-07 23:56:53,629 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:56:53,629 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:57:00,125 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1369, 'loss': 0.2305, 'load_time': 2.5336, 'process_time': 97.4664}
2020-09-07 23:57:00,126 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1369, 'loss': 0.2305, 'load_time': 2.5336, 'process_time': 97.4664}
2020-09-07 23:57:00,126 - algorithms.Algorithm - INFO   - Training epoch [141 / 200]
2020-09-07 23:57:00,126 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:57:00,126 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:57:05,734 - algorithms.Algorithm - INFO   - ==> Iteration [141][  50 /  469]: {'prec1': 98.4766, 'loss': 0.0374, 'load_time': 42.7204, 'process_time': 57.2796}
2020-09-07 23:57:11,393 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 100 /  469]: {'prec1': 98.4336, 'loss': 0.0392, 'load_time': 43.6354, 'process_time': 56.3646}
2020-09-07 23:57:17,046 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 150 /  469]: {'prec1': 98.3737, 'loss': 0.0399, 'load_time': 44.6117, 'process_time': 55.3883}
2020-09-07 23:57:22,647 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 200 /  469]: {'prec1': 98.3799, 'loss': 0.0394, 'load_time': 44.9065, 'process_time': 55.0935}
2020-09-07 23:57:28,286 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 250 /  469]: {'prec1': 98.3781, 'loss': 0.0394, 'load_time': 45.0873, 'process_time': 54.9127}
2020-09-07 23:57:33,917 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 300 /  469]: {'prec1': 98.3665, 'loss': 0.0397, 'load_time': 45.3202, 'process_time': 54.6798}
2020-09-07 23:57:39,577 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 350 /  469]: {'prec1': 98.3571, 'loss': 0.04, 'load_time': 45.6301, 'process_time': 54.3699}
2020-09-07 23:57:45,318 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 400 /  469]: {'prec1': 98.3398, 'loss': 0.0403, 'load_time': 45.8349, 'process_time': 54.1651}
2020-09-07 23:57:51,048 - algorithms.Algorithm - INFO   - ==> Iteration [141][ 450 /  469]: {'prec1': 98.3181, 'loss': 0.0406, 'load_time': 46.1645, 'process_time': 53.8355}
2020-09-07 23:57:53,211 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3088, 'loss': 0.0408, 'load_time': 46.2817, 'process_time': 53.7183}
2020-09-07 23:57:53,287 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:57:53,287 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:57:59,953 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2185, 'loss': 0.2135, 'load_time': 2.5409, 'process_time': 97.4591}
2020-09-07 23:57:59,953 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2185, 'loss': 0.2135, 'load_time': 2.5409, 'process_time': 97.4591}
2020-09-07 23:57:59,953 - algorithms.Algorithm - INFO   - Training epoch [142 / 200]
2020-09-07 23:57:59,953 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:57:59,953 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:58:05,698 - algorithms.Algorithm - INFO   - ==> Iteration [142][  50 /  469]: {'prec1': 98.2578, 'loss': 0.0415, 'load_time': 47.3861, 'process_time': 52.6139}
2020-09-07 23:58:11,244 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 100 /  469]: {'prec1': 98.2539, 'loss': 0.0415, 'load_time': 45.2904, 'process_time': 54.7096}
2020-09-07 23:58:16,829 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 150 /  469]: {'prec1': 98.3151, 'loss': 0.0404, 'load_time': 45.0144, 'process_time': 54.9856}
2020-09-07 23:58:22,443 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 200 /  469]: {'prec1': 98.3008, 'loss': 0.0403, 'load_time': 45.0759, 'process_time': 54.9241}
2020-09-07 23:58:28,081 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 250 /  469]: {'prec1': 98.2961, 'loss': 0.0403, 'load_time': 45.1003, 'process_time': 54.8997}
2020-09-07 23:58:33,699 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 300 /  469]: {'prec1': 98.2904, 'loss': 0.0405, 'load_time': 45.1962, 'process_time': 54.8038}
2020-09-07 23:58:39,362 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 350 /  469]: {'prec1': 98.3103, 'loss': 0.04, 'load_time': 45.338, 'process_time': 54.662}
2020-09-07 23:58:45,084 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 400 /  469]: {'prec1': 98.3228, 'loss': 0.0397, 'load_time': 46.1706, 'process_time': 53.8294}
2020-09-07 23:58:50,740 - algorithms.Algorithm - INFO   - ==> Iteration [142][ 450 /  469]: {'prec1': 98.322, 'loss': 0.04, 'load_time': 46.6044, 'process_time': 53.3956}
2020-09-07 23:58:52,918 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3173, 'loss': 0.0401, 'load_time': 46.9338, 'process_time': 53.0662}
2020-09-07 23:58:53,000 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:58:53,000 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:58:59,558 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3248, 'loss': 0.2109, 'load_time': 2.4167, 'process_time': 97.5833}
2020-09-07 23:58:59,558 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3248, 'loss': 0.2109, 'load_time': 2.4167, 'process_time': 97.5833}
2020-09-07 23:58:59,558 - algorithms.Algorithm - INFO   - Training epoch [143 / 200]
2020-09-07 23:58:59,558 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:58:59,558 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-07 23:59:05,217 - algorithms.Algorithm - INFO   - ==> Iteration [143][  50 /  469]: {'prec1': 98.5586, 'loss': 0.0346, 'load_time': 42.1162, 'process_time': 57.8838}
2020-09-07 23:59:10,754 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 100 /  469]: {'prec1': 98.4785, 'loss': 0.0371, 'load_time': 42.8203, 'process_time': 57.1797}
2020-09-07 23:59:16,252 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 150 /  469]: {'prec1': 98.4023, 'loss': 0.0385, 'load_time': 42.7245, 'process_time': 57.2755}
2020-09-07 23:59:21,855 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 200 /  469]: {'prec1': 98.3496, 'loss': 0.0399, 'load_time': 43.3555, 'process_time': 56.6445}
2020-09-07 23:59:27,459 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 250 /  469]: {'prec1': 98.2938, 'loss': 0.0409, 'load_time': 43.8785, 'process_time': 56.1215}
2020-09-07 23:59:33,068 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 300 /  469]: {'prec1': 98.3229, 'loss': 0.0404, 'load_time': 43.9109, 'process_time': 56.0891}
2020-09-07 23:59:38,699 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 350 /  469]: {'prec1': 98.3287, 'loss': 0.0401, 'load_time': 43.8828, 'process_time': 56.1172}
2020-09-07 23:59:44,345 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 400 /  469]: {'prec1': 98.3311, 'loss': 0.0401, 'load_time': 44.5501, 'process_time': 55.4499}
2020-09-07 23:59:50,012 - algorithms.Algorithm - INFO   - ==> Iteration [143][ 450 /  469]: {'prec1': 98.3481, 'loss': 0.0398, 'load_time': 45.1526, 'process_time': 54.8474}
2020-09-07 23:59:52,112 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3441, 'loss': 0.0399, 'load_time': 45.2633, 'process_time': 54.7367}
2020-09-07 23:59:52,192 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-07 23:59:52,192 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-07 23:59:58,646 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4459, 'loss': 0.2096, 'load_time': 2.4355, 'process_time': 97.5645}
2020-09-07 23:59:58,646 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4459, 'loss': 0.2096, 'load_time': 2.4355, 'process_time': 97.5645}
2020-09-07 23:59:58,646 - algorithms.Algorithm - INFO   - Training epoch [144 / 200]
2020-09-07 23:59:58,646 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-07 23:59:58,646 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:00:04,338 - algorithms.Algorithm - INFO   - ==> Iteration [144][  50 /  469]: {'prec1': 98.3086, 'loss': 0.0399, 'load_time': 43.2006, 'process_time': 56.7994}
2020-09-08 00:00:09,855 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 100 /  469]: {'prec1': 98.3027, 'loss': 0.0408, 'load_time': 41.5091, 'process_time': 58.4909}
2020-09-08 00:00:15,381 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 150 /  469]: {'prec1': 98.3164, 'loss': 0.0407, 'load_time': 41.194, 'process_time': 58.806}
2020-09-08 00:00:20,948 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 200 /  469]: {'prec1': 98.3447, 'loss': 0.0401, 'load_time': 42.8502, 'process_time': 57.1498}
2020-09-08 00:00:26,533 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 250 /  469]: {'prec1': 98.3422, 'loss': 0.0402, 'load_time': 43.3447, 'process_time': 56.6553}
2020-09-08 00:00:32,087 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 300 /  469]: {'prec1': 98.3444, 'loss': 0.0401, 'load_time': 43.3663, 'process_time': 56.6337}
2020-09-08 00:00:37,705 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 350 /  469]: {'prec1': 98.351, 'loss': 0.0402, 'load_time': 43.5096, 'process_time': 56.4904}
2020-09-08 00:00:43,307 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 400 /  469]: {'prec1': 98.3276, 'loss': 0.0406, 'load_time': 43.995, 'process_time': 56.005}
2020-09-08 00:00:48,945 - algorithms.Algorithm - INFO   - ==> Iteration [144][ 450 /  469]: {'prec1': 98.3025, 'loss': 0.0412, 'load_time': 44.2878, 'process_time': 55.7122}
2020-09-08 00:00:51,082 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.308, 'loss': 0.0411, 'load_time': 44.4494, 'process_time': 55.5506}
2020-09-08 00:00:51,165 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:00:51,165 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:00:57,716 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1295, 'loss': 0.2204, 'load_time': 2.5317, 'process_time': 97.4683}
2020-09-08 00:00:57,716 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1295, 'loss': 0.2204, 'load_time': 2.5317, 'process_time': 97.4683}
2020-09-08 00:00:57,716 - algorithms.Algorithm - INFO   - Training epoch [145 / 200]
2020-09-08 00:00:57,716 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:00:57,716 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:01:03,325 - algorithms.Algorithm - INFO   - ==> Iteration [145][  50 /  469]: {'prec1': 98.1914, 'loss': 0.0422, 'load_time': 44.3532, 'process_time': 55.6468}
2020-09-08 00:01:08,897 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 100 /  469]: {'prec1': 98.3105, 'loss': 0.0409, 'load_time': 44.4971, 'process_time': 55.5029}
2020-09-08 00:01:14,402 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 150 /  469]: {'prec1': 98.3685, 'loss': 0.0399, 'load_time': 44.4638, 'process_time': 55.5362}
2020-09-08 00:01:19,999 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 200 /  469]: {'prec1': 98.3496, 'loss': 0.0403, 'load_time': 44.8308, 'process_time': 55.1692}
2020-09-08 00:01:25,519 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 250 /  469]: {'prec1': 98.3422, 'loss': 0.0406, 'load_time': 44.5748, 'process_time': 55.4252}
2020-09-08 00:01:31,179 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 300 /  469]: {'prec1': 98.3268, 'loss': 0.0409, 'load_time': 44.3068, 'process_time': 55.6932}
2020-09-08 00:01:36,717 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 350 /  469]: {'prec1': 98.3075, 'loss': 0.0413, 'load_time': 44.4964, 'process_time': 55.5036}
2020-09-08 00:01:42,272 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 400 /  469]: {'prec1': 98.313, 'loss': 0.041, 'load_time': 44.8014, 'process_time': 55.1986}
2020-09-08 00:01:47,933 - algorithms.Algorithm - INFO   - ==> Iteration [145][ 450 /  469]: {'prec1': 98.3312, 'loss': 0.0405, 'load_time': 45.0284, 'process_time': 54.9716}
2020-09-08 00:01:50,069 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3363, 'loss': 0.0404, 'load_time': 45.327, 'process_time': 54.673}
2020-09-08 00:01:50,151 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:01:50,151 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:01:56,590 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3544, 'loss': 0.2185, 'load_time': 2.5617, 'process_time': 97.4383}
2020-09-08 00:01:56,590 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3544, 'loss': 0.2185, 'load_time': 2.5617, 'process_time': 97.4383}
2020-09-08 00:01:56,590 - algorithms.Algorithm - INFO   - Training epoch [146 / 200]
2020-09-08 00:01:56,590 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:01:56,590 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:02:02,157 - algorithms.Algorithm - INFO   - ==> Iteration [146][  50 /  469]: {'prec1': 98.4297, 'loss': 0.038, 'load_time': 40.2061, 'process_time': 59.7939}
2020-09-08 00:02:07,674 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 100 /  469]: {'prec1': 98.4824, 'loss': 0.0377, 'load_time': 41.9798, 'process_time': 58.0202}
2020-09-08 00:02:13,208 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 150 /  469]: {'prec1': 98.4388, 'loss': 0.0379, 'load_time': 41.9327, 'process_time': 58.0673}
2020-09-08 00:02:18,699 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 200 /  469]: {'prec1': 98.459, 'loss': 0.0373, 'load_time': 42.0746, 'process_time': 57.9254}
2020-09-08 00:02:24,270 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 250 /  469]: {'prec1': 98.4242, 'loss': 0.0383, 'load_time': 42.4435, 'process_time': 57.5565}
2020-09-08 00:02:29,844 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 300 /  469]: {'prec1': 98.3926, 'loss': 0.0389, 'load_time': 42.8558, 'process_time': 57.1442}
2020-09-08 00:02:35,426 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 350 /  469]: {'prec1': 98.3532, 'loss': 0.0398, 'load_time': 42.8917, 'process_time': 57.1083}
2020-09-08 00:02:41,035 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 400 /  469]: {'prec1': 98.3135, 'loss': 0.0404, 'load_time': 43.2497, 'process_time': 56.7503}
2020-09-08 00:02:46,647 - algorithms.Algorithm - INFO   - ==> Iteration [146][ 450 /  469]: {'prec1': 98.3333, 'loss': 0.0402, 'load_time': 43.4733, 'process_time': 56.5267}
2020-09-08 00:02:48,759 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3348, 'loss': 0.0401, 'load_time': 43.5773, 'process_time': 56.4227}
2020-09-08 00:02:48,844 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:02:48,844 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:02:55,242 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3594, 'loss': 0.2172, 'load_time': 2.5104, 'process_time': 97.4896}
2020-09-08 00:02:55,242 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3594, 'loss': 0.2172, 'load_time': 2.5104, 'process_time': 97.4896}
2020-09-08 00:02:55,242 - algorithms.Algorithm - INFO   - Training epoch [147 / 200]
2020-09-08 00:02:55,242 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:02:55,242 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:03:00,837 - algorithms.Algorithm - INFO   - ==> Iteration [147][  50 /  469]: {'prec1': 98.5039, 'loss': 0.0384, 'load_time': 43.7091, 'process_time': 56.2909}
2020-09-08 00:03:06,387 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 100 /  469]: {'prec1': 98.4609, 'loss': 0.0392, 'load_time': 43.7318, 'process_time': 56.2682}
2020-09-08 00:03:11,938 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 150 /  469]: {'prec1': 98.4635, 'loss': 0.0385, 'load_time': 44.8073, 'process_time': 55.1927}
2020-09-08 00:03:17,540 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 200 /  469]: {'prec1': 98.5186, 'loss': 0.0373, 'load_time': 44.9703, 'process_time': 55.0297}
2020-09-08 00:03:23,123 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 250 /  469]: {'prec1': 98.4711, 'loss': 0.0384, 'load_time': 44.8615, 'process_time': 55.1385}
2020-09-08 00:03:28,700 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 300 /  469]: {'prec1': 98.4616, 'loss': 0.0384, 'load_time': 44.8154, 'process_time': 55.1846}
2020-09-08 00:03:34,307 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 350 /  469]: {'prec1': 98.4342, 'loss': 0.0387, 'load_time': 45.1485, 'process_time': 54.8515}
2020-09-08 00:03:39,926 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 400 /  469]: {'prec1': 98.4043, 'loss': 0.0392, 'load_time': 45.4568, 'process_time': 54.5432}
2020-09-08 00:03:45,543 - algorithms.Algorithm - INFO   - ==> Iteration [147][ 450 /  469]: {'prec1': 98.4067, 'loss': 0.039, 'load_time': 45.5219, 'process_time': 54.4781}
2020-09-08 00:03:47,707 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4102, 'loss': 0.0389, 'load_time': 45.6192, 'process_time': 54.3808}
2020-09-08 00:03:47,785 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:03:47,785 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:03:54,258 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2704, 'loss': 0.2286, 'load_time': 2.5515, 'process_time': 97.4485}
2020-09-08 00:03:54,259 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2704, 'loss': 0.2286, 'load_time': 2.5515, 'process_time': 97.4485}
2020-09-08 00:03:54,259 - algorithms.Algorithm - INFO   - Training epoch [148 / 200]
2020-09-08 00:03:54,259 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:03:54,259 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:03:59,872 - algorithms.Algorithm - INFO   - ==> Iteration [148][  50 /  469]: {'prec1': 98.3555, 'loss': 0.0395, 'load_time': 43.1999, 'process_time': 56.8001}
2020-09-08 00:04:05,449 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 100 /  469]: {'prec1': 98.3438, 'loss': 0.0397, 'load_time': 43.0582, 'process_time': 56.9418}
2020-09-08 00:04:11,057 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 150 /  469]: {'prec1': 98.4154, 'loss': 0.0385, 'load_time': 43.6825, 'process_time': 56.3175}
2020-09-08 00:04:16,577 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 200 /  469]: {'prec1': 98.4414, 'loss': 0.0387, 'load_time': 44.2231, 'process_time': 55.7769}
2020-09-08 00:04:22,142 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 250 /  469]: {'prec1': 98.4297, 'loss': 0.039, 'load_time': 44.2439, 'process_time': 55.7561}
2020-09-08 00:04:27,739 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 300 /  469]: {'prec1': 98.4173, 'loss': 0.0392, 'load_time': 44.0983, 'process_time': 55.9017}
2020-09-08 00:04:33,345 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 350 /  469]: {'prec1': 98.3823, 'loss': 0.04, 'load_time': 44.4378, 'process_time': 55.5622}
2020-09-08 00:04:38,933 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 400 /  469]: {'prec1': 98.3647, 'loss': 0.0402, 'load_time': 44.6154, 'process_time': 55.3846}
2020-09-08 00:04:44,497 - algorithms.Algorithm - INFO   - ==> Iteration [148][ 450 /  469]: {'prec1': 98.355, 'loss': 0.0402, 'load_time': 44.7676, 'process_time': 55.2324}
2020-09-08 00:04:46,637 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3593, 'loss': 0.0402, 'load_time': 45.0084, 'process_time': 54.9916}
2020-09-08 00:04:46,719 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:04:46,719 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:04:53,191 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3173, 'loss': 0.2177, 'load_time': 2.5218, 'process_time': 97.4782}
2020-09-08 00:04:53,191 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3173, 'loss': 0.2177, 'load_time': 2.5218, 'process_time': 97.4782}
2020-09-08 00:04:53,191 - algorithms.Algorithm - INFO   - Training epoch [149 / 200]
2020-09-08 00:04:53,191 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:04:53,191 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:04:58,773 - algorithms.Algorithm - INFO   - ==> Iteration [149][  50 /  469]: {'prec1': 98.3438, 'loss': 0.0416, 'load_time': 44.0452, 'process_time': 55.9548}
2020-09-08 00:05:04,289 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 100 /  469]: {'prec1': 98.3105, 'loss': 0.0418, 'load_time': 44.4436, 'process_time': 55.5564}
2020-09-08 00:05:09,793 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 150 /  469]: {'prec1': 98.3281, 'loss': 0.0412, 'load_time': 43.6048, 'process_time': 56.3952}
2020-09-08 00:05:15,426 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 200 /  469]: {'prec1': 98.4072, 'loss': 0.0395, 'load_time': 43.3493, 'process_time': 56.6507}
2020-09-08 00:05:20,982 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 250 /  469]: {'prec1': 98.418, 'loss': 0.0392, 'load_time': 43.7226, 'process_time': 56.2774}
2020-09-08 00:05:26,658 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 300 /  469]: {'prec1': 98.3815, 'loss': 0.04, 'load_time': 43.6815, 'process_time': 56.3185}
2020-09-08 00:05:32,221 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 350 /  469]: {'prec1': 98.4124, 'loss': 0.0392, 'load_time': 43.8865, 'process_time': 56.1135}
2020-09-08 00:05:37,787 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 400 /  469]: {'prec1': 98.4106, 'loss': 0.0393, 'load_time': 44.0502, 'process_time': 55.9498}
2020-09-08 00:05:43,382 - algorithms.Algorithm - INFO   - ==> Iteration [149][ 450 /  469]: {'prec1': 98.4136, 'loss': 0.0391, 'load_time': 44.2227, 'process_time': 55.7773}
2020-09-08 00:05:45,543 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4117, 'loss': 0.0392, 'load_time': 44.3446, 'process_time': 55.6554}
2020-09-08 00:05:45,621 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:05:45,621 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:05:52,080 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1517, 'loss': 0.2257, 'load_time': 2.4995, 'process_time': 97.5005}
2020-09-08 00:05:52,080 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1517, 'loss': 0.2257, 'load_time': 2.4995, 'process_time': 97.5005}
2020-09-08 00:05:52,080 - algorithms.Algorithm - INFO   - Training epoch [150 / 200]
2020-09-08 00:05:52,080 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:05:52,080 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:05:57,593 - algorithms.Algorithm - INFO   - ==> Iteration [150][  50 /  469]: {'prec1': 98.7461, 'loss': 0.033, 'load_time': 42.7425, 'process_time': 57.2575}
2020-09-08 00:06:03,088 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 100 /  469]: {'prec1': 98.625, 'loss': 0.0348, 'load_time': 41.6984, 'process_time': 58.3016}
2020-09-08 00:06:08,624 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 150 /  469]: {'prec1': 98.4948, 'loss': 0.0377, 'load_time': 42.5164, 'process_time': 57.4836}
2020-09-08 00:06:14,114 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 200 /  469]: {'prec1': 98.4609, 'loss': 0.0383, 'load_time': 43.331, 'process_time': 56.669}
2020-09-08 00:06:19,665 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 250 /  469]: {'prec1': 98.4133, 'loss': 0.0393, 'load_time': 44.0796, 'process_time': 55.9204}
2020-09-08 00:06:25,360 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 300 /  469]: {'prec1': 98.3939, 'loss': 0.0393, 'load_time': 45.0046, 'process_time': 54.9954}
2020-09-08 00:06:30,948 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 350 /  469]: {'prec1': 98.3627, 'loss': 0.0397, 'load_time': 45.1108, 'process_time': 54.8892}
2020-09-08 00:06:36,513 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 400 /  469]: {'prec1': 98.3496, 'loss': 0.04, 'load_time': 44.8598, 'process_time': 55.1402}
2020-09-08 00:06:42,108 - algorithms.Algorithm - INFO   - ==> Iteration [150][ 450 /  469]: {'prec1': 98.3281, 'loss': 0.0404, 'load_time': 44.6752, 'process_time': 55.3248}
2020-09-08 00:06:44,244 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3313, 'loss': 0.0403, 'load_time': 44.6871, 'process_time': 55.3129}
2020-09-08 00:06:44,325 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:06:44,326 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:06:50,848 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1987, 'loss': 0.224, 'load_time': 2.5361, 'process_time': 97.4639}
2020-09-08 00:06:50,848 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1987, 'loss': 0.224, 'load_time': 2.5361, 'process_time': 97.4639}
2020-09-08 00:06:50,848 - algorithms.Algorithm - INFO   - Training epoch [151 / 200]
2020-09-08 00:06:50,848 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:06:50,848 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:06:56,434 - algorithms.Algorithm - INFO   - ==> Iteration [151][  50 /  469]: {'prec1': 98.4883, 'loss': 0.036, 'load_time': 42.9907, 'process_time': 57.0093}
2020-09-08 00:07:02,011 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 100 /  469]: {'prec1': 98.5, 'loss': 0.0367, 'load_time': 43.1558, 'process_time': 56.8442}
2020-09-08 00:07:07,573 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 150 /  469]: {'prec1': 98.4232, 'loss': 0.0383, 'load_time': 44.3366, 'process_time': 55.6634}
2020-09-08 00:07:13,064 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 200 /  469]: {'prec1': 98.4414, 'loss': 0.0375, 'load_time': 44.2358, 'process_time': 55.7642}
2020-09-08 00:07:18,625 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 250 /  469]: {'prec1': 98.4008, 'loss': 0.0382, 'load_time': 44.7575, 'process_time': 55.2425}
2020-09-08 00:07:24,243 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 300 /  469]: {'prec1': 98.3268, 'loss': 0.0394, 'load_time': 45.2132, 'process_time': 54.7868}
2020-09-08 00:07:29,852 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 350 /  469]: {'prec1': 98.3331, 'loss': 0.0395, 'load_time': 45.1315, 'process_time': 54.8685}
2020-09-08 00:07:35,484 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 400 /  469]: {'prec1': 98.3701, 'loss': 0.0391, 'load_time': 45.1705, 'process_time': 54.8295}
2020-09-08 00:07:41,041 - algorithms.Algorithm - INFO   - ==> Iteration [151][ 450 /  469]: {'prec1': 98.3394, 'loss': 0.0397, 'load_time': 44.9927, 'process_time': 55.0073}
2020-09-08 00:07:43,145 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3505, 'loss': 0.0396, 'load_time': 45.2373, 'process_time': 54.7627}
2020-09-08 00:07:43,222 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:07:43,222 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:07:49,661 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2185, 'loss': 0.2243, 'load_time': 2.7126, 'process_time': 97.2874}
2020-09-08 00:07:49,661 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2185, 'loss': 0.2243, 'load_time': 2.7126, 'process_time': 97.2874}
2020-09-08 00:07:49,661 - algorithms.Algorithm - INFO   - Training epoch [152 / 200]
2020-09-08 00:07:49,661 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:07:49,661 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:07:55,314 - algorithms.Algorithm - INFO   - ==> Iteration [152][  50 /  469]: {'prec1': 98.7109, 'loss': 0.0337, 'load_time': 46.4459, 'process_time': 53.5541}
2020-09-08 00:08:00,795 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 100 /  469]: {'prec1': 98.5508, 'loss': 0.0366, 'load_time': 44.2766, 'process_time': 55.7234}
2020-09-08 00:08:06,412 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 150 /  469]: {'prec1': 98.5833, 'loss': 0.036, 'load_time': 42.5592, 'process_time': 57.4408}
2020-09-08 00:08:11,881 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 200 /  469]: {'prec1': 98.5547, 'loss': 0.0365, 'load_time': 42.7371, 'process_time': 57.2629}
2020-09-08 00:08:17,475 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 250 /  469]: {'prec1': 98.5375, 'loss': 0.0367, 'load_time': 42.7718, 'process_time': 57.2282}
2020-09-08 00:08:23,063 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 300 /  469]: {'prec1': 98.4987, 'loss': 0.0374, 'load_time': 42.5567, 'process_time': 57.4433}
2020-09-08 00:08:28,681 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 350 /  469]: {'prec1': 98.447, 'loss': 0.0384, 'load_time': 42.9971, 'process_time': 57.0029}
2020-09-08 00:08:34,229 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 400 /  469]: {'prec1': 98.4546, 'loss': 0.0383, 'load_time': 42.8128, 'process_time': 57.1872}
2020-09-08 00:08:39,767 - algorithms.Algorithm - INFO   - ==> Iteration [152][ 450 /  469]: {'prec1': 98.428, 'loss': 0.0388, 'load_time': 42.6301, 'process_time': 57.3699}
2020-09-08 00:08:41,845 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4188, 'loss': 0.0391, 'load_time': 42.812, 'process_time': 57.188}
2020-09-08 00:08:41,925 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:08:41,926 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:08:48,415 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.0528, 'loss': 0.215, 'load_time': 2.566, 'process_time': 97.434}
2020-09-08 00:08:48,415 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.0528, 'loss': 0.215, 'load_time': 2.566, 'process_time': 97.434}
2020-09-08 00:08:48,415 - algorithms.Algorithm - INFO   - Training epoch [153 / 200]
2020-09-08 00:08:48,415 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:08:48,415 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:08:53,986 - algorithms.Algorithm - INFO   - ==> Iteration [153][  50 /  469]: {'prec1': 98.7812, 'loss': 0.0313, 'load_time': 41.0662, 'process_time': 58.9338}
2020-09-08 00:08:59,445 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 100 /  469]: {'prec1': 98.5977, 'loss': 0.034, 'load_time': 40.506, 'process_time': 59.494}
2020-09-08 00:09:04,994 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 150 /  469]: {'prec1': 98.5208, 'loss': 0.0357, 'load_time': 40.9149, 'process_time': 59.0851}
2020-09-08 00:09:10,492 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 200 /  469]: {'prec1': 98.4873, 'loss': 0.037, 'load_time': 41.1031, 'process_time': 58.8969}
2020-09-08 00:09:16,168 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 250 /  469]: {'prec1': 98.4547, 'loss': 0.0375, 'load_time': 42.0902, 'process_time': 57.9098}
2020-09-08 00:09:21,727 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 300 /  469]: {'prec1': 98.4616, 'loss': 0.0375, 'load_time': 42.8035, 'process_time': 57.1965}
2020-09-08 00:09:27,308 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 350 /  469]: {'prec1': 98.4481, 'loss': 0.0379, 'load_time': 42.4874, 'process_time': 57.5126}
2020-09-08 00:09:32,934 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 400 /  469]: {'prec1': 98.3936, 'loss': 0.0387, 'load_time': 42.4664, 'process_time': 57.5336}
2020-09-08 00:09:38,603 - algorithms.Algorithm - INFO   - ==> Iteration [153][ 450 /  469]: {'prec1': 98.3763, 'loss': 0.039, 'load_time': 42.6866, 'process_time': 57.3134}
2020-09-08 00:09:40,748 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3746, 'loss': 0.0391, 'load_time': 42.8036, 'process_time': 57.1964}
2020-09-08 00:09:40,830 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:09:40,830 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:09:47,413 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4162, 'loss': 0.2179, 'load_time': 2.5661, 'process_time': 97.4339}
2020-09-08 00:09:47,413 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4162, 'loss': 0.2179, 'load_time': 2.5661, 'process_time': 97.4339}
2020-09-08 00:09:47,413 - algorithms.Algorithm - INFO   - Training epoch [154 / 200]
2020-09-08 00:09:47,413 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:09:47,413 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:09:53,044 - algorithms.Algorithm - INFO   - ==> Iteration [154][  50 /  469]: {'prec1': 98.4258, 'loss': 0.0394, 'load_time': 42.8465, 'process_time': 57.1535}
2020-09-08 00:09:58,492 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 100 /  469]: {'prec1': 98.5254, 'loss': 0.037, 'load_time': 41.1572, 'process_time': 58.8428}
2020-09-08 00:10:03,976 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 150 /  469]: {'prec1': 98.4609, 'loss': 0.0376, 'load_time': 39.9, 'process_time': 60.1}
2020-09-08 00:10:09,587 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 200 /  469]: {'prec1': 98.4141, 'loss': 0.0384, 'load_time': 40.0932, 'process_time': 59.9068}
2020-09-08 00:10:15,119 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 250 /  469]: {'prec1': 98.3852, 'loss': 0.0392, 'load_time': 41.193, 'process_time': 58.807}
2020-09-08 00:10:20,750 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 300 /  469]: {'prec1': 98.3939, 'loss': 0.0391, 'load_time': 41.7759, 'process_time': 58.2241}
2020-09-08 00:10:26,318 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 350 /  469]: {'prec1': 98.3929, 'loss': 0.0392, 'load_time': 42.032, 'process_time': 57.968}
2020-09-08 00:10:31,925 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 400 /  469]: {'prec1': 98.3721, 'loss': 0.0398, 'load_time': 42.4883, 'process_time': 57.5117}
2020-09-08 00:10:37,512 - algorithms.Algorithm - INFO   - ==> Iteration [154][ 450 /  469]: {'prec1': 98.3707, 'loss': 0.04, 'load_time': 42.6746, 'process_time': 57.3254}
2020-09-08 00:10:39,626 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.3793, 'loss': 0.0398, 'load_time': 42.7865, 'process_time': 57.2135}
2020-09-08 00:10:39,706 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:10:39,706 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:10:46,143 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.5077, 'loss': 0.2138, 'load_time': 2.4304, 'process_time': 97.5696}
2020-09-08 00:10:46,143 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.5077, 'loss': 0.2138, 'load_time': 2.4304, 'process_time': 97.5696}
2020-09-08 00:10:46,143 - algorithms.Algorithm - INFO   - Training epoch [155 / 200]
2020-09-08 00:10:46,143 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:10:46,143 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:10:51,710 - algorithms.Algorithm - INFO   - ==> Iteration [155][  50 /  469]: {'prec1': 98.7266, 'loss': 0.0329, 'load_time': 46.0817, 'process_time': 53.9183}
2020-09-08 00:10:57,251 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 100 /  469]: {'prec1': 98.6543, 'loss': 0.0348, 'load_time': 43.7518, 'process_time': 56.2482}
2020-09-08 00:11:02,738 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 150 /  469]: {'prec1': 98.5625, 'loss': 0.0367, 'load_time': 43.6307, 'process_time': 56.3693}
2020-09-08 00:11:08,240 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 200 /  469]: {'prec1': 98.5332, 'loss': 0.0369, 'load_time': 43.1091, 'process_time': 56.8909}
2020-09-08 00:11:13,903 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 250 /  469]: {'prec1': 98.4875, 'loss': 0.0381, 'load_time': 43.7022, 'process_time': 56.2978}
2020-09-08 00:11:19,451 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 300 /  469]: {'prec1': 98.4798, 'loss': 0.0385, 'load_time': 43.7198, 'process_time': 56.2802}
2020-09-08 00:11:25,096 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 350 /  469]: {'prec1': 98.4676, 'loss': 0.0387, 'load_time': 44.4363, 'process_time': 55.5637}
2020-09-08 00:11:30,647 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 400 /  469]: {'prec1': 98.4526, 'loss': 0.0389, 'load_time': 44.5292, 'process_time': 55.4708}
2020-09-08 00:11:36,229 - algorithms.Algorithm - INFO   - ==> Iteration [155][ 450 /  469]: {'prec1': 98.4345, 'loss': 0.039, 'load_time': 44.5893, 'process_time': 55.4107}
2020-09-08 00:11:38,340 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4278, 'loss': 0.0391, 'load_time': 44.8985, 'process_time': 55.1015}
2020-09-08 00:11:38,419 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:11:38,419 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:11:44,880 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2407, 'loss': 0.2215, 'load_time': 2.5227, 'process_time': 97.4773}
2020-09-08 00:11:44,880 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2407, 'loss': 0.2215, 'load_time': 2.5227, 'process_time': 97.4773}
2020-09-08 00:11:44,881 - algorithms.Algorithm - INFO   - Training epoch [156 / 200]
2020-09-08 00:11:44,881 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:11:44,881 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:11:50,510 - algorithms.Algorithm - INFO   - ==> Iteration [156][  50 /  469]: {'prec1': 98.4102, 'loss': 0.0384, 'load_time': 43.0568, 'process_time': 56.9432}
2020-09-08 00:11:56,118 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 100 /  469]: {'prec1': 98.4395, 'loss': 0.038, 'load_time': 43.6168, 'process_time': 56.3832}
2020-09-08 00:12:01,732 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 150 /  469]: {'prec1': 98.5026, 'loss': 0.0369, 'load_time': 43.9134, 'process_time': 56.0866}
2020-09-08 00:12:07,235 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 200 /  469]: {'prec1': 98.4639, 'loss': 0.0378, 'load_time': 43.7251, 'process_time': 56.2749}
2020-09-08 00:12:12,758 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 250 /  469]: {'prec1': 98.4508, 'loss': 0.038, 'load_time': 43.6317, 'process_time': 56.3683}
2020-09-08 00:12:18,314 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 300 /  469]: {'prec1': 98.4271, 'loss': 0.0386, 'load_time': 44.0721, 'process_time': 55.9279}
2020-09-08 00:12:23,839 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 350 /  469]: {'prec1': 98.4358, 'loss': 0.0386, 'load_time': 44.3692, 'process_time': 55.6308}
2020-09-08 00:12:29,452 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 400 /  469]: {'prec1': 98.4443, 'loss': 0.0385, 'load_time': 44.5985, 'process_time': 55.4015}
2020-09-08 00:12:35,093 - algorithms.Algorithm - INFO   - ==> Iteration [156][ 450 /  469]: {'prec1': 98.4149, 'loss': 0.0391, 'load_time': 44.765, 'process_time': 55.235}
2020-09-08 00:12:37,188 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4183, 'loss': 0.0389, 'load_time': 44.7325, 'process_time': 55.2675}
2020-09-08 00:12:37,265 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:12:37,265 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:12:43,696 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.5275, 'loss': 0.216, 'load_time': 2.4707, 'process_time': 97.5293}
2020-09-08 00:12:43,696 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.5275, 'loss': 0.216, 'load_time': 2.4707, 'process_time': 97.5293}
2020-09-08 00:12:43,696 - algorithms.Algorithm - INFO   - Training epoch [157 / 200]
2020-09-08 00:12:43,696 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:12:43,696 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:12:49,250 - algorithms.Algorithm - INFO   - ==> Iteration [157][  50 /  469]: {'prec1': 98.625, 'loss': 0.0344, 'load_time': 42.287, 'process_time': 57.713}
2020-09-08 00:12:54,659 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 100 /  469]: {'prec1': 98.459, 'loss': 0.0379, 'load_time': 42.9008, 'process_time': 57.0992}
2020-09-08 00:13:00,212 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 150 /  469]: {'prec1': 98.4531, 'loss': 0.0383, 'load_time': 43.5547, 'process_time': 56.4453}
2020-09-08 00:13:05,765 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 200 /  469]: {'prec1': 98.4297, 'loss': 0.0388, 'load_time': 42.6703, 'process_time': 57.3297}
2020-09-08 00:13:11,253 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 250 /  469]: {'prec1': 98.4281, 'loss': 0.0387, 'load_time': 43.0635, 'process_time': 56.9365}
2020-09-08 00:13:16,862 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 300 /  469]: {'prec1': 98.4616, 'loss': 0.0378, 'load_time': 43.7742, 'process_time': 56.2258}
2020-09-08 00:13:22,528 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 350 /  469]: {'prec1': 98.4626, 'loss': 0.0379, 'load_time': 43.8514, 'process_time': 56.1486}
2020-09-08 00:13:28,125 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 400 /  469]: {'prec1': 98.4478, 'loss': 0.0383, 'load_time': 43.9941, 'process_time': 56.0059}
2020-09-08 00:13:33,767 - algorithms.Algorithm - INFO   - ==> Iteration [157][ 450 /  469]: {'prec1': 98.4175, 'loss': 0.039, 'load_time': 43.9592, 'process_time': 56.0408}
2020-09-08 00:13:35,910 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4206, 'loss': 0.039, 'load_time': 44.0569, 'process_time': 55.9431}
2020-09-08 00:13:35,990 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:13:35,990 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:13:42,404 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1344, 'loss': 0.2269, 'load_time': 2.4227, 'process_time': 97.5773}
2020-09-08 00:13:42,405 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1344, 'loss': 0.2269, 'load_time': 2.4227, 'process_time': 97.5773}
2020-09-08 00:13:42,405 - algorithms.Algorithm - INFO   - Training epoch [158 / 200]
2020-09-08 00:13:42,405 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:13:42,405 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:13:47,985 - algorithms.Algorithm - INFO   - ==> Iteration [158][  50 /  469]: {'prec1': 98.4805, 'loss': 0.038, 'load_time': 44.3586, 'process_time': 55.6414}
2020-09-08 00:13:53,540 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 100 /  469]: {'prec1': 98.5547, 'loss': 0.0364, 'load_time': 43.6419, 'process_time': 56.3581}
2020-09-08 00:13:59,119 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 150 /  469]: {'prec1': 98.4935, 'loss': 0.037, 'load_time': 44.8211, 'process_time': 55.1789}
2020-09-08 00:14:04,619 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 200 /  469]: {'prec1': 98.4824, 'loss': 0.0374, 'load_time': 44.0067, 'process_time': 55.9933}
2020-09-08 00:14:10,090 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 250 /  469]: {'prec1': 98.493, 'loss': 0.0374, 'load_time': 44.0191, 'process_time': 55.9809}
2020-09-08 00:14:15,711 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 300 /  469]: {'prec1': 98.4648, 'loss': 0.0379, 'load_time': 44.1871, 'process_time': 55.8129}
2020-09-08 00:14:21,330 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 350 /  469]: {'prec1': 98.4347, 'loss': 0.0385, 'load_time': 44.3179, 'process_time': 55.6821}
2020-09-08 00:14:26,977 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 400 /  469]: {'prec1': 98.4297, 'loss': 0.0387, 'load_time': 44.5204, 'process_time': 55.4796}
2020-09-08 00:14:32,587 - algorithms.Algorithm - INFO   - ==> Iteration [158][ 450 /  469]: {'prec1': 98.4262, 'loss': 0.0387, 'load_time': 44.5067, 'process_time': 55.4933}
2020-09-08 00:14:34,719 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4095, 'loss': 0.039, 'load_time': 44.5523, 'process_time': 55.4477}
2020-09-08 00:14:34,797 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:14:34,797 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:14:41,245 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 92.9391, 'loss': 0.225, 'load_time': 2.4498, 'process_time': 97.5502}
2020-09-08 00:14:41,245 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 92.9391, 'loss': 0.225, 'load_time': 2.4498, 'process_time': 97.5502}
2020-09-08 00:14:41,245 - algorithms.Algorithm - INFO   - Training epoch [159 / 200]
2020-09-08 00:14:41,245 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:14:41,245 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:14:46,880 - algorithms.Algorithm - INFO   - ==> Iteration [159][  50 /  469]: {'prec1': 98.5352, 'loss': 0.0364, 'load_time': 47.2733, 'process_time': 52.7267}
2020-09-08 00:14:52,365 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 100 /  469]: {'prec1': 98.5664, 'loss': 0.0361, 'load_time': 44.9853, 'process_time': 55.0147}
2020-09-08 00:14:57,926 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 150 /  469]: {'prec1': 98.5339, 'loss': 0.0368, 'load_time': 44.5871, 'process_time': 55.4129}
2020-09-08 00:15:03,541 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 200 /  469]: {'prec1': 98.4941, 'loss': 0.0381, 'load_time': 45.3504, 'process_time': 54.6496}
2020-09-08 00:15:09,067 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 250 /  469]: {'prec1': 98.4758, 'loss': 0.0383, 'load_time': 45.7141, 'process_time': 54.2859}
2020-09-08 00:15:14,678 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 300 /  469]: {'prec1': 98.4759, 'loss': 0.0381, 'load_time': 45.853, 'process_time': 54.147}
2020-09-08 00:15:20,217 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 350 /  469]: {'prec1': 98.4325, 'loss': 0.0389, 'load_time': 45.9101, 'process_time': 54.0899}
2020-09-08 00:15:25,823 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 400 /  469]: {'prec1': 98.4243, 'loss': 0.0389, 'load_time': 45.6387, 'process_time': 54.3613}
2020-09-08 00:15:31,425 - algorithms.Algorithm - INFO   - ==> Iteration [159][ 450 /  469]: {'prec1': 98.4115, 'loss': 0.039, 'load_time': 45.7101, 'process_time': 54.2899}
2020-09-08 00:15:33,534 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4163, 'loss': 0.039, 'load_time': 45.704, 'process_time': 54.296}
2020-09-08 00:15:33,612 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:15:33,612 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:15:40,068 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.263, 'loss': 0.2231, 'load_time': 2.4392, 'process_time': 97.5608}
2020-09-08 00:15:40,068 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.263, 'loss': 0.2231, 'load_time': 2.4392, 'process_time': 97.5608}
2020-09-08 00:15:40,068 - algorithms.Algorithm - INFO   - Training epoch [160 / 200]
2020-09-08 00:15:40,068 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0040000000
2020-09-08 00:15:40,068 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:15:45,692 - algorithms.Algorithm - INFO   - ==> Iteration [160][  50 /  469]: {'prec1': 98.6211, 'loss': 0.0337, 'load_time': 43.3847, 'process_time': 56.6153}
2020-09-08 00:15:51,271 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 100 /  469]: {'prec1': 98.5059, 'loss': 0.0363, 'load_time': 41.1744, 'process_time': 58.8256}
2020-09-08 00:15:56,795 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 150 /  469]: {'prec1': 98.5612, 'loss': 0.0358, 'load_time': 41.8593, 'process_time': 58.1407}
2020-09-08 00:16:02,429 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 200 /  469]: {'prec1': 98.5322, 'loss': 0.0366, 'load_time': 42.6594, 'process_time': 57.3406}
2020-09-08 00:16:08,047 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 250 /  469]: {'prec1': 98.4891, 'loss': 0.0374, 'load_time': 42.6487, 'process_time': 57.3513}
2020-09-08 00:16:13,613 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 300 /  469]: {'prec1': 98.4805, 'loss': 0.0378, 'load_time': 42.6668, 'process_time': 57.3332}
2020-09-08 00:16:19,185 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 350 /  469]: {'prec1': 98.4927, 'loss': 0.0377, 'load_time': 42.8509, 'process_time': 57.1491}
2020-09-08 00:16:24,793 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 400 /  469]: {'prec1': 98.4951, 'loss': 0.0378, 'load_time': 42.8554, 'process_time': 57.1446}
2020-09-08 00:16:30,469 - algorithms.Algorithm - INFO   - ==> Iteration [160][ 450 /  469]: {'prec1': 98.4874, 'loss': 0.0379, 'load_time': 43.4501, 'process_time': 56.5499}
2020-09-08 00:16:32,596 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.4793, 'loss': 0.0381, 'load_time': 43.6874, 'process_time': 56.3126}
2020-09-08 00:16:32,677 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:16:32,677 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:16:39,251 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1542, 'loss': 0.2265, 'load_time': 2.4754, 'process_time': 97.5246}
2020-09-08 00:16:39,251 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1542, 'loss': 0.2265, 'load_time': 2.4754, 'process_time': 97.5246}
2020-09-08 00:16:39,251 - algorithms.Algorithm - INFO   - Training epoch [161 / 200]
2020-09-08 00:16:39,251 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:16:39,252 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:16:44,825 - algorithms.Algorithm - INFO   - ==> Iteration [161][  50 /  469]: {'prec1': 98.7617, 'loss': 0.0316, 'load_time': 40.32, 'process_time': 59.68}
2020-09-08 00:16:50,338 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 100 /  469]: {'prec1': 98.8164, 'loss': 0.03, 'load_time': 40.7232, 'process_time': 59.2768}
2020-09-08 00:16:55,900 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 150 /  469]: {'prec1': 98.8242, 'loss': 0.03, 'load_time': 41.9211, 'process_time': 58.0789}
2020-09-08 00:17:01,457 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 200 /  469]: {'prec1': 98.8232, 'loss': 0.0298, 'load_time': 41.7833, 'process_time': 58.2167}
2020-09-08 00:17:07,006 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 250 /  469]: {'prec1': 98.8773, 'loss': 0.0287, 'load_time': 41.5543, 'process_time': 58.4457}
2020-09-08 00:17:12,653 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 300 /  469]: {'prec1': 98.9089, 'loss': 0.0282, 'load_time': 41.8593, 'process_time': 58.1407}
2020-09-08 00:17:18,285 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 350 /  469]: {'prec1': 98.9431, 'loss': 0.0274, 'load_time': 42.3887, 'process_time': 57.6113}
2020-09-08 00:17:23,958 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 400 /  469]: {'prec1': 98.9692, 'loss': 0.027, 'load_time': 42.4161, 'process_time': 57.5839}
2020-09-08 00:17:29,614 - algorithms.Algorithm - INFO   - ==> Iteration [161][ 450 /  469]: {'prec1': 98.9857, 'loss': 0.0266, 'load_time': 42.8765, 'process_time': 57.1235}
2020-09-08 00:17:31,848 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 98.989, 'loss': 0.0266, 'load_time': 43.1969, 'process_time': 56.8031}
2020-09-08 00:17:31,928 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:17:31,928 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:17:38,388 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3445, 'loss': 0.2335, 'load_time': 2.5444, 'process_time': 97.4556}
2020-09-08 00:17:38,388 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3445, 'loss': 0.2335, 'load_time': 2.5444, 'process_time': 97.4556}
2020-09-08 00:17:38,388 - algorithms.Algorithm - INFO   - Training epoch [162 / 200]
2020-09-08 00:17:38,388 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:17:38,388 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:17:44,097 - algorithms.Algorithm - INFO   - ==> Iteration [162][  50 /  469]: {'prec1': 99.0664, 'loss': 0.0243, 'load_time': 45.9964, 'process_time': 54.0036}
2020-09-08 00:17:49,704 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 100 /  469]: {'prec1': 99.2188, 'loss': 0.0224, 'load_time': 44.2114, 'process_time': 55.7886}
2020-09-08 00:17:55,245 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 150 /  469]: {'prec1': 99.224, 'loss': 0.0222, 'load_time': 44.2093, 'process_time': 55.7907}
2020-09-08 00:18:00,875 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 200 /  469]: {'prec1': 99.1992, 'loss': 0.0226, 'load_time': 44.5908, 'process_time': 55.4092}
2020-09-08 00:18:06,480 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 250 /  469]: {'prec1': 99.1781, 'loss': 0.0228, 'load_time': 44.2317, 'process_time': 55.7683}
2020-09-08 00:18:12,261 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 300 /  469]: {'prec1': 99.1758, 'loss': 0.0228, 'load_time': 45.4112, 'process_time': 54.5888}
2020-09-08 00:18:18,094 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 350 /  469]: {'prec1': 99.1719, 'loss': 0.0226, 'load_time': 45.6718, 'process_time': 54.3282}
2020-09-08 00:18:23,720 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 400 /  469]: {'prec1': 99.1611, 'loss': 0.0229, 'load_time': 45.2408, 'process_time': 54.7592}
2020-09-08 00:18:29,428 - algorithms.Algorithm - INFO   - ==> Iteration [162][ 450 /  469]: {'prec1': 99.168, 'loss': 0.0226, 'load_time': 44.9948, 'process_time': 55.0052}
2020-09-08 00:18:31,632 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.1685, 'loss': 0.0226, 'load_time': 45.0551, 'process_time': 54.9449}
2020-09-08 00:18:31,713 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:18:31,713 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:18:38,305 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3594, 'loss': 0.2397, 'load_time': 2.6534, 'process_time': 97.3466}
2020-09-08 00:18:38,305 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3594, 'loss': 0.2397, 'load_time': 2.6534, 'process_time': 97.3466}
2020-09-08 00:18:38,305 - algorithms.Algorithm - INFO   - Training epoch [163 / 200]
2020-09-08 00:18:38,305 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:18:38,305 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:18:43,992 - algorithms.Algorithm - INFO   - ==> Iteration [163][  50 /  469]: {'prec1': 99.2031, 'loss': 0.0213, 'load_time': 41.6657, 'process_time': 58.3343}
2020-09-08 00:18:49,586 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 100 /  469]: {'prec1': 99.2891, 'loss': 0.0194, 'load_time': 41.6842, 'process_time': 58.3158}
2020-09-08 00:18:55,218 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 150 /  469]: {'prec1': 99.2995, 'loss': 0.0191, 'load_time': 42.52, 'process_time': 57.48}
2020-09-08 00:19:00,987 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 200 /  469]: {'prec1': 99.3193, 'loss': 0.0186, 'load_time': 43.8215, 'process_time': 56.1785}
2020-09-08 00:19:06,831 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 250 /  469]: {'prec1': 99.2898, 'loss': 0.0193, 'load_time': 44.9695, 'process_time': 55.0305}
2020-09-08 00:19:12,652 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 300 /  469]: {'prec1': 99.2552, 'loss': 0.0203, 'load_time': 45.5677, 'process_time': 54.4323}
2020-09-08 00:19:18,502 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 350 /  469]: {'prec1': 99.2439, 'loss': 0.0204, 'load_time': 45.8586, 'process_time': 54.1414}
2020-09-08 00:19:24,325 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 400 /  469]: {'prec1': 99.2373, 'loss': 0.0205, 'load_time': 46.1089, 'process_time': 53.8911}
2020-09-08 00:19:30,156 - algorithms.Algorithm - INFO   - ==> Iteration [163][ 450 /  469]: {'prec1': 99.2357, 'loss': 0.0205, 'load_time': 46.5053, 'process_time': 53.4947}
2020-09-08 00:19:32,352 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.2222, 'loss': 0.0207, 'load_time': 46.4824, 'process_time': 53.5176}
2020-09-08 00:19:32,434 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:19:32,434 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:19:39,087 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4533, 'loss': 0.2422, 'load_time': 2.5567, 'process_time': 97.4433}
2020-09-08 00:19:39,088 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4533, 'loss': 0.2422, 'load_time': 2.5567, 'process_time': 97.4433}
2020-09-08 00:19:39,088 - algorithms.Algorithm - INFO   - Training epoch [164 / 200]
2020-09-08 00:19:39,088 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:19:39,088 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:19:44,691 - algorithms.Algorithm - INFO   - ==> Iteration [164][  50 /  469]: {'prec1': 99.3047, 'loss': 0.0187, 'load_time': 40.9058, 'process_time': 59.0942}
2020-09-08 00:19:50,371 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 100 /  469]: {'prec1': 99.3027, 'loss': 0.0189, 'load_time': 42.0929, 'process_time': 57.9071}
2020-09-08 00:19:56,027 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 150 /  469]: {'prec1': 99.3112, 'loss': 0.0189, 'load_time': 42.1929, 'process_time': 57.8071}
2020-09-08 00:20:01,737 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 200 /  469]: {'prec1': 99.2676, 'loss': 0.02, 'load_time': 43.2709, 'process_time': 56.7291}
2020-09-08 00:20:07,603 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 250 /  469]: {'prec1': 99.2711, 'loss': 0.02, 'load_time': 43.9563, 'process_time': 56.0437}
2020-09-08 00:20:13,373 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 300 /  469]: {'prec1': 99.2695, 'loss': 0.0199, 'load_time': 44.4614, 'process_time': 55.5386}
2020-09-08 00:20:19,140 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 350 /  469]: {'prec1': 99.2796, 'loss': 0.0195, 'load_time': 44.8805, 'process_time': 55.1195}
2020-09-08 00:20:24,968 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 400 /  469]: {'prec1': 99.2759, 'loss': 0.0197, 'load_time': 45.1812, 'process_time': 54.8188}
2020-09-08 00:20:30,772 - algorithms.Algorithm - INFO   - ==> Iteration [164][ 450 /  469]: {'prec1': 99.2804, 'loss': 0.0195, 'load_time': 45.6045, 'process_time': 54.3955}
2020-09-08 00:20:32,983 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.279, 'loss': 0.0196, 'load_time': 46.0078, 'process_time': 53.9922}
2020-09-08 00:20:33,065 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:20:33,065 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:20:39,682 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.389, 'loss': 0.2448, 'load_time': 2.5611, 'process_time': 97.4389}
2020-09-08 00:20:39,683 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.389, 'loss': 0.2448, 'load_time': 2.5611, 'process_time': 97.4389}
2020-09-08 00:20:39,683 - algorithms.Algorithm - INFO   - Training epoch [165 / 200]
2020-09-08 00:20:39,683 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:20:39,683 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:20:45,241 - algorithms.Algorithm - INFO   - ==> Iteration [165][  50 /  469]: {'prec1': 99.2695, 'loss': 0.0201, 'load_time': 40.4244, 'process_time': 59.5756}
2020-09-08 00:20:50,985 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 100 /  469]: {'prec1': 99.375, 'loss': 0.0178, 'load_time': 42.8586, 'process_time': 57.1414}
2020-09-08 00:20:56,746 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 150 /  469]: {'prec1': 99.3555, 'loss': 0.0182, 'load_time': 44.7164, 'process_time': 55.2836}
2020-09-08 00:21:02,478 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 200 /  469]: {'prec1': 99.3438, 'loss': 0.0185, 'load_time': 45.6762, 'process_time': 54.3238}
2020-09-08 00:21:08,247 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 250 /  469]: {'prec1': 99.3242, 'loss': 0.0188, 'load_time': 46.2272, 'process_time': 53.7728}
2020-09-08 00:21:13,969 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 300 /  469]: {'prec1': 99.3418, 'loss': 0.0184, 'load_time': 45.9296, 'process_time': 54.0704}
2020-09-08 00:21:19,724 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 350 /  469]: {'prec1': 99.3359, 'loss': 0.0186, 'load_time': 46.2107, 'process_time': 53.7893}
2020-09-08 00:21:25,536 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 400 /  469]: {'prec1': 99.311, 'loss': 0.019, 'load_time': 46.6883, 'process_time': 53.3117}
2020-09-08 00:21:31,342 - algorithms.Algorithm - INFO   - ==> Iteration [165][ 450 /  469]: {'prec1': 99.3025, 'loss': 0.0191, 'load_time': 46.7368, 'process_time': 53.2632}
2020-09-08 00:21:33,534 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.3061, 'loss': 0.0191, 'load_time': 46.6986, 'process_time': 53.3014}
2020-09-08 00:21:33,617 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:21:33,617 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:21:40,272 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3643, 'loss': 0.2491, 'load_time': 2.6434, 'process_time': 97.3566}
2020-09-08 00:21:40,272 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3643, 'loss': 0.2491, 'load_time': 2.6434, 'process_time': 97.3566}
2020-09-08 00:21:40,272 - algorithms.Algorithm - INFO   - Training epoch [166 / 200]
2020-09-08 00:21:40,272 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:21:40,273 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:21:45,930 - algorithms.Algorithm - INFO   - ==> Iteration [166][  50 /  469]: {'prec1': 99.3008, 'loss': 0.0197, 'load_time': 38.3601, 'process_time': 61.6399}
2020-09-08 00:21:51,535 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 100 /  469]: {'prec1': 99.3984, 'loss': 0.0178, 'load_time': 39.7103, 'process_time': 60.2897}
2020-09-08 00:21:57,297 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 150 /  469]: {'prec1': 99.4049, 'loss': 0.0173, 'load_time': 41.2572, 'process_time': 58.7428}
2020-09-08 00:22:03,089 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 200 /  469]: {'prec1': 99.4111, 'loss': 0.0169, 'load_time': 42.1867, 'process_time': 57.8133}
2020-09-08 00:22:08,881 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 250 /  469]: {'prec1': 99.4102, 'loss': 0.0172, 'load_time': 43.0305, 'process_time': 56.9695}
2020-09-08 00:22:14,683 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 300 /  469]: {'prec1': 99.3809, 'loss': 0.0177, 'load_time': 43.6712, 'process_time': 56.3288}
2020-09-08 00:22:20,467 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 350 /  469]: {'prec1': 99.3633, 'loss': 0.018, 'load_time': 44.1081, 'process_time': 55.8919}
2020-09-08 00:22:26,172 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 400 /  469]: {'prec1': 99.3589, 'loss': 0.018, 'load_time': 44.4857, 'process_time': 55.5143}
2020-09-08 00:22:31,902 - algorithms.Algorithm - INFO   - ==> Iteration [166][ 450 /  469]: {'prec1': 99.3407, 'loss': 0.0182, 'load_time': 44.3977, 'process_time': 55.6023}
2020-09-08 00:22:34,088 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.3415, 'loss': 0.0182, 'load_time': 44.3981, 'process_time': 55.6019}
2020-09-08 00:22:34,170 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:22:34,170 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:22:40,907 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3816, 'loss': 0.2502, 'load_time': 2.7003, 'process_time': 97.2997}
2020-09-08 00:22:40,907 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3816, 'loss': 0.2502, 'load_time': 2.7003, 'process_time': 97.2997}
2020-09-08 00:22:40,907 - algorithms.Algorithm - INFO   - Training epoch [167 / 200]
2020-09-08 00:22:40,907 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:22:40,907 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:22:46,580 - algorithms.Algorithm - INFO   - ==> Iteration [167][  50 /  469]: {'prec1': 99.3633, 'loss': 0.0184, 'load_time': 41.8286, 'process_time': 58.1714}
2020-09-08 00:22:52,252 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 100 /  469]: {'prec1': 99.3789, 'loss': 0.018, 'load_time': 41.9942, 'process_time': 58.0058}
2020-09-08 00:22:57,947 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 150 /  469]: {'prec1': 99.362, 'loss': 0.018, 'load_time': 43.8861, 'process_time': 56.1139}
2020-09-08 00:23:03,708 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 200 /  469]: {'prec1': 99.375, 'loss': 0.0175, 'load_time': 44.925, 'process_time': 55.075}
2020-09-08 00:23:09,440 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 250 /  469]: {'prec1': 99.3625, 'loss': 0.0175, 'load_time': 45.2405, 'process_time': 54.7595}
2020-09-08 00:23:15,274 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 300 /  469]: {'prec1': 99.3535, 'loss': 0.0179, 'load_time': 45.1863, 'process_time': 54.8137}
2020-09-08 00:23:21,062 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 350 /  469]: {'prec1': 99.3588, 'loss': 0.0178, 'load_time': 45.5956, 'process_time': 54.4044}
2020-09-08 00:23:26,879 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 400 /  469]: {'prec1': 99.353, 'loss': 0.0179, 'load_time': 45.8215, 'process_time': 54.1785}
2020-09-08 00:23:32,686 - algorithms.Algorithm - INFO   - ==> Iteration [167][ 450 /  469]: {'prec1': 99.3498, 'loss': 0.018, 'load_time': 46.008, 'process_time': 53.992}
2020-09-08 00:23:34,885 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.3519, 'loss': 0.0179, 'load_time': 45.9631, 'process_time': 54.0369}
2020-09-08 00:23:34,962 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:23:34,963 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:23:41,607 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4682, 'loss': 0.2511, 'load_time': 2.5483, 'process_time': 97.4517}
2020-09-08 00:23:41,607 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4682, 'loss': 0.2511, 'load_time': 2.5483, 'process_time': 97.4517}
2020-09-08 00:23:41,607 - algorithms.Algorithm - INFO   - Training epoch [168 / 200]
2020-09-08 00:23:41,607 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:23:41,607 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:23:47,224 - algorithms.Algorithm - INFO   - ==> Iteration [168][  50 /  469]: {'prec1': 99.3906, 'loss': 0.0176, 'load_time': 38.8478, 'process_time': 61.1522}
2020-09-08 00:23:52,757 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 100 /  469]: {'prec1': 99.4082, 'loss': 0.0166, 'load_time': 38.7888, 'process_time': 61.2112}
2020-09-08 00:23:58,480 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 150 /  469]: {'prec1': 99.4115, 'loss': 0.0168, 'load_time': 40.4067, 'process_time': 59.5933}
2020-09-08 00:24:04,282 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 200 /  469]: {'prec1': 99.4229, 'loss': 0.0166, 'load_time': 41.4273, 'process_time': 58.5727}
2020-09-08 00:24:10,043 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 250 /  469]: {'prec1': 99.4078, 'loss': 0.0167, 'load_time': 41.8162, 'process_time': 58.1838}
2020-09-08 00:24:15,808 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 300 /  469]: {'prec1': 99.4069, 'loss': 0.0167, 'load_time': 42.7171, 'process_time': 57.2829}
2020-09-08 00:24:21,558 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 350 /  469]: {'prec1': 99.3923, 'loss': 0.0169, 'load_time': 42.8225, 'process_time': 57.1775}
2020-09-08 00:24:27,288 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 400 /  469]: {'prec1': 99.3818, 'loss': 0.0172, 'load_time': 43.1548, 'process_time': 56.8452}
2020-09-08 00:24:33,104 - algorithms.Algorithm - INFO   - ==> Iteration [168][ 450 /  469]: {'prec1': 99.3911, 'loss': 0.017, 'load_time': 43.8066, 'process_time': 56.1934}
2020-09-08 00:24:35,297 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.3964, 'loss': 0.0169, 'load_time': 43.9241, 'process_time': 56.0759}
2020-09-08 00:24:35,378 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:24:35,378 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:24:41,968 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4162, 'loss': 0.2554, 'load_time': 2.6804, 'process_time': 97.3196}
2020-09-08 00:24:41,968 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4162, 'loss': 0.2554, 'load_time': 2.6804, 'process_time': 97.3196}
2020-09-08 00:24:41,968 - algorithms.Algorithm - INFO   - Training epoch [169 / 200]
2020-09-08 00:24:41,968 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:24:41,968 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:24:47,677 - algorithms.Algorithm - INFO   - ==> Iteration [169][  50 /  469]: {'prec1': 99.3711, 'loss': 0.0169, 'load_time': 40.52, 'process_time': 59.48}
2020-09-08 00:24:53,352 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 100 /  469]: {'prec1': 99.3828, 'loss': 0.0165, 'load_time': 41.8232, 'process_time': 58.1768}
2020-09-08 00:24:59,117 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 150 /  469]: {'prec1': 99.4141, 'loss': 0.0162, 'load_time': 42.1742, 'process_time': 57.8258}
2020-09-08 00:25:04,894 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 200 /  469]: {'prec1': 99.4131, 'loss': 0.0163, 'load_time': 42.798, 'process_time': 57.202}
2020-09-08 00:25:10,701 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 250 /  469]: {'prec1': 99.4398, 'loss': 0.0157, 'load_time': 44.1826, 'process_time': 55.8174}
2020-09-08 00:25:16,425 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 300 /  469]: {'prec1': 99.4258, 'loss': 0.0161, 'load_time': 44.3527, 'process_time': 55.6473}
2020-09-08 00:25:22,271 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 350 /  469]: {'prec1': 99.4124, 'loss': 0.0165, 'load_time': 44.8393, 'process_time': 55.1607}
2020-09-08 00:25:28,020 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 400 /  469]: {'prec1': 99.4092, 'loss': 0.0166, 'load_time': 44.8364, 'process_time': 55.1636}
2020-09-08 00:25:33,790 - algorithms.Algorithm - INFO   - ==> Iteration [169][ 450 /  469]: {'prec1': 99.4049, 'loss': 0.0165, 'load_time': 45.1241, 'process_time': 54.8759}
2020-09-08 00:25:35,961 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.4084, 'loss': 0.0165, 'load_time': 45.0719, 'process_time': 54.9281}
2020-09-08 00:25:36,043 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:25:36,043 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:25:42,691 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4088, 'loss': 0.2583, 'load_time': 2.6232, 'process_time': 97.3768}
2020-09-08 00:25:42,691 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4088, 'loss': 0.2583, 'load_time': 2.6232, 'process_time': 97.3768}
2020-09-08 00:25:42,691 - algorithms.Algorithm - INFO   - Training epoch [170 / 200]
2020-09-08 00:25:42,691 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:25:42,691 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:25:48,340 - algorithms.Algorithm - INFO   - ==> Iteration [170][  50 /  469]: {'prec1': 99.5273, 'loss': 0.014, 'load_time': 40.9036, 'process_time': 59.0964}
2020-09-08 00:25:54,061 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 100 /  469]: {'prec1': 99.5, 'loss': 0.0141, 'load_time': 43.8819, 'process_time': 56.1181}
2020-09-08 00:25:59,798 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 150 /  469]: {'prec1': 99.4896, 'loss': 0.0149, 'load_time': 44.511, 'process_time': 55.489}
2020-09-08 00:26:05,534 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 200 /  469]: {'prec1': 99.4697, 'loss': 0.0152, 'load_time': 45.3492, 'process_time': 54.6508}
2020-09-08 00:26:11,326 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 250 /  469]: {'prec1': 99.4727, 'loss': 0.0151, 'load_time': 46.9112, 'process_time': 53.0888}
2020-09-08 00:26:17,103 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 300 /  469]: {'prec1': 99.4831, 'loss': 0.0147, 'load_time': 47.0205, 'process_time': 52.9795}
2020-09-08 00:26:22,805 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 350 /  469]: {'prec1': 99.4632, 'loss': 0.0151, 'load_time': 46.2176, 'process_time': 53.7824}
2020-09-08 00:26:28,633 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 400 /  469]: {'prec1': 99.4561, 'loss': 0.0154, 'load_time': 46.3374, 'process_time': 53.6626}
2020-09-08 00:26:34,362 - algorithms.Algorithm - INFO   - ==> Iteration [170][ 450 /  469]: {'prec1': 99.4431, 'loss': 0.0156, 'load_time': 46.0991, 'process_time': 53.9009}
2020-09-08 00:26:36,530 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.4432, 'loss': 0.0157, 'load_time': 46.1783, 'process_time': 53.8217}
2020-09-08 00:26:36,608 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:26:36,608 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:26:43,149 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.4509, 'loss': 0.2563, 'load_time': 2.5734, 'process_time': 97.4266}
2020-09-08 00:26:43,150 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.4509, 'loss': 0.2563, 'load_time': 2.5734, 'process_time': 97.4266}
2020-09-08 00:26:43,150 - algorithms.Algorithm - INFO   - Training epoch [171 / 200]
2020-09-08 00:26:43,150 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:26:43,150 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:26:48,872 - algorithms.Algorithm - INFO   - ==> Iteration [171][  50 /  469]: {'prec1': 99.5898, 'loss': 0.0135, 'load_time': 45.2837, 'process_time': 54.7163}
2020-09-08 00:26:54,551 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 100 /  469]: {'prec1': 99.5469, 'loss': 0.0141, 'load_time': 44.3883, 'process_time': 55.6117}
2020-09-08 00:27:00,263 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 150 /  469]: {'prec1': 99.5156, 'loss': 0.0142, 'load_time': 44.9389, 'process_time': 55.0611}
2020-09-08 00:27:06,084 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 200 /  469]: {'prec1': 99.5234, 'loss': 0.014, 'load_time': 45.57, 'process_time': 54.43}
2020-09-08 00:27:11,919 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 250 /  469]: {'prec1': 99.5016, 'loss': 0.0144, 'load_time': 46.1466, 'process_time': 53.8534}
2020-09-08 00:27:17,670 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 300 /  469]: {'prec1': 99.5026, 'loss': 0.0146, 'load_time': 46.5725, 'process_time': 53.4275}
2020-09-08 00:27:23,376 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 350 /  469]: {'prec1': 99.4922, 'loss': 0.0148, 'load_time': 46.483, 'process_time': 53.517}
2020-09-08 00:27:29,125 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 400 /  469]: {'prec1': 99.48, 'loss': 0.015, 'load_time': 46.8136, 'process_time': 53.1864}
2020-09-08 00:27:34,893 - algorithms.Algorithm - INFO   - ==> Iteration [171][ 450 /  469]: {'prec1': 99.4714, 'loss': 0.0151, 'load_time': 47.2401, 'process_time': 52.7599}
2020-09-08 00:27:37,122 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.465, 'loss': 0.0152, 'load_time': 47.4166, 'process_time': 52.5834}
2020-09-08 00:27:37,204 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:27:37,205 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:27:43,642 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.263, 'loss': 0.2657, 'load_time': 2.5496, 'process_time': 97.4504}
2020-09-08 00:27:43,642 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.263, 'loss': 0.2657, 'load_time': 2.5496, 'process_time': 97.4504}
2020-09-08 00:27:43,642 - algorithms.Algorithm - INFO   - Training epoch [172 / 200]
2020-09-08 00:27:43,642 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:27:43,642 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:27:49,334 - algorithms.Algorithm - INFO   - ==> Iteration [172][  50 /  469]: {'prec1': 99.4844, 'loss': 0.0152, 'load_time': 41.1198, 'process_time': 58.8802}
2020-09-08 00:27:54,923 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 100 /  469]: {'prec1': 99.4688, 'loss': 0.0155, 'load_time': 42.1802, 'process_time': 57.8198}
2020-09-08 00:28:00,550 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 150 /  469]: {'prec1': 99.4857, 'loss': 0.015, 'load_time': 42.8945, 'process_time': 57.1055}
2020-09-08 00:28:06,337 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 200 /  469]: {'prec1': 99.501, 'loss': 0.0148, 'load_time': 43.7744, 'process_time': 56.2256}
2020-09-08 00:28:12,073 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 250 /  469]: {'prec1': 99.4898, 'loss': 0.0149, 'load_time': 43.9852, 'process_time': 56.0148}
2020-09-08 00:28:17,808 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 300 /  469]: {'prec1': 99.4935, 'loss': 0.0147, 'load_time': 44.4085, 'process_time': 55.5915}
2020-09-08 00:28:23,553 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 350 /  469]: {'prec1': 99.4816, 'loss': 0.0149, 'load_time': 44.9846, 'process_time': 55.0154}
2020-09-08 00:28:29,352 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 400 /  469]: {'prec1': 99.4746, 'loss': 0.0151, 'load_time': 45.5889, 'process_time': 54.4111}
2020-09-08 00:28:35,154 - algorithms.Algorithm - INFO   - ==> Iteration [172][ 450 /  469]: {'prec1': 99.4757, 'loss': 0.015, 'load_time': 45.5962, 'process_time': 54.4038}
2020-09-08 00:28:37,422 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.4688, 'loss': 0.0152, 'load_time': 45.8941, 'process_time': 54.1059}
2020-09-08 00:28:37,503 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:28:37,503 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:28:44,079 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3371, 'loss': 0.2686, 'load_time': 2.9768, 'process_time': 97.0232}
2020-09-08 00:28:44,079 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3371, 'loss': 0.2686, 'load_time': 2.9768, 'process_time': 97.0232}
2020-09-08 00:28:44,079 - algorithms.Algorithm - INFO   - Training epoch [173 / 200]
2020-09-08 00:28:44,079 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:28:44,079 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:28:49,752 - algorithms.Algorithm - INFO   - ==> Iteration [173][  50 /  469]: {'prec1': 99.4336, 'loss': 0.0159, 'load_time': 45.5573, 'process_time': 54.4427}
2020-09-08 00:28:55,400 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 100 /  469]: {'prec1': 99.459, 'loss': 0.0156, 'load_time': 46.527, 'process_time': 53.473}
2020-09-08 00:29:01,036 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 150 /  469]: {'prec1': 99.4974, 'loss': 0.0146, 'load_time': 45.7437, 'process_time': 54.2563}
2020-09-08 00:29:06,807 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 200 /  469]: {'prec1': 99.5293, 'loss': 0.014, 'load_time': 45.91, 'process_time': 54.09}
2020-09-08 00:29:12,574 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 250 /  469]: {'prec1': 99.5187, 'loss': 0.0142, 'load_time': 46.4685, 'process_time': 53.5315}
2020-09-08 00:29:18,277 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 300 /  469]: {'prec1': 99.5182, 'loss': 0.0144, 'load_time': 45.9622, 'process_time': 54.0378}
2020-09-08 00:29:23,980 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 350 /  469]: {'prec1': 99.505, 'loss': 0.0145, 'load_time': 46.1547, 'process_time': 53.8453}
2020-09-08 00:29:29,736 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 400 /  469]: {'prec1': 99.4971, 'loss': 0.0146, 'load_time': 46.4508, 'process_time': 53.5492}
2020-09-08 00:29:35,601 - algorithms.Algorithm - INFO   - ==> Iteration [173][ 450 /  469]: {'prec1': 99.4918, 'loss': 0.0147, 'load_time': 46.5628, 'process_time': 53.4372}
2020-09-08 00:29:37,842 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.4878, 'loss': 0.0148, 'load_time': 46.7821, 'process_time': 53.2179}
2020-09-08 00:29:37,925 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:29:37,925 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:29:44,439 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2728, 'loss': 0.2693, 'load_time': 2.5606, 'process_time': 97.4394}
2020-09-08 00:29:44,439 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2728, 'loss': 0.2693, 'load_time': 2.5606, 'process_time': 97.4394}
2020-09-08 00:29:44,439 - algorithms.Algorithm - INFO   - Training epoch [174 / 200]
2020-09-08 00:29:44,440 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:29:44,440 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:29:50,233 - algorithms.Algorithm - INFO   - ==> Iteration [174][  50 /  469]: {'prec1': 99.5742, 'loss': 0.013, 'load_time': 44.0684, 'process_time': 55.9316}
2020-09-08 00:29:55,809 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 100 /  469]: {'prec1': 99.5684, 'loss': 0.0128, 'load_time': 42.1263, 'process_time': 57.8737}
2020-09-08 00:30:01,557 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 150 /  469]: {'prec1': 99.5794, 'loss': 0.0126, 'load_time': 43.3156, 'process_time': 56.6844}
2020-09-08 00:30:07,290 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 200 /  469]: {'prec1': 99.5479, 'loss': 0.0132, 'load_time': 43.478, 'process_time': 56.522}
2020-09-08 00:30:13,065 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 250 /  469]: {'prec1': 99.5375, 'loss': 0.0133, 'load_time': 43.5881, 'process_time': 56.4119}
2020-09-08 00:30:18,747 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 300 /  469]: {'prec1': 99.5241, 'loss': 0.0137, 'load_time': 43.6244, 'process_time': 56.3756}
2020-09-08 00:30:24,546 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 350 /  469]: {'prec1': 99.5156, 'loss': 0.014, 'load_time': 44.2694, 'process_time': 55.7306}
2020-09-08 00:30:30,341 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 400 /  469]: {'prec1': 99.5073, 'loss': 0.0142, 'load_time': 44.4311, 'process_time': 55.5689}
2020-09-08 00:30:36,129 - algorithms.Algorithm - INFO   - ==> Iteration [174][ 450 /  469]: {'prec1': 99.5117, 'loss': 0.0142, 'load_time': 44.4944, 'process_time': 55.5056}
2020-09-08 00:30:38,376 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5044, 'loss': 0.0143, 'load_time': 44.8803, 'process_time': 55.1197}
2020-09-08 00:30:38,460 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:30:38,460 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:30:45,009 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2086, 'loss': 0.2737, 'load_time': 2.5909, 'process_time': 97.4091}
2020-09-08 00:30:45,009 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2086, 'loss': 0.2737, 'load_time': 2.5909, 'process_time': 97.4091}
2020-09-08 00:30:45,009 - algorithms.Algorithm - INFO   - Training epoch [175 / 200]
2020-09-08 00:30:45,009 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:30:45,009 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:30:50,547 - algorithms.Algorithm - INFO   - ==> Iteration [175][  50 /  469]: {'prec1': 99.5781, 'loss': 0.0127, 'load_time': 37.0572, 'process_time': 62.9428}
2020-09-08 00:30:56,179 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 100 /  469]: {'prec1': 99.5605, 'loss': 0.0128, 'load_time': 39.0713, 'process_time': 60.9287}
2020-09-08 00:31:01,885 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 150 /  469]: {'prec1': 99.5208, 'loss': 0.0136, 'load_time': 40.1601, 'process_time': 59.8399}
2020-09-08 00:31:07,728 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 200 /  469]: {'prec1': 99.5205, 'loss': 0.0136, 'load_time': 41.729, 'process_time': 58.271}
2020-09-08 00:31:13,567 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 250 /  469]: {'prec1': 99.5086, 'loss': 0.014, 'load_time': 43.6957, 'process_time': 56.3043}
2020-09-08 00:31:19,259 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 300 /  469]: {'prec1': 99.5111, 'loss': 0.0141, 'load_time': 43.8149, 'process_time': 56.1851}
2020-09-08 00:31:25,092 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 350 /  469]: {'prec1': 99.5011, 'loss': 0.0142, 'load_time': 44.0738, 'process_time': 55.9262}
2020-09-08 00:31:30,847 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 400 /  469]: {'prec1': 99.5059, 'loss': 0.0141, 'load_time': 44.011, 'process_time': 55.989}
2020-09-08 00:31:36,620 - algorithms.Algorithm - INFO   - ==> Iteration [175][ 450 /  469]: {'prec1': 99.5082, 'loss': 0.014, 'load_time': 44.2024, 'process_time': 55.7976}
2020-09-08 00:31:38,798 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5048, 'loss': 0.0141, 'load_time': 44.3111, 'process_time': 55.6889}
2020-09-08 00:31:38,881 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:31:38,881 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:31:45,462 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1418, 'loss': 0.277, 'load_time': 2.5923, 'process_time': 97.4077}
2020-09-08 00:31:45,462 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1418, 'loss': 0.277, 'load_time': 2.5923, 'process_time': 97.4077}
2020-09-08 00:31:45,462 - algorithms.Algorithm - INFO   - Training epoch [176 / 200]
2020-09-08 00:31:45,462 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:31:45,462 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:31:51,116 - algorithms.Algorithm - INFO   - ==> Iteration [176][  50 /  469]: {'prec1': 99.6055, 'loss': 0.0124, 'load_time': 41.1201, 'process_time': 58.8799}
2020-09-08 00:31:56,820 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 100 /  469]: {'prec1': 99.5898, 'loss': 0.0126, 'load_time': 42.5199, 'process_time': 57.4801}
2020-09-08 00:32:02,517 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 150 /  469]: {'prec1': 99.612, 'loss': 0.0121, 'load_time': 43.6467, 'process_time': 56.3533}
2020-09-08 00:32:08,331 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 200 /  469]: {'prec1': 99.6035, 'loss': 0.0122, 'load_time': 44.3591, 'process_time': 55.6409}
2020-09-08 00:32:14,035 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 250 /  469]: {'prec1': 99.5828, 'loss': 0.0127, 'load_time': 45.1329, 'process_time': 54.8671}
2020-09-08 00:32:19,786 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 300 /  469]: {'prec1': 99.5781, 'loss': 0.0128, 'load_time': 45.1965, 'process_time': 54.8035}
2020-09-08 00:32:25,591 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 350 /  469]: {'prec1': 99.5692, 'loss': 0.0129, 'load_time': 45.3619, 'process_time': 54.6381}
2020-09-08 00:32:31,301 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 400 /  469]: {'prec1': 99.5532, 'loss': 0.0133, 'load_time': 45.3137, 'process_time': 54.6863}
2020-09-08 00:32:37,032 - algorithms.Algorithm - INFO   - ==> Iteration [176][ 450 /  469]: {'prec1': 99.5534, 'loss': 0.0133, 'load_time': 45.6704, 'process_time': 54.3296}
2020-09-08 00:32:39,245 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5464, 'loss': 0.0134, 'load_time': 45.669, 'process_time': 54.331}
2020-09-08 00:32:39,325 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:32:39,326 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:32:45,844 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.258, 'loss': 0.2758, 'load_time': 2.6168, 'process_time': 97.3832}
2020-09-08 00:32:45,845 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.258, 'loss': 0.2758, 'load_time': 2.6168, 'process_time': 97.3832}
2020-09-08 00:32:45,845 - algorithms.Algorithm - INFO   - Training epoch [177 / 200]
2020-09-08 00:32:45,845 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:32:45,845 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:32:51,546 - algorithms.Algorithm - INFO   - ==> Iteration [177][  50 /  469]: {'prec1': 99.5586, 'loss': 0.0129, 'load_time': 44.1011, 'process_time': 55.8989}
2020-09-08 00:32:57,179 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 100 /  469]: {'prec1': 99.5195, 'loss': 0.0137, 'load_time': 42.6941, 'process_time': 57.3059}
2020-09-08 00:33:02,923 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 150 /  469]: {'prec1': 99.543, 'loss': 0.0133, 'load_time': 44.5094, 'process_time': 55.4906}
2020-09-08 00:33:08,689 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 200 /  469]: {'prec1': 99.543, 'loss': 0.0133, 'load_time': 45.054, 'process_time': 54.946}
2020-09-08 00:33:14,414 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 250 /  469]: {'prec1': 99.5469, 'loss': 0.0134, 'load_time': 45.4816, 'process_time': 54.5184}
2020-09-08 00:33:20,234 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 300 /  469]: {'prec1': 99.5436, 'loss': 0.0135, 'load_time': 46.4396, 'process_time': 53.5604}
2020-09-08 00:33:25,999 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 350 /  469]: {'prec1': 99.5497, 'loss': 0.0135, 'load_time': 46.5349, 'process_time': 53.4651}
2020-09-08 00:33:31,807 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 400 /  469]: {'prec1': 99.5444, 'loss': 0.0134, 'load_time': 46.913, 'process_time': 53.087}
2020-09-08 00:33:37,553 - algorithms.Algorithm - INFO   - ==> Iteration [177][ 450 /  469]: {'prec1': 99.5408, 'loss': 0.0134, 'load_time': 47.04, 'process_time': 52.96}
2020-09-08 00:33:39,753 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5319, 'loss': 0.0136, 'load_time': 47.3006, 'process_time': 52.6994}
2020-09-08 00:33:39,834 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:33:39,834 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:33:46,315 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.258, 'loss': 0.2801, 'load_time': 2.5372, 'process_time': 97.4628}
2020-09-08 00:33:46,315 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.258, 'loss': 0.2801, 'load_time': 2.5372, 'process_time': 97.4628}
2020-09-08 00:33:46,315 - algorithms.Algorithm - INFO   - Training epoch [178 / 200]
2020-09-08 00:33:46,315 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:33:46,315 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:33:52,047 - algorithms.Algorithm - INFO   - ==> Iteration [178][  50 /  469]: {'prec1': 99.5664, 'loss': 0.0135, 'load_time': 45.3052, 'process_time': 54.6948}
2020-09-08 00:33:57,732 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 100 /  469]: {'prec1': 99.5664, 'loss': 0.0128, 'load_time': 43.5859, 'process_time': 56.4141}
2020-09-08 00:34:03,535 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 150 /  469]: {'prec1': 99.5859, 'loss': 0.0125, 'load_time': 44.3574, 'process_time': 55.6426}
2020-09-08 00:34:09,367 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 200 /  469]: {'prec1': 99.5635, 'loss': 0.0128, 'load_time': 44.8758, 'process_time': 55.1242}
2020-09-08 00:34:15,188 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 250 /  469]: {'prec1': 99.5641, 'loss': 0.0129, 'load_time': 45.3613, 'process_time': 54.6387}
2020-09-08 00:34:21,012 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 300 /  469]: {'prec1': 99.5566, 'loss': 0.013, 'load_time': 45.7118, 'process_time': 54.2882}
2020-09-08 00:34:26,738 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 350 /  469]: {'prec1': 99.5536, 'loss': 0.0131, 'load_time': 45.3067, 'process_time': 54.6933}
2020-09-08 00:34:32,553 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 400 /  469]: {'prec1': 99.5562, 'loss': 0.013, 'load_time': 45.8544, 'process_time': 54.1456}
2020-09-08 00:34:38,323 - algorithms.Algorithm - INFO   - ==> Iteration [178][ 450 /  469]: {'prec1': 99.5634, 'loss': 0.0129, 'load_time': 46.0363, 'process_time': 53.9637}
2020-09-08 00:34:40,535 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.555, 'loss': 0.0131, 'load_time': 46.0984, 'process_time': 53.9016}
2020-09-08 00:34:40,618 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:34:40,618 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:34:47,147 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3, 'loss': 0.2779, 'load_time': 2.6572, 'process_time': 97.3428}
2020-09-08 00:34:47,148 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3, 'loss': 0.2779, 'load_time': 2.6572, 'process_time': 97.3428}
2020-09-08 00:34:47,148 - algorithms.Algorithm - INFO   - Training epoch [179 / 200]
2020-09-08 00:34:47,148 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:34:47,148 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:34:52,852 - algorithms.Algorithm - INFO   - ==> Iteration [179][  50 /  469]: {'prec1': 99.5391, 'loss': 0.013, 'load_time': 45.2762, 'process_time': 54.7238}
2020-09-08 00:34:58,586 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 100 /  469]: {'prec1': 99.5508, 'loss': 0.0127, 'load_time': 44.3314, 'process_time': 55.6686}
2020-09-08 00:35:04,336 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 150 /  469]: {'prec1': 99.5794, 'loss': 0.0126, 'load_time': 44.4769, 'process_time': 55.5231}
2020-09-08 00:35:10,197 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 200 /  469]: {'prec1': 99.5674, 'loss': 0.0127, 'load_time': 46.0773, 'process_time': 53.9227}
2020-09-08 00:35:16,049 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 250 /  469]: {'prec1': 99.5586, 'loss': 0.013, 'load_time': 46.6057, 'process_time': 53.3943}
2020-09-08 00:35:21,814 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 300 /  469]: {'prec1': 99.5749, 'loss': 0.0127, 'load_time': 46.5292, 'process_time': 53.4708}
2020-09-08 00:35:27,621 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 350 /  469]: {'prec1': 99.567, 'loss': 0.0128, 'load_time': 46.3606, 'process_time': 53.6394}
2020-09-08 00:35:33,449 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 400 /  469]: {'prec1': 99.5762, 'loss': 0.0126, 'load_time': 46.2978, 'process_time': 53.7022}
2020-09-08 00:35:39,319 - algorithms.Algorithm - INFO   - ==> Iteration [179][ 450 /  469]: {'prec1': 99.5629, 'loss': 0.0128, 'load_time': 46.3704, 'process_time': 53.6296}
2020-09-08 00:35:41,483 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5643, 'loss': 0.0128, 'load_time': 46.1684, 'process_time': 53.8316}
2020-09-08 00:35:41,567 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:35:41,567 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:35:48,223 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3792, 'loss': 0.2814, 'load_time': 2.7213, 'process_time': 97.2787}
2020-09-08 00:35:48,223 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3792, 'loss': 0.2814, 'load_time': 2.7213, 'process_time': 97.2787}
2020-09-08 00:35:48,224 - algorithms.Algorithm - INFO   - Training epoch [180 / 200]
2020-09-08 00:35:48,224 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:35:48,224 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:35:53,889 - algorithms.Algorithm - INFO   - ==> Iteration [180][  50 /  469]: {'prec1': 99.5625, 'loss': 0.0122, 'load_time': 42.0478, 'process_time': 57.9522}
2020-09-08 00:35:59,574 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 100 /  469]: {'prec1': 99.6016, 'loss': 0.0118, 'load_time': 43.8816, 'process_time': 56.1184}
2020-09-08 00:36:05,237 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 150 /  469]: {'prec1': 99.5938, 'loss': 0.0121, 'load_time': 43.9588, 'process_time': 56.0412}
2020-09-08 00:36:11,109 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 200 /  469]: {'prec1': 99.6016, 'loss': 0.012, 'load_time': 45.022, 'process_time': 54.978}
2020-09-08 00:36:16,885 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 250 /  469]: {'prec1': 99.5969, 'loss': 0.0121, 'load_time': 45.4871, 'process_time': 54.5129}
2020-09-08 00:36:22,641 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 300 /  469]: {'prec1': 99.5788, 'loss': 0.0124, 'load_time': 45.6377, 'process_time': 54.3623}
2020-09-08 00:36:28,413 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 350 /  469]: {'prec1': 99.5831, 'loss': 0.0123, 'load_time': 45.7265, 'process_time': 54.2735}
2020-09-08 00:36:34,178 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 400 /  469]: {'prec1': 99.5776, 'loss': 0.0123, 'load_time': 45.7274, 'process_time': 54.2726}
2020-09-08 00:36:39,930 - algorithms.Algorithm - INFO   - ==> Iteration [180][ 450 /  469]: {'prec1': 99.5647, 'loss': 0.0125, 'load_time': 45.7662, 'process_time': 54.2338}
2020-09-08 00:36:42,138 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5647, 'loss': 0.0125, 'load_time': 45.8314, 'process_time': 54.1686}
2020-09-08 00:36:42,217 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:36:42,218 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:36:48,829 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1245, 'loss': 0.2897, 'load_time': 2.5685, 'process_time': 97.4315}
2020-09-08 00:36:48,829 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1245, 'loss': 0.2897, 'load_time': 2.5685, 'process_time': 97.4315}
2020-09-08 00:36:48,829 - algorithms.Algorithm - INFO   - Training epoch [181 / 200]
2020-09-08 00:36:48,829 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:36:48,829 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:36:54,527 - algorithms.Algorithm - INFO   - ==> Iteration [181][  50 /  469]: {'prec1': 99.6055, 'loss': 0.0116, 'load_time': 41.8457, 'process_time': 58.1543}
2020-09-08 00:37:00,214 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 100 /  469]: {'prec1': 99.6074, 'loss': 0.0121, 'load_time': 41.2924, 'process_time': 58.7076}
2020-09-08 00:37:05,978 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 150 /  469]: {'prec1': 99.5911, 'loss': 0.0123, 'load_time': 41.9642, 'process_time': 58.0358}
2020-09-08 00:37:11,743 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 200 /  469]: {'prec1': 99.585, 'loss': 0.0124, 'load_time': 42.7937, 'process_time': 57.2063}
2020-09-08 00:37:17,526 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 250 /  469]: {'prec1': 99.5875, 'loss': 0.0123, 'load_time': 43.211, 'process_time': 56.789}
2020-09-08 00:37:23,301 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 300 /  469]: {'prec1': 99.5924, 'loss': 0.0122, 'load_time': 43.9618, 'process_time': 56.0382}
2020-09-08 00:37:29,053 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 350 /  469]: {'prec1': 99.6021, 'loss': 0.0121, 'load_time': 44.3436, 'process_time': 55.6564}
2020-09-08 00:37:34,853 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 400 /  469]: {'prec1': 99.5972, 'loss': 0.0122, 'load_time': 44.7689, 'process_time': 55.2311}
2020-09-08 00:37:40,655 - algorithms.Algorithm - INFO   - ==> Iteration [181][ 450 /  469]: {'prec1': 99.5955, 'loss': 0.0123, 'load_time': 45.1979, 'process_time': 54.8021}
2020-09-08 00:37:42,834 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5899, 'loss': 0.0123, 'load_time': 45.233, 'process_time': 54.767}
2020-09-08 00:37:42,916 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:37:42,916 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:37:49,409 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3025, 'loss': 0.2835, 'load_time': 2.5788, 'process_time': 97.4212}
2020-09-08 00:37:49,409 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3025, 'loss': 0.2835, 'load_time': 2.5788, 'process_time': 97.4212}
2020-09-08 00:37:49,409 - algorithms.Algorithm - INFO   - Training epoch [182 / 200]
2020-09-08 00:37:49,409 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:37:49,409 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:37:55,124 - algorithms.Algorithm - INFO   - ==> Iteration [182][  50 /  469]: {'prec1': 99.6641, 'loss': 0.0105, 'load_time': 45.6153, 'process_time': 54.3847}
2020-09-08 00:38:00,771 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 100 /  469]: {'prec1': 99.6738, 'loss': 0.0103, 'load_time': 45.8803, 'process_time': 54.1197}
2020-09-08 00:38:06,476 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 150 /  469]: {'prec1': 99.6224, 'loss': 0.0112, 'load_time': 46.4217, 'process_time': 53.5783}
2020-09-08 00:38:12,260 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 200 /  469]: {'prec1': 99.6299, 'loss': 0.0111, 'load_time': 47.6324, 'process_time': 52.3676}
2020-09-08 00:38:18,072 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 250 /  469]: {'prec1': 99.6195, 'loss': 0.0113, 'load_time': 46.9676, 'process_time': 53.0324}
2020-09-08 00:38:23,876 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 300 /  469]: {'prec1': 99.6068, 'loss': 0.0117, 'load_time': 47.6487, 'process_time': 52.3513}
2020-09-08 00:38:29,692 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 350 /  469]: {'prec1': 99.601, 'loss': 0.0119, 'load_time': 48.2895, 'process_time': 51.7105}
2020-09-08 00:38:35,509 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 400 /  469]: {'prec1': 99.5801, 'loss': 0.0123, 'load_time': 47.7555, 'process_time': 52.2445}
2020-09-08 00:38:41,235 - algorithms.Algorithm - INFO   - ==> Iteration [182][ 450 /  469]: {'prec1': 99.5855, 'loss': 0.0122, 'load_time': 47.5134, 'process_time': 52.4866}
2020-09-08 00:38:43,413 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.589, 'loss': 0.0121, 'load_time': 47.4911, 'process_time': 52.5089}
2020-09-08 00:38:43,492 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:38:43,493 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:38:50,185 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3, 'loss': 0.2822, 'load_time': 2.5792, 'process_time': 97.4208}
2020-09-08 00:38:50,186 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3, 'loss': 0.2822, 'load_time': 2.5792, 'process_time': 97.4208}
2020-09-08 00:38:50,186 - algorithms.Algorithm - INFO   - Training epoch [183 / 200]
2020-09-08 00:38:50,186 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:38:50,186 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:38:55,883 - algorithms.Algorithm - INFO   - ==> Iteration [183][  50 /  469]: {'prec1': 99.6406, 'loss': 0.011, 'load_time': 42.156, 'process_time': 57.844}
2020-09-08 00:39:01,547 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 100 /  469]: {'prec1': 99.6621, 'loss': 0.0106, 'load_time': 43.1265, 'process_time': 56.8735}
2020-09-08 00:39:07,276 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 150 /  469]: {'prec1': 99.6172, 'loss': 0.0116, 'load_time': 44.9613, 'process_time': 55.0387}
2020-09-08 00:39:13,039 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 200 /  469]: {'prec1': 99.6299, 'loss': 0.0114, 'load_time': 45.6872, 'process_time': 54.3128}
2020-09-08 00:39:18,741 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 250 /  469]: {'prec1': 99.6148, 'loss': 0.0115, 'load_time': 46.0578, 'process_time': 53.9422}
2020-09-08 00:39:24,561 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 300 /  469]: {'prec1': 99.6217, 'loss': 0.0116, 'load_time': 46.6463, 'process_time': 53.3537}
2020-09-08 00:39:30,325 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 350 /  469]: {'prec1': 99.6256, 'loss': 0.0114, 'load_time': 46.9473, 'process_time': 53.0527}
2020-09-08 00:39:36,130 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 400 /  469]: {'prec1': 99.6196, 'loss': 0.0114, 'load_time': 47.5734, 'process_time': 52.4266}
2020-09-08 00:39:41,829 - algorithms.Algorithm - INFO   - ==> Iteration [183][ 450 /  469]: {'prec1': 99.6198, 'loss': 0.0115, 'load_time': 47.8772, 'process_time': 52.1228}
2020-09-08 00:39:44,057 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6221, 'loss': 0.0114, 'load_time': 48.0811, 'process_time': 51.9189}
2020-09-08 00:39:44,139 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:39:44,139 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:39:50,572 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2926, 'loss': 0.2875, 'load_time': 2.6145, 'process_time': 97.3855}
2020-09-08 00:39:50,573 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2926, 'loss': 0.2875, 'load_time': 2.6145, 'process_time': 97.3855}
2020-09-08 00:39:50,573 - algorithms.Algorithm - INFO   - Training epoch [184 / 200]
2020-09-08 00:39:50,573 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:39:50,573 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:39:56,239 - algorithms.Algorithm - INFO   - ==> Iteration [184][  50 /  469]: {'prec1': 99.6602, 'loss': 0.0106, 'load_time': 43.0238, 'process_time': 56.9762}
2020-09-08 00:40:01,948 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 100 /  469]: {'prec1': 99.6328, 'loss': 0.0113, 'load_time': 44.5943, 'process_time': 55.4057}
2020-09-08 00:40:07,763 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 150 /  469]: {'prec1': 99.6211, 'loss': 0.0113, 'load_time': 45.1286, 'process_time': 54.8714}
2020-09-08 00:40:13,528 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 200 /  469]: {'prec1': 99.6221, 'loss': 0.0113, 'load_time': 45.9877, 'process_time': 54.0123}
2020-09-08 00:40:19,320 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 250 /  469]: {'prec1': 99.625, 'loss': 0.0113, 'load_time': 45.7947, 'process_time': 54.2053}
2020-09-08 00:40:25,070 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 300 /  469]: {'prec1': 99.61, 'loss': 0.0117, 'load_time': 45.6345, 'process_time': 54.3655}
2020-09-08 00:40:30,847 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 350 /  469]: {'prec1': 99.6116, 'loss': 0.0116, 'load_time': 45.9156, 'process_time': 54.0844}
2020-09-08 00:40:36,632 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 400 /  469]: {'prec1': 99.5913, 'loss': 0.012, 'load_time': 46.1667, 'process_time': 53.8333}
2020-09-08 00:40:42,376 - algorithms.Algorithm - INFO   - ==> Iteration [184][ 450 /  469]: {'prec1': 99.5812, 'loss': 0.0121, 'load_time': 46.3552, 'process_time': 53.6448}
2020-09-08 00:40:44,549 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.5865, 'loss': 0.012, 'load_time': 46.4588, 'process_time': 53.5412}
2020-09-08 00:40:44,629 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:40:44,630 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:40:51,123 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3248, 'loss': 0.2814, 'load_time': 2.5399, 'process_time': 97.4601}
2020-09-08 00:40:51,123 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3248, 'loss': 0.2814, 'load_time': 2.5399, 'process_time': 97.4601}
2020-09-08 00:40:51,123 - algorithms.Algorithm - INFO   - Training epoch [185 / 200]
2020-09-08 00:40:51,123 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:40:51,123 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:40:56,823 - algorithms.Algorithm - INFO   - ==> Iteration [185][  50 /  469]: {'prec1': 99.6484, 'loss': 0.0109, 'load_time': 43.7518, 'process_time': 56.2482}
2020-09-08 00:41:02,440 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 100 /  469]: {'prec1': 99.6191, 'loss': 0.0116, 'load_time': 43.9252, 'process_time': 56.0748}
2020-09-08 00:41:08,251 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 150 /  469]: {'prec1': 99.6237, 'loss': 0.0112, 'load_time': 45.7588, 'process_time': 54.2412}
2020-09-08 00:41:13,992 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 200 /  469]: {'prec1': 99.625, 'loss': 0.0112, 'load_time': 47.3053, 'process_time': 52.6947}
2020-09-08 00:41:19,773 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 250 /  469]: {'prec1': 99.6305, 'loss': 0.0112, 'load_time': 47.5364, 'process_time': 52.4636}
2020-09-08 00:41:25,575 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 300 /  469]: {'prec1': 99.6165, 'loss': 0.0116, 'load_time': 47.6321, 'process_time': 52.3679}
2020-09-08 00:41:31,348 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 350 /  469]: {'prec1': 99.6049, 'loss': 0.0118, 'load_time': 48.011, 'process_time': 51.989}
2020-09-08 00:41:37,131 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 400 /  469]: {'prec1': 99.5942, 'loss': 0.012, 'load_time': 47.4647, 'process_time': 52.5353}
2020-09-08 00:41:42,922 - algorithms.Algorithm - INFO   - ==> Iteration [185][ 450 /  469]: {'prec1': 99.6011, 'loss': 0.0118, 'load_time': 47.3621, 'process_time': 52.6379}
2020-09-08 00:41:45,080 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6023, 'loss': 0.0118, 'load_time': 47.3661, 'process_time': 52.6339}
2020-09-08 00:41:45,161 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:41:45,161 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:41:51,811 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3445, 'loss': 0.2827, 'load_time': 2.5025, 'process_time': 97.4975}
2020-09-08 00:41:51,812 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3445, 'loss': 0.2827, 'load_time': 2.5025, 'process_time': 97.4975}
2020-09-08 00:41:51,812 - algorithms.Algorithm - INFO   - Training epoch [186 / 200]
2020-09-08 00:41:51,812 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:41:51,812 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:41:57,542 - algorithms.Algorithm - INFO   - ==> Iteration [186][  50 /  469]: {'prec1': 99.7227, 'loss': 0.0093, 'load_time': 42.3837, 'process_time': 57.6163}
2020-09-08 00:42:03,213 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 100 /  469]: {'prec1': 99.6875, 'loss': 0.0101, 'load_time': 43.8096, 'process_time': 56.1904}
2020-09-08 00:42:08,966 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 150 /  469]: {'prec1': 99.6836, 'loss': 0.0101, 'load_time': 45.7312, 'process_time': 54.2688}
2020-09-08 00:42:14,769 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 200 /  469]: {'prec1': 99.6582, 'loss': 0.0105, 'load_time': 46.5202, 'process_time': 53.4798}
2020-09-08 00:42:20,487 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 250 /  469]: {'prec1': 99.6703, 'loss': 0.0104, 'load_time': 46.6837, 'process_time': 53.3163}
2020-09-08 00:42:26,323 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 300 /  469]: {'prec1': 99.6615, 'loss': 0.0105, 'load_time': 46.5379, 'process_time': 53.4621}
2020-09-08 00:42:32,082 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 350 /  469]: {'prec1': 99.6417, 'loss': 0.0108, 'load_time': 46.7538, 'process_time': 53.2462}
2020-09-08 00:42:37,802 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 400 /  469]: {'prec1': 99.6411, 'loss': 0.0109, 'load_time': 46.7197, 'process_time': 53.2803}
2020-09-08 00:42:43,524 - algorithms.Algorithm - INFO   - ==> Iteration [186][ 450 /  469]: {'prec1': 99.6311, 'loss': 0.0111, 'load_time': 46.7413, 'process_time': 53.2587}
2020-09-08 00:42:45,719 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.631, 'loss': 0.0112, 'load_time': 46.8377, 'process_time': 53.1623}
2020-09-08 00:42:45,800 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:42:45,800 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:42:52,270 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2704, 'loss': 0.2892, 'load_time': 2.5807, 'process_time': 97.4193}
2020-09-08 00:42:52,270 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2704, 'loss': 0.2892, 'load_time': 2.5807, 'process_time': 97.4193}
2020-09-08 00:42:52,270 - algorithms.Algorithm - INFO   - Training epoch [187 / 200]
2020-09-08 00:42:52,271 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:42:52,271 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:42:58,004 - algorithms.Algorithm - INFO   - ==> Iteration [187][  50 /  469]: {'prec1': 99.6094, 'loss': 0.0116, 'load_time': 46.5486, 'process_time': 53.4514}
2020-09-08 00:43:03,727 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 100 /  469]: {'prec1': 99.6621, 'loss': 0.0105, 'load_time': 45.81, 'process_time': 54.19}
2020-09-08 00:43:09,566 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 150 /  469]: {'prec1': 99.6628, 'loss': 0.0105, 'load_time': 47.0185, 'process_time': 52.9815}
2020-09-08 00:43:15,338 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 200 /  469]: {'prec1': 99.666, 'loss': 0.0104, 'load_time': 47.7581, 'process_time': 52.2419}
2020-09-08 00:43:21,157 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 250 /  469]: {'prec1': 99.6719, 'loss': 0.0102, 'load_time': 47.8717, 'process_time': 52.1283}
2020-09-08 00:43:26,972 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 300 /  469]: {'prec1': 99.6641, 'loss': 0.0105, 'load_time': 47.438, 'process_time': 52.562}
2020-09-08 00:43:32,727 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 350 /  469]: {'prec1': 99.6607, 'loss': 0.0105, 'load_time': 47.4201, 'process_time': 52.5799}
2020-09-08 00:43:38,503 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 400 /  469]: {'prec1': 99.6572, 'loss': 0.0105, 'load_time': 47.6425, 'process_time': 52.3575}
2020-09-08 00:43:44,190 - algorithms.Algorithm - INFO   - ==> Iteration [187][ 450 /  469]: {'prec1': 99.6541, 'loss': 0.0106, 'load_time': 47.5769, 'process_time': 52.4231}
2020-09-08 00:43:46,362 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6541, 'loss': 0.0106, 'load_time': 47.6982, 'process_time': 52.3018}
2020-09-08 00:43:46,443 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:43:46,443 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:43:52,990 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3643, 'loss': 0.2856, 'load_time': 2.4859, 'process_time': 97.5141}
2020-09-08 00:43:52,990 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3643, 'loss': 0.2856, 'load_time': 2.4859, 'process_time': 97.5141}
2020-09-08 00:43:52,990 - algorithms.Algorithm - INFO   - Training epoch [188 / 200]
2020-09-08 00:43:52,990 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:43:52,990 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:43:58,682 - algorithms.Algorithm - INFO   - ==> Iteration [188][  50 /  469]: {'prec1': 99.6445, 'loss': 0.0096, 'load_time': 41.2672, 'process_time': 58.7328}
2020-09-08 00:44:04,289 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 100 /  469]: {'prec1': 99.6641, 'loss': 0.0095, 'load_time': 42.0868, 'process_time': 57.9132}
2020-09-08 00:44:10,039 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 150 /  469]: {'prec1': 99.6628, 'loss': 0.0103, 'load_time': 44.8965, 'process_time': 55.1035}
2020-09-08 00:44:15,802 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 200 /  469]: {'prec1': 99.6348, 'loss': 0.0111, 'load_time': 46.2288, 'process_time': 53.7712}
2020-09-08 00:44:21,664 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 250 /  469]: {'prec1': 99.6281, 'loss': 0.0112, 'load_time': 46.9116, 'process_time': 53.0884}
2020-09-08 00:44:27,362 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 300 /  469]: {'prec1': 99.6419, 'loss': 0.0109, 'load_time': 46.9552, 'process_time': 53.0448}
2020-09-08 00:44:33,097 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 350 /  469]: {'prec1': 99.6401, 'loss': 0.0109, 'load_time': 47.21, 'process_time': 52.79}
2020-09-08 00:44:38,951 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 400 /  469]: {'prec1': 99.6338, 'loss': 0.0109, 'load_time': 47.4419, 'process_time': 52.5581}
2020-09-08 00:44:44,687 - algorithms.Algorithm - INFO   - ==> Iteration [188][ 450 /  469]: {'prec1': 99.6341, 'loss': 0.0109, 'load_time': 47.2647, 'process_time': 52.7353}
2020-09-08 00:44:46,913 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6288, 'loss': 0.011, 'load_time': 47.3319, 'process_time': 52.6681}
2020-09-08 00:44:46,995 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:44:46,995 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:44:53,638 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.389, 'loss': 0.282, 'load_time': 2.6258, 'process_time': 97.3742}
2020-09-08 00:44:53,638 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.389, 'loss': 0.282, 'load_time': 2.6258, 'process_time': 97.3742}
2020-09-08 00:44:53,638 - algorithms.Algorithm - INFO   - Training epoch [189 / 200]
2020-09-08 00:44:53,638 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:44:53,638 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:44:59,272 - algorithms.Algorithm - INFO   - ==> Iteration [189][  50 /  469]: {'prec1': 99.6719, 'loss': 0.0114, 'load_time': 42.1788, 'process_time': 57.8212}
2020-09-08 00:45:04,920 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 100 /  469]: {'prec1': 99.6992, 'loss': 0.0101, 'load_time': 45.6803, 'process_time': 54.3197}
2020-09-08 00:45:10,623 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 150 /  469]: {'prec1': 99.6536, 'loss': 0.0111, 'load_time': 45.9921, 'process_time': 54.0079}
2020-09-08 00:45:16,331 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 200 /  469]: {'prec1': 99.6582, 'loss': 0.0107, 'load_time': 47.102, 'process_time': 52.898}
2020-09-08 00:45:22,099 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 250 /  469]: {'prec1': 99.6586, 'loss': 0.0107, 'load_time': 46.6332, 'process_time': 53.3668}
2020-09-08 00:45:27,779 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 300 /  469]: {'prec1': 99.668, 'loss': 0.0105, 'load_time': 46.6104, 'process_time': 53.3896}
2020-09-08 00:45:33,578 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 350 /  469]: {'prec1': 99.6652, 'loss': 0.0104, 'load_time': 46.6987, 'process_time': 53.3013}
2020-09-08 00:45:39,333 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 400 /  469]: {'prec1': 99.6577, 'loss': 0.0106, 'load_time': 47.0314, 'process_time': 52.9686}
2020-09-08 00:45:45,055 - algorithms.Algorithm - INFO   - ==> Iteration [189][ 450 /  469]: {'prec1': 99.6437, 'loss': 0.0108, 'load_time': 46.9529, 'process_time': 53.0471}
2020-09-08 00:45:47,269 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6435, 'loss': 0.0108, 'load_time': 46.986, 'process_time': 53.014}
2020-09-08 00:45:47,353 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:45:47,353 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:45:53,957 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2036, 'loss': 0.295, 'load_time': 2.6915, 'process_time': 97.3085}
2020-09-08 00:45:53,957 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2036, 'loss': 0.295, 'load_time': 2.6915, 'process_time': 97.3085}
2020-09-08 00:45:53,957 - algorithms.Algorithm - INFO   - Training epoch [190 / 200]
2020-09-08 00:45:53,957 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:45:53,957 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:45:59,578 - algorithms.Algorithm - INFO   - ==> Iteration [190][  50 /  469]: {'prec1': 99.707, 'loss': 0.0088, 'load_time': 41.0133, 'process_time': 58.9867}
2020-09-08 00:46:05,240 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 100 /  469]: {'prec1': 99.6934, 'loss': 0.0095, 'load_time': 41.8872, 'process_time': 58.1128}
2020-09-08 00:46:10,866 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 150 /  469]: {'prec1': 99.6732, 'loss': 0.0099, 'load_time': 42.2102, 'process_time': 57.7898}
2020-09-08 00:46:16,652 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 200 /  469]: {'prec1': 99.6572, 'loss': 0.0102, 'load_time': 43.8419, 'process_time': 56.1581}
2020-09-08 00:46:22,417 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 250 /  469]: {'prec1': 99.6508, 'loss': 0.0102, 'load_time': 44.4578, 'process_time': 55.5422}
2020-09-08 00:46:28,189 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 300 /  469]: {'prec1': 99.6523, 'loss': 0.0103, 'load_time': 44.8654, 'process_time': 55.1346}
2020-09-08 00:46:34,045 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 350 /  469]: {'prec1': 99.6613, 'loss': 0.0103, 'load_time': 45.3864, 'process_time': 54.6136}
2020-09-08 00:46:39,723 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 400 /  469]: {'prec1': 99.6621, 'loss': 0.0103, 'load_time': 45.2256, 'process_time': 54.7744}
2020-09-08 00:46:45,522 - algorithms.Algorithm - INFO   - ==> Iteration [190][ 450 /  469]: {'prec1': 99.6615, 'loss': 0.0103, 'load_time': 45.5843, 'process_time': 54.4157}
2020-09-08 00:46:47,709 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6607, 'loss': 0.0103, 'load_time': 45.796, 'process_time': 54.204}
2020-09-08 00:46:47,787 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:46:47,787 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:46:54,376 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2308, 'loss': 0.296, 'load_time': 2.5908, 'process_time': 97.4092}
2020-09-08 00:46:54,376 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2308, 'loss': 0.296, 'load_time': 2.5908, 'process_time': 97.4092}
2020-09-08 00:46:54,376 - algorithms.Algorithm - INFO   - Training epoch [191 / 200]
2020-09-08 00:46:54,376 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:46:54,376 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:47:00,008 - algorithms.Algorithm - INFO   - ==> Iteration [191][  50 /  469]: {'prec1': 99.7148, 'loss': 0.0092, 'load_time': 41.7114, 'process_time': 58.2886}
2020-09-08 00:47:05,722 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 100 /  469]: {'prec1': 99.6797, 'loss': 0.01, 'load_time': 43.2675, 'process_time': 56.7325}
2020-09-08 00:47:11,561 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 150 /  469]: {'prec1': 99.668, 'loss': 0.0103, 'load_time': 43.9244, 'process_time': 56.0756}
2020-09-08 00:47:17,342 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 200 /  469]: {'prec1': 99.6572, 'loss': 0.0104, 'load_time': 44.9621, 'process_time': 55.0379}
2020-09-08 00:47:23,122 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 250 /  469]: {'prec1': 99.6516, 'loss': 0.0103, 'load_time': 45.4063, 'process_time': 54.5937}
2020-09-08 00:47:28,873 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 300 /  469]: {'prec1': 99.6621, 'loss': 0.0103, 'load_time': 45.5106, 'process_time': 54.4894}
2020-09-08 00:47:34,712 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 350 /  469]: {'prec1': 99.6629, 'loss': 0.0102, 'load_time': 45.9237, 'process_time': 54.0763}
2020-09-08 00:47:40,488 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 400 /  469]: {'prec1': 99.6636, 'loss': 0.0101, 'load_time': 45.7717, 'process_time': 54.2283}
2020-09-08 00:47:46,313 - algorithms.Algorithm - INFO   - ==> Iteration [191][ 450 /  469]: {'prec1': 99.6584, 'loss': 0.0103, 'load_time': 45.6011, 'process_time': 54.3989}
2020-09-08 00:47:48,500 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6549, 'loss': 0.0104, 'load_time': 45.7034, 'process_time': 54.2966}
2020-09-08 00:47:48,582 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:47:48,582 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:47:55,078 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.263, 'loss': 0.2916, 'load_time': 2.5215, 'process_time': 97.4785}
2020-09-08 00:47:55,078 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.263, 'loss': 0.2916, 'load_time': 2.5215, 'process_time': 97.4785}
2020-09-08 00:47:55,078 - algorithms.Algorithm - INFO   - Training epoch [192 / 200]
2020-09-08 00:47:55,078 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:47:55,078 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:48:00,797 - algorithms.Algorithm - INFO   - ==> Iteration [192][  50 /  469]: {'prec1': 99.7109, 'loss': 0.0093, 'load_time': 43.5623, 'process_time': 56.4377}
2020-09-08 00:48:06,488 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 100 /  469]: {'prec1': 99.748, 'loss': 0.0086, 'load_time': 44.2727, 'process_time': 55.7273}
2020-09-08 00:48:12,164 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 150 /  469]: {'prec1': 99.7487, 'loss': 0.0085, 'load_time': 45.3708, 'process_time': 54.6292}
2020-09-08 00:48:17,887 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 200 /  469]: {'prec1': 99.751, 'loss': 0.0086, 'load_time': 46.3557, 'process_time': 53.6443}
2020-09-08 00:48:23,656 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 250 /  469]: {'prec1': 99.7297, 'loss': 0.0088, 'load_time': 46.2834, 'process_time': 53.7166}
2020-09-08 00:48:29,431 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 300 /  469]: {'prec1': 99.7331, 'loss': 0.0087, 'load_time': 46.3805, 'process_time': 53.6195}
2020-09-08 00:48:35,283 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 350 /  469]: {'prec1': 99.7232, 'loss': 0.0089, 'load_time': 46.5974, 'process_time': 53.4026}
2020-09-08 00:48:41,004 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 400 /  469]: {'prec1': 99.7002, 'loss': 0.0095, 'load_time': 46.3926, 'process_time': 53.6074}
2020-09-08 00:48:46,757 - algorithms.Algorithm - INFO   - ==> Iteration [192][ 450 /  469]: {'prec1': 99.6875, 'loss': 0.0098, 'load_time': 46.3753, 'process_time': 53.6247}
2020-09-08 00:48:48,887 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6856, 'loss': 0.0099, 'load_time': 46.1871, 'process_time': 53.8129}
2020-09-08 00:48:48,969 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:48:48,969 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:48:55,576 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1319, 'loss': 0.2962, 'load_time': 2.6034, 'process_time': 97.3966}
2020-09-08 00:48:55,576 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1319, 'loss': 0.2962, 'load_time': 2.6034, 'process_time': 97.3966}
2020-09-08 00:48:55,576 - algorithms.Algorithm - INFO   - Training epoch [193 / 200]
2020-09-08 00:48:55,576 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:48:55,576 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:49:01,251 - algorithms.Algorithm - INFO   - ==> Iteration [193][  50 /  469]: {'prec1': 99.6797, 'loss': 0.0092, 'load_time': 41.6095, 'process_time': 58.3905}
2020-09-08 00:49:06,905 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 100 /  469]: {'prec1': 99.6973, 'loss': 0.0092, 'load_time': 40.8831, 'process_time': 59.1169}
2020-09-08 00:49:12,710 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 150 /  469]: {'prec1': 99.6823, 'loss': 0.0096, 'load_time': 43.1884, 'process_time': 56.8116}
2020-09-08 00:49:18,513 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 200 /  469]: {'prec1': 99.6787, 'loss': 0.0096, 'load_time': 43.5514, 'process_time': 56.4486}
2020-09-08 00:49:24,274 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 250 /  469]: {'prec1': 99.6836, 'loss': 0.0096, 'load_time': 44.4192, 'process_time': 55.5808}
2020-09-08 00:49:30,079 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 300 /  469]: {'prec1': 99.6953, 'loss': 0.0095, 'load_time': 44.3369, 'process_time': 55.6631}
2020-09-08 00:49:35,913 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 350 /  469]: {'prec1': 99.6942, 'loss': 0.0096, 'load_time': 44.717, 'process_time': 55.283}
2020-09-08 00:49:41,635 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 400 /  469]: {'prec1': 99.6943, 'loss': 0.0096, 'load_time': 44.5732, 'process_time': 55.4268}
2020-09-08 00:49:47,365 - algorithms.Algorithm - INFO   - ==> Iteration [193][ 450 /  469]: {'prec1': 99.6901, 'loss': 0.0097, 'load_time': 44.5926, 'process_time': 55.4074}
2020-09-08 00:49:49,566 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6882, 'loss': 0.0098, 'load_time': 44.7077, 'process_time': 55.2923}
2020-09-08 00:49:49,649 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:49:49,649 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:49:56,276 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3198, 'loss': 0.293, 'load_time': 2.6404, 'process_time': 97.3596}
2020-09-08 00:49:56,276 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3198, 'loss': 0.293, 'load_time': 2.6404, 'process_time': 97.3596}
2020-09-08 00:49:56,276 - algorithms.Algorithm - INFO   - Training epoch [194 / 200]
2020-09-08 00:49:56,276 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:49:56,276 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:50:01,933 - algorithms.Algorithm - INFO   - ==> Iteration [194][  50 /  469]: {'prec1': 99.7227, 'loss': 0.0089, 'load_time': 40.6887, 'process_time': 59.3113}
2020-09-08 00:50:07,627 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 100 /  469]: {'prec1': 99.7227, 'loss': 0.009, 'load_time': 41.6546, 'process_time': 58.3454}
2020-09-08 00:50:13,352 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 150 /  469]: {'prec1': 99.7018, 'loss': 0.0095, 'load_time': 43.0458, 'process_time': 56.9542}
2020-09-08 00:50:19,032 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 200 /  469]: {'prec1': 99.7002, 'loss': 0.0095, 'load_time': 43.3358, 'process_time': 56.6642}
2020-09-08 00:50:24,815 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 250 /  469]: {'prec1': 99.6922, 'loss': 0.0098, 'load_time': 43.8912, 'process_time': 56.1088}
2020-09-08 00:50:30,550 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 300 /  469]: {'prec1': 99.6764, 'loss': 0.0101, 'load_time': 43.6415, 'process_time': 56.3585}
2020-09-08 00:50:36,293 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 350 /  469]: {'prec1': 99.6635, 'loss': 0.0103, 'load_time': 43.7135, 'process_time': 56.2865}
2020-09-08 00:50:42,037 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 400 /  469]: {'prec1': 99.6621, 'loss': 0.0103, 'load_time': 43.7726, 'process_time': 56.2274}
2020-09-08 00:50:47,780 - algorithms.Algorithm - INFO   - ==> Iteration [194][ 450 /  469]: {'prec1': 99.6684, 'loss': 0.0102, 'load_time': 44.0161, 'process_time': 55.9839}
2020-09-08 00:50:50,027 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6684, 'loss': 0.0102, 'load_time': 44.2152, 'process_time': 55.7848}
2020-09-08 00:50:50,110 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:50:50,111 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:50:56,695 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2011, 'loss': 0.297, 'load_time': 2.6071, 'process_time': 97.3929}
2020-09-08 00:50:56,695 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2011, 'loss': 0.297, 'load_time': 2.6071, 'process_time': 97.3929}
2020-09-08 00:50:56,695 - algorithms.Algorithm - INFO   - Training epoch [195 / 200]
2020-09-08 00:50:56,695 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:50:56,695 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:51:02,376 - algorithms.Algorithm - INFO   - ==> Iteration [195][  50 /  469]: {'prec1': 99.7227, 'loss': 0.0079, 'load_time': 40.0578, 'process_time': 59.9422}
2020-09-08 00:51:08,140 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 100 /  469]: {'prec1': 99.709, 'loss': 0.0084, 'load_time': 42.2411, 'process_time': 57.7589}
2020-09-08 00:51:13,862 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 150 /  469]: {'prec1': 99.7018, 'loss': 0.0088, 'load_time': 44.1968, 'process_time': 55.8032}
2020-09-08 00:51:19,605 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 200 /  469]: {'prec1': 99.7061, 'loss': 0.0088, 'load_time': 44.5269, 'process_time': 55.4731}
2020-09-08 00:51:25,383 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 250 /  469]: {'prec1': 99.7062, 'loss': 0.0089, 'load_time': 45.3637, 'process_time': 54.6363}
2020-09-08 00:51:31,206 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 300 /  469]: {'prec1': 99.7083, 'loss': 0.0088, 'load_time': 45.9795, 'process_time': 54.0205}
2020-09-08 00:51:36,926 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 350 /  469]: {'prec1': 99.7037, 'loss': 0.009, 'load_time': 46.0461, 'process_time': 53.9539}
2020-09-08 00:51:42,655 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 400 /  469]: {'prec1': 99.7012, 'loss': 0.0091, 'load_time': 46.278, 'process_time': 53.722}
2020-09-08 00:51:48,427 - algorithms.Algorithm - INFO   - ==> Iteration [195][ 450 /  469]: {'prec1': 99.6966, 'loss': 0.0093, 'load_time': 46.4526, 'process_time': 53.5474}
2020-09-08 00:51:50,576 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6946, 'loss': 0.0093, 'load_time': 46.5065, 'process_time': 53.4935}
2020-09-08 00:51:50,661 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:51:50,661 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:51:57,241 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1962, 'loss': 0.2994, 'load_time': 2.637, 'process_time': 97.363}
2020-09-08 00:51:57,241 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1962, 'loss': 0.2994, 'load_time': 2.637, 'process_time': 97.363}
2020-09-08 00:51:57,242 - algorithms.Algorithm - INFO   - Training epoch [196 / 200]
2020-09-08 00:51:57,242 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:51:57,242 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:52:02,971 - algorithms.Algorithm - INFO   - ==> Iteration [196][  50 /  469]: {'prec1': 99.7461, 'loss': 0.0078, 'load_time': 41.9701, 'process_time': 58.0299}
2020-09-08 00:52:08,631 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 100 /  469]: {'prec1': 99.7227, 'loss': 0.0083, 'load_time': 42.4894, 'process_time': 57.5106}
2020-09-08 00:52:14,260 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 150 /  469]: {'prec1': 99.7331, 'loss': 0.0083, 'load_time': 42.8783, 'process_time': 57.1217}
2020-09-08 00:52:20,025 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 200 /  469]: {'prec1': 99.7295, 'loss': 0.0085, 'load_time': 43.5493, 'process_time': 56.4507}
2020-09-08 00:52:25,805 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 250 /  469]: {'prec1': 99.732, 'loss': 0.0085, 'load_time': 43.6454, 'process_time': 56.3546}
2020-09-08 00:52:31,608 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 300 /  469]: {'prec1': 99.7214, 'loss': 0.0088, 'load_time': 44.2426, 'process_time': 55.7574}
2020-09-08 00:52:37,322 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 350 /  469]: {'prec1': 99.7238, 'loss': 0.0088, 'load_time': 44.5396, 'process_time': 55.4604}
2020-09-08 00:52:43,212 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 400 /  469]: {'prec1': 99.7212, 'loss': 0.009, 'load_time': 45.8477, 'process_time': 54.1523}
2020-09-08 00:52:48,935 - algorithms.Algorithm - INFO   - ==> Iteration [196][ 450 /  469]: {'prec1': 99.7122, 'loss': 0.0092, 'load_time': 45.7927, 'process_time': 54.2073}
2020-09-08 00:52:51,171 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.706, 'loss': 0.0093, 'load_time': 46.0023, 'process_time': 53.9977}
2020-09-08 00:52:51,252 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:52:51,252 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:52:57,765 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.3025, 'loss': 0.3, 'load_time': 2.602, 'process_time': 97.398}
2020-09-08 00:52:57,765 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.3025, 'loss': 0.3, 'load_time': 2.602, 'process_time': 97.398}
2020-09-08 00:52:57,765 - algorithms.Algorithm - INFO   - Training epoch [197 / 200]
2020-09-08 00:52:57,765 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:52:57,765 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:53:03,473 - algorithms.Algorithm - INFO   - ==> Iteration [197][  50 /  469]: {'prec1': 99.7578, 'loss': 0.0081, 'load_time': 43.0363, 'process_time': 56.9637}
2020-09-08 00:53:09,122 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 100 /  469]: {'prec1': 99.7578, 'loss': 0.0084, 'load_time': 43.4447, 'process_time': 56.5553}
2020-09-08 00:53:14,825 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 150 /  469]: {'prec1': 99.7682, 'loss': 0.0081, 'load_time': 43.8164, 'process_time': 56.1836}
2020-09-08 00:53:20,609 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 200 /  469]: {'prec1': 99.75, 'loss': 0.0085, 'load_time': 44.7719, 'process_time': 55.2281}
2020-09-08 00:53:26,426 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 250 /  469]: {'prec1': 99.7336, 'loss': 0.0087, 'load_time': 45.1323, 'process_time': 54.8677}
2020-09-08 00:53:32,252 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 300 /  469]: {'prec1': 99.7305, 'loss': 0.0088, 'load_time': 45.3558, 'process_time': 54.6442}
2020-09-08 00:53:38,009 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 350 /  469]: {'prec1': 99.7282, 'loss': 0.0088, 'load_time': 45.3971, 'process_time': 54.6029}
2020-09-08 00:53:43,770 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 400 /  469]: {'prec1': 99.7271, 'loss': 0.0088, 'load_time': 45.6112, 'process_time': 54.3888}
2020-09-08 00:53:49,587 - algorithms.Algorithm - INFO   - ==> Iteration [197][ 450 /  469]: {'prec1': 99.7257, 'loss': 0.0089, 'load_time': 45.7208, 'process_time': 54.2792}
2020-09-08 00:53:51,802 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.7271, 'loss': 0.0089, 'load_time': 45.7201, 'process_time': 54.2799}
2020-09-08 00:53:51,885 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:53:51,885 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:53:58,389 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2951, 'loss': 0.2943, 'load_time': 2.4818, 'process_time': 97.5182}
2020-09-08 00:53:58,389 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2951, 'loss': 0.2943, 'load_time': 2.4818, 'process_time': 97.5182}
2020-09-08 00:53:58,389 - algorithms.Algorithm - INFO   - Training epoch [198 / 200]
2020-09-08 00:53:58,389 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:53:58,389 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:54:04,105 - algorithms.Algorithm - INFO   - ==> Iteration [198][  50 /  469]: {'prec1': 99.7617, 'loss': 0.0083, 'load_time': 39.9997, 'process_time': 60.0003}
2020-09-08 00:54:09,838 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 100 /  469]: {'prec1': 99.6875, 'loss': 0.0098, 'load_time': 43.3529, 'process_time': 56.6471}
2020-09-08 00:54:15,557 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 150 /  469]: {'prec1': 99.7005, 'loss': 0.0094, 'load_time': 43.9721, 'process_time': 56.0279}
2020-09-08 00:54:21,352 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 200 /  469]: {'prec1': 99.7188, 'loss': 0.009, 'load_time': 44.6415, 'process_time': 55.3585}
2020-09-08 00:54:27,157 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 250 /  469]: {'prec1': 99.7156, 'loss': 0.009, 'load_time': 45.0758, 'process_time': 54.9242}
2020-09-08 00:54:32,914 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 300 /  469]: {'prec1': 99.7207, 'loss': 0.0089, 'load_time': 45.0575, 'process_time': 54.9425}
2020-09-08 00:54:38,606 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 350 /  469]: {'prec1': 99.7154, 'loss': 0.0091, 'load_time': 44.9559, 'process_time': 55.0441}
2020-09-08 00:54:44,470 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 400 /  469]: {'prec1': 99.7124, 'loss': 0.0092, 'load_time': 45.0932, 'process_time': 54.9068}
2020-09-08 00:54:50,260 - algorithms.Algorithm - INFO   - ==> Iteration [198][ 450 /  469]: {'prec1': 99.7066, 'loss': 0.0093, 'load_time': 45.5605, 'process_time': 54.4395}
2020-09-08 00:54:52,436 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.7079, 'loss': 0.0093, 'load_time': 45.6388, 'process_time': 54.3612}
2020-09-08 00:54:52,520 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:54:52,520 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:54:59,165 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2803, 'loss': 0.2986, 'load_time': 2.635, 'process_time': 97.365}
2020-09-08 00:54:59,166 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2803, 'loss': 0.2986, 'load_time': 2.635, 'process_time': 97.365}
2020-09-08 00:54:59,166 - algorithms.Algorithm - INFO   - Training epoch [199 / 200]
2020-09-08 00:54:59,166 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:54:59,166 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:55:04,936 - algorithms.Algorithm - INFO   - ==> Iteration [199][  50 /  469]: {'prec1': 99.6797, 'loss': 0.0094, 'load_time': 44.0263, 'process_time': 55.9737}
2020-09-08 00:55:10,576 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 100 /  469]: {'prec1': 99.6797, 'loss': 0.0093, 'load_time': 42.4236, 'process_time': 57.5764}
2020-09-08 00:55:16,332 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 150 /  469]: {'prec1': 99.7005, 'loss': 0.0091, 'load_time': 43.6816, 'process_time': 56.3184}
2020-09-08 00:55:22,064 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 200 /  469]: {'prec1': 99.6904, 'loss': 0.0094, 'load_time': 43.9364, 'process_time': 56.0636}
2020-09-08 00:55:27,889 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 250 /  469]: {'prec1': 99.6875, 'loss': 0.0094, 'load_time': 44.0476, 'process_time': 55.9524}
2020-09-08 00:55:33,725 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 300 /  469]: {'prec1': 99.6934, 'loss': 0.0093, 'load_time': 44.7933, 'process_time': 55.2067}
2020-09-08 00:55:39,581 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 350 /  469]: {'prec1': 99.6975, 'loss': 0.0092, 'load_time': 45.0146, 'process_time': 54.9854}
2020-09-08 00:55:45,465 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 400 /  469]: {'prec1': 99.6938, 'loss': 0.0093, 'load_time': 45.9195, 'process_time': 54.0805}
2020-09-08 00:55:51,295 - algorithms.Algorithm - INFO   - ==> Iteration [199][ 450 /  469]: {'prec1': 99.6866, 'loss': 0.0093, 'load_time': 46.3598, 'process_time': 53.6402}
2020-09-08 00:55:53,463 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.6867, 'loss': 0.0094, 'load_time': 46.3948, 'process_time': 53.6052}
2020-09-08 00:55:53,547 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:55:53,548 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:56:00,185 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.1517, 'loss': 0.3008, 'load_time': 2.6183, 'process_time': 97.3817}
2020-09-08 00:56:00,185 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.1517, 'loss': 0.3008, 'load_time': 2.6183, 'process_time': 97.3817}
2020-09-08 00:56:00,185 - algorithms.Algorithm - INFO   - Training epoch [200 / 200]
2020-09-08 00:56:00,185 - algorithms.Algorithm - INFO   - ==> Set to model optimizer lr = 0.0008000000
2020-09-08 00:56:00,185 - algorithms.Algorithm - INFO   - Training: MNIST_RotNet_NIN4blocks
2020-09-08 00:56:05,833 - algorithms.Algorithm - INFO   - ==> Iteration [200][  50 /  469]: {'prec1': 99.7578, 'loss': 0.0081, 'load_time': 38.7623, 'process_time': 61.2377}
2020-09-08 00:56:11,489 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 100 /  469]: {'prec1': 99.7363, 'loss': 0.0089, 'load_time': 42.0134, 'process_time': 57.9866}
2020-09-08 00:56:17,309 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 150 /  469]: {'prec1': 99.7539, 'loss': 0.0085, 'load_time': 43.8982, 'process_time': 56.1018}
2020-09-08 00:56:23,099 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 200 /  469]: {'prec1': 99.7588, 'loss': 0.0083, 'load_time': 44.7332, 'process_time': 55.2668}
2020-09-08 00:56:28,795 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 250 /  469]: {'prec1': 99.75, 'loss': 0.0084, 'load_time': 45.0669, 'process_time': 54.9331}
2020-09-08 00:56:34,570 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 300 /  469]: {'prec1': 99.7396, 'loss': 0.0086, 'load_time': 45.6471, 'process_time': 54.3529}
2020-09-08 00:56:40,378 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 350 /  469]: {'prec1': 99.721, 'loss': 0.0089, 'load_time': 46.0264, 'process_time': 53.9736}
2020-09-08 00:56:46,233 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 400 /  469]: {'prec1': 99.7134, 'loss': 0.009, 'load_time': 46.4317, 'process_time': 53.5683}
2020-09-08 00:56:52,016 - algorithms.Algorithm - INFO   - ==> Iteration [200][ 450 /  469]: {'prec1': 99.7092, 'loss': 0.0092, 'load_time': 46.3434, 'process_time': 53.6566}
2020-09-08 00:56:54,226 - algorithms.Algorithm - INFO   - ==> Training stats: {'prec1': 99.7096, 'loss': 0.0092, 'load_time': 46.3967, 'process_time': 53.6033}
2020-09-08 00:56:54,311 - algorithms.Algorithm - INFO   - Evaluating: MNIST_RotNet_NIN4blocks
2020-09-08 00:56:54,312 - algorithms.Algorithm - INFO   - ==> Dataset: mnist_test [79 images]
2020-09-08 00:57:00,930 - algorithms.Algorithm - INFO   - ==> Results: {'prec1': 93.2061, 'loss': 0.2949, 'load_time': 2.6453, 'process_time': 97.3547}
2020-09-08 00:57:00,930 - algorithms.Algorithm - INFO   - ==> Evaluation stats: {'prec1': 93.2061, 'loss': 0.2949, 'load_time': 2.6453, 'process_time': 97.3547}
