chunk-english / training.log
alanakbik's picture
Update model for torch 2.0
ba93b25
2023-04-05 11:29:16,133 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,133 Model: "SequenceTagger(
(embeddings): StackedEmbeddings(
(list_embedding_0): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.05, inplace=False)
(encoder): Embedding(300, 100)
(rnn): LSTM(100, 2048)
)
)
(list_embedding_1): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.05, inplace=False)
(encoder): Embedding(300, 100)
(rnn): LSTM(100, 2048)
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(embedding2nn): Linear(in_features=4096, out_features=4096, bias=True)
(rnn): LSTM(4096, 256, batch_first=True, bidirectional=True)
(linear): Linear(in_features=512, out_features=47, bias=True)
(loss_function): ViterbiLoss()
(crf): CRF()
)"
2023-04-05 11:29:16,133 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,134 Corpus: "Corpus: 8042 train + 894 dev + 2012 test sentences"
2023-04-05 11:29:16,134 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,134 Parameters:
2023-04-05 11:29:16,134 - learning_rate: "0.100000"
2023-04-05 11:29:16,134 - mini_batch_size: "32"
2023-04-05 11:29:16,134 - patience: "3"
2023-04-05 11:29:16,134 - anneal_factor: "0.5"
2023-04-05 11:29:16,134 - max_epochs: "150"
2023-04-05 11:29:16,134 - shuffle: "True"
2023-04-05 11:29:16,134 - train_with_dev: "True"
2023-04-05 11:29:16,134 - batch_growth_annealing: "False"
2023-04-05 11:29:16,134 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,134 Model training base path: "resources/taggers/release-chunk-0"
2023-04-05 11:29:16,134 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,134 Device: cuda:3
2023-04-05 11:29:16,134 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:16,134 Embeddings storage mode: cpu
2023-04-05 11:29:16,134 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:20,904 epoch 1 - iter 28/280 - loss 2.37282876 - time (sec): 4.77 - samples/sec: 4432.43 - lr: 0.100000
2023-04-05 11:29:24,490 epoch 1 - iter 56/280 - loss 1.73442584 - time (sec): 8.36 - samples/sec: 5102.03 - lr: 0.100000
2023-04-05 11:29:28,013 epoch 1 - iter 84/280 - loss 1.39084026 - time (sec): 11.88 - samples/sec: 5382.16 - lr: 0.100000
2023-04-05 11:29:33,009 epoch 1 - iter 112/280 - loss 1.17618757 - time (sec): 16.88 - samples/sec: 5028.12 - lr: 0.100000
2023-04-05 11:29:36,729 epoch 1 - iter 140/280 - loss 1.01802104 - time (sec): 20.59 - samples/sec: 5195.77 - lr: 0.100000
2023-04-05 11:29:40,304 epoch 1 - iter 168/280 - loss 0.90572495 - time (sec): 24.17 - samples/sec: 5289.08 - lr: 0.100000
2023-04-05 11:29:43,736 epoch 1 - iter 196/280 - loss 0.82891649 - time (sec): 27.60 - samples/sec: 5357.88 - lr: 0.100000
2023-04-05 11:29:47,291 epoch 1 - iter 224/280 - loss 0.76158106 - time (sec): 31.16 - samples/sec: 5444.79 - lr: 0.100000
2023-04-05 11:29:50,847 epoch 1 - iter 252/280 - loss 0.70683343 - time (sec): 34.71 - samples/sec: 5496.58 - lr: 0.100000
2023-04-05 11:29:54,384 epoch 1 - iter 280/280 - loss 0.66134975 - time (sec): 38.25 - samples/sec: 5534.41 - lr: 0.100000
2023-04-05 11:29:54,384 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:54,384 EPOCH 1 done: loss 0.6613 - lr 0.100000
2023-04-05 11:29:54,384 BAD EPOCHS (no improvement): 0
2023-04-05 11:29:54,387 ----------------------------------------------------------------------------------------------------
2023-04-05 11:29:56,124 epoch 2 - iter 28/280 - loss 0.24668011 - time (sec): 1.74 - samples/sec: 12130.51 - lr: 0.100000
2023-04-05 11:29:57,899 epoch 2 - iter 56/280 - loss 0.24616989 - time (sec): 3.51 - samples/sec: 12029.61 - lr: 0.100000
2023-04-05 11:29:59,712 epoch 2 - iter 84/280 - loss 0.23759242 - time (sec): 5.32 - samples/sec: 11832.70 - lr: 0.100000
2023-04-05 11:30:01,551 epoch 2 - iter 112/280 - loss 0.22930022 - time (sec): 7.16 - samples/sec: 11789.17 - lr: 0.100000
2023-04-05 11:30:03,348 epoch 2 - iter 140/280 - loss 0.22235325 - time (sec): 8.96 - samples/sec: 11781.96 - lr: 0.100000
2023-04-05 11:30:05,149 epoch 2 - iter 168/280 - loss 0.21541826 - time (sec): 10.76 - samples/sec: 11783.35 - lr: 0.100000
2023-04-05 11:30:06,952 epoch 2 - iter 196/280 - loss 0.21196149 - time (sec): 12.56 - samples/sec: 11783.15 - lr: 0.100000
2023-04-05 11:30:08,784 epoch 2 - iter 224/280 - loss 0.21048863 - time (sec): 14.40 - samples/sec: 11772.43 - lr: 0.100000
2023-04-05 11:30:10,584 epoch 2 - iter 252/280 - loss 0.20862461 - time (sec): 16.20 - samples/sec: 11777.92 - lr: 0.100000
2023-04-05 11:30:12,361 epoch 2 - iter 280/280 - loss 0.20466419 - time (sec): 17.97 - samples/sec: 11778.29 - lr: 0.100000
2023-04-05 11:30:12,361 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:12,361 EPOCH 2 done: loss 0.2047 - lr 0.100000
2023-04-05 11:30:12,361 BAD EPOCHS (no improvement): 0
2023-04-05 11:30:12,363 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:14,195 epoch 3 - iter 28/280 - loss 0.16277843 - time (sec): 1.83 - samples/sec: 11616.71 - lr: 0.100000
2023-04-05 11:30:16,031 epoch 3 - iter 56/280 - loss 0.17432135 - time (sec): 3.67 - samples/sec: 11684.18 - lr: 0.100000
2023-04-05 11:30:17,808 epoch 3 - iter 84/280 - loss 0.16850032 - time (sec): 5.44 - samples/sec: 11803.52 - lr: 0.100000
2023-04-05 11:30:19,567 epoch 3 - iter 112/280 - loss 0.16801260 - time (sec): 7.20 - samples/sec: 11785.46 - lr: 0.100000
2023-04-05 11:30:21,364 epoch 3 - iter 140/280 - loss 0.16475608 - time (sec): 9.00 - samples/sec: 11795.95 - lr: 0.100000
2023-04-05 11:30:23,182 epoch 3 - iter 168/280 - loss 0.16252822 - time (sec): 10.82 - samples/sec: 11787.04 - lr: 0.100000
2023-04-05 11:30:24,948 epoch 3 - iter 196/280 - loss 0.16073945 - time (sec): 12.58 - samples/sec: 11766.81 - lr: 0.100000
2023-04-05 11:30:26,745 epoch 3 - iter 224/280 - loss 0.15922105 - time (sec): 14.38 - samples/sec: 11756.76 - lr: 0.100000
2023-04-05 11:30:28,582 epoch 3 - iter 252/280 - loss 0.15826088 - time (sec): 16.22 - samples/sec: 11761.51 - lr: 0.100000
2023-04-05 11:30:30,368 epoch 3 - iter 280/280 - loss 0.15778524 - time (sec): 18.00 - samples/sec: 11757.82 - lr: 0.100000
2023-04-05 11:30:30,368 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:30,368 EPOCH 3 done: loss 0.1578 - lr 0.100000
2023-04-05 11:30:30,368 BAD EPOCHS (no improvement): 0
2023-04-05 11:30:30,371 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:32,169 epoch 4 - iter 28/280 - loss 0.14274724 - time (sec): 1.80 - samples/sec: 11788.44 - lr: 0.100000
2023-04-05 11:30:33,965 epoch 4 - iter 56/280 - loss 0.14312035 - time (sec): 3.59 - samples/sec: 11819.57 - lr: 0.100000
2023-04-05 11:30:35,737 epoch 4 - iter 84/280 - loss 0.13768537 - time (sec): 5.37 - samples/sec: 11847.30 - lr: 0.100000
2023-04-05 11:30:37,479 epoch 4 - iter 112/280 - loss 0.13556362 - time (sec): 7.11 - samples/sec: 11916.08 - lr: 0.100000
2023-04-05 11:30:39,336 epoch 4 - iter 140/280 - loss 0.13667169 - time (sec): 8.97 - samples/sec: 11818.26 - lr: 0.100000
2023-04-05 11:30:41,119 epoch 4 - iter 168/280 - loss 0.13595646 - time (sec): 10.75 - samples/sec: 11803.97 - lr: 0.100000
2023-04-05 11:30:42,896 epoch 4 - iter 196/280 - loss 0.13611689 - time (sec): 12.52 - samples/sec: 11778.91 - lr: 0.100000
2023-04-05 11:30:44,728 epoch 4 - iter 224/280 - loss 0.13479738 - time (sec): 14.36 - samples/sec: 11773.31 - lr: 0.100000
2023-04-05 11:30:46,561 epoch 4 - iter 252/280 - loss 0.13301677 - time (sec): 16.19 - samples/sec: 11780.00 - lr: 0.100000
2023-04-05 11:30:48,327 epoch 4 - iter 280/280 - loss 0.13254673 - time (sec): 17.96 - samples/sec: 11789.74 - lr: 0.100000
2023-04-05 11:30:48,327 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:48,327 EPOCH 4 done: loss 0.1325 - lr 0.100000
2023-04-05 11:30:48,327 BAD EPOCHS (no improvement): 0
2023-04-05 11:30:48,330 ----------------------------------------------------------------------------------------------------
2023-04-05 11:30:50,128 epoch 5 - iter 28/280 - loss 0.12537979 - time (sec): 1.80 - samples/sec: 11431.83 - lr: 0.100000
2023-04-05 11:30:51,955 epoch 5 - iter 56/280 - loss 0.12291704 - time (sec): 3.63 - samples/sec: 11609.58 - lr: 0.100000
2023-04-05 11:30:53,744 epoch 5 - iter 84/280 - loss 0.11978898 - time (sec): 5.41 - samples/sec: 11717.65 - lr: 0.100000
2023-04-05 11:30:55,531 epoch 5 - iter 112/280 - loss 0.11880713 - time (sec): 7.20 - samples/sec: 11688.63 - lr: 0.100000
2023-04-05 11:30:57,348 epoch 5 - iter 140/280 - loss 0.11870187 - time (sec): 9.02 - samples/sec: 11686.40 - lr: 0.100000
2023-04-05 11:30:59,163 epoch 5 - iter 168/280 - loss 0.11853175 - time (sec): 10.83 - samples/sec: 11685.86 - lr: 0.100000
2023-04-05 11:31:00,955 epoch 5 - iter 196/280 - loss 0.11923794 - time (sec): 12.63 - samples/sec: 11701.98 - lr: 0.100000
2023-04-05 11:31:02,891 epoch 5 - iter 224/280 - loss 0.11909223 - time (sec): 14.56 - samples/sec: 11623.20 - lr: 0.100000
2023-04-05 11:31:04,734 epoch 5 - iter 252/280 - loss 0.11794536 - time (sec): 16.40 - samples/sec: 11633.82 - lr: 0.100000
2023-04-05 11:31:06,505 epoch 5 - iter 280/280 - loss 0.11774263 - time (sec): 18.18 - samples/sec: 11647.06 - lr: 0.100000
2023-04-05 11:31:06,505 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:06,505 EPOCH 5 done: loss 0.1177 - lr 0.100000
2023-04-05 11:31:06,505 BAD EPOCHS (no improvement): 0
2023-04-05 11:31:06,508 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:08,257 epoch 6 - iter 28/280 - loss 0.10801801 - time (sec): 1.75 - samples/sec: 11894.68 - lr: 0.100000
2023-04-05 11:31:10,057 epoch 6 - iter 56/280 - loss 0.10536099 - time (sec): 3.55 - samples/sec: 11890.34 - lr: 0.100000
2023-04-05 11:31:11,853 epoch 6 - iter 84/280 - loss 0.10593172 - time (sec): 5.34 - samples/sec: 11855.36 - lr: 0.100000
2023-04-05 11:31:13,642 epoch 6 - iter 112/280 - loss 0.10568821 - time (sec): 7.13 - samples/sec: 11912.10 - lr: 0.100000
2023-04-05 11:31:15,482 epoch 6 - iter 140/280 - loss 0.10486267 - time (sec): 8.97 - samples/sec: 11865.52 - lr: 0.100000
2023-04-05 11:31:17,306 epoch 6 - iter 168/280 - loss 0.10671355 - time (sec): 10.80 - samples/sec: 11840.71 - lr: 0.100000
2023-04-05 11:31:19,103 epoch 6 - iter 196/280 - loss 0.10612224 - time (sec): 12.59 - samples/sec: 11813.09 - lr: 0.100000
2023-04-05 11:31:20,911 epoch 6 - iter 224/280 - loss 0.10697215 - time (sec): 14.40 - samples/sec: 11805.82 - lr: 0.100000
2023-04-05 11:31:22,703 epoch 6 - iter 252/280 - loss 0.10663050 - time (sec): 16.19 - samples/sec: 11796.44 - lr: 0.100000
2023-04-05 11:31:24,415 epoch 6 - iter 280/280 - loss 0.10712894 - time (sec): 17.91 - samples/sec: 11821.96 - lr: 0.100000
2023-04-05 11:31:24,415 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:24,415 EPOCH 6 done: loss 0.1071 - lr 0.100000
2023-04-05 11:31:24,416 BAD EPOCHS (no improvement): 0
2023-04-05 11:31:24,418 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:26,222 epoch 7 - iter 28/280 - loss 0.10256719 - time (sec): 1.80 - samples/sec: 12127.62 - lr: 0.100000
2023-04-05 11:31:27,993 epoch 7 - iter 56/280 - loss 0.10351566 - time (sec): 3.57 - samples/sec: 12053.90 - lr: 0.100000
2023-04-05 11:31:29,792 epoch 7 - iter 84/280 - loss 0.10268535 - time (sec): 5.37 - samples/sec: 11992.86 - lr: 0.100000
2023-04-05 11:31:31,574 epoch 7 - iter 112/280 - loss 0.10340487 - time (sec): 7.16 - samples/sec: 11931.98 - lr: 0.100000
2023-04-05 11:31:33,397 epoch 7 - iter 140/280 - loss 0.10325865 - time (sec): 8.98 - samples/sec: 11884.65 - lr: 0.100000
2023-04-05 11:31:35,220 epoch 7 - iter 168/280 - loss 0.10161036 - time (sec): 10.80 - samples/sec: 11818.19 - lr: 0.100000
2023-04-05 11:31:36,970 epoch 7 - iter 196/280 - loss 0.10121591 - time (sec): 12.55 - samples/sec: 11836.74 - lr: 0.100000
2023-04-05 11:31:38,814 epoch 7 - iter 224/280 - loss 0.10067595 - time (sec): 14.40 - samples/sec: 11793.36 - lr: 0.100000
2023-04-05 11:31:40,682 epoch 7 - iter 252/280 - loss 0.10019403 - time (sec): 16.26 - samples/sec: 11766.37 - lr: 0.100000
2023-04-05 11:31:42,426 epoch 7 - iter 280/280 - loss 0.10001916 - time (sec): 18.01 - samples/sec: 11755.30 - lr: 0.100000
2023-04-05 11:31:42,427 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:42,427 EPOCH 7 done: loss 0.1000 - lr 0.100000
2023-04-05 11:31:42,427 BAD EPOCHS (no improvement): 0
2023-04-05 11:31:42,430 ----------------------------------------------------------------------------------------------------
2023-04-05 11:31:44,225 epoch 8 - iter 28/280 - loss 0.08849263 - time (sec): 1.80 - samples/sec: 11727.64 - lr: 0.100000
2023-04-05 11:31:46,035 epoch 8 - iter 56/280 - loss 0.09232933 - time (sec): 3.60 - samples/sec: 11868.37 - lr: 0.100000
2023-04-05 11:31:47,863 epoch 8 - iter 84/280 - loss 0.09227452 - time (sec): 5.43 - samples/sec: 11817.83 - lr: 0.100000
2023-04-05 11:31:49,637 epoch 8 - iter 112/280 - loss 0.09299395 - time (sec): 7.21 - samples/sec: 11913.64 - lr: 0.100000
2023-04-05 11:31:51,441 epoch 8 - iter 140/280 - loss 0.09202120 - time (sec): 9.01 - samples/sec: 11861.14 - lr: 0.100000
2023-04-05 11:31:53,117 epoch 8 - iter 168/280 - loss 0.09216183 - time (sec): 10.69 - samples/sec: 11887.35 - lr: 0.100000
2023-04-05 11:31:54,910 epoch 8 - iter 196/280 - loss 0.09194170 - time (sec): 12.48 - samples/sec: 11868.36 - lr: 0.100000
2023-04-05 11:31:56,734 epoch 8 - iter 224/280 - loss 0.09123647 - time (sec): 14.30 - samples/sec: 11844.22 - lr: 0.100000
2023-04-05 11:31:58,628 epoch 8 - iter 252/280 - loss 0.09127536 - time (sec): 16.20 - samples/sec: 11809.29 - lr: 0.100000
2023-04-05 11:32:00,394 epoch 8 - iter 280/280 - loss 0.09166344 - time (sec): 17.96 - samples/sec: 11784.09 - lr: 0.100000
2023-04-05 11:32:00,395 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:00,395 EPOCH 8 done: loss 0.0917 - lr 0.100000
2023-04-05 11:32:00,395 BAD EPOCHS (no improvement): 0
2023-04-05 11:32:00,397 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:02,250 epoch 9 - iter 28/280 - loss 0.08691646 - time (sec): 1.85 - samples/sec: 11541.27 - lr: 0.100000
2023-04-05 11:32:04,097 epoch 9 - iter 56/280 - loss 0.08739923 - time (sec): 3.70 - samples/sec: 11396.09 - lr: 0.100000
2023-04-05 11:32:05,937 epoch 9 - iter 84/280 - loss 0.08610714 - time (sec): 5.54 - samples/sec: 11526.95 - lr: 0.100000
2023-04-05 11:32:07,775 epoch 9 - iter 112/280 - loss 0.08638211 - time (sec): 7.38 - samples/sec: 11570.04 - lr: 0.100000
2023-04-05 11:32:09,594 epoch 9 - iter 140/280 - loss 0.08613884 - time (sec): 9.20 - samples/sec: 11595.80 - lr: 0.100000
2023-04-05 11:32:11,380 epoch 9 - iter 168/280 - loss 0.08523617 - time (sec): 10.98 - samples/sec: 11614.54 - lr: 0.100000
2023-04-05 11:32:13,220 epoch 9 - iter 196/280 - loss 0.08655958 - time (sec): 12.82 - samples/sec: 11599.92 - lr: 0.100000
2023-04-05 11:32:15,104 epoch 9 - iter 224/280 - loss 0.08703691 - time (sec): 14.71 - samples/sec: 11585.91 - lr: 0.100000
2023-04-05 11:32:16,878 epoch 9 - iter 252/280 - loss 0.08710248 - time (sec): 16.48 - samples/sec: 11595.87 - lr: 0.100000
2023-04-05 11:32:18,643 epoch 9 - iter 280/280 - loss 0.08699147 - time (sec): 18.25 - samples/sec: 11602.48 - lr: 0.100000
2023-04-05 11:32:18,643 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:18,643 EPOCH 9 done: loss 0.0870 - lr 0.100000
2023-04-05 11:32:18,643 BAD EPOCHS (no improvement): 0
2023-04-05 11:32:18,647 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:20,427 epoch 10 - iter 28/280 - loss 0.08535297 - time (sec): 1.78 - samples/sec: 11948.04 - lr: 0.100000
2023-04-05 11:32:22,196 epoch 10 - iter 56/280 - loss 0.08225209 - time (sec): 3.55 - samples/sec: 11858.92 - lr: 0.100000
2023-04-05 11:32:24,001 epoch 10 - iter 84/280 - loss 0.08155333 - time (sec): 5.35 - samples/sec: 11868.84 - lr: 0.100000
2023-04-05 11:32:25,771 epoch 10 - iter 112/280 - loss 0.08096331 - time (sec): 7.12 - samples/sec: 11912.14 - lr: 0.100000
2023-04-05 11:32:27,573 epoch 10 - iter 140/280 - loss 0.08188113 - time (sec): 8.93 - samples/sec: 11910.16 - lr: 0.100000
2023-04-05 11:32:29,400 epoch 10 - iter 168/280 - loss 0.08212457 - time (sec): 10.75 - samples/sec: 11849.47 - lr: 0.100000
2023-04-05 11:32:31,185 epoch 10 - iter 196/280 - loss 0.08269054 - time (sec): 12.54 - samples/sec: 11829.85 - lr: 0.100000
2023-04-05 11:32:33,060 epoch 10 - iter 224/280 - loss 0.08137674 - time (sec): 14.41 - samples/sec: 11793.96 - lr: 0.100000
2023-04-05 11:32:34,796 epoch 10 - iter 252/280 - loss 0.08172281 - time (sec): 16.15 - samples/sec: 11838.84 - lr: 0.100000
2023-04-05 11:32:36,527 epoch 10 - iter 280/280 - loss 0.08182399 - time (sec): 17.88 - samples/sec: 11839.46 - lr: 0.100000
2023-04-05 11:32:36,527 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:36,527 EPOCH 10 done: loss 0.0818 - lr 0.100000
2023-04-05 11:32:36,528 BAD EPOCHS (no improvement): 0
2023-04-05 11:32:36,531 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:38,288 epoch 11 - iter 28/280 - loss 0.07156185 - time (sec): 1.76 - samples/sec: 12189.09 - lr: 0.100000
2023-04-05 11:32:40,074 epoch 11 - iter 56/280 - loss 0.07200991 - time (sec): 3.54 - samples/sec: 11957.20 - lr: 0.100000
2023-04-05 11:32:41,935 epoch 11 - iter 84/280 - loss 0.07392035 - time (sec): 5.40 - samples/sec: 11782.18 - lr: 0.100000
2023-04-05 11:32:43,701 epoch 11 - iter 112/280 - loss 0.07559662 - time (sec): 7.17 - samples/sec: 11808.79 - lr: 0.100000
2023-04-05 11:32:45,544 epoch 11 - iter 140/280 - loss 0.07517000 - time (sec): 9.01 - samples/sec: 11760.89 - lr: 0.100000
2023-04-05 11:32:47,398 epoch 11 - iter 168/280 - loss 0.07561808 - time (sec): 10.87 - samples/sec: 11698.21 - lr: 0.100000
2023-04-05 11:32:49,244 epoch 11 - iter 196/280 - loss 0.07684873 - time (sec): 12.71 - samples/sec: 11666.50 - lr: 0.100000
2023-04-05 11:32:51,090 epoch 11 - iter 224/280 - loss 0.07733744 - time (sec): 14.56 - samples/sec: 11670.83 - lr: 0.100000
2023-04-05 11:32:52,871 epoch 11 - iter 252/280 - loss 0.07693746 - time (sec): 16.34 - samples/sec: 11691.73 - lr: 0.100000
2023-04-05 11:32:54,614 epoch 11 - iter 280/280 - loss 0.07701976 - time (sec): 18.08 - samples/sec: 11706.81 - lr: 0.100000
2023-04-05 11:32:54,614 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:54,614 EPOCH 11 done: loss 0.0770 - lr 0.100000
2023-04-05 11:32:54,614 BAD EPOCHS (no improvement): 0
2023-04-05 11:32:54,617 ----------------------------------------------------------------------------------------------------
2023-04-05 11:32:56,400 epoch 12 - iter 28/280 - loss 0.07852467 - time (sec): 1.78 - samples/sec: 12119.72 - lr: 0.100000
2023-04-05 11:32:58,132 epoch 12 - iter 56/280 - loss 0.07356340 - time (sec): 3.51 - samples/sec: 12017.71 - lr: 0.100000
2023-04-05 11:32:59,959 epoch 12 - iter 84/280 - loss 0.07042798 - time (sec): 5.34 - samples/sec: 11975.28 - lr: 0.100000
2023-04-05 11:33:01,732 epoch 12 - iter 112/280 - loss 0.07134553 - time (sec): 7.12 - samples/sec: 11931.58 - lr: 0.100000
2023-04-05 11:33:03,583 epoch 12 - iter 140/280 - loss 0.07158955 - time (sec): 8.97 - samples/sec: 11865.90 - lr: 0.100000
2023-04-05 11:33:06,726 epoch 12 - iter 168/280 - loss 0.07262901 - time (sec): 12.11 - samples/sec: 10551.86 - lr: 0.100000
2023-04-05 11:33:08,550 epoch 12 - iter 196/280 - loss 0.07252849 - time (sec): 13.93 - samples/sec: 10721.54 - lr: 0.100000
2023-04-05 11:33:10,301 epoch 12 - iter 224/280 - loss 0.07348081 - time (sec): 15.68 - samples/sec: 10853.72 - lr: 0.100000
2023-04-05 11:33:12,090 epoch 12 - iter 252/280 - loss 0.07351550 - time (sec): 17.47 - samples/sec: 10951.22 - lr: 0.100000
2023-04-05 11:33:13,763 epoch 12 - iter 280/280 - loss 0.07405583 - time (sec): 19.15 - samples/sec: 11056.70 - lr: 0.100000
2023-04-05 11:33:13,763 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:13,763 EPOCH 12 done: loss 0.0741 - lr 0.100000
2023-04-05 11:33:13,764 BAD EPOCHS (no improvement): 0
2023-04-05 11:33:13,766 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:15,580 epoch 13 - iter 28/280 - loss 0.06782838 - time (sec): 1.81 - samples/sec: 11959.83 - lr: 0.100000
2023-04-05 11:33:17,339 epoch 13 - iter 56/280 - loss 0.07030787 - time (sec): 3.57 - samples/sec: 11861.03 - lr: 0.100000
2023-04-05 11:33:19,117 epoch 13 - iter 84/280 - loss 0.07030536 - time (sec): 5.35 - samples/sec: 11829.81 - lr: 0.100000
2023-04-05 11:33:21,039 epoch 13 - iter 112/280 - loss 0.07025503 - time (sec): 7.27 - samples/sec: 11750.55 - lr: 0.100000
2023-04-05 11:33:22,846 epoch 13 - iter 140/280 - loss 0.07055923 - time (sec): 9.08 - samples/sec: 11789.86 - lr: 0.100000
2023-04-05 11:33:24,670 epoch 13 - iter 168/280 - loss 0.06975797 - time (sec): 10.90 - samples/sec: 11769.79 - lr: 0.100000
2023-04-05 11:33:26,470 epoch 13 - iter 196/280 - loss 0.07023482 - time (sec): 12.70 - samples/sec: 11766.83 - lr: 0.100000
2023-04-05 11:33:28,217 epoch 13 - iter 224/280 - loss 0.07091191 - time (sec): 14.45 - samples/sec: 11756.14 - lr: 0.100000
2023-04-05 11:33:30,052 epoch 13 - iter 252/280 - loss 0.07062376 - time (sec): 16.29 - samples/sec: 11744.18 - lr: 0.100000
2023-04-05 11:33:31,768 epoch 13 - iter 280/280 - loss 0.07032591 - time (sec): 18.00 - samples/sec: 11759.28 - lr: 0.100000
2023-04-05 11:33:31,769 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:31,769 EPOCH 13 done: loss 0.0703 - lr 0.100000
2023-04-05 11:33:31,769 BAD EPOCHS (no improvement): 0
2023-04-05 11:33:31,772 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:33,600 epoch 14 - iter 28/280 - loss 0.07117781 - time (sec): 1.83 - samples/sec: 11609.76 - lr: 0.100000
2023-04-05 11:33:35,435 epoch 14 - iter 56/280 - loss 0.06757552 - time (sec): 3.66 - samples/sec: 11617.06 - lr: 0.100000
2023-04-05 11:33:37,265 epoch 14 - iter 84/280 - loss 0.06749817 - time (sec): 5.49 - samples/sec: 11710.48 - lr: 0.100000
2023-04-05 11:33:39,018 epoch 14 - iter 112/280 - loss 0.06813775 - time (sec): 7.25 - samples/sec: 11720.08 - lr: 0.100000
2023-04-05 11:33:40,814 epoch 14 - iter 140/280 - loss 0.06788856 - time (sec): 9.04 - samples/sec: 11699.16 - lr: 0.100000
2023-04-05 11:33:42,579 epoch 14 - iter 168/280 - loss 0.06731170 - time (sec): 10.81 - samples/sec: 11767.24 - lr: 0.100000
2023-04-05 11:33:44,381 epoch 14 - iter 196/280 - loss 0.06638080 - time (sec): 12.61 - samples/sec: 11750.60 - lr: 0.100000
2023-04-05 11:33:46,167 epoch 14 - iter 224/280 - loss 0.06650452 - time (sec): 14.39 - samples/sec: 11756.55 - lr: 0.100000
2023-04-05 11:33:47,990 epoch 14 - iter 252/280 - loss 0.06709942 - time (sec): 16.22 - samples/sec: 11752.33 - lr: 0.100000
2023-04-05 11:33:49,736 epoch 14 - iter 280/280 - loss 0.06682125 - time (sec): 17.96 - samples/sec: 11784.56 - lr: 0.100000
2023-04-05 11:33:49,736 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:49,736 EPOCH 14 done: loss 0.0668 - lr 0.100000
2023-04-05 11:33:49,736 BAD EPOCHS (no improvement): 0
2023-04-05 11:33:49,739 ----------------------------------------------------------------------------------------------------
2023-04-05 11:33:51,533 epoch 15 - iter 28/280 - loss 0.06164767 - time (sec): 1.79 - samples/sec: 11630.68 - lr: 0.100000
2023-04-05 11:33:53,314 epoch 15 - iter 56/280 - loss 0.06217384 - time (sec): 3.58 - samples/sec: 11862.10 - lr: 0.100000
2023-04-05 11:33:55,129 epoch 15 - iter 84/280 - loss 0.06421412 - time (sec): 5.39 - samples/sec: 11809.56 - lr: 0.100000
2023-04-05 11:33:56,965 epoch 15 - iter 112/280 - loss 0.06330052 - time (sec): 7.23 - samples/sec: 11802.89 - lr: 0.100000
2023-04-05 11:33:58,798 epoch 15 - iter 140/280 - loss 0.06302798 - time (sec): 9.06 - samples/sec: 11713.93 - lr: 0.100000
2023-04-05 11:34:00,606 epoch 15 - iter 168/280 - loss 0.06315935 - time (sec): 10.87 - samples/sec: 11696.09 - lr: 0.100000
2023-04-05 11:34:02,382 epoch 15 - iter 196/280 - loss 0.06322420 - time (sec): 12.64 - samples/sec: 11717.82 - lr: 0.100000
2023-04-05 11:34:04,205 epoch 15 - iter 224/280 - loss 0.06382788 - time (sec): 14.47 - samples/sec: 11713.74 - lr: 0.100000
2023-04-05 11:34:06,017 epoch 15 - iter 252/280 - loss 0.06386257 - time (sec): 16.28 - samples/sec: 11711.88 - lr: 0.100000
2023-04-05 11:34:07,788 epoch 15 - iter 280/280 - loss 0.06432687 - time (sec): 18.05 - samples/sec: 11728.90 - lr: 0.100000
2023-04-05 11:34:07,788 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:07,788 EPOCH 15 done: loss 0.0643 - lr 0.100000
2023-04-05 11:34:07,788 BAD EPOCHS (no improvement): 0
2023-04-05 11:34:07,791 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:09,596 epoch 16 - iter 28/280 - loss 0.06262701 - time (sec): 1.80 - samples/sec: 11828.01 - lr: 0.100000
2023-04-05 11:34:11,429 epoch 16 - iter 56/280 - loss 0.06408094 - time (sec): 3.64 - samples/sec: 11646.70 - lr: 0.100000
2023-04-05 11:34:13,212 epoch 16 - iter 84/280 - loss 0.06321444 - time (sec): 5.42 - samples/sec: 11726.49 - lr: 0.100000
2023-04-05 11:34:15,000 epoch 16 - iter 112/280 - loss 0.06311591 - time (sec): 7.21 - samples/sec: 11727.57 - lr: 0.100000
2023-04-05 11:34:16,796 epoch 16 - iter 140/280 - loss 0.06314014 - time (sec): 9.00 - samples/sec: 11800.46 - lr: 0.100000
2023-04-05 11:34:18,600 epoch 16 - iter 168/280 - loss 0.06342748 - time (sec): 10.81 - samples/sec: 11798.24 - lr: 0.100000
2023-04-05 11:34:20,375 epoch 16 - iter 196/280 - loss 0.06338833 - time (sec): 12.58 - samples/sec: 11844.19 - lr: 0.100000
2023-04-05 11:34:22,158 epoch 16 - iter 224/280 - loss 0.06271106 - time (sec): 14.37 - samples/sec: 11832.71 - lr: 0.100000
2023-04-05 11:34:23,943 epoch 16 - iter 252/280 - loss 0.06257842 - time (sec): 16.15 - samples/sec: 11825.27 - lr: 0.100000
2023-04-05 11:34:25,716 epoch 16 - iter 280/280 - loss 0.06212692 - time (sec): 17.93 - samples/sec: 11809.79 - lr: 0.100000
2023-04-05 11:34:25,717 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:25,717 EPOCH 16 done: loss 0.0621 - lr 0.100000
2023-04-05 11:34:25,717 BAD EPOCHS (no improvement): 0
2023-04-05 11:34:25,720 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:27,508 epoch 17 - iter 28/280 - loss 0.05288342 - time (sec): 1.79 - samples/sec: 11609.24 - lr: 0.100000
2023-04-05 11:34:29,286 epoch 17 - iter 56/280 - loss 0.05480018 - time (sec): 3.57 - samples/sec: 11868.54 - lr: 0.100000
2023-04-05 11:34:31,110 epoch 17 - iter 84/280 - loss 0.05705219 - time (sec): 5.39 - samples/sec: 11852.73 - lr: 0.100000
2023-04-05 11:34:33,001 epoch 17 - iter 112/280 - loss 0.05931561 - time (sec): 7.28 - samples/sec: 11726.22 - lr: 0.100000
2023-04-05 11:34:34,797 epoch 17 - iter 140/280 - loss 0.05948492 - time (sec): 9.08 - samples/sec: 11741.35 - lr: 0.100000
2023-04-05 11:34:36,620 epoch 17 - iter 168/280 - loss 0.05906552 - time (sec): 10.90 - samples/sec: 11687.50 - lr: 0.100000
2023-04-05 11:34:38,479 epoch 17 - iter 196/280 - loss 0.05925180 - time (sec): 12.76 - samples/sec: 11668.79 - lr: 0.100000
2023-04-05 11:34:40,227 epoch 17 - iter 224/280 - loss 0.05954558 - time (sec): 14.51 - samples/sec: 11691.53 - lr: 0.100000
2023-04-05 11:34:42,071 epoch 17 - iter 252/280 - loss 0.05948937 - time (sec): 16.35 - samples/sec: 11687.91 - lr: 0.100000
2023-04-05 11:34:43,825 epoch 17 - iter 280/280 - loss 0.05899674 - time (sec): 18.11 - samples/sec: 11692.31 - lr: 0.100000
2023-04-05 11:34:43,825 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:43,825 EPOCH 17 done: loss 0.0590 - lr 0.100000
2023-04-05 11:34:43,825 BAD EPOCHS (no improvement): 0
2023-04-05 11:34:43,828 ----------------------------------------------------------------------------------------------------
2023-04-05 11:34:45,643 epoch 18 - iter 28/280 - loss 0.05825112 - time (sec): 1.81 - samples/sec: 11393.99 - lr: 0.100000
2023-04-05 11:34:47,447 epoch 18 - iter 56/280 - loss 0.05855799 - time (sec): 3.62 - samples/sec: 11555.67 - lr: 0.100000
2023-04-05 11:34:49,212 epoch 18 - iter 84/280 - loss 0.05819408 - time (sec): 5.38 - samples/sec: 11687.96 - lr: 0.100000
2023-04-05 11:34:51,012 epoch 18 - iter 112/280 - loss 0.05842853 - time (sec): 7.18 - samples/sec: 11698.82 - lr: 0.100000
2023-04-05 11:34:52,817 epoch 18 - iter 140/280 - loss 0.05969303 - time (sec): 8.99 - samples/sec: 11733.02 - lr: 0.100000
2023-04-05 11:34:54,550 epoch 18 - iter 168/280 - loss 0.05938442 - time (sec): 10.72 - samples/sec: 11794.60 - lr: 0.100000
2023-04-05 11:34:56,337 epoch 18 - iter 196/280 - loss 0.05886669 - time (sec): 12.51 - samples/sec: 11803.83 - lr: 0.100000
2023-04-05 11:34:58,157 epoch 18 - iter 224/280 - loss 0.05813409 - time (sec): 14.33 - samples/sec: 11807.20 - lr: 0.100000
2023-04-05 11:35:00,015 epoch 18 - iter 252/280 - loss 0.05876983 - time (sec): 16.19 - samples/sec: 11774.36 - lr: 0.100000
2023-04-05 11:35:01,856 epoch 18 - iter 280/280 - loss 0.05829040 - time (sec): 18.03 - samples/sec: 11742.40 - lr: 0.100000
2023-04-05 11:35:01,856 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:01,856 EPOCH 18 done: loss 0.0583 - lr 0.100000
2023-04-05 11:35:01,856 BAD EPOCHS (no improvement): 0
2023-04-05 11:35:01,859 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:03,648 epoch 19 - iter 28/280 - loss 0.05283264 - time (sec): 1.79 - samples/sec: 11861.88 - lr: 0.100000
2023-04-05 11:35:05,399 epoch 19 - iter 56/280 - loss 0.05393442 - time (sec): 3.54 - samples/sec: 11919.42 - lr: 0.100000
2023-04-05 11:35:07,216 epoch 19 - iter 84/280 - loss 0.05440639 - time (sec): 5.36 - samples/sec: 11911.11 - lr: 0.100000
2023-04-05 11:35:09,008 epoch 19 - iter 112/280 - loss 0.05531663 - time (sec): 7.15 - samples/sec: 11909.93 - lr: 0.100000
2023-04-05 11:35:10,840 epoch 19 - iter 140/280 - loss 0.05565688 - time (sec): 8.98 - samples/sec: 11841.81 - lr: 0.100000
2023-04-05 11:35:12,599 epoch 19 - iter 168/280 - loss 0.05529086 - time (sec): 10.74 - samples/sec: 11830.34 - lr: 0.100000
2023-04-05 11:35:14,463 epoch 19 - iter 196/280 - loss 0.05545870 - time (sec): 12.60 - samples/sec: 11799.00 - lr: 0.100000
2023-04-05 11:35:16,261 epoch 19 - iter 224/280 - loss 0.05566567 - time (sec): 14.40 - samples/sec: 11790.06 - lr: 0.100000
2023-04-05 11:35:18,080 epoch 19 - iter 252/280 - loss 0.05539139 - time (sec): 16.22 - samples/sec: 11789.98 - lr: 0.100000
2023-04-05 11:35:19,860 epoch 19 - iter 280/280 - loss 0.05608728 - time (sec): 18.00 - samples/sec: 11759.72 - lr: 0.100000
2023-04-05 11:35:19,861 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:19,861 EPOCH 19 done: loss 0.0561 - lr 0.100000
2023-04-05 11:35:19,861 BAD EPOCHS (no improvement): 0
2023-04-05 11:35:19,863 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:21,682 epoch 20 - iter 28/280 - loss 0.05218948 - time (sec): 1.82 - samples/sec: 11864.34 - lr: 0.100000
2023-04-05 11:35:23,429 epoch 20 - iter 56/280 - loss 0.05439578 - time (sec): 3.57 - samples/sec: 11775.62 - lr: 0.100000
2023-04-05 11:35:25,252 epoch 20 - iter 84/280 - loss 0.05408566 - time (sec): 5.39 - samples/sec: 11811.45 - lr: 0.100000
2023-04-05 11:35:27,093 epoch 20 - iter 112/280 - loss 0.05399655 - time (sec): 7.23 - samples/sec: 11838.21 - lr: 0.100000
2023-04-05 11:35:28,853 epoch 20 - iter 140/280 - loss 0.05421216 - time (sec): 8.99 - samples/sec: 11840.90 - lr: 0.100000
2023-04-05 11:35:30,569 epoch 20 - iter 168/280 - loss 0.05381559 - time (sec): 10.71 - samples/sec: 11886.54 - lr: 0.100000
2023-04-05 11:35:32,406 epoch 20 - iter 196/280 - loss 0.05400375 - time (sec): 12.54 - samples/sec: 11866.18 - lr: 0.100000
2023-04-05 11:35:34,260 epoch 20 - iter 224/280 - loss 0.05410216 - time (sec): 14.40 - samples/sec: 11851.80 - lr: 0.100000
2023-04-05 11:35:36,025 epoch 20 - iter 252/280 - loss 0.05360529 - time (sec): 16.16 - samples/sec: 11823.32 - lr: 0.100000
2023-04-05 11:35:37,750 epoch 20 - iter 280/280 - loss 0.05352429 - time (sec): 17.89 - samples/sec: 11835.02 - lr: 0.100000
2023-04-05 11:35:37,751 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:37,751 EPOCH 20 done: loss 0.0535 - lr 0.100000
2023-04-05 11:35:37,751 BAD EPOCHS (no improvement): 0
2023-04-05 11:35:37,753 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:39,571 epoch 21 - iter 28/280 - loss 0.04843651 - time (sec): 1.82 - samples/sec: 11976.57 - lr: 0.100000
2023-04-05 11:35:41,349 epoch 21 - iter 56/280 - loss 0.05169687 - time (sec): 3.60 - samples/sec: 11948.84 - lr: 0.100000
2023-04-05 11:35:43,134 epoch 21 - iter 84/280 - loss 0.05002623 - time (sec): 5.38 - samples/sec: 11953.90 - lr: 0.100000
2023-04-05 11:35:44,933 epoch 21 - iter 112/280 - loss 0.05033864 - time (sec): 7.18 - samples/sec: 11975.88 - lr: 0.100000
2023-04-05 11:35:46,748 epoch 21 - iter 140/280 - loss 0.05125730 - time (sec): 8.99 - samples/sec: 11935.95 - lr: 0.100000
2023-04-05 11:35:48,512 epoch 21 - iter 168/280 - loss 0.05090290 - time (sec): 10.76 - samples/sec: 11926.32 - lr: 0.100000
2023-04-05 11:35:50,313 epoch 21 - iter 196/280 - loss 0.05134009 - time (sec): 12.56 - samples/sec: 11917.05 - lr: 0.100000
2023-04-05 11:35:52,116 epoch 21 - iter 224/280 - loss 0.05141356 - time (sec): 14.36 - samples/sec: 11898.55 - lr: 0.100000
2023-04-05 11:35:53,893 epoch 21 - iter 252/280 - loss 0.05179103 - time (sec): 16.14 - samples/sec: 11859.25 - lr: 0.100000
2023-04-05 11:35:55,614 epoch 21 - iter 280/280 - loss 0.05202194 - time (sec): 17.86 - samples/sec: 11852.58 - lr: 0.100000
2023-04-05 11:35:55,614 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:55,614 EPOCH 21 done: loss 0.0520 - lr 0.100000
2023-04-05 11:35:55,614 BAD EPOCHS (no improvement): 0
2023-04-05 11:35:55,617 ----------------------------------------------------------------------------------------------------
2023-04-05 11:35:57,426 epoch 22 - iter 28/280 - loss 0.05265036 - time (sec): 1.81 - samples/sec: 11809.34 - lr: 0.100000
2023-04-05 11:35:59,213 epoch 22 - iter 56/280 - loss 0.05228089 - time (sec): 3.60 - samples/sec: 11790.63 - lr: 0.100000
2023-04-05 11:36:00,990 epoch 22 - iter 84/280 - loss 0.05085628 - time (sec): 5.37 - samples/sec: 11832.29 - lr: 0.100000
2023-04-05 11:36:02,793 epoch 22 - iter 112/280 - loss 0.05016075 - time (sec): 7.18 - samples/sec: 11827.93 - lr: 0.100000
2023-04-05 11:36:04,557 epoch 22 - iter 140/280 - loss 0.05025752 - time (sec): 8.94 - samples/sec: 11881.74 - lr: 0.100000
2023-04-05 11:36:06,352 epoch 22 - iter 168/280 - loss 0.05001551 - time (sec): 10.73 - samples/sec: 11869.36 - lr: 0.100000
2023-04-05 11:36:08,162 epoch 22 - iter 196/280 - loss 0.05019254 - time (sec): 12.55 - samples/sec: 11875.55 - lr: 0.100000
2023-04-05 11:36:09,933 epoch 22 - iter 224/280 - loss 0.05035007 - time (sec): 14.32 - samples/sec: 11856.65 - lr: 0.100000
2023-04-05 11:36:11,752 epoch 22 - iter 252/280 - loss 0.04997119 - time (sec): 16.14 - samples/sec: 11859.88 - lr: 0.100000
2023-04-05 11:36:13,507 epoch 22 - iter 280/280 - loss 0.04996262 - time (sec): 17.89 - samples/sec: 11832.64 - lr: 0.100000
2023-04-05 11:36:13,508 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:13,508 EPOCH 22 done: loss 0.0500 - lr 0.100000
2023-04-05 11:36:13,508 BAD EPOCHS (no improvement): 0
2023-04-05 11:36:13,510 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:15,315 epoch 23 - iter 28/280 - loss 0.04413645 - time (sec): 1.80 - samples/sec: 12073.50 - lr: 0.100000
2023-04-05 11:36:17,041 epoch 23 - iter 56/280 - loss 0.04875877 - time (sec): 3.53 - samples/sec: 12101.00 - lr: 0.100000
2023-04-05 11:36:18,832 epoch 23 - iter 84/280 - loss 0.04898522 - time (sec): 5.32 - samples/sec: 12026.44 - lr: 0.100000
2023-04-05 11:36:20,638 epoch 23 - iter 112/280 - loss 0.04899564 - time (sec): 7.13 - samples/sec: 11926.44 - lr: 0.100000
2023-04-05 11:36:22,493 epoch 23 - iter 140/280 - loss 0.04896253 - time (sec): 8.98 - samples/sec: 11880.38 - lr: 0.100000
2023-04-05 11:36:24,290 epoch 23 - iter 168/280 - loss 0.04848346 - time (sec): 10.78 - samples/sec: 11869.02 - lr: 0.100000
2023-04-05 11:36:26,066 epoch 23 - iter 196/280 - loss 0.04878206 - time (sec): 12.56 - samples/sec: 11844.14 - lr: 0.100000
2023-04-05 11:36:27,870 epoch 23 - iter 224/280 - loss 0.04872234 - time (sec): 14.36 - samples/sec: 11856.29 - lr: 0.100000
2023-04-05 11:36:29,681 epoch 23 - iter 252/280 - loss 0.04921133 - time (sec): 16.17 - samples/sec: 11830.39 - lr: 0.100000
2023-04-05 11:36:31,462 epoch 23 - iter 280/280 - loss 0.04937451 - time (sec): 17.95 - samples/sec: 11792.19 - lr: 0.100000
2023-04-05 11:36:31,463 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:31,463 EPOCH 23 done: loss 0.0494 - lr 0.100000
2023-04-05 11:36:31,463 BAD EPOCHS (no improvement): 0
2023-04-05 11:36:31,465 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:33,286 epoch 24 - iter 28/280 - loss 0.04552134 - time (sec): 1.82 - samples/sec: 11836.10 - lr: 0.100000
2023-04-05 11:36:35,051 epoch 24 - iter 56/280 - loss 0.04245978 - time (sec): 3.59 - samples/sec: 11851.03 - lr: 0.100000
2023-04-05 11:36:36,883 epoch 24 - iter 84/280 - loss 0.04482955 - time (sec): 5.42 - samples/sec: 11776.35 - lr: 0.100000
2023-04-05 11:36:38,691 epoch 24 - iter 112/280 - loss 0.04568848 - time (sec): 7.23 - samples/sec: 11749.75 - lr: 0.100000
2023-04-05 11:36:40,537 epoch 24 - iter 140/280 - loss 0.04675023 - time (sec): 9.07 - samples/sec: 11723.74 - lr: 0.100000
2023-04-05 11:36:42,277 epoch 24 - iter 168/280 - loss 0.04727348 - time (sec): 10.81 - samples/sec: 11816.75 - lr: 0.100000
2023-04-05 11:36:44,027 epoch 24 - iter 196/280 - loss 0.04740621 - time (sec): 12.56 - samples/sec: 11812.06 - lr: 0.100000
2023-04-05 11:36:45,809 epoch 24 - iter 224/280 - loss 0.04746922 - time (sec): 14.34 - samples/sec: 11843.15 - lr: 0.100000
2023-04-05 11:36:47,572 epoch 24 - iter 252/280 - loss 0.04769287 - time (sec): 16.11 - samples/sec: 11853.42 - lr: 0.100000
2023-04-05 11:36:49,355 epoch 24 - iter 280/280 - loss 0.04779525 - time (sec): 17.89 - samples/sec: 11833.34 - lr: 0.100000
2023-04-05 11:36:49,355 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:49,355 EPOCH 24 done: loss 0.0478 - lr 0.100000
2023-04-05 11:36:49,355 BAD EPOCHS (no improvement): 0
2023-04-05 11:36:49,358 ----------------------------------------------------------------------------------------------------
2023-04-05 11:36:51,116 epoch 25 - iter 28/280 - loss 0.04124236 - time (sec): 1.76 - samples/sec: 11761.53 - lr: 0.100000
2023-04-05 11:36:52,887 epoch 25 - iter 56/280 - loss 0.04181873 - time (sec): 3.53 - samples/sec: 11813.75 - lr: 0.100000
2023-04-05 11:36:54,651 epoch 25 - iter 84/280 - loss 0.04423627 - time (sec): 5.29 - samples/sec: 11846.35 - lr: 0.100000
2023-04-05 11:36:56,478 epoch 25 - iter 112/280 - loss 0.04517841 - time (sec): 7.12 - samples/sec: 11790.36 - lr: 0.100000
2023-04-05 11:36:58,285 epoch 25 - iter 140/280 - loss 0.04565567 - time (sec): 8.93 - samples/sec: 11797.90 - lr: 0.100000
2023-04-05 11:37:00,043 epoch 25 - iter 168/280 - loss 0.04520782 - time (sec): 10.69 - samples/sec: 11844.63 - lr: 0.100000
2023-04-05 11:37:01,927 epoch 25 - iter 196/280 - loss 0.04512460 - time (sec): 12.57 - samples/sec: 11808.10 - lr: 0.100000
2023-04-05 11:37:03,756 epoch 25 - iter 224/280 - loss 0.04511967 - time (sec): 14.40 - samples/sec: 11777.13 - lr: 0.100000
2023-04-05 11:37:05,589 epoch 25 - iter 252/280 - loss 0.04524566 - time (sec): 16.23 - samples/sec: 11772.05 - lr: 0.100000
2023-04-05 11:37:07,335 epoch 25 - iter 280/280 - loss 0.04590508 - time (sec): 17.98 - samples/sec: 11775.74 - lr: 0.100000
2023-04-05 11:37:07,335 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:07,335 EPOCH 25 done: loss 0.0459 - lr 0.100000
2023-04-05 11:37:07,335 BAD EPOCHS (no improvement): 0
2023-04-05 11:37:07,338 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:09,132 epoch 26 - iter 28/280 - loss 0.04089327 - time (sec): 1.79 - samples/sec: 11935.93 - lr: 0.100000
2023-04-05 11:37:10,911 epoch 26 - iter 56/280 - loss 0.04435597 - time (sec): 3.57 - samples/sec: 11817.77 - lr: 0.100000
2023-04-05 11:37:12,717 epoch 26 - iter 84/280 - loss 0.04331287 - time (sec): 5.38 - samples/sec: 11709.68 - lr: 0.100000
2023-04-05 11:37:14,522 epoch 26 - iter 112/280 - loss 0.04340537 - time (sec): 7.18 - samples/sec: 11739.55 - lr: 0.100000
2023-04-05 11:37:16,273 epoch 26 - iter 140/280 - loss 0.04434313 - time (sec): 8.94 - samples/sec: 11756.57 - lr: 0.100000
2023-04-05 11:37:18,075 epoch 26 - iter 168/280 - loss 0.04410324 - time (sec): 10.74 - samples/sec: 11791.15 - lr: 0.100000
2023-04-05 11:37:19,845 epoch 26 - iter 196/280 - loss 0.04412420 - time (sec): 12.51 - samples/sec: 11819.23 - lr: 0.100000
2023-04-05 11:37:21,630 epoch 26 - iter 224/280 - loss 0.04430673 - time (sec): 14.29 - samples/sec: 11817.98 - lr: 0.100000
2023-04-05 11:37:23,436 epoch 26 - iter 252/280 - loss 0.04446632 - time (sec): 16.10 - samples/sec: 11821.47 - lr: 0.100000
2023-04-05 11:37:25,257 epoch 26 - iter 280/280 - loss 0.04501354 - time (sec): 17.92 - samples/sec: 11813.76 - lr: 0.100000
2023-04-05 11:37:25,257 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:25,257 EPOCH 26 done: loss 0.0450 - lr 0.100000
2023-04-05 11:37:25,257 BAD EPOCHS (no improvement): 0
2023-04-05 11:37:25,260 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:27,025 epoch 27 - iter 28/280 - loss 0.03851357 - time (sec): 1.77 - samples/sec: 12051.51 - lr: 0.100000
2023-04-05 11:37:28,838 epoch 27 - iter 56/280 - loss 0.04014540 - time (sec): 3.58 - samples/sec: 11914.90 - lr: 0.100000
2023-04-05 11:37:30,664 epoch 27 - iter 84/280 - loss 0.04133777 - time (sec): 5.40 - samples/sec: 11789.93 - lr: 0.100000
2023-04-05 11:37:32,408 epoch 27 - iter 112/280 - loss 0.04193196 - time (sec): 7.15 - samples/sec: 11846.44 - lr: 0.100000
2023-04-05 11:37:34,182 epoch 27 - iter 140/280 - loss 0.04183586 - time (sec): 8.92 - samples/sec: 11863.34 - lr: 0.100000
2023-04-05 11:37:35,977 epoch 27 - iter 168/280 - loss 0.04189724 - time (sec): 10.72 - samples/sec: 11884.31 - lr: 0.100000
2023-04-05 11:37:37,810 epoch 27 - iter 196/280 - loss 0.04244932 - time (sec): 12.55 - samples/sec: 11857.76 - lr: 0.100000
2023-04-05 11:37:39,646 epoch 27 - iter 224/280 - loss 0.04281068 - time (sec): 14.39 - samples/sec: 11790.05 - lr: 0.100000
2023-04-05 11:37:41,440 epoch 27 - iter 252/280 - loss 0.04280542 - time (sec): 16.18 - samples/sec: 11783.33 - lr: 0.100000
2023-04-05 11:37:43,228 epoch 27 - iter 280/280 - loss 0.04399544 - time (sec): 17.97 - samples/sec: 11781.91 - lr: 0.100000
2023-04-05 11:37:43,228 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:43,228 EPOCH 27 done: loss 0.0440 - lr 0.100000
2023-04-05 11:37:43,228 BAD EPOCHS (no improvement): 0
2023-04-05 11:37:43,231 ----------------------------------------------------------------------------------------------------
2023-04-05 11:37:45,052 epoch 28 - iter 28/280 - loss 0.03782082 - time (sec): 1.82 - samples/sec: 11549.39 - lr: 0.100000
2023-04-05 11:37:46,899 epoch 28 - iter 56/280 - loss 0.04120980 - time (sec): 3.67 - samples/sec: 11594.96 - lr: 0.100000
2023-04-05 11:37:48,678 epoch 28 - iter 84/280 - loss 0.04173927 - time (sec): 5.45 - samples/sec: 11658.57 - lr: 0.100000
2023-04-05 11:37:50,453 epoch 28 - iter 112/280 - loss 0.04021163 - time (sec): 7.22 - samples/sec: 11735.56 - lr: 0.100000
2023-04-05 11:37:52,317 epoch 28 - iter 140/280 - loss 0.04071840 - time (sec): 9.09 - samples/sec: 11737.51 - lr: 0.100000
2023-04-05 11:37:54,164 epoch 28 - iter 168/280 - loss 0.04090358 - time (sec): 10.93 - samples/sec: 11696.43 - lr: 0.100000
2023-04-05 11:37:55,996 epoch 28 - iter 196/280 - loss 0.04071248 - time (sec): 12.76 - samples/sec: 11732.91 - lr: 0.100000
2023-04-05 11:37:57,799 epoch 28 - iter 224/280 - loss 0.04154954 - time (sec): 14.57 - samples/sec: 11710.96 - lr: 0.100000
2023-04-05 11:37:59,572 epoch 28 - iter 252/280 - loss 0.04182913 - time (sec): 16.34 - samples/sec: 11703.81 - lr: 0.100000
2023-04-05 11:38:01,307 epoch 28 - iter 280/280 - loss 0.04174203 - time (sec): 18.08 - samples/sec: 11710.77 - lr: 0.100000
2023-04-05 11:38:01,308 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:01,308 EPOCH 28 done: loss 0.0417 - lr 0.100000
2023-04-05 11:38:01,308 BAD EPOCHS (no improvement): 0
2023-04-05 11:38:01,310 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:03,076 epoch 29 - iter 28/280 - loss 0.04221041 - time (sec): 1.77 - samples/sec: 11874.64 - lr: 0.100000
2023-04-05 11:38:04,896 epoch 29 - iter 56/280 - loss 0.04149599 - time (sec): 3.59 - samples/sec: 11866.19 - lr: 0.100000
2023-04-05 11:38:06,691 epoch 29 - iter 84/280 - loss 0.04060912 - time (sec): 5.38 - samples/sec: 11852.32 - lr: 0.100000
2023-04-05 11:38:08,518 epoch 29 - iter 112/280 - loss 0.04082735 - time (sec): 7.21 - samples/sec: 11806.45 - lr: 0.100000
2023-04-05 11:38:10,352 epoch 29 - iter 140/280 - loss 0.04116983 - time (sec): 9.04 - samples/sec: 11777.70 - lr: 0.100000
2023-04-05 11:38:12,130 epoch 29 - iter 168/280 - loss 0.04118497 - time (sec): 10.82 - samples/sec: 11814.34 - lr: 0.100000
2023-04-05 11:38:13,976 epoch 29 - iter 196/280 - loss 0.04185893 - time (sec): 12.67 - samples/sec: 11780.51 - lr: 0.100000
2023-04-05 11:38:15,759 epoch 29 - iter 224/280 - loss 0.04171785 - time (sec): 14.45 - samples/sec: 11783.56 - lr: 0.100000
2023-04-05 11:38:17,560 epoch 29 - iter 252/280 - loss 0.04155907 - time (sec): 16.25 - samples/sec: 11768.06 - lr: 0.100000
2023-04-05 11:38:19,319 epoch 29 - iter 280/280 - loss 0.04183624 - time (sec): 18.01 - samples/sec: 11754.88 - lr: 0.100000
2023-04-05 11:38:19,319 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:19,320 EPOCH 29 done: loss 0.0418 - lr 0.100000
2023-04-05 11:38:19,320 BAD EPOCHS (no improvement): 1
2023-04-05 11:38:19,322 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:21,198 epoch 30 - iter 28/280 - loss 0.03779117 - time (sec): 1.88 - samples/sec: 11594.86 - lr: 0.100000
2023-04-05 11:38:23,011 epoch 30 - iter 56/280 - loss 0.03672050 - time (sec): 3.69 - samples/sec: 11721.53 - lr: 0.100000
2023-04-05 11:38:24,808 epoch 30 - iter 84/280 - loss 0.03610688 - time (sec): 5.49 - samples/sec: 11732.88 - lr: 0.100000
2023-04-05 11:38:26,627 epoch 30 - iter 112/280 - loss 0.03689068 - time (sec): 7.30 - samples/sec: 11662.28 - lr: 0.100000
2023-04-05 11:38:28,391 epoch 30 - iter 140/280 - loss 0.03771745 - time (sec): 9.07 - samples/sec: 11707.12 - lr: 0.100000
2023-04-05 11:38:30,250 epoch 30 - iter 168/280 - loss 0.03810714 - time (sec): 10.93 - samples/sec: 11690.48 - lr: 0.100000
2023-04-05 11:38:32,026 epoch 30 - iter 196/280 - loss 0.03878411 - time (sec): 12.70 - samples/sec: 11698.03 - lr: 0.100000
2023-04-05 11:38:33,775 epoch 30 - iter 224/280 - loss 0.03871405 - time (sec): 14.45 - samples/sec: 11689.34 - lr: 0.100000
2023-04-05 11:38:35,555 epoch 30 - iter 252/280 - loss 0.03891072 - time (sec): 16.23 - samples/sec: 11723.14 - lr: 0.100000
2023-04-05 11:38:37,407 epoch 30 - iter 280/280 - loss 0.03988472 - time (sec): 18.08 - samples/sec: 11705.56 - lr: 0.100000
2023-04-05 11:38:37,407 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:37,407 EPOCH 30 done: loss 0.0399 - lr 0.100000
2023-04-05 11:38:37,407 BAD EPOCHS (no improvement): 0
2023-04-05 11:38:37,410 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:39,189 epoch 31 - iter 28/280 - loss 0.03808612 - time (sec): 1.78 - samples/sec: 11713.27 - lr: 0.100000
2023-04-05 11:38:40,986 epoch 31 - iter 56/280 - loss 0.03951726 - time (sec): 3.58 - samples/sec: 11768.47 - lr: 0.100000
2023-04-05 11:38:42,789 epoch 31 - iter 84/280 - loss 0.03882489 - time (sec): 5.38 - samples/sec: 11759.99 - lr: 0.100000
2023-04-05 11:38:44,634 epoch 31 - iter 112/280 - loss 0.03841884 - time (sec): 7.22 - samples/sec: 11719.98 - lr: 0.100000
2023-04-05 11:38:46,458 epoch 31 - iter 140/280 - loss 0.03871293 - time (sec): 9.05 - samples/sec: 11726.56 - lr: 0.100000
2023-04-05 11:38:48,240 epoch 31 - iter 168/280 - loss 0.03824375 - time (sec): 10.83 - samples/sec: 11741.80 - lr: 0.100000
2023-04-05 11:38:50,051 epoch 31 - iter 196/280 - loss 0.03852520 - time (sec): 12.64 - samples/sec: 11731.73 - lr: 0.100000
2023-04-05 11:38:51,894 epoch 31 - iter 224/280 - loss 0.03860727 - time (sec): 14.48 - samples/sec: 11745.08 - lr: 0.100000
2023-04-05 11:38:53,696 epoch 31 - iter 252/280 - loss 0.03860575 - time (sec): 16.29 - samples/sec: 11752.51 - lr: 0.100000
2023-04-05 11:38:55,401 epoch 31 - iter 280/280 - loss 0.03881480 - time (sec): 17.99 - samples/sec: 11766.56 - lr: 0.100000
2023-04-05 11:38:55,402 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:55,402 EPOCH 31 done: loss 0.0388 - lr 0.100000
2023-04-05 11:38:55,402 BAD EPOCHS (no improvement): 0
2023-04-05 11:38:55,405 ----------------------------------------------------------------------------------------------------
2023-04-05 11:38:57,211 epoch 32 - iter 28/280 - loss 0.03945079 - time (sec): 1.81 - samples/sec: 11607.57 - lr: 0.100000
2023-04-05 11:38:59,049 epoch 32 - iter 56/280 - loss 0.03949573 - time (sec): 3.64 - samples/sec: 11526.26 - lr: 0.100000
2023-04-05 11:39:00,902 epoch 32 - iter 84/280 - loss 0.03816195 - time (sec): 5.50 - samples/sec: 11484.70 - lr: 0.100000
2023-04-05 11:39:02,761 epoch 32 - iter 112/280 - loss 0.03736938 - time (sec): 7.36 - samples/sec: 11435.90 - lr: 0.100000
2023-04-05 11:39:04,649 epoch 32 - iter 140/280 - loss 0.03739442 - time (sec): 9.24 - samples/sec: 11448.83 - lr: 0.100000
2023-04-05 11:39:06,460 epoch 32 - iter 168/280 - loss 0.03769359 - time (sec): 11.06 - samples/sec: 11460.45 - lr: 0.100000
2023-04-05 11:39:08,292 epoch 32 - iter 196/280 - loss 0.03894570 - time (sec): 12.89 - samples/sec: 11468.50 - lr: 0.100000
2023-04-05 11:39:10,081 epoch 32 - iter 224/280 - loss 0.03866787 - time (sec): 14.68 - samples/sec: 11536.25 - lr: 0.100000
2023-04-05 11:39:11,946 epoch 32 - iter 252/280 - loss 0.03846310 - time (sec): 16.54 - samples/sec: 11559.07 - lr: 0.100000
2023-04-05 11:39:13,705 epoch 32 - iter 280/280 - loss 0.03827095 - time (sec): 18.30 - samples/sec: 11567.44 - lr: 0.100000
2023-04-05 11:39:13,706 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:13,706 EPOCH 32 done: loss 0.0383 - lr 0.100000
2023-04-05 11:39:13,706 BAD EPOCHS (no improvement): 0
2023-04-05 11:39:13,711 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:15,506 epoch 33 - iter 28/280 - loss 0.03470166 - time (sec): 1.80 - samples/sec: 11891.82 - lr: 0.100000
2023-04-05 11:39:17,347 epoch 33 - iter 56/280 - loss 0.03871269 - time (sec): 3.64 - samples/sec: 11764.20 - lr: 0.100000
2023-04-05 11:39:19,149 epoch 33 - iter 84/280 - loss 0.03902470 - time (sec): 5.44 - samples/sec: 11845.71 - lr: 0.100000
2023-04-05 11:39:20,974 epoch 33 - iter 112/280 - loss 0.03725963 - time (sec): 7.26 - samples/sec: 11817.48 - lr: 0.100000
2023-04-05 11:39:22,800 epoch 33 - iter 140/280 - loss 0.03723502 - time (sec): 9.09 - samples/sec: 11800.84 - lr: 0.100000
2023-04-05 11:39:24,589 epoch 33 - iter 168/280 - loss 0.03721689 - time (sec): 10.88 - samples/sec: 11781.01 - lr: 0.100000
2023-04-05 11:39:26,406 epoch 33 - iter 196/280 - loss 0.03801672 - time (sec): 12.70 - samples/sec: 11770.68 - lr: 0.100000
2023-04-05 11:39:28,199 epoch 33 - iter 224/280 - loss 0.03776562 - time (sec): 14.49 - samples/sec: 11736.76 - lr: 0.100000
2023-04-05 11:39:29,975 epoch 33 - iter 252/280 - loss 0.03802663 - time (sec): 16.26 - samples/sec: 11734.95 - lr: 0.100000
2023-04-05 11:39:31,811 epoch 33 - iter 280/280 - loss 0.03831009 - time (sec): 18.10 - samples/sec: 11696.04 - lr: 0.100000
2023-04-05 11:39:31,811 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:31,811 EPOCH 33 done: loss 0.0383 - lr 0.100000
2023-04-05 11:39:31,811 BAD EPOCHS (no improvement): 1
2023-04-05 11:39:31,814 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:33,627 epoch 34 - iter 28/280 - loss 0.03620962 - time (sec): 1.81 - samples/sec: 11603.36 - lr: 0.100000
2023-04-05 11:39:35,513 epoch 34 - iter 56/280 - loss 0.03513302 - time (sec): 3.70 - samples/sec: 11433.87 - lr: 0.100000
2023-04-05 11:39:37,359 epoch 34 - iter 84/280 - loss 0.03536669 - time (sec): 5.55 - samples/sec: 11446.28 - lr: 0.100000
2023-04-05 11:39:39,180 epoch 34 - iter 112/280 - loss 0.03499080 - time (sec): 7.37 - samples/sec: 11483.59 - lr: 0.100000
2023-04-05 11:39:41,027 epoch 34 - iter 140/280 - loss 0.03522558 - time (sec): 9.21 - samples/sec: 11487.75 - lr: 0.100000
2023-04-05 11:39:42,870 epoch 34 - iter 168/280 - loss 0.03490538 - time (sec): 11.06 - samples/sec: 11475.42 - lr: 0.100000
2023-04-05 11:39:44,748 epoch 34 - iter 196/280 - loss 0.03561561 - time (sec): 12.93 - samples/sec: 11478.01 - lr: 0.100000
2023-04-05 11:39:46,578 epoch 34 - iter 224/280 - loss 0.03601340 - time (sec): 14.76 - samples/sec: 11481.38 - lr: 0.100000
2023-04-05 11:39:48,401 epoch 34 - iter 252/280 - loss 0.03618573 - time (sec): 16.59 - samples/sec: 11498.93 - lr: 0.100000
2023-04-05 11:39:50,175 epoch 34 - iter 280/280 - loss 0.03598665 - time (sec): 18.36 - samples/sec: 11529.49 - lr: 0.100000
2023-04-05 11:39:50,175 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:50,175 EPOCH 34 done: loss 0.0360 - lr 0.100000
2023-04-05 11:39:50,175 BAD EPOCHS (no improvement): 0
2023-04-05 11:39:50,178 ----------------------------------------------------------------------------------------------------
2023-04-05 11:39:52,001 epoch 35 - iter 28/280 - loss 0.03397965 - time (sec): 1.82 - samples/sec: 11880.73 - lr: 0.100000
2023-04-05 11:39:53,871 epoch 35 - iter 56/280 - loss 0.03403821 - time (sec): 3.69 - samples/sec: 11604.62 - lr: 0.100000
2023-04-05 11:39:55,714 epoch 35 - iter 84/280 - loss 0.03543108 - time (sec): 5.54 - samples/sec: 11550.94 - lr: 0.100000
2023-04-05 11:39:57,476 epoch 35 - iter 112/280 - loss 0.03645667 - time (sec): 7.30 - samples/sec: 11612.08 - lr: 0.100000
2023-04-05 11:40:00,675 epoch 35 - iter 140/280 - loss 0.03658092 - time (sec): 10.50 - samples/sec: 10120.05 - lr: 0.100000
2023-04-05 11:40:02,447 epoch 35 - iter 168/280 - loss 0.03659507 - time (sec): 12.27 - samples/sec: 10348.01 - lr: 0.100000
2023-04-05 11:40:04,244 epoch 35 - iter 196/280 - loss 0.03646809 - time (sec): 14.07 - samples/sec: 10573.14 - lr: 0.100000
2023-04-05 11:40:06,078 epoch 35 - iter 224/280 - loss 0.03662898 - time (sec): 15.90 - samples/sec: 10707.60 - lr: 0.100000
2023-04-05 11:40:07,909 epoch 35 - iter 252/280 - loss 0.03633694 - time (sec): 17.73 - samples/sec: 10804.47 - lr: 0.100000
2023-04-05 11:40:09,582 epoch 35 - iter 280/280 - loss 0.03636577 - time (sec): 19.40 - samples/sec: 10909.83 - lr: 0.100000
2023-04-05 11:40:09,582 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:09,582 EPOCH 35 done: loss 0.0364 - lr 0.100000
2023-04-05 11:40:09,582 BAD EPOCHS (no improvement): 1
2023-04-05 11:40:09,585 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:11,364 epoch 36 - iter 28/280 - loss 0.03712210 - time (sec): 1.78 - samples/sec: 11737.86 - lr: 0.100000
2023-04-05 11:40:13,181 epoch 36 - iter 56/280 - loss 0.03619270 - time (sec): 3.60 - samples/sec: 11743.46 - lr: 0.100000
2023-04-05 11:40:15,010 epoch 36 - iter 84/280 - loss 0.03484479 - time (sec): 5.43 - samples/sec: 11766.34 - lr: 0.100000
2023-04-05 11:40:16,861 epoch 36 - iter 112/280 - loss 0.03427536 - time (sec): 7.28 - samples/sec: 11707.46 - lr: 0.100000
2023-04-05 11:40:18,638 epoch 36 - iter 140/280 - loss 0.03509265 - time (sec): 9.05 - samples/sec: 11718.62 - lr: 0.100000
2023-04-05 11:40:20,450 epoch 36 - iter 168/280 - loss 0.03530102 - time (sec): 10.86 - samples/sec: 11719.62 - lr: 0.100000
2023-04-05 11:40:22,286 epoch 36 - iter 196/280 - loss 0.03531748 - time (sec): 12.70 - samples/sec: 11740.50 - lr: 0.100000
2023-04-05 11:40:24,112 epoch 36 - iter 224/280 - loss 0.03480613 - time (sec): 14.53 - samples/sec: 11705.97 - lr: 0.100000
2023-04-05 11:40:25,885 epoch 36 - iter 252/280 - loss 0.03473059 - time (sec): 16.30 - samples/sec: 11739.57 - lr: 0.100000
2023-04-05 11:40:27,616 epoch 36 - iter 280/280 - loss 0.03488935 - time (sec): 18.03 - samples/sec: 11740.50 - lr: 0.100000
2023-04-05 11:40:27,616 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:27,616 EPOCH 36 done: loss 0.0349 - lr 0.100000
2023-04-05 11:40:27,617 BAD EPOCHS (no improvement): 0
2023-04-05 11:40:27,619 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:29,394 epoch 37 - iter 28/280 - loss 0.03492849 - time (sec): 1.77 - samples/sec: 11767.27 - lr: 0.100000
2023-04-05 11:40:31,178 epoch 37 - iter 56/280 - loss 0.03533917 - time (sec): 3.56 - samples/sec: 11780.53 - lr: 0.100000
2023-04-05 11:40:32,938 epoch 37 - iter 84/280 - loss 0.03550122 - time (sec): 5.32 - samples/sec: 11868.57 - lr: 0.100000
2023-04-05 11:40:34,740 epoch 37 - iter 112/280 - loss 0.03508579 - time (sec): 7.12 - samples/sec: 11885.04 - lr: 0.100000
2023-04-05 11:40:36,570 epoch 37 - iter 140/280 - loss 0.03527674 - time (sec): 8.95 - samples/sec: 11892.16 - lr: 0.100000
2023-04-05 11:40:38,341 epoch 37 - iter 168/280 - loss 0.03503908 - time (sec): 10.72 - samples/sec: 11862.46 - lr: 0.100000
2023-04-05 11:40:40,125 epoch 37 - iter 196/280 - loss 0.03501984 - time (sec): 12.51 - samples/sec: 11897.99 - lr: 0.100000
2023-04-05 11:40:41,952 epoch 37 - iter 224/280 - loss 0.03484890 - time (sec): 14.33 - samples/sec: 11864.14 - lr: 0.100000
2023-04-05 11:40:43,789 epoch 37 - iter 252/280 - loss 0.03482832 - time (sec): 16.17 - samples/sec: 11817.38 - lr: 0.100000
2023-04-05 11:40:45,557 epoch 37 - iter 280/280 - loss 0.03452807 - time (sec): 17.94 - samples/sec: 11801.10 - lr: 0.100000
2023-04-05 11:40:45,557 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:45,557 EPOCH 37 done: loss 0.0345 - lr 0.100000
2023-04-05 11:40:45,557 BAD EPOCHS (no improvement): 0
2023-04-05 11:40:45,560 ----------------------------------------------------------------------------------------------------
2023-04-05 11:40:47,406 epoch 38 - iter 28/280 - loss 0.02924971 - time (sec): 1.85 - samples/sec: 11611.39 - lr: 0.100000
2023-04-05 11:40:49,219 epoch 38 - iter 56/280 - loss 0.03094036 - time (sec): 3.66 - samples/sec: 11604.83 - lr: 0.100000
2023-04-05 11:40:50,991 epoch 38 - iter 84/280 - loss 0.03150412 - time (sec): 5.43 - samples/sec: 11644.00 - lr: 0.100000
2023-04-05 11:40:52,762 epoch 38 - iter 112/280 - loss 0.03200344 - time (sec): 7.20 - samples/sec: 11697.88 - lr: 0.100000
2023-04-05 11:40:54,595 epoch 38 - iter 140/280 - loss 0.03235991 - time (sec): 9.04 - samples/sec: 11660.33 - lr: 0.100000
2023-04-05 11:40:56,427 epoch 38 - iter 168/280 - loss 0.03299630 - time (sec): 10.87 - samples/sec: 11703.53 - lr: 0.100000
2023-04-05 11:40:58,210 epoch 38 - iter 196/280 - loss 0.03320721 - time (sec): 12.65 - samples/sec: 11748.67 - lr: 0.100000
2023-04-05 11:40:59,979 epoch 38 - iter 224/280 - loss 0.03320812 - time (sec): 14.42 - samples/sec: 11769.27 - lr: 0.100000
2023-04-05 11:41:01,826 epoch 38 - iter 252/280 - loss 0.03377228 - time (sec): 16.27 - samples/sec: 11758.88 - lr: 0.100000
2023-04-05 11:41:03,578 epoch 38 - iter 280/280 - loss 0.03376645 - time (sec): 18.02 - samples/sec: 11748.69 - lr: 0.100000
2023-04-05 11:41:03,579 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:03,579 EPOCH 38 done: loss 0.0338 - lr 0.100000
2023-04-05 11:41:03,579 BAD EPOCHS (no improvement): 0
2023-04-05 11:41:03,581 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:05,387 epoch 39 - iter 28/280 - loss 0.03031979 - time (sec): 1.81 - samples/sec: 11728.83 - lr: 0.100000
2023-04-05 11:41:07,231 epoch 39 - iter 56/280 - loss 0.02972548 - time (sec): 3.65 - samples/sec: 11672.13 - lr: 0.100000
2023-04-05 11:41:09,037 epoch 39 - iter 84/280 - loss 0.03052992 - time (sec): 5.46 - samples/sec: 11787.83 - lr: 0.100000
2023-04-05 11:41:10,831 epoch 39 - iter 112/280 - loss 0.03130694 - time (sec): 7.25 - samples/sec: 11794.77 - lr: 0.100000
2023-04-05 11:41:12,615 epoch 39 - iter 140/280 - loss 0.03137877 - time (sec): 9.03 - samples/sec: 11794.71 - lr: 0.100000
2023-04-05 11:41:14,382 epoch 39 - iter 168/280 - loss 0.03151465 - time (sec): 10.80 - samples/sec: 11804.13 - lr: 0.100000
2023-04-05 11:41:16,168 epoch 39 - iter 196/280 - loss 0.03181991 - time (sec): 12.59 - samples/sec: 11817.23 - lr: 0.100000
2023-04-05 11:41:17,936 epoch 39 - iter 224/280 - loss 0.03256943 - time (sec): 14.35 - samples/sec: 11837.75 - lr: 0.100000
2023-04-05 11:41:19,715 epoch 39 - iter 252/280 - loss 0.03243855 - time (sec): 16.13 - samples/sec: 11838.64 - lr: 0.100000
2023-04-05 11:41:21,472 epoch 39 - iter 280/280 - loss 0.03261390 - time (sec): 17.89 - samples/sec: 11832.89 - lr: 0.100000
2023-04-05 11:41:21,472 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:21,472 EPOCH 39 done: loss 0.0326 - lr 0.100000
2023-04-05 11:41:21,472 BAD EPOCHS (no improvement): 0
2023-04-05 11:41:21,475 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:23,315 epoch 40 - iter 28/280 - loss 0.03397579 - time (sec): 1.84 - samples/sec: 11546.81 - lr: 0.100000
2023-04-05 11:41:25,119 epoch 40 - iter 56/280 - loss 0.03076253 - time (sec): 3.64 - samples/sec: 11691.29 - lr: 0.100000
2023-04-05 11:41:26,945 epoch 40 - iter 84/280 - loss 0.03167224 - time (sec): 5.47 - samples/sec: 11712.08 - lr: 0.100000
2023-04-05 11:41:28,773 epoch 40 - iter 112/280 - loss 0.03213338 - time (sec): 7.30 - samples/sec: 11699.56 - lr: 0.100000
2023-04-05 11:41:30,596 epoch 40 - iter 140/280 - loss 0.03252726 - time (sec): 9.12 - samples/sec: 11672.06 - lr: 0.100000
2023-04-05 11:41:32,379 epoch 40 - iter 168/280 - loss 0.03257365 - time (sec): 10.90 - samples/sec: 11710.12 - lr: 0.100000
2023-04-05 11:41:34,181 epoch 40 - iter 196/280 - loss 0.03206865 - time (sec): 12.71 - samples/sec: 11706.58 - lr: 0.100000
2023-04-05 11:41:35,995 epoch 40 - iter 224/280 - loss 0.03212630 - time (sec): 14.52 - samples/sec: 11724.25 - lr: 0.100000
2023-04-05 11:41:37,779 epoch 40 - iter 252/280 - loss 0.03168467 - time (sec): 16.30 - samples/sec: 11717.51 - lr: 0.100000
2023-04-05 11:41:39,526 epoch 40 - iter 280/280 - loss 0.03170537 - time (sec): 18.05 - samples/sec: 11727.64 - lr: 0.100000
2023-04-05 11:41:39,526 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:39,526 EPOCH 40 done: loss 0.0317 - lr 0.100000
2023-04-05 11:41:39,526 BAD EPOCHS (no improvement): 0
2023-04-05 11:41:39,529 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:41,335 epoch 41 - iter 28/280 - loss 0.03169512 - time (sec): 1.81 - samples/sec: 11598.46 - lr: 0.100000
2023-04-05 11:41:43,098 epoch 41 - iter 56/280 - loss 0.02987874 - time (sec): 3.57 - samples/sec: 11810.77 - lr: 0.100000
2023-04-05 11:41:44,865 epoch 41 - iter 84/280 - loss 0.03034049 - time (sec): 5.34 - samples/sec: 11813.64 - lr: 0.100000
2023-04-05 11:41:46,692 epoch 41 - iter 112/280 - loss 0.03132979 - time (sec): 7.16 - samples/sec: 11779.38 - lr: 0.100000
2023-04-05 11:41:48,455 epoch 41 - iter 140/280 - loss 0.03185747 - time (sec): 8.93 - samples/sec: 11816.74 - lr: 0.100000
2023-04-05 11:41:50,213 epoch 41 - iter 168/280 - loss 0.03162195 - time (sec): 10.68 - samples/sec: 11890.39 - lr: 0.100000
2023-04-05 11:41:52,007 epoch 41 - iter 196/280 - loss 0.03175273 - time (sec): 12.48 - samples/sec: 11888.61 - lr: 0.100000
2023-04-05 11:41:53,812 epoch 41 - iter 224/280 - loss 0.03205507 - time (sec): 14.28 - samples/sec: 11896.56 - lr: 0.100000
2023-04-05 11:41:55,647 epoch 41 - iter 252/280 - loss 0.03203207 - time (sec): 16.12 - samples/sec: 11878.15 - lr: 0.100000
2023-04-05 11:41:57,387 epoch 41 - iter 280/280 - loss 0.03188554 - time (sec): 17.86 - samples/sec: 11854.14 - lr: 0.100000
2023-04-05 11:41:57,388 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:57,388 EPOCH 41 done: loss 0.0319 - lr 0.100000
2023-04-05 11:41:57,388 BAD EPOCHS (no improvement): 1
2023-04-05 11:41:57,390 ----------------------------------------------------------------------------------------------------
2023-04-05 11:41:59,142 epoch 42 - iter 28/280 - loss 0.03157143 - time (sec): 1.75 - samples/sec: 11974.81 - lr: 0.100000
2023-04-05 11:42:00,913 epoch 42 - iter 56/280 - loss 0.03096020 - time (sec): 3.52 - samples/sec: 11857.82 - lr: 0.100000
2023-04-05 11:42:02,712 epoch 42 - iter 84/280 - loss 0.02972157 - time (sec): 5.32 - samples/sec: 11865.20 - lr: 0.100000
2023-04-05 11:42:04,600 epoch 42 - iter 112/280 - loss 0.02970780 - time (sec): 7.21 - samples/sec: 11771.44 - lr: 0.100000
2023-04-05 11:42:06,417 epoch 42 - iter 140/280 - loss 0.02974788 - time (sec): 9.03 - samples/sec: 11741.13 - lr: 0.100000
2023-04-05 11:42:08,270 epoch 42 - iter 168/280 - loss 0.03005308 - time (sec): 10.88 - samples/sec: 11736.30 - lr: 0.100000
2023-04-05 11:42:10,041 epoch 42 - iter 196/280 - loss 0.03029969 - time (sec): 12.65 - samples/sec: 11748.92 - lr: 0.100000
2023-04-05 11:42:11,771 epoch 42 - iter 224/280 - loss 0.03050950 - time (sec): 14.38 - samples/sec: 11790.59 - lr: 0.100000
2023-04-05 11:42:13,609 epoch 42 - iter 252/280 - loss 0.03047451 - time (sec): 16.22 - samples/sec: 11754.92 - lr: 0.100000
2023-04-05 11:42:15,413 epoch 42 - iter 280/280 - loss 0.03062606 - time (sec): 18.02 - samples/sec: 11745.72 - lr: 0.100000
2023-04-05 11:42:15,413 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:15,413 EPOCH 42 done: loss 0.0306 - lr 0.100000
2023-04-05 11:42:15,413 BAD EPOCHS (no improvement): 0
2023-04-05 11:42:15,416 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:17,201 epoch 43 - iter 28/280 - loss 0.02888818 - time (sec): 1.78 - samples/sec: 11822.28 - lr: 0.100000
2023-04-05 11:42:18,957 epoch 43 - iter 56/280 - loss 0.03051591 - time (sec): 3.54 - samples/sec: 11887.82 - lr: 0.100000
2023-04-05 11:42:20,742 epoch 43 - iter 84/280 - loss 0.03089329 - time (sec): 5.33 - samples/sec: 11842.28 - lr: 0.100000
2023-04-05 11:42:22,543 epoch 43 - iter 112/280 - loss 0.03001506 - time (sec): 7.13 - samples/sec: 11793.84 - lr: 0.100000
2023-04-05 11:42:24,357 epoch 43 - iter 140/280 - loss 0.03062371 - time (sec): 8.94 - samples/sec: 11794.48 - lr: 0.100000
2023-04-05 11:42:26,161 epoch 43 - iter 168/280 - loss 0.03061882 - time (sec): 10.74 - samples/sec: 11826.85 - lr: 0.100000
2023-04-05 11:42:27,938 epoch 43 - iter 196/280 - loss 0.03063456 - time (sec): 12.52 - samples/sec: 11844.31 - lr: 0.100000
2023-04-05 11:42:29,743 epoch 43 - iter 224/280 - loss 0.03074782 - time (sec): 14.33 - samples/sec: 11847.45 - lr: 0.100000
2023-04-05 11:42:31,503 epoch 43 - iter 252/280 - loss 0.03092329 - time (sec): 16.09 - samples/sec: 11832.74 - lr: 0.100000
2023-04-05 11:42:33,328 epoch 43 - iter 280/280 - loss 0.03123207 - time (sec): 17.91 - samples/sec: 11818.61 - lr: 0.100000
2023-04-05 11:42:33,328 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:33,328 EPOCH 43 done: loss 0.0312 - lr 0.100000
2023-04-05 11:42:33,328 BAD EPOCHS (no improvement): 1
2023-04-05 11:42:33,331 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:35,147 epoch 44 - iter 28/280 - loss 0.03121475 - time (sec): 1.82 - samples/sec: 11716.67 - lr: 0.100000
2023-04-05 11:42:36,939 epoch 44 - iter 56/280 - loss 0.02878473 - time (sec): 3.61 - samples/sec: 11672.15 - lr: 0.100000
2023-04-05 11:42:38,779 epoch 44 - iter 84/280 - loss 0.02950205 - time (sec): 5.45 - samples/sec: 11656.66 - lr: 0.100000
2023-04-05 11:42:40,600 epoch 44 - iter 112/280 - loss 0.02907250 - time (sec): 7.27 - samples/sec: 11638.75 - lr: 0.100000
2023-04-05 11:42:42,391 epoch 44 - iter 140/280 - loss 0.02904973 - time (sec): 9.06 - samples/sec: 11665.38 - lr: 0.100000
2023-04-05 11:42:44,256 epoch 44 - iter 168/280 - loss 0.02978426 - time (sec): 10.92 - samples/sec: 11662.02 - lr: 0.100000
2023-04-05 11:42:46,011 epoch 44 - iter 196/280 - loss 0.02983154 - time (sec): 12.68 - samples/sec: 11701.67 - lr: 0.100000
2023-04-05 11:42:47,816 epoch 44 - iter 224/280 - loss 0.03043928 - time (sec): 14.48 - samples/sec: 11703.66 - lr: 0.100000
2023-04-05 11:42:49,641 epoch 44 - iter 252/280 - loss 0.03049655 - time (sec): 16.31 - samples/sec: 11698.92 - lr: 0.100000
2023-04-05 11:42:51,431 epoch 44 - iter 280/280 - loss 0.03030984 - time (sec): 18.10 - samples/sec: 11695.89 - lr: 0.100000
2023-04-05 11:42:51,431 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:51,432 EPOCH 44 done: loss 0.0303 - lr 0.100000
2023-04-05 11:42:51,432 BAD EPOCHS (no improvement): 0
2023-04-05 11:42:51,434 ----------------------------------------------------------------------------------------------------
2023-04-05 11:42:53,275 epoch 45 - iter 28/280 - loss 0.02896127 - time (sec): 1.84 - samples/sec: 11898.32 - lr: 0.100000
2023-04-05 11:42:55,161 epoch 45 - iter 56/280 - loss 0.02902596 - time (sec): 3.73 - samples/sec: 11596.78 - lr: 0.100000
2023-04-05 11:42:56,942 epoch 45 - iter 84/280 - loss 0.02973355 - time (sec): 5.51 - samples/sec: 11640.30 - lr: 0.100000
2023-04-05 11:42:58,729 epoch 45 - iter 112/280 - loss 0.02931551 - time (sec): 7.29 - samples/sec: 11705.45 - lr: 0.100000
2023-04-05 11:43:00,578 epoch 45 - iter 140/280 - loss 0.03045931 - time (sec): 9.14 - samples/sec: 11720.89 - lr: 0.100000
2023-04-05 11:43:02,399 epoch 45 - iter 168/280 - loss 0.03026622 - time (sec): 10.97 - samples/sec: 11685.01 - lr: 0.100000
2023-04-05 11:43:04,158 epoch 45 - iter 196/280 - loss 0.03005424 - time (sec): 12.72 - samples/sec: 11725.25 - lr: 0.100000
2023-04-05 11:43:05,933 epoch 45 - iter 224/280 - loss 0.03001498 - time (sec): 14.50 - samples/sec: 11770.86 - lr: 0.100000
2023-04-05 11:43:07,644 epoch 45 - iter 252/280 - loss 0.02994644 - time (sec): 16.21 - samples/sec: 11781.67 - lr: 0.100000
2023-04-05 11:43:09,397 epoch 45 - iter 280/280 - loss 0.02986544 - time (sec): 17.96 - samples/sec: 11784.63 - lr: 0.100000
2023-04-05 11:43:09,398 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:09,398 EPOCH 45 done: loss 0.0299 - lr 0.100000
2023-04-05 11:43:09,398 BAD EPOCHS (no improvement): 0
2023-04-05 11:43:09,400 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:11,291 epoch 46 - iter 28/280 - loss 0.02874955 - time (sec): 1.89 - samples/sec: 11491.82 - lr: 0.100000
2023-04-05 11:43:13,112 epoch 46 - iter 56/280 - loss 0.02883285 - time (sec): 3.71 - samples/sec: 11573.99 - lr: 0.100000
2023-04-05 11:43:14,889 epoch 46 - iter 84/280 - loss 0.02929241 - time (sec): 5.49 - samples/sec: 11626.20 - lr: 0.100000
2023-04-05 11:43:16,703 epoch 46 - iter 112/280 - loss 0.02970739 - time (sec): 7.30 - samples/sec: 11651.95 - lr: 0.100000
2023-04-05 11:43:18,501 epoch 46 - iter 140/280 - loss 0.02881331 - time (sec): 9.10 - samples/sec: 11665.65 - lr: 0.100000
2023-04-05 11:43:20,282 epoch 46 - iter 168/280 - loss 0.02958618 - time (sec): 10.88 - samples/sec: 11699.47 - lr: 0.100000
2023-04-05 11:43:22,112 epoch 46 - iter 196/280 - loss 0.02936984 - time (sec): 12.71 - samples/sec: 11691.44 - lr: 0.100000
2023-04-05 11:43:23,921 epoch 46 - iter 224/280 - loss 0.02939788 - time (sec): 14.52 - samples/sec: 11705.87 - lr: 0.100000
2023-04-05 11:43:25,754 epoch 46 - iter 252/280 - loss 0.02939409 - time (sec): 16.35 - samples/sec: 11682.39 - lr: 0.100000
2023-04-05 11:43:27,518 epoch 46 - iter 280/280 - loss 0.02941412 - time (sec): 18.12 - samples/sec: 11684.41 - lr: 0.100000
2023-04-05 11:43:27,518 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:27,518 EPOCH 46 done: loss 0.0294 - lr 0.100000
2023-04-05 11:43:27,518 BAD EPOCHS (no improvement): 0
2023-04-05 11:43:27,521 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:29,321 epoch 47 - iter 28/280 - loss 0.02794756 - time (sec): 1.80 - samples/sec: 11780.73 - lr: 0.100000
2023-04-05 11:43:31,155 epoch 47 - iter 56/280 - loss 0.02907753 - time (sec): 3.63 - samples/sec: 11718.88 - lr: 0.100000
2023-04-05 11:43:33,025 epoch 47 - iter 84/280 - loss 0.02881838 - time (sec): 5.50 - samples/sec: 11461.42 - lr: 0.100000
2023-04-05 11:43:34,830 epoch 47 - iter 112/280 - loss 0.02858291 - time (sec): 7.31 - samples/sec: 11603.37 - lr: 0.100000
2023-04-05 11:43:36,635 epoch 47 - iter 140/280 - loss 0.02878100 - time (sec): 9.11 - samples/sec: 11688.91 - lr: 0.100000
2023-04-05 11:43:38,427 epoch 47 - iter 168/280 - loss 0.02846553 - time (sec): 10.91 - samples/sec: 11715.47 - lr: 0.100000
2023-04-05 11:43:40,221 epoch 47 - iter 196/280 - loss 0.02847962 - time (sec): 12.70 - samples/sec: 11734.04 - lr: 0.100000
2023-04-05 11:43:41,985 epoch 47 - iter 224/280 - loss 0.02853331 - time (sec): 14.46 - samples/sec: 11756.76 - lr: 0.100000
2023-04-05 11:43:43,730 epoch 47 - iter 252/280 - loss 0.02860707 - time (sec): 16.21 - samples/sec: 11815.10 - lr: 0.100000
2023-04-05 11:43:45,482 epoch 47 - iter 280/280 - loss 0.02920642 - time (sec): 17.96 - samples/sec: 11786.24 - lr: 0.100000
2023-04-05 11:43:45,482 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:45,482 EPOCH 47 done: loss 0.0292 - lr 0.100000
2023-04-05 11:43:45,482 BAD EPOCHS (no improvement): 0
2023-04-05 11:43:45,485 ----------------------------------------------------------------------------------------------------
2023-04-05 11:43:47,276 epoch 48 - iter 28/280 - loss 0.02428445 - time (sec): 1.79 - samples/sec: 11705.37 - lr: 0.100000
2023-04-05 11:43:49,137 epoch 48 - iter 56/280 - loss 0.02632186 - time (sec): 3.65 - samples/sec: 11564.76 - lr: 0.100000
2023-04-05 11:43:50,948 epoch 48 - iter 84/280 - loss 0.02574135 - time (sec): 5.46 - samples/sec: 11634.40 - lr: 0.100000
2023-04-05 11:43:52,707 epoch 48 - iter 112/280 - loss 0.02590516 - time (sec): 7.22 - samples/sec: 11685.99 - lr: 0.100000
2023-04-05 11:43:54,499 epoch 48 - iter 140/280 - loss 0.02668638 - time (sec): 9.01 - samples/sec: 11716.51 - lr: 0.100000
2023-04-05 11:43:56,347 epoch 48 - iter 168/280 - loss 0.02697613 - time (sec): 10.86 - samples/sec: 11713.05 - lr: 0.100000
2023-04-05 11:43:58,115 epoch 48 - iter 196/280 - loss 0.02711778 - time (sec): 12.63 - samples/sec: 11751.00 - lr: 0.100000
2023-04-05 11:43:59,977 epoch 48 - iter 224/280 - loss 0.02735087 - time (sec): 14.49 - samples/sec: 11699.28 - lr: 0.100000
2023-04-05 11:44:01,733 epoch 48 - iter 252/280 - loss 0.02799781 - time (sec): 16.25 - samples/sec: 11733.54 - lr: 0.100000
2023-04-05 11:44:03,495 epoch 48 - iter 280/280 - loss 0.02796271 - time (sec): 18.01 - samples/sec: 11754.51 - lr: 0.100000
2023-04-05 11:44:03,495 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:03,495 EPOCH 48 done: loss 0.0280 - lr 0.100000
2023-04-05 11:44:03,495 BAD EPOCHS (no improvement): 0
2023-04-05 11:44:03,497 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:05,307 epoch 49 - iter 28/280 - loss 0.02556972 - time (sec): 1.81 - samples/sec: 11696.44 - lr: 0.100000
2023-04-05 11:44:07,160 epoch 49 - iter 56/280 - loss 0.02542350 - time (sec): 3.66 - samples/sec: 11647.07 - lr: 0.100000
2023-04-05 11:44:08,938 epoch 49 - iter 84/280 - loss 0.02693832 - time (sec): 5.44 - samples/sec: 11787.37 - lr: 0.100000
2023-04-05 11:44:10,729 epoch 49 - iter 112/280 - loss 0.02745584 - time (sec): 7.23 - samples/sec: 11809.17 - lr: 0.100000
2023-04-05 11:44:12,493 epoch 49 - iter 140/280 - loss 0.02753203 - time (sec): 9.00 - samples/sec: 11843.58 - lr: 0.100000
2023-04-05 11:44:14,318 epoch 49 - iter 168/280 - loss 0.02702621 - time (sec): 10.82 - samples/sec: 11847.97 - lr: 0.100000
2023-04-05 11:44:16,019 epoch 49 - iter 196/280 - loss 0.02737883 - time (sec): 12.52 - samples/sec: 11913.15 - lr: 0.100000
2023-04-05 11:44:17,771 epoch 49 - iter 224/280 - loss 0.02754981 - time (sec): 14.27 - samples/sec: 11941.14 - lr: 0.100000
2023-04-05 11:44:19,586 epoch 49 - iter 252/280 - loss 0.02795361 - time (sec): 16.09 - samples/sec: 11908.24 - lr: 0.100000
2023-04-05 11:44:21,302 epoch 49 - iter 280/280 - loss 0.02805351 - time (sec): 17.80 - samples/sec: 11889.42 - lr: 0.100000
2023-04-05 11:44:21,302 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:21,302 EPOCH 49 done: loss 0.0281 - lr 0.100000
2023-04-05 11:44:21,302 BAD EPOCHS (no improvement): 1
2023-04-05 11:44:21,305 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:23,116 epoch 50 - iter 28/280 - loss 0.02906077 - time (sec): 1.81 - samples/sec: 11457.17 - lr: 0.100000
2023-04-05 11:44:24,901 epoch 50 - iter 56/280 - loss 0.02667004 - time (sec): 3.60 - samples/sec: 11595.45 - lr: 0.100000
2023-04-05 11:44:26,681 epoch 50 - iter 84/280 - loss 0.02672700 - time (sec): 5.38 - samples/sec: 11681.60 - lr: 0.100000
2023-04-05 11:44:28,525 epoch 50 - iter 112/280 - loss 0.02685015 - time (sec): 7.22 - samples/sec: 11743.79 - lr: 0.100000
2023-04-05 11:44:30,355 epoch 50 - iter 140/280 - loss 0.02701378 - time (sec): 9.05 - samples/sec: 11751.69 - lr: 0.100000
2023-04-05 11:44:32,167 epoch 50 - iter 168/280 - loss 0.02729387 - time (sec): 10.86 - samples/sec: 11773.73 - lr: 0.100000
2023-04-05 11:44:33,953 epoch 50 - iter 196/280 - loss 0.02713707 - time (sec): 12.65 - samples/sec: 11779.39 - lr: 0.100000
2023-04-05 11:44:35,753 epoch 50 - iter 224/280 - loss 0.02736079 - time (sec): 14.45 - samples/sec: 11786.89 - lr: 0.100000
2023-04-05 11:44:37,586 epoch 50 - iter 252/280 - loss 0.02710110 - time (sec): 16.28 - samples/sec: 11751.41 - lr: 0.100000
2023-04-05 11:44:39,318 epoch 50 - iter 280/280 - loss 0.02771860 - time (sec): 18.01 - samples/sec: 11752.23 - lr: 0.100000
2023-04-05 11:44:39,318 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:39,318 EPOCH 50 done: loss 0.0277 - lr 0.100000
2023-04-05 11:44:39,319 BAD EPOCHS (no improvement): 0
2023-04-05 11:44:39,321 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:41,100 epoch 51 - iter 28/280 - loss 0.02350058 - time (sec): 1.78 - samples/sec: 11836.78 - lr: 0.100000
2023-04-05 11:44:42,911 epoch 51 - iter 56/280 - loss 0.02420945 - time (sec): 3.59 - samples/sec: 11847.84 - lr: 0.100000
2023-04-05 11:44:44,712 epoch 51 - iter 84/280 - loss 0.02473076 - time (sec): 5.39 - samples/sec: 11801.65 - lr: 0.100000
2023-04-05 11:44:46,501 epoch 51 - iter 112/280 - loss 0.02477368 - time (sec): 7.18 - samples/sec: 11840.18 - lr: 0.100000
2023-04-05 11:44:48,289 epoch 51 - iter 140/280 - loss 0.02580652 - time (sec): 8.97 - samples/sec: 11823.40 - lr: 0.100000
2023-04-05 11:44:50,050 epoch 51 - iter 168/280 - loss 0.02607423 - time (sec): 10.73 - samples/sec: 11835.60 - lr: 0.100000
2023-04-05 11:44:51,832 epoch 51 - iter 196/280 - loss 0.02660144 - time (sec): 12.51 - samples/sec: 11847.44 - lr: 0.100000
2023-04-05 11:44:53,652 epoch 51 - iter 224/280 - loss 0.02666990 - time (sec): 14.33 - samples/sec: 11825.20 - lr: 0.100000
2023-04-05 11:44:55,433 epoch 51 - iter 252/280 - loss 0.02671405 - time (sec): 16.11 - samples/sec: 11824.06 - lr: 0.100000
2023-04-05 11:44:57,228 epoch 51 - iter 280/280 - loss 0.02692566 - time (sec): 17.91 - samples/sec: 11822.23 - lr: 0.100000
2023-04-05 11:44:57,228 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:57,228 EPOCH 51 done: loss 0.0269 - lr 0.100000
2023-04-05 11:44:57,228 BAD EPOCHS (no improvement): 0
2023-04-05 11:44:57,231 ----------------------------------------------------------------------------------------------------
2023-04-05 11:44:58,996 epoch 52 - iter 28/280 - loss 0.02849583 - time (sec): 1.76 - samples/sec: 11766.61 - lr: 0.100000
2023-04-05 11:45:00,784 epoch 52 - iter 56/280 - loss 0.02784938 - time (sec): 3.55 - samples/sec: 11788.74 - lr: 0.100000
2023-04-05 11:45:02,638 epoch 52 - iter 84/280 - loss 0.02732094 - time (sec): 5.41 - samples/sec: 11696.04 - lr: 0.100000
2023-04-05 11:45:04,469 epoch 52 - iter 112/280 - loss 0.02625954 - time (sec): 7.24 - samples/sec: 11662.46 - lr: 0.100000
2023-04-05 11:45:06,286 epoch 52 - iter 140/280 - loss 0.02580923 - time (sec): 9.05 - samples/sec: 11690.99 - lr: 0.100000
2023-04-05 11:45:08,164 epoch 52 - iter 168/280 - loss 0.02643554 - time (sec): 10.93 - samples/sec: 11661.45 - lr: 0.100000
2023-04-05 11:45:09,946 epoch 52 - iter 196/280 - loss 0.02655338 - time (sec): 12.71 - samples/sec: 11705.51 - lr: 0.100000
2023-04-05 11:45:11,736 epoch 52 - iter 224/280 - loss 0.02671910 - time (sec): 14.50 - samples/sec: 11701.04 - lr: 0.100000
2023-04-05 11:45:13,568 epoch 52 - iter 252/280 - loss 0.02708245 - time (sec): 16.34 - samples/sec: 11711.16 - lr: 0.100000
2023-04-05 11:45:15,331 epoch 52 - iter 280/280 - loss 0.02728734 - time (sec): 18.10 - samples/sec: 11695.78 - lr: 0.100000
2023-04-05 11:45:15,331 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:15,331 EPOCH 52 done: loss 0.0273 - lr 0.100000
2023-04-05 11:45:15,331 BAD EPOCHS (no improvement): 1
2023-04-05 11:45:15,334 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:17,140 epoch 53 - iter 28/280 - loss 0.02533256 - time (sec): 1.81 - samples/sec: 11696.33 - lr: 0.100000
2023-04-05 11:45:18,940 epoch 53 - iter 56/280 - loss 0.02437152 - time (sec): 3.61 - samples/sec: 11666.63 - lr: 0.100000
2023-04-05 11:45:20,732 epoch 53 - iter 84/280 - loss 0.02387980 - time (sec): 5.40 - samples/sec: 11715.45 - lr: 0.100000
2023-04-05 11:45:22,516 epoch 53 - iter 112/280 - loss 0.02437736 - time (sec): 7.18 - samples/sec: 11772.71 - lr: 0.100000
2023-04-05 11:45:24,282 epoch 53 - iter 140/280 - loss 0.02439935 - time (sec): 8.95 - samples/sec: 11771.17 - lr: 0.100000
2023-04-05 11:45:26,074 epoch 53 - iter 168/280 - loss 0.02496549 - time (sec): 10.74 - samples/sec: 11765.96 - lr: 0.100000
2023-04-05 11:45:27,824 epoch 53 - iter 196/280 - loss 0.02508578 - time (sec): 12.49 - samples/sec: 11795.54 - lr: 0.100000
2023-04-05 11:45:29,690 epoch 53 - iter 224/280 - loss 0.02524693 - time (sec): 14.36 - samples/sec: 11784.35 - lr: 0.100000
2023-04-05 11:45:31,467 epoch 53 - iter 252/280 - loss 0.02574224 - time (sec): 16.13 - samples/sec: 11825.58 - lr: 0.100000
2023-04-05 11:45:33,264 epoch 53 - iter 280/280 - loss 0.02595837 - time (sec): 17.93 - samples/sec: 11806.11 - lr: 0.100000
2023-04-05 11:45:33,265 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:33,265 EPOCH 53 done: loss 0.0260 - lr 0.100000
2023-04-05 11:45:33,265 BAD EPOCHS (no improvement): 0
2023-04-05 11:45:33,268 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:35,085 epoch 54 - iter 28/280 - loss 0.02266209 - time (sec): 1.82 - samples/sec: 11721.92 - lr: 0.100000
2023-04-05 11:45:36,812 epoch 54 - iter 56/280 - loss 0.02346853 - time (sec): 3.54 - samples/sec: 11871.18 - lr: 0.100000
2023-04-05 11:45:38,626 epoch 54 - iter 84/280 - loss 0.02445412 - time (sec): 5.36 - samples/sec: 11761.12 - lr: 0.100000
2023-04-05 11:45:40,394 epoch 54 - iter 112/280 - loss 0.02538483 - time (sec): 7.13 - samples/sec: 11784.64 - lr: 0.100000
2023-04-05 11:45:42,274 epoch 54 - iter 140/280 - loss 0.02514364 - time (sec): 9.01 - samples/sec: 11730.59 - lr: 0.100000
2023-04-05 11:45:44,060 epoch 54 - iter 168/280 - loss 0.02503993 - time (sec): 10.79 - samples/sec: 11702.27 - lr: 0.100000
2023-04-05 11:45:45,875 epoch 54 - iter 196/280 - loss 0.02473764 - time (sec): 12.61 - samples/sec: 11727.31 - lr: 0.100000
2023-04-05 11:45:47,709 epoch 54 - iter 224/280 - loss 0.02487582 - time (sec): 14.44 - samples/sec: 11723.03 - lr: 0.100000
2023-04-05 11:45:49,561 epoch 54 - iter 252/280 - loss 0.02518813 - time (sec): 16.29 - samples/sec: 11727.97 - lr: 0.100000
2023-04-05 11:45:51,312 epoch 54 - iter 280/280 - loss 0.02523044 - time (sec): 18.04 - samples/sec: 11732.04 - lr: 0.100000
2023-04-05 11:45:51,312 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:51,312 EPOCH 54 done: loss 0.0252 - lr 0.100000
2023-04-05 11:45:51,312 BAD EPOCHS (no improvement): 0
2023-04-05 11:45:51,315 ----------------------------------------------------------------------------------------------------
2023-04-05 11:45:53,095 epoch 55 - iter 28/280 - loss 0.02419197 - time (sec): 1.78 - samples/sec: 11657.83 - lr: 0.100000
2023-04-05 11:45:54,895 epoch 55 - iter 56/280 - loss 0.02390033 - time (sec): 3.58 - samples/sec: 11763.92 - lr: 0.100000
2023-04-05 11:45:56,670 epoch 55 - iter 84/280 - loss 0.02326678 - time (sec): 5.36 - samples/sec: 11838.22 - lr: 0.100000
2023-04-05 11:45:58,516 epoch 55 - iter 112/280 - loss 0.02357985 - time (sec): 7.20 - samples/sec: 11771.52 - lr: 0.100000
2023-04-05 11:46:00,367 epoch 55 - iter 140/280 - loss 0.02334431 - time (sec): 9.05 - samples/sec: 11676.62 - lr: 0.100000
2023-04-05 11:46:02,209 epoch 55 - iter 168/280 - loss 0.02453248 - time (sec): 10.89 - samples/sec: 11700.92 - lr: 0.100000
2023-04-05 11:46:04,035 epoch 55 - iter 196/280 - loss 0.02460046 - time (sec): 12.72 - samples/sec: 11711.65 - lr: 0.100000
2023-04-05 11:46:05,822 epoch 55 - iter 224/280 - loss 0.02451103 - time (sec): 14.51 - samples/sec: 11745.80 - lr: 0.100000
2023-04-05 11:46:07,569 epoch 55 - iter 252/280 - loss 0.02475261 - time (sec): 16.25 - samples/sec: 11739.64 - lr: 0.100000
2023-04-05 11:46:09,275 epoch 55 - iter 280/280 - loss 0.02505652 - time (sec): 17.96 - samples/sec: 11786.38 - lr: 0.100000
2023-04-05 11:46:09,276 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:09,276 EPOCH 55 done: loss 0.0251 - lr 0.100000
2023-04-05 11:46:09,276 BAD EPOCHS (no improvement): 0
2023-04-05 11:46:09,279 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:11,121 epoch 56 - iter 28/280 - loss 0.02534903 - time (sec): 1.84 - samples/sec: 11537.50 - lr: 0.100000
2023-04-05 11:46:12,952 epoch 56 - iter 56/280 - loss 0.02312786 - time (sec): 3.67 - samples/sec: 11590.10 - lr: 0.100000
2023-04-05 11:46:14,764 epoch 56 - iter 84/280 - loss 0.02350779 - time (sec): 5.49 - samples/sec: 11640.24 - lr: 0.100000
2023-04-05 11:46:16,592 epoch 56 - iter 112/280 - loss 0.02437309 - time (sec): 7.31 - samples/sec: 11651.13 - lr: 0.100000
2023-04-05 11:46:18,433 epoch 56 - iter 140/280 - loss 0.02497722 - time (sec): 9.15 - samples/sec: 11666.28 - lr: 0.100000
2023-04-05 11:46:20,224 epoch 56 - iter 168/280 - loss 0.02502714 - time (sec): 10.95 - samples/sec: 11688.51 - lr: 0.100000
2023-04-05 11:46:21,994 epoch 56 - iter 196/280 - loss 0.02447913 - time (sec): 12.72 - samples/sec: 11736.33 - lr: 0.100000
2023-04-05 11:46:23,758 epoch 56 - iter 224/280 - loss 0.02436970 - time (sec): 14.48 - samples/sec: 11753.58 - lr: 0.100000
2023-04-05 11:46:25,625 epoch 56 - iter 252/280 - loss 0.02461723 - time (sec): 16.35 - samples/sec: 11720.79 - lr: 0.100000
2023-04-05 11:46:27,343 epoch 56 - iter 280/280 - loss 0.02473187 - time (sec): 18.06 - samples/sec: 11718.65 - lr: 0.100000
2023-04-05 11:46:27,344 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:27,344 EPOCH 56 done: loss 0.0247 - lr 0.100000
2023-04-05 11:46:27,344 BAD EPOCHS (no improvement): 0
2023-04-05 11:46:27,347 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:29,165 epoch 57 - iter 28/280 - loss 0.02300805 - time (sec): 1.82 - samples/sec: 11918.47 - lr: 0.100000
2023-04-05 11:46:31,071 epoch 57 - iter 56/280 - loss 0.02443349 - time (sec): 3.72 - samples/sec: 11661.30 - lr: 0.100000
2023-04-05 11:46:32,831 epoch 57 - iter 84/280 - loss 0.02385236 - time (sec): 5.48 - samples/sec: 11774.37 - lr: 0.100000
2023-04-05 11:46:34,559 epoch 57 - iter 112/280 - loss 0.02480441 - time (sec): 7.21 - samples/sec: 11857.70 - lr: 0.100000
2023-04-05 11:46:36,389 epoch 57 - iter 140/280 - loss 0.02529544 - time (sec): 9.04 - samples/sec: 11836.25 - lr: 0.100000
2023-04-05 11:46:38,158 epoch 57 - iter 168/280 - loss 0.02547511 - time (sec): 10.81 - samples/sec: 11830.68 - lr: 0.100000
2023-04-05 11:46:39,909 epoch 57 - iter 196/280 - loss 0.02566177 - time (sec): 12.56 - samples/sec: 11838.22 - lr: 0.100000
2023-04-05 11:46:41,767 epoch 57 - iter 224/280 - loss 0.02583997 - time (sec): 14.42 - samples/sec: 11801.28 - lr: 0.100000
2023-04-05 11:46:43,555 epoch 57 - iter 252/280 - loss 0.02549325 - time (sec): 16.21 - samples/sec: 11813.12 - lr: 0.100000
2023-04-05 11:46:45,288 epoch 57 - iter 280/280 - loss 0.02543841 - time (sec): 17.94 - samples/sec: 11799.28 - lr: 0.100000
2023-04-05 11:46:45,288 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:45,288 EPOCH 57 done: loss 0.0254 - lr 0.100000
2023-04-05 11:46:45,288 BAD EPOCHS (no improvement): 1
2023-04-05 11:46:45,291 ----------------------------------------------------------------------------------------------------
2023-04-05 11:46:47,028 epoch 58 - iter 28/280 - loss 0.02102086 - time (sec): 1.74 - samples/sec: 11827.35 - lr: 0.100000
2023-04-05 11:46:48,858 epoch 58 - iter 56/280 - loss 0.02181777 - time (sec): 3.57 - samples/sec: 11693.47 - lr: 0.100000
2023-04-05 11:46:50,653 epoch 58 - iter 84/280 - loss 0.02283550 - time (sec): 5.36 - samples/sec: 11811.40 - lr: 0.100000
2023-04-05 11:46:52,438 epoch 58 - iter 112/280 - loss 0.02324083 - time (sec): 7.15 - samples/sec: 11844.21 - lr: 0.100000
2023-04-05 11:46:54,211 epoch 58 - iter 140/280 - loss 0.02409030 - time (sec): 8.92 - samples/sec: 11815.01 - lr: 0.100000
2023-04-05 11:46:56,021 epoch 58 - iter 168/280 - loss 0.02362296 - time (sec): 10.73 - samples/sec: 11840.57 - lr: 0.100000
2023-04-05 11:46:57,852 epoch 58 - iter 196/280 - loss 0.02361396 - time (sec): 12.56 - samples/sec: 11828.75 - lr: 0.100000
2023-04-05 11:46:59,698 epoch 58 - iter 224/280 - loss 0.02422569 - time (sec): 14.41 - samples/sec: 11797.26 - lr: 0.100000
2023-04-05 11:47:02,950 epoch 58 - iter 252/280 - loss 0.02416822 - time (sec): 17.66 - samples/sec: 10835.21 - lr: 0.100000
2023-04-05 11:47:04,731 epoch 58 - iter 280/280 - loss 0.02446460 - time (sec): 19.44 - samples/sec: 10889.42 - lr: 0.100000
2023-04-05 11:47:04,732 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:04,732 EPOCH 58 done: loss 0.0245 - lr 0.100000
2023-04-05 11:47:04,732 BAD EPOCHS (no improvement): 0
2023-04-05 11:47:04,735 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:06,541 epoch 59 - iter 28/280 - loss 0.02619119 - time (sec): 1.81 - samples/sec: 11788.65 - lr: 0.100000
2023-04-05 11:47:08,361 epoch 59 - iter 56/280 - loss 0.02429308 - time (sec): 3.63 - samples/sec: 11778.78 - lr: 0.100000
2023-04-05 11:47:10,134 epoch 59 - iter 84/280 - loss 0.02429658 - time (sec): 5.40 - samples/sec: 11799.85 - lr: 0.100000
2023-04-05 11:47:11,948 epoch 59 - iter 112/280 - loss 0.02515254 - time (sec): 7.21 - samples/sec: 11789.29 - lr: 0.100000
2023-04-05 11:47:13,769 epoch 59 - iter 140/280 - loss 0.02469885 - time (sec): 9.03 - samples/sec: 11820.21 - lr: 0.100000
2023-04-05 11:47:15,523 epoch 59 - iter 168/280 - loss 0.02447338 - time (sec): 10.79 - samples/sec: 11844.87 - lr: 0.100000
2023-04-05 11:47:17,345 epoch 59 - iter 196/280 - loss 0.02495776 - time (sec): 12.61 - samples/sec: 11833.71 - lr: 0.100000
2023-04-05 11:47:19,102 epoch 59 - iter 224/280 - loss 0.02497418 - time (sec): 14.37 - samples/sec: 11858.57 - lr: 0.100000
2023-04-05 11:47:20,829 epoch 59 - iter 252/280 - loss 0.02465591 - time (sec): 16.09 - samples/sec: 11861.35 - lr: 0.100000
2023-04-05 11:47:22,581 epoch 59 - iter 280/280 - loss 0.02507243 - time (sec): 17.85 - samples/sec: 11862.29 - lr: 0.100000
2023-04-05 11:47:22,581 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:22,581 EPOCH 59 done: loss 0.0251 - lr 0.100000
2023-04-05 11:47:22,581 BAD EPOCHS (no improvement): 1
2023-04-05 11:47:22,584 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:24,360 epoch 60 - iter 28/280 - loss 0.02113266 - time (sec): 1.78 - samples/sec: 11928.35 - lr: 0.100000
2023-04-05 11:47:26,155 epoch 60 - iter 56/280 - loss 0.02145107 - time (sec): 3.57 - samples/sec: 11872.75 - lr: 0.100000
2023-04-05 11:47:27,970 epoch 60 - iter 84/280 - loss 0.02205379 - time (sec): 5.39 - samples/sec: 11874.60 - lr: 0.100000
2023-04-05 11:47:29,755 epoch 60 - iter 112/280 - loss 0.02269022 - time (sec): 7.17 - samples/sec: 11861.87 - lr: 0.100000
2023-04-05 11:47:31,594 epoch 60 - iter 140/280 - loss 0.02282305 - time (sec): 9.01 - samples/sec: 11818.68 - lr: 0.100000
2023-04-05 11:47:33,486 epoch 60 - iter 168/280 - loss 0.02345920 - time (sec): 10.90 - samples/sec: 11731.73 - lr: 0.100000
2023-04-05 11:47:35,307 epoch 60 - iter 196/280 - loss 0.02317190 - time (sec): 12.72 - samples/sec: 11729.85 - lr: 0.100000
2023-04-05 11:47:37,088 epoch 60 - iter 224/280 - loss 0.02340442 - time (sec): 14.50 - samples/sec: 11718.86 - lr: 0.100000
2023-04-05 11:47:38,884 epoch 60 - iter 252/280 - loss 0.02340842 - time (sec): 16.30 - samples/sec: 11717.21 - lr: 0.100000
2023-04-05 11:47:40,667 epoch 60 - iter 280/280 - loss 0.02382782 - time (sec): 18.08 - samples/sec: 11706.96 - lr: 0.100000
2023-04-05 11:47:40,667 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:40,667 EPOCH 60 done: loss 0.0238 - lr 0.100000
2023-04-05 11:47:40,667 BAD EPOCHS (no improvement): 0
2023-04-05 11:47:40,670 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:42,508 epoch 61 - iter 28/280 - loss 0.02188785 - time (sec): 1.84 - samples/sec: 11782.04 - lr: 0.100000
2023-04-05 11:47:44,271 epoch 61 - iter 56/280 - loss 0.02242564 - time (sec): 3.60 - samples/sec: 11821.43 - lr: 0.100000
2023-04-05 11:47:46,085 epoch 61 - iter 84/280 - loss 0.02297340 - time (sec): 5.42 - samples/sec: 11778.55 - lr: 0.100000
2023-04-05 11:47:47,880 epoch 61 - iter 112/280 - loss 0.02249226 - time (sec): 7.21 - samples/sec: 11752.88 - lr: 0.100000
2023-04-05 11:47:49,655 epoch 61 - iter 140/280 - loss 0.02255858 - time (sec): 8.99 - samples/sec: 11727.47 - lr: 0.100000
2023-04-05 11:47:51,450 epoch 61 - iter 168/280 - loss 0.02330611 - time (sec): 10.78 - samples/sec: 11754.71 - lr: 0.100000
2023-04-05 11:47:53,257 epoch 61 - iter 196/280 - loss 0.02347869 - time (sec): 12.59 - samples/sec: 11767.26 - lr: 0.100000
2023-04-05 11:47:55,094 epoch 61 - iter 224/280 - loss 0.02357455 - time (sec): 14.42 - samples/sec: 11756.03 - lr: 0.100000
2023-04-05 11:47:56,896 epoch 61 - iter 252/280 - loss 0.02331765 - time (sec): 16.23 - samples/sec: 11748.69 - lr: 0.100000
2023-04-05 11:47:58,695 epoch 61 - iter 280/280 - loss 0.02335792 - time (sec): 18.03 - samples/sec: 11744.17 - lr: 0.100000
2023-04-05 11:47:58,695 ----------------------------------------------------------------------------------------------------
2023-04-05 11:47:58,695 EPOCH 61 done: loss 0.0234 - lr 0.100000
2023-04-05 11:47:58,695 BAD EPOCHS (no improvement): 0
2023-04-05 11:47:58,697 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:00,512 epoch 62 - iter 28/280 - loss 0.02323850 - time (sec): 1.81 - samples/sec: 11839.29 - lr: 0.100000
2023-04-05 11:48:02,268 epoch 62 - iter 56/280 - loss 0.02418270 - time (sec): 3.57 - samples/sec: 11981.55 - lr: 0.100000
2023-04-05 11:48:04,073 epoch 62 - iter 84/280 - loss 0.02399754 - time (sec): 5.38 - samples/sec: 11947.92 - lr: 0.100000
2023-04-05 11:48:05,910 epoch 62 - iter 112/280 - loss 0.02400588 - time (sec): 7.21 - samples/sec: 11942.51 - lr: 0.100000
2023-04-05 11:48:07,710 epoch 62 - iter 140/280 - loss 0.02466488 - time (sec): 9.01 - samples/sec: 11944.01 - lr: 0.100000
2023-04-05 11:48:09,527 epoch 62 - iter 168/280 - loss 0.02430790 - time (sec): 10.83 - samples/sec: 11824.20 - lr: 0.100000
2023-04-05 11:48:11,352 epoch 62 - iter 196/280 - loss 0.02400981 - time (sec): 12.65 - samples/sec: 11798.90 - lr: 0.100000
2023-04-05 11:48:13,164 epoch 62 - iter 224/280 - loss 0.02408896 - time (sec): 14.47 - samples/sec: 11762.72 - lr: 0.100000
2023-04-05 11:48:14,952 epoch 62 - iter 252/280 - loss 0.02416502 - time (sec): 16.25 - samples/sec: 11760.69 - lr: 0.100000
2023-04-05 11:48:16,705 epoch 62 - iter 280/280 - loss 0.02405755 - time (sec): 18.01 - samples/sec: 11755.45 - lr: 0.100000
2023-04-05 11:48:16,706 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:16,706 EPOCH 62 done: loss 0.0241 - lr 0.100000
2023-04-05 11:48:16,706 BAD EPOCHS (no improvement): 1
2023-04-05 11:48:16,709 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:18,500 epoch 63 - iter 28/280 - loss 0.02399210 - time (sec): 1.79 - samples/sec: 11865.63 - lr: 0.100000
2023-04-05 11:48:20,351 epoch 63 - iter 56/280 - loss 0.02311333 - time (sec): 3.64 - samples/sec: 11764.21 - lr: 0.100000
2023-04-05 11:48:22,168 epoch 63 - iter 84/280 - loss 0.02283618 - time (sec): 5.46 - samples/sec: 11743.53 - lr: 0.100000
2023-04-05 11:48:23,951 epoch 63 - iter 112/280 - loss 0.02289443 - time (sec): 7.24 - samples/sec: 11781.37 - lr: 0.100000
2023-04-05 11:48:25,784 epoch 63 - iter 140/280 - loss 0.02282495 - time (sec): 9.07 - samples/sec: 11784.54 - lr: 0.100000
2023-04-05 11:48:27,502 epoch 63 - iter 168/280 - loss 0.02239201 - time (sec): 10.79 - samples/sec: 11828.14 - lr: 0.100000
2023-04-05 11:48:29,288 epoch 63 - iter 196/280 - loss 0.02290296 - time (sec): 12.58 - samples/sec: 11855.04 - lr: 0.100000
2023-04-05 11:48:31,061 epoch 63 - iter 224/280 - loss 0.02269834 - time (sec): 14.35 - samples/sec: 11836.38 - lr: 0.100000
2023-04-05 11:48:32,875 epoch 63 - iter 252/280 - loss 0.02259157 - time (sec): 16.17 - samples/sec: 11850.83 - lr: 0.100000
2023-04-05 11:48:34,629 epoch 63 - iter 280/280 - loss 0.02291769 - time (sec): 17.92 - samples/sec: 11813.53 - lr: 0.100000
2023-04-05 11:48:34,629 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:34,629 EPOCH 63 done: loss 0.0229 - lr 0.100000
2023-04-05 11:48:34,629 BAD EPOCHS (no improvement): 0
2023-04-05 11:48:34,632 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:36,416 epoch 64 - iter 28/280 - loss 0.02256941 - time (sec): 1.78 - samples/sec: 12046.75 - lr: 0.100000
2023-04-05 11:48:38,220 epoch 64 - iter 56/280 - loss 0.02283717 - time (sec): 3.59 - samples/sec: 12080.67 - lr: 0.100000
2023-04-05 11:48:40,072 epoch 64 - iter 84/280 - loss 0.02293735 - time (sec): 5.44 - samples/sec: 11894.21 - lr: 0.100000
2023-04-05 11:48:41,928 epoch 64 - iter 112/280 - loss 0.02269072 - time (sec): 7.30 - samples/sec: 11826.81 - lr: 0.100000
2023-04-05 11:48:43,696 epoch 64 - iter 140/280 - loss 0.02339030 - time (sec): 9.06 - samples/sec: 11859.71 - lr: 0.100000
2023-04-05 11:48:45,516 epoch 64 - iter 168/280 - loss 0.02326319 - time (sec): 10.88 - samples/sec: 11814.03 - lr: 0.100000
2023-04-05 11:48:47,310 epoch 64 - iter 196/280 - loss 0.02272604 - time (sec): 12.68 - samples/sec: 11823.75 - lr: 0.100000
2023-04-05 11:48:49,113 epoch 64 - iter 224/280 - loss 0.02247590 - time (sec): 14.48 - samples/sec: 11828.52 - lr: 0.100000
2023-04-05 11:48:50,940 epoch 64 - iter 252/280 - loss 0.02279041 - time (sec): 16.31 - samples/sec: 11758.11 - lr: 0.100000
2023-04-05 11:48:52,669 epoch 64 - iter 280/280 - loss 0.02302565 - time (sec): 18.04 - samples/sec: 11736.76 - lr: 0.100000
2023-04-05 11:48:52,669 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:52,669 EPOCH 64 done: loss 0.0230 - lr 0.100000
2023-04-05 11:48:52,669 BAD EPOCHS (no improvement): 1
2023-04-05 11:48:52,672 ----------------------------------------------------------------------------------------------------
2023-04-05 11:48:54,483 epoch 65 - iter 28/280 - loss 0.02109243 - time (sec): 1.81 - samples/sec: 11720.69 - lr: 0.100000
2023-04-05 11:48:56,278 epoch 65 - iter 56/280 - loss 0.02157008 - time (sec): 3.61 - samples/sec: 11860.30 - lr: 0.100000
2023-04-05 11:48:58,069 epoch 65 - iter 84/280 - loss 0.02115013 - time (sec): 5.40 - samples/sec: 11777.23 - lr: 0.100000
2023-04-05 11:48:59,872 epoch 65 - iter 112/280 - loss 0.02153102 - time (sec): 7.20 - samples/sec: 11748.63 - lr: 0.100000
2023-04-05 11:49:01,683 epoch 65 - iter 140/280 - loss 0.02208391 - time (sec): 9.01 - samples/sec: 11757.75 - lr: 0.100000
2023-04-05 11:49:03,468 epoch 65 - iter 168/280 - loss 0.02213290 - time (sec): 10.80 - samples/sec: 11766.42 - lr: 0.100000
2023-04-05 11:49:05,233 epoch 65 - iter 196/280 - loss 0.02250858 - time (sec): 12.56 - samples/sec: 11792.34 - lr: 0.100000
2023-04-05 11:49:07,029 epoch 65 - iter 224/280 - loss 0.02244799 - time (sec): 14.36 - samples/sec: 11810.18 - lr: 0.100000
2023-04-05 11:49:08,849 epoch 65 - iter 252/280 - loss 0.02239353 - time (sec): 16.18 - samples/sec: 11789.44 - lr: 0.100000
2023-04-05 11:49:10,597 epoch 65 - iter 280/280 - loss 0.02259849 - time (sec): 17.93 - samples/sec: 11809.53 - lr: 0.100000
2023-04-05 11:49:10,597 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:10,598 EPOCH 65 done: loss 0.0226 - lr 0.100000
2023-04-05 11:49:10,598 BAD EPOCHS (no improvement): 0
2023-04-05 11:49:10,600 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:12,439 epoch 66 - iter 28/280 - loss 0.02173673 - time (sec): 1.84 - samples/sec: 11630.28 - lr: 0.100000
2023-04-05 11:49:14,352 epoch 66 - iter 56/280 - loss 0.02164669 - time (sec): 3.75 - samples/sec: 11389.82 - lr: 0.100000
2023-04-05 11:49:16,177 epoch 66 - iter 84/280 - loss 0.02117474 - time (sec): 5.58 - samples/sec: 11438.32 - lr: 0.100000
2023-04-05 11:49:17,979 epoch 66 - iter 112/280 - loss 0.02168819 - time (sec): 7.38 - samples/sec: 11518.55 - lr: 0.100000
2023-04-05 11:49:19,865 epoch 66 - iter 140/280 - loss 0.02228495 - time (sec): 9.26 - samples/sec: 11500.09 - lr: 0.100000
2023-04-05 11:49:21,678 epoch 66 - iter 168/280 - loss 0.02238455 - time (sec): 11.08 - samples/sec: 11498.08 - lr: 0.100000
2023-04-05 11:49:23,544 epoch 66 - iter 196/280 - loss 0.02269903 - time (sec): 12.94 - samples/sec: 11468.78 - lr: 0.100000
2023-04-05 11:49:25,472 epoch 66 - iter 224/280 - loss 0.02294796 - time (sec): 14.87 - samples/sec: 11422.39 - lr: 0.100000
2023-04-05 11:49:27,332 epoch 66 - iter 252/280 - loss 0.02301732 - time (sec): 16.73 - samples/sec: 11429.27 - lr: 0.100000
2023-04-05 11:49:29,139 epoch 66 - iter 280/280 - loss 0.02321416 - time (sec): 18.54 - samples/sec: 11419.00 - lr: 0.100000
2023-04-05 11:49:29,139 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:29,139 EPOCH 66 done: loss 0.0232 - lr 0.100000
2023-04-05 11:49:29,139 BAD EPOCHS (no improvement): 1
2023-04-05 11:49:29,142 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:30,937 epoch 67 - iter 28/280 - loss 0.02118564 - time (sec): 1.80 - samples/sec: 11651.72 - lr: 0.100000
2023-04-05 11:49:32,738 epoch 67 - iter 56/280 - loss 0.02083372 - time (sec): 3.60 - samples/sec: 11722.32 - lr: 0.100000
2023-04-05 11:49:34,668 epoch 67 - iter 84/280 - loss 0.02069451 - time (sec): 5.53 - samples/sec: 11528.32 - lr: 0.100000
2023-04-05 11:49:36,428 epoch 67 - iter 112/280 - loss 0.02137567 - time (sec): 7.29 - samples/sec: 11648.89 - lr: 0.100000
2023-04-05 11:49:38,263 epoch 67 - iter 140/280 - loss 0.02156501 - time (sec): 9.12 - samples/sec: 11644.34 - lr: 0.100000
2023-04-05 11:49:40,047 epoch 67 - iter 168/280 - loss 0.02227597 - time (sec): 10.91 - samples/sec: 11691.65 - lr: 0.100000
2023-04-05 11:49:41,847 epoch 67 - iter 196/280 - loss 0.02273584 - time (sec): 12.71 - samples/sec: 11697.50 - lr: 0.100000
2023-04-05 11:49:43,742 epoch 67 - iter 224/280 - loss 0.02281440 - time (sec): 14.60 - samples/sec: 11656.97 - lr: 0.100000
2023-04-05 11:49:45,576 epoch 67 - iter 252/280 - loss 0.02269671 - time (sec): 16.43 - samples/sec: 11645.39 - lr: 0.100000
2023-04-05 11:49:47,322 epoch 67 - iter 280/280 - loss 0.02260637 - time (sec): 18.18 - samples/sec: 11644.08 - lr: 0.100000
2023-04-05 11:49:47,322 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:47,322 EPOCH 67 done: loss 0.0226 - lr 0.100000
2023-04-05 11:49:47,322 BAD EPOCHS (no improvement): 2
2023-04-05 11:49:47,325 ----------------------------------------------------------------------------------------------------
2023-04-05 11:49:49,145 epoch 68 - iter 28/280 - loss 0.01995264 - time (sec): 1.82 - samples/sec: 11760.90 - lr: 0.100000
2023-04-05 11:49:50,925 epoch 68 - iter 56/280 - loss 0.02301703 - time (sec): 3.60 - samples/sec: 11685.25 - lr: 0.100000
2023-04-05 11:49:52,853 epoch 68 - iter 84/280 - loss 0.02168046 - time (sec): 5.53 - samples/sec: 11463.48 - lr: 0.100000
2023-04-05 11:49:54,695 epoch 68 - iter 112/280 - loss 0.02146049 - time (sec): 7.37 - samples/sec: 11497.24 - lr: 0.100000
2023-04-05 11:49:56,551 epoch 68 - iter 140/280 - loss 0.02188571 - time (sec): 9.23 - samples/sec: 11465.11 - lr: 0.100000
2023-04-05 11:49:58,447 epoch 68 - iter 168/280 - loss 0.02185243 - time (sec): 11.12 - samples/sec: 11428.60 - lr: 0.100000
2023-04-05 11:50:00,327 epoch 68 - iter 196/280 - loss 0.02184818 - time (sec): 13.00 - samples/sec: 11393.16 - lr: 0.100000
2023-04-05 11:50:02,208 epoch 68 - iter 224/280 - loss 0.02168539 - time (sec): 14.88 - samples/sec: 11381.98 - lr: 0.100000
2023-04-05 11:50:04,163 epoch 68 - iter 252/280 - loss 0.02169250 - time (sec): 16.84 - samples/sec: 11354.46 - lr: 0.100000
2023-04-05 11:50:05,996 epoch 68 - iter 280/280 - loss 0.02202710 - time (sec): 18.67 - samples/sec: 11337.80 - lr: 0.100000
2023-04-05 11:50:05,996 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:05,996 EPOCH 68 done: loss 0.0220 - lr 0.100000
2023-04-05 11:50:05,997 BAD EPOCHS (no improvement): 0
2023-04-05 11:50:05,999 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:07,855 epoch 69 - iter 28/280 - loss 0.02384428 - time (sec): 1.86 - samples/sec: 11205.34 - lr: 0.100000
2023-04-05 11:50:09,712 epoch 69 - iter 56/280 - loss 0.02214349 - time (sec): 3.71 - samples/sec: 11346.57 - lr: 0.100000
2023-04-05 11:50:11,580 epoch 69 - iter 84/280 - loss 0.02205930 - time (sec): 5.58 - samples/sec: 11352.85 - lr: 0.100000
2023-04-05 11:50:13,515 epoch 69 - iter 112/280 - loss 0.02269737 - time (sec): 7.52 - samples/sec: 11288.43 - lr: 0.100000
2023-04-05 11:50:15,316 epoch 69 - iter 140/280 - loss 0.02233032 - time (sec): 9.32 - samples/sec: 11335.06 - lr: 0.100000
2023-04-05 11:50:17,095 epoch 69 - iter 168/280 - loss 0.02254028 - time (sec): 11.10 - samples/sec: 11378.08 - lr: 0.100000
2023-04-05 11:50:18,893 epoch 69 - iter 196/280 - loss 0.02286921 - time (sec): 12.89 - samples/sec: 11429.12 - lr: 0.100000
2023-04-05 11:50:20,697 epoch 69 - iter 224/280 - loss 0.02247976 - time (sec): 14.70 - samples/sec: 11499.50 - lr: 0.100000
2023-04-05 11:50:22,502 epoch 69 - iter 252/280 - loss 0.02243047 - time (sec): 16.50 - samples/sec: 11533.11 - lr: 0.100000
2023-04-05 11:50:24,306 epoch 69 - iter 280/280 - loss 0.02259251 - time (sec): 18.31 - samples/sec: 11563.56 - lr: 0.100000
2023-04-05 11:50:24,306 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:24,306 EPOCH 69 done: loss 0.0226 - lr 0.100000
2023-04-05 11:50:24,306 BAD EPOCHS (no improvement): 1
2023-04-05 11:50:24,309 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:26,128 epoch 70 - iter 28/280 - loss 0.02043274 - time (sec): 1.82 - samples/sec: 12043.46 - lr: 0.100000
2023-04-05 11:50:27,893 epoch 70 - iter 56/280 - loss 0.02185234 - time (sec): 3.58 - samples/sec: 12005.44 - lr: 0.100000
2023-04-05 11:50:29,701 epoch 70 - iter 84/280 - loss 0.02104883 - time (sec): 5.39 - samples/sec: 11916.91 - lr: 0.100000
2023-04-05 11:50:31,436 epoch 70 - iter 112/280 - loss 0.02097437 - time (sec): 7.13 - samples/sec: 11971.67 - lr: 0.100000
2023-04-05 11:50:33,238 epoch 70 - iter 140/280 - loss 0.02153211 - time (sec): 8.93 - samples/sec: 11930.38 - lr: 0.100000
2023-04-05 11:50:35,047 epoch 70 - iter 168/280 - loss 0.02199826 - time (sec): 10.74 - samples/sec: 11892.64 - lr: 0.100000
2023-04-05 11:50:36,897 epoch 70 - iter 196/280 - loss 0.02243874 - time (sec): 12.59 - samples/sec: 11835.21 - lr: 0.100000
2023-04-05 11:50:38,693 epoch 70 - iter 224/280 - loss 0.02245933 - time (sec): 14.38 - samples/sec: 11816.14 - lr: 0.100000
2023-04-05 11:50:40,516 epoch 70 - iter 252/280 - loss 0.02208386 - time (sec): 16.21 - samples/sec: 11788.31 - lr: 0.100000
2023-04-05 11:50:42,372 epoch 70 - iter 280/280 - loss 0.02221598 - time (sec): 18.06 - samples/sec: 11719.59 - lr: 0.100000
2023-04-05 11:50:42,373 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:42,373 EPOCH 70 done: loss 0.0222 - lr 0.100000
2023-04-05 11:50:42,373 BAD EPOCHS (no improvement): 2
2023-04-05 11:50:42,376 ----------------------------------------------------------------------------------------------------
2023-04-05 11:50:44,138 epoch 71 - iter 28/280 - loss 0.02135674 - time (sec): 1.76 - samples/sec: 11812.23 - lr: 0.100000
2023-04-05 11:50:45,971 epoch 71 - iter 56/280 - loss 0.02388856 - time (sec): 3.60 - samples/sec: 11699.07 - lr: 0.100000
2023-04-05 11:50:47,694 epoch 71 - iter 84/280 - loss 0.02384579 - time (sec): 5.32 - samples/sec: 11827.05 - lr: 0.100000
2023-04-05 11:50:49,448 epoch 71 - iter 112/280 - loss 0.02313819 - time (sec): 7.07 - samples/sec: 11849.37 - lr: 0.100000
2023-04-05 11:50:51,283 epoch 71 - iter 140/280 - loss 0.02235630 - time (sec): 8.91 - samples/sec: 11849.30 - lr: 0.100000
2023-04-05 11:50:53,084 epoch 71 - iter 168/280 - loss 0.02215512 - time (sec): 10.71 - samples/sec: 11834.74 - lr: 0.100000
2023-04-05 11:50:54,898 epoch 71 - iter 196/280 - loss 0.02187449 - time (sec): 12.52 - samples/sec: 11815.25 - lr: 0.100000
2023-04-05 11:50:56,703 epoch 71 - iter 224/280 - loss 0.02162644 - time (sec): 14.33 - samples/sec: 11843.04 - lr: 0.100000
2023-04-05 11:50:58,538 epoch 71 - iter 252/280 - loss 0.02167685 - time (sec): 16.16 - samples/sec: 11818.34 - lr: 0.100000
2023-04-05 11:51:00,330 epoch 71 - iter 280/280 - loss 0.02160666 - time (sec): 17.95 - samples/sec: 11790.37 - lr: 0.100000
2023-04-05 11:51:00,331 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:00,331 EPOCH 71 done: loss 0.0216 - lr 0.100000
2023-04-05 11:51:00,331 BAD EPOCHS (no improvement): 0
2023-04-05 11:51:00,334 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:02,125 epoch 72 - iter 28/280 - loss 0.01890931 - time (sec): 1.79 - samples/sec: 12039.23 - lr: 0.100000
2023-04-05 11:51:03,914 epoch 72 - iter 56/280 - loss 0.02099879 - time (sec): 3.58 - samples/sec: 11818.67 - lr: 0.100000
2023-04-05 11:51:05,666 epoch 72 - iter 84/280 - loss 0.02116803 - time (sec): 5.33 - samples/sec: 11860.73 - lr: 0.100000
2023-04-05 11:51:07,560 epoch 72 - iter 112/280 - loss 0.02147318 - time (sec): 7.23 - samples/sec: 11785.55 - lr: 0.100000
2023-04-05 11:51:09,337 epoch 72 - iter 140/280 - loss 0.02120447 - time (sec): 9.00 - samples/sec: 11815.66 - lr: 0.100000
2023-04-05 11:51:11,159 epoch 72 - iter 168/280 - loss 0.02106742 - time (sec): 10.82 - samples/sec: 11771.86 - lr: 0.100000
2023-04-05 11:51:13,003 epoch 72 - iter 196/280 - loss 0.02108144 - time (sec): 12.67 - samples/sec: 11749.95 - lr: 0.100000
2023-04-05 11:51:14,795 epoch 72 - iter 224/280 - loss 0.02124388 - time (sec): 14.46 - samples/sec: 11750.01 - lr: 0.100000
2023-04-05 11:51:16,617 epoch 72 - iter 252/280 - loss 0.02123163 - time (sec): 16.28 - samples/sec: 11739.45 - lr: 0.100000
2023-04-05 11:51:18,406 epoch 72 - iter 280/280 - loss 0.02130043 - time (sec): 18.07 - samples/sec: 11714.22 - lr: 0.100000
2023-04-05 11:51:18,406 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:18,406 EPOCH 72 done: loss 0.0213 - lr 0.100000
2023-04-05 11:51:18,406 BAD EPOCHS (no improvement): 0
2023-04-05 11:51:18,408 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:20,177 epoch 73 - iter 28/280 - loss 0.01976903 - time (sec): 1.77 - samples/sec: 11802.86 - lr: 0.100000
2023-04-05 11:51:22,042 epoch 73 - iter 56/280 - loss 0.02012165 - time (sec): 3.63 - samples/sec: 11745.01 - lr: 0.100000
2023-04-05 11:51:23,876 epoch 73 - iter 84/280 - loss 0.02110452 - time (sec): 5.47 - samples/sec: 11655.87 - lr: 0.100000
2023-04-05 11:51:25,730 epoch 73 - iter 112/280 - loss 0.02103326 - time (sec): 7.32 - samples/sec: 11591.09 - lr: 0.100000
2023-04-05 11:51:27,657 epoch 73 - iter 140/280 - loss 0.02114601 - time (sec): 9.25 - samples/sec: 11528.85 - lr: 0.100000
2023-04-05 11:51:29,494 epoch 73 - iter 168/280 - loss 0.02116793 - time (sec): 11.09 - samples/sec: 11528.62 - lr: 0.100000
2023-04-05 11:51:31,360 epoch 73 - iter 196/280 - loss 0.02169981 - time (sec): 12.95 - samples/sec: 11492.76 - lr: 0.100000
2023-04-05 11:51:33,268 epoch 73 - iter 224/280 - loss 0.02152706 - time (sec): 14.86 - samples/sec: 11458.53 - lr: 0.100000
2023-04-05 11:51:35,118 epoch 73 - iter 252/280 - loss 0.02150310 - time (sec): 16.71 - samples/sec: 11445.54 - lr: 0.100000
2023-04-05 11:51:36,928 epoch 73 - iter 280/280 - loss 0.02157205 - time (sec): 18.52 - samples/sec: 11430.48 - lr: 0.100000
2023-04-05 11:51:36,929 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:36,929 EPOCH 73 done: loss 0.0216 - lr 0.100000
2023-04-05 11:51:36,929 BAD EPOCHS (no improvement): 1
2023-04-05 11:51:36,932 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:38,754 epoch 74 - iter 28/280 - loss 0.02098983 - time (sec): 1.82 - samples/sec: 11538.43 - lr: 0.100000
2023-04-05 11:51:40,544 epoch 74 - iter 56/280 - loss 0.02232177 - time (sec): 3.61 - samples/sec: 11716.26 - lr: 0.100000
2023-04-05 11:51:42,441 epoch 74 - iter 84/280 - loss 0.02161001 - time (sec): 5.51 - samples/sec: 11514.39 - lr: 0.100000
2023-04-05 11:51:44,324 epoch 74 - iter 112/280 - loss 0.02150725 - time (sec): 7.39 - samples/sec: 11435.70 - lr: 0.100000
2023-04-05 11:51:46,311 epoch 74 - iter 140/280 - loss 0.02151222 - time (sec): 9.38 - samples/sec: 11291.40 - lr: 0.100000
2023-04-05 11:51:48,299 epoch 74 - iter 168/280 - loss 0.02103056 - time (sec): 11.37 - samples/sec: 11162.32 - lr: 0.100000
2023-04-05 11:51:50,339 epoch 74 - iter 196/280 - loss 0.02144645 - time (sec): 13.41 - samples/sec: 11090.46 - lr: 0.100000
2023-04-05 11:51:52,337 epoch 74 - iter 224/280 - loss 0.02149728 - time (sec): 15.41 - samples/sec: 11026.00 - lr: 0.100000
2023-04-05 11:51:54,291 epoch 74 - iter 252/280 - loss 0.02160198 - time (sec): 17.36 - samples/sec: 11014.47 - lr: 0.100000
2023-04-05 11:51:56,165 epoch 74 - iter 280/280 - loss 0.02192832 - time (sec): 19.23 - samples/sec: 11006.63 - lr: 0.100000
2023-04-05 11:51:56,165 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:56,165 EPOCH 74 done: loss 0.0219 - lr 0.100000
2023-04-05 11:51:56,165 BAD EPOCHS (no improvement): 2
2023-04-05 11:51:56,168 ----------------------------------------------------------------------------------------------------
2023-04-05 11:51:58,145 epoch 75 - iter 28/280 - loss 0.02163516 - time (sec): 1.98 - samples/sec: 10959.87 - lr: 0.100000
2023-04-05 11:52:00,155 epoch 75 - iter 56/280 - loss 0.02022709 - time (sec): 3.99 - samples/sec: 10698.71 - lr: 0.100000
2023-04-05 11:52:02,113 epoch 75 - iter 84/280 - loss 0.01975822 - time (sec): 5.95 - samples/sec: 10746.03 - lr: 0.100000
2023-04-05 11:52:04,081 epoch 75 - iter 112/280 - loss 0.01920793 - time (sec): 7.91 - samples/sec: 10697.91 - lr: 0.100000
2023-04-05 11:52:06,058 epoch 75 - iter 140/280 - loss 0.02015015 - time (sec): 9.89 - samples/sec: 10655.64 - lr: 0.100000
2023-04-05 11:52:07,993 epoch 75 - iter 168/280 - loss 0.01994776 - time (sec): 11.82 - samples/sec: 10689.25 - lr: 0.100000
2023-04-05 11:52:10,004 epoch 75 - iter 196/280 - loss 0.02006121 - time (sec): 13.84 - samples/sec: 10654.79 - lr: 0.100000
2023-04-05 11:52:11,996 epoch 75 - iter 224/280 - loss 0.02013890 - time (sec): 15.83 - samples/sec: 10679.64 - lr: 0.100000
2023-04-05 11:52:13,984 epoch 75 - iter 252/280 - loss 0.02005821 - time (sec): 17.82 - samples/sec: 10718.56 - lr: 0.100000
2023-04-05 11:52:15,962 epoch 75 - iter 280/280 - loss 0.02010611 - time (sec): 19.79 - samples/sec: 10694.62 - lr: 0.100000
2023-04-05 11:52:15,962 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:15,962 EPOCH 75 done: loss 0.0201 - lr 0.100000
2023-04-05 11:52:15,962 BAD EPOCHS (no improvement): 0
2023-04-05 11:52:15,966 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:17,913 epoch 76 - iter 28/280 - loss 0.02009897 - time (sec): 1.95 - samples/sec: 10528.73 - lr: 0.100000
2023-04-05 11:52:19,913 epoch 76 - iter 56/280 - loss 0.02041120 - time (sec): 3.95 - samples/sec: 10793.65 - lr: 0.100000
2023-04-05 11:52:21,821 epoch 76 - iter 84/280 - loss 0.02021270 - time (sec): 5.85 - samples/sec: 10799.07 - lr: 0.100000
2023-04-05 11:52:23,776 epoch 76 - iter 112/280 - loss 0.02062628 - time (sec): 7.81 - samples/sec: 10791.17 - lr: 0.100000
2023-04-05 11:52:25,752 epoch 76 - iter 140/280 - loss 0.02060800 - time (sec): 9.79 - samples/sec: 10792.35 - lr: 0.100000
2023-04-05 11:52:27,762 epoch 76 - iter 168/280 - loss 0.02062550 - time (sec): 11.80 - samples/sec: 10779.58 - lr: 0.100000
2023-04-05 11:52:29,825 epoch 76 - iter 196/280 - loss 0.02044274 - time (sec): 13.86 - samples/sec: 10693.55 - lr: 0.100000
2023-04-05 11:52:31,860 epoch 76 - iter 224/280 - loss 0.02058202 - time (sec): 15.89 - samples/sec: 10676.97 - lr: 0.100000
2023-04-05 11:52:33,844 epoch 76 - iter 252/280 - loss 0.02050834 - time (sec): 17.88 - samples/sec: 10699.86 - lr: 0.100000
2023-04-05 11:52:35,786 epoch 76 - iter 280/280 - loss 0.02065733 - time (sec): 19.82 - samples/sec: 10680.96 - lr: 0.100000
2023-04-05 11:52:35,786 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:35,786 EPOCH 76 done: loss 0.0207 - lr 0.100000
2023-04-05 11:52:35,786 BAD EPOCHS (no improvement): 1
2023-04-05 11:52:35,789 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:37,656 epoch 77 - iter 28/280 - loss 0.01708299 - time (sec): 1.87 - samples/sec: 11328.85 - lr: 0.100000
2023-04-05 11:52:39,508 epoch 77 - iter 56/280 - loss 0.01835746 - time (sec): 3.72 - samples/sec: 11216.92 - lr: 0.100000
2023-04-05 11:52:41,457 epoch 77 - iter 84/280 - loss 0.01816650 - time (sec): 5.67 - samples/sec: 11046.04 - lr: 0.100000
2023-04-05 11:52:43,471 epoch 77 - iter 112/280 - loss 0.01800813 - time (sec): 7.68 - samples/sec: 11005.54 - lr: 0.100000
2023-04-05 11:52:45,481 epoch 77 - iter 140/280 - loss 0.01872334 - time (sec): 9.69 - samples/sec: 10905.81 - lr: 0.100000
2023-04-05 11:52:47,452 epoch 77 - iter 168/280 - loss 0.01877902 - time (sec): 11.66 - samples/sec: 10864.91 - lr: 0.100000
2023-04-05 11:52:49,467 epoch 77 - iter 196/280 - loss 0.01931188 - time (sec): 13.68 - samples/sec: 10831.79 - lr: 0.100000
2023-04-05 11:52:51,434 epoch 77 - iter 224/280 - loss 0.01892929 - time (sec): 15.65 - samples/sec: 10786.03 - lr: 0.100000
2023-04-05 11:52:53,477 epoch 77 - iter 252/280 - loss 0.01900827 - time (sec): 17.69 - samples/sec: 10753.37 - lr: 0.100000
2023-04-05 11:52:55,491 epoch 77 - iter 280/280 - loss 0.01923144 - time (sec): 19.70 - samples/sec: 10744.68 - lr: 0.100000
2023-04-05 11:52:55,491 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:55,491 EPOCH 77 done: loss 0.0192 - lr 0.100000
2023-04-05 11:52:55,491 BAD EPOCHS (no improvement): 0
2023-04-05 11:52:55,494 ----------------------------------------------------------------------------------------------------
2023-04-05 11:52:57,541 epoch 78 - iter 28/280 - loss 0.01864592 - time (sec): 2.05 - samples/sec: 10644.55 - lr: 0.100000
2023-04-05 11:52:59,641 epoch 78 - iter 56/280 - loss 0.01924173 - time (sec): 4.15 - samples/sec: 10454.88 - lr: 0.100000
2023-04-05 11:53:01,587 epoch 78 - iter 84/280 - loss 0.02014696 - time (sec): 6.09 - samples/sec: 10579.81 - lr: 0.100000
2023-04-05 11:53:03,600 epoch 78 - iter 112/280 - loss 0.02033438 - time (sec): 8.11 - samples/sec: 10532.85 - lr: 0.100000
2023-04-05 11:53:05,598 epoch 78 - iter 140/280 - loss 0.02047643 - time (sec): 10.10 - samples/sec: 10571.05 - lr: 0.100000
2023-04-05 11:53:07,574 epoch 78 - iter 168/280 - loss 0.02001348 - time (sec): 12.08 - samples/sec: 10600.97 - lr: 0.100000
2023-04-05 11:53:09,570 epoch 78 - iter 196/280 - loss 0.02019327 - time (sec): 14.08 - samples/sec: 10627.97 - lr: 0.100000
2023-04-05 11:53:11,491 epoch 78 - iter 224/280 - loss 0.02017045 - time (sec): 16.00 - samples/sec: 10672.50 - lr: 0.100000
2023-04-05 11:53:13,370 epoch 78 - iter 252/280 - loss 0.02035093 - time (sec): 17.88 - samples/sec: 10713.10 - lr: 0.100000
2023-04-05 11:53:15,225 epoch 78 - iter 280/280 - loss 0.02009911 - time (sec): 19.73 - samples/sec: 10728.89 - lr: 0.100000
2023-04-05 11:53:15,225 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:15,225 EPOCH 78 done: loss 0.0201 - lr 0.100000
2023-04-05 11:53:15,225 BAD EPOCHS (no improvement): 1
2023-04-05 11:53:15,228 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:17,114 epoch 79 - iter 28/280 - loss 0.01783447 - time (sec): 1.89 - samples/sec: 11037.25 - lr: 0.100000
2023-04-05 11:53:19,050 epoch 79 - iter 56/280 - loss 0.01858716 - time (sec): 3.82 - samples/sec: 11139.95 - lr: 0.100000
2023-04-05 11:53:20,983 epoch 79 - iter 84/280 - loss 0.01899187 - time (sec): 5.76 - samples/sec: 11028.72 - lr: 0.100000
2023-04-05 11:53:22,946 epoch 79 - iter 112/280 - loss 0.02012692 - time (sec): 7.72 - samples/sec: 10994.80 - lr: 0.100000
2023-04-05 11:53:24,883 epoch 79 - iter 140/280 - loss 0.02015825 - time (sec): 9.65 - samples/sec: 10985.12 - lr: 0.100000
2023-04-05 11:53:26,825 epoch 79 - iter 168/280 - loss 0.01938708 - time (sec): 11.60 - samples/sec: 10988.93 - lr: 0.100000
2023-04-05 11:53:28,716 epoch 79 - iter 196/280 - loss 0.01987789 - time (sec): 13.49 - samples/sec: 11028.83 - lr: 0.100000
2023-04-05 11:53:30,574 epoch 79 - iter 224/280 - loss 0.02005371 - time (sec): 15.35 - samples/sec: 11059.26 - lr: 0.100000
2023-04-05 11:53:32,493 epoch 79 - iter 252/280 - loss 0.01968046 - time (sec): 17.27 - samples/sec: 11074.23 - lr: 0.100000
2023-04-05 11:53:34,397 epoch 79 - iter 280/280 - loss 0.01984077 - time (sec): 19.17 - samples/sec: 11043.63 - lr: 0.100000
2023-04-05 11:53:34,397 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:34,397 EPOCH 79 done: loss 0.0198 - lr 0.100000
2023-04-05 11:53:34,397 BAD EPOCHS (no improvement): 2
2023-04-05 11:53:34,400 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:36,329 epoch 80 - iter 28/280 - loss 0.01788696 - time (sec): 1.93 - samples/sec: 10749.08 - lr: 0.100000
2023-04-05 11:53:38,120 epoch 80 - iter 56/280 - loss 0.01844709 - time (sec): 3.72 - samples/sec: 11228.81 - lr: 0.100000
2023-04-05 11:53:40,103 epoch 80 - iter 84/280 - loss 0.01779718 - time (sec): 5.70 - samples/sec: 11080.50 - lr: 0.100000
2023-04-05 11:53:42,022 epoch 80 - iter 112/280 - loss 0.01782455 - time (sec): 7.62 - samples/sec: 11099.74 - lr: 0.100000
2023-04-05 11:53:43,974 epoch 80 - iter 140/280 - loss 0.01820559 - time (sec): 9.57 - samples/sec: 11094.76 - lr: 0.100000
2023-04-05 11:53:45,867 epoch 80 - iter 168/280 - loss 0.01849651 - time (sec): 11.47 - samples/sec: 11123.55 - lr: 0.100000
2023-04-05 11:53:47,804 epoch 80 - iter 196/280 - loss 0.01958702 - time (sec): 13.40 - samples/sec: 11107.42 - lr: 0.100000
2023-04-05 11:53:49,709 epoch 80 - iter 224/280 - loss 0.01931824 - time (sec): 15.31 - samples/sec: 11118.66 - lr: 0.100000
2023-04-05 11:53:51,600 epoch 80 - iter 252/280 - loss 0.01955896 - time (sec): 17.20 - samples/sec: 11109.95 - lr: 0.100000
2023-04-05 11:53:53,469 epoch 80 - iter 280/280 - loss 0.01963729 - time (sec): 19.07 - samples/sec: 11101.09 - lr: 0.100000
2023-04-05 11:53:53,470 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:53,470 EPOCH 80 done: loss 0.0196 - lr 0.100000
2023-04-05 11:53:53,470 BAD EPOCHS (no improvement): 3
2023-04-05 11:53:53,473 ----------------------------------------------------------------------------------------------------
2023-04-05 11:53:55,432 epoch 81 - iter 28/280 - loss 0.01999609 - time (sec): 1.96 - samples/sec: 11004.59 - lr: 0.100000
2023-04-05 11:53:57,294 epoch 81 - iter 56/280 - loss 0.02234605 - time (sec): 3.82 - samples/sec: 11092.64 - lr: 0.100000
2023-04-05 11:53:59,227 epoch 81 - iter 84/280 - loss 0.02102149 - time (sec): 5.75 - samples/sec: 10995.46 - lr: 0.100000
2023-04-05 11:54:01,169 epoch 81 - iter 112/280 - loss 0.02068849 - time (sec): 7.70 - samples/sec: 10971.77 - lr: 0.100000
2023-04-05 11:54:04,572 epoch 81 - iter 140/280 - loss 0.02105535 - time (sec): 11.10 - samples/sec: 9548.58 - lr: 0.100000
2023-04-05 11:54:06,435 epoch 81 - iter 168/280 - loss 0.02063509 - time (sec): 12.96 - samples/sec: 9825.20 - lr: 0.100000
2023-04-05 11:54:08,354 epoch 81 - iter 196/280 - loss 0.02065726 - time (sec): 14.88 - samples/sec: 10000.69 - lr: 0.100000
2023-04-05 11:54:10,334 epoch 81 - iter 224/280 - loss 0.02047387 - time (sec): 16.86 - samples/sec: 10095.44 - lr: 0.100000
2023-04-05 11:54:12,256 epoch 81 - iter 252/280 - loss 0.02026883 - time (sec): 18.78 - samples/sec: 10198.90 - lr: 0.100000
2023-04-05 11:54:14,089 epoch 81 - iter 280/280 - loss 0.02002583 - time (sec): 20.62 - samples/sec: 10268.24 - lr: 0.100000
2023-04-05 11:54:14,089 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:14,089 EPOCH 81 done: loss 0.0200 - lr 0.100000
2023-04-05 11:54:14,089 Epoch 81: reducing learning rate of group 0 to 5.0000e-02.
2023-04-05 11:54:14,089 BAD EPOCHS (no improvement): 4
2023-04-05 11:54:14,092 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:15,965 epoch 82 - iter 28/280 - loss 0.01860981 - time (sec): 1.87 - samples/sec: 11077.36 - lr: 0.050000
2023-04-05 11:54:17,953 epoch 82 - iter 56/280 - loss 0.01974103 - time (sec): 3.86 - samples/sec: 10991.65 - lr: 0.050000
2023-04-05 11:54:19,875 epoch 82 - iter 84/280 - loss 0.01921790 - time (sec): 5.78 - samples/sec: 11036.31 - lr: 0.050000
2023-04-05 11:54:21,702 epoch 82 - iter 112/280 - loss 0.01860644 - time (sec): 7.61 - samples/sec: 11177.80 - lr: 0.050000
2023-04-05 11:54:23,609 epoch 82 - iter 140/280 - loss 0.01830974 - time (sec): 9.52 - samples/sec: 11121.33 - lr: 0.050000
2023-04-05 11:54:25,584 epoch 82 - iter 168/280 - loss 0.01827574 - time (sec): 11.49 - samples/sec: 11080.97 - lr: 0.050000
2023-04-05 11:54:27,617 epoch 82 - iter 196/280 - loss 0.01837247 - time (sec): 13.53 - samples/sec: 10995.59 - lr: 0.050000
2023-04-05 11:54:29,608 epoch 82 - iter 224/280 - loss 0.01842828 - time (sec): 15.52 - samples/sec: 10943.35 - lr: 0.050000
2023-04-05 11:54:31,584 epoch 82 - iter 252/280 - loss 0.01837193 - time (sec): 17.49 - samples/sec: 10924.48 - lr: 0.050000
2023-04-05 11:54:33,535 epoch 82 - iter 280/280 - loss 0.01856906 - time (sec): 19.44 - samples/sec: 10887.33 - lr: 0.050000
2023-04-05 11:54:33,536 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:33,536 EPOCH 82 done: loss 0.0186 - lr 0.050000
2023-04-05 11:54:33,536 BAD EPOCHS (no improvement): 0
2023-04-05 11:54:33,539 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:35,624 epoch 83 - iter 28/280 - loss 0.01842064 - time (sec): 2.08 - samples/sec: 10262.66 - lr: 0.050000
2023-04-05 11:54:37,549 epoch 83 - iter 56/280 - loss 0.01690092 - time (sec): 4.01 - samples/sec: 10608.83 - lr: 0.050000
2023-04-05 11:54:39,605 epoch 83 - iter 84/280 - loss 0.01784087 - time (sec): 6.07 - samples/sec: 10616.14 - lr: 0.050000
2023-04-05 11:54:41,630 epoch 83 - iter 112/280 - loss 0.01842300 - time (sec): 8.09 - samples/sec: 10629.69 - lr: 0.050000
2023-04-05 11:54:43,627 epoch 83 - iter 140/280 - loss 0.01803914 - time (sec): 10.09 - samples/sec: 10645.63 - lr: 0.050000
2023-04-05 11:54:45,683 epoch 83 - iter 168/280 - loss 0.01799391 - time (sec): 12.14 - samples/sec: 10605.06 - lr: 0.050000
2023-04-05 11:54:47,739 epoch 83 - iter 196/280 - loss 0.01789924 - time (sec): 14.20 - samples/sec: 10531.43 - lr: 0.050000
2023-04-05 11:54:49,630 epoch 83 - iter 224/280 - loss 0.01795461 - time (sec): 16.09 - samples/sec: 10572.30 - lr: 0.050000
2023-04-05 11:54:51,672 epoch 83 - iter 252/280 - loss 0.01752941 - time (sec): 18.13 - samples/sec: 10566.80 - lr: 0.050000
2023-04-05 11:54:53,560 epoch 83 - iter 280/280 - loss 0.01755867 - time (sec): 20.02 - samples/sec: 10573.69 - lr: 0.050000
2023-04-05 11:54:53,560 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:53,560 EPOCH 83 done: loss 0.0176 - lr 0.050000
2023-04-05 11:54:53,560 BAD EPOCHS (no improvement): 0
2023-04-05 11:54:53,563 ----------------------------------------------------------------------------------------------------
2023-04-05 11:54:55,540 epoch 84 - iter 28/280 - loss 0.01463967 - time (sec): 1.98 - samples/sec: 10708.68 - lr: 0.050000
2023-04-05 11:54:57,501 epoch 84 - iter 56/280 - loss 0.01594683 - time (sec): 3.94 - samples/sec: 10895.68 - lr: 0.050000
2023-04-05 11:54:59,447 epoch 84 - iter 84/280 - loss 0.01600441 - time (sec): 5.88 - samples/sec: 10835.67 - lr: 0.050000
2023-04-05 11:55:01,489 epoch 84 - iter 112/280 - loss 0.01638562 - time (sec): 7.93 - samples/sec: 10750.12 - lr: 0.050000
2023-04-05 11:55:03,395 epoch 84 - iter 140/280 - loss 0.01677881 - time (sec): 9.83 - samples/sec: 10776.07 - lr: 0.050000
2023-04-05 11:55:05,381 epoch 84 - iter 168/280 - loss 0.01656132 - time (sec): 11.82 - samples/sec: 10768.96 - lr: 0.050000
2023-04-05 11:55:07,372 epoch 84 - iter 196/280 - loss 0.01653145 - time (sec): 13.81 - samples/sec: 10755.67 - lr: 0.050000
2023-04-05 11:55:09,306 epoch 84 - iter 224/280 - loss 0.01648739 - time (sec): 15.74 - samples/sec: 10796.01 - lr: 0.050000
2023-04-05 11:55:11,285 epoch 84 - iter 252/280 - loss 0.01642549 - time (sec): 17.72 - samples/sec: 10797.73 - lr: 0.050000
2023-04-05 11:55:13,130 epoch 84 - iter 280/280 - loss 0.01655025 - time (sec): 19.57 - samples/sec: 10818.82 - lr: 0.050000
2023-04-05 11:55:13,130 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:13,130 EPOCH 84 done: loss 0.0166 - lr 0.050000
2023-04-05 11:55:13,130 BAD EPOCHS (no improvement): 0
2023-04-05 11:55:13,133 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:15,097 epoch 85 - iter 28/280 - loss 0.01594061 - time (sec): 1.96 - samples/sec: 10711.62 - lr: 0.050000
2023-04-05 11:55:17,013 epoch 85 - iter 56/280 - loss 0.01557143 - time (sec): 3.88 - samples/sec: 10768.49 - lr: 0.050000
2023-04-05 11:55:19,002 epoch 85 - iter 84/280 - loss 0.01557014 - time (sec): 5.87 - samples/sec: 10739.06 - lr: 0.050000
2023-04-05 11:55:20,962 epoch 85 - iter 112/280 - loss 0.01544992 - time (sec): 7.83 - samples/sec: 10722.08 - lr: 0.050000
2023-04-05 11:55:22,995 epoch 85 - iter 140/280 - loss 0.01610699 - time (sec): 9.86 - samples/sec: 10693.99 - lr: 0.050000
2023-04-05 11:55:24,944 epoch 85 - iter 168/280 - loss 0.01614985 - time (sec): 11.81 - samples/sec: 10721.61 - lr: 0.050000
2023-04-05 11:55:26,975 epoch 85 - iter 196/280 - loss 0.01637534 - time (sec): 13.84 - samples/sec: 10720.76 - lr: 0.050000
2023-04-05 11:55:28,962 epoch 85 - iter 224/280 - loss 0.01637429 - time (sec): 15.83 - samples/sec: 10718.18 - lr: 0.050000
2023-04-05 11:55:30,925 epoch 85 - iter 252/280 - loss 0.01640293 - time (sec): 17.79 - samples/sec: 10715.15 - lr: 0.050000
2023-04-05 11:55:32,870 epoch 85 - iter 280/280 - loss 0.01626972 - time (sec): 19.74 - samples/sec: 10725.72 - lr: 0.050000
2023-04-05 11:55:32,870 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:32,870 EPOCH 85 done: loss 0.0163 - lr 0.050000
2023-04-05 11:55:32,870 BAD EPOCHS (no improvement): 0
2023-04-05 11:55:32,873 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:34,740 epoch 86 - iter 28/280 - loss 0.01560746 - time (sec): 1.87 - samples/sec: 11305.00 - lr: 0.050000
2023-04-05 11:55:36,676 epoch 86 - iter 56/280 - loss 0.01594714 - time (sec): 3.80 - samples/sec: 10942.16 - lr: 0.050000
2023-04-05 11:55:38,736 epoch 86 - iter 84/280 - loss 0.01693447 - time (sec): 5.86 - samples/sec: 10861.55 - lr: 0.050000
2023-04-05 11:55:40,721 epoch 86 - iter 112/280 - loss 0.01679641 - time (sec): 7.85 - samples/sec: 10849.76 - lr: 0.050000
2023-04-05 11:55:42,693 epoch 86 - iter 140/280 - loss 0.01650936 - time (sec): 9.82 - samples/sec: 10780.19 - lr: 0.050000
2023-04-05 11:55:44,629 epoch 86 - iter 168/280 - loss 0.01615554 - time (sec): 11.76 - samples/sec: 10795.85 - lr: 0.050000
2023-04-05 11:55:46,514 epoch 86 - iter 196/280 - loss 0.01619688 - time (sec): 13.64 - samples/sec: 10826.39 - lr: 0.050000
2023-04-05 11:55:48,523 epoch 86 - iter 224/280 - loss 0.01624418 - time (sec): 15.65 - samples/sec: 10824.24 - lr: 0.050000
2023-04-05 11:55:50,515 epoch 86 - iter 252/280 - loss 0.01664642 - time (sec): 17.64 - samples/sec: 10821.70 - lr: 0.050000
2023-04-05 11:55:52,456 epoch 86 - iter 280/280 - loss 0.01670856 - time (sec): 19.58 - samples/sec: 10809.77 - lr: 0.050000
2023-04-05 11:55:52,456 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:52,457 EPOCH 86 done: loss 0.0167 - lr 0.050000
2023-04-05 11:55:52,457 BAD EPOCHS (no improvement): 1
2023-04-05 11:55:52,459 ----------------------------------------------------------------------------------------------------
2023-04-05 11:55:54,414 epoch 87 - iter 28/280 - loss 0.01526542 - time (sec): 1.95 - samples/sec: 11024.05 - lr: 0.050000
2023-04-05 11:55:56,338 epoch 87 - iter 56/280 - loss 0.01534677 - time (sec): 3.88 - samples/sec: 11112.07 - lr: 0.050000
2023-04-05 11:55:58,290 epoch 87 - iter 84/280 - loss 0.01460912 - time (sec): 5.83 - samples/sec: 11062.58 - lr: 0.050000
2023-04-05 11:56:00,190 epoch 87 - iter 112/280 - loss 0.01418288 - time (sec): 7.73 - samples/sec: 11012.47 - lr: 0.050000
2023-04-05 11:56:02,156 epoch 87 - iter 140/280 - loss 0.01427603 - time (sec): 9.70 - samples/sec: 10999.97 - lr: 0.050000
2023-04-05 11:56:04,018 epoch 87 - iter 168/280 - loss 0.01479369 - time (sec): 11.56 - samples/sec: 11039.29 - lr: 0.050000
2023-04-05 11:56:05,883 epoch 87 - iter 196/280 - loss 0.01478301 - time (sec): 13.42 - samples/sec: 11100.90 - lr: 0.050000
2023-04-05 11:56:07,688 epoch 87 - iter 224/280 - loss 0.01476124 - time (sec): 15.23 - samples/sec: 11158.32 - lr: 0.050000
2023-04-05 11:56:09,505 epoch 87 - iter 252/280 - loss 0.01498062 - time (sec): 17.05 - samples/sec: 11224.51 - lr: 0.050000
2023-04-05 11:56:11,310 epoch 87 - iter 280/280 - loss 0.01496752 - time (sec): 18.85 - samples/sec: 11229.54 - lr: 0.050000
2023-04-05 11:56:11,310 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:11,310 EPOCH 87 done: loss 0.0150 - lr 0.050000
2023-04-05 11:56:11,311 BAD EPOCHS (no improvement): 0
2023-04-05 11:56:11,313 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:13,188 epoch 88 - iter 28/280 - loss 0.01420705 - time (sec): 1.88 - samples/sec: 11137.37 - lr: 0.050000
2023-04-05 11:56:15,022 epoch 88 - iter 56/280 - loss 0.01550309 - time (sec): 3.71 - samples/sec: 11267.02 - lr: 0.050000
2023-04-05 11:56:16,917 epoch 88 - iter 84/280 - loss 0.01510743 - time (sec): 5.60 - samples/sec: 11261.87 - lr: 0.050000
2023-04-05 11:56:18,852 epoch 88 - iter 112/280 - loss 0.01540760 - time (sec): 7.54 - samples/sec: 11173.18 - lr: 0.050000
2023-04-05 11:56:20,825 epoch 88 - iter 140/280 - loss 0.01488094 - time (sec): 9.51 - samples/sec: 11110.78 - lr: 0.050000
2023-04-05 11:56:22,749 epoch 88 - iter 168/280 - loss 0.01474611 - time (sec): 11.44 - samples/sec: 11085.11 - lr: 0.050000
2023-04-05 11:56:24,677 epoch 88 - iter 196/280 - loss 0.01467050 - time (sec): 13.36 - samples/sec: 11070.49 - lr: 0.050000
2023-04-05 11:56:26,603 epoch 88 - iter 224/280 - loss 0.01460222 - time (sec): 15.29 - samples/sec: 11046.32 - lr: 0.050000
2023-04-05 11:56:28,539 epoch 88 - iter 252/280 - loss 0.01480295 - time (sec): 17.23 - samples/sec: 11043.20 - lr: 0.050000
2023-04-05 11:56:30,541 epoch 88 - iter 280/280 - loss 0.01480336 - time (sec): 19.23 - samples/sec: 11009.48 - lr: 0.050000
2023-04-05 11:56:30,541 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:30,541 EPOCH 88 done: loss 0.0148 - lr 0.050000
2023-04-05 11:56:30,541 BAD EPOCHS (no improvement): 0
2023-04-05 11:56:30,544 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:32,544 epoch 89 - iter 28/280 - loss 0.01797876 - time (sec): 2.00 - samples/sec: 10748.89 - lr: 0.050000
2023-04-05 11:56:34,510 epoch 89 - iter 56/280 - loss 0.01629157 - time (sec): 3.97 - samples/sec: 10779.99 - lr: 0.050000
2023-04-05 11:56:36,468 epoch 89 - iter 84/280 - loss 0.01545197 - time (sec): 5.92 - samples/sec: 10815.12 - lr: 0.050000
2023-04-05 11:56:38,498 epoch 89 - iter 112/280 - loss 0.01472171 - time (sec): 7.95 - samples/sec: 10766.30 - lr: 0.050000
2023-04-05 11:56:40,408 epoch 89 - iter 140/280 - loss 0.01415684 - time (sec): 9.86 - samples/sec: 10764.13 - lr: 0.050000
2023-04-05 11:56:42,350 epoch 89 - iter 168/280 - loss 0.01405974 - time (sec): 11.81 - samples/sec: 10787.01 - lr: 0.050000
2023-04-05 11:56:44,316 epoch 89 - iter 196/280 - loss 0.01411571 - time (sec): 13.77 - samples/sec: 10810.09 - lr: 0.050000
2023-04-05 11:56:46,335 epoch 89 - iter 224/280 - loss 0.01464182 - time (sec): 15.79 - samples/sec: 10783.34 - lr: 0.050000
2023-04-05 11:56:48,307 epoch 89 - iter 252/280 - loss 0.01457484 - time (sec): 17.76 - samples/sec: 10757.54 - lr: 0.050000
2023-04-05 11:56:50,240 epoch 89 - iter 280/280 - loss 0.01471727 - time (sec): 19.70 - samples/sec: 10748.03 - lr: 0.050000
2023-04-05 11:56:50,241 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:50,241 EPOCH 89 done: loss 0.0147 - lr 0.050000
2023-04-05 11:56:50,241 BAD EPOCHS (no improvement): 0
2023-04-05 11:56:50,243 ----------------------------------------------------------------------------------------------------
2023-04-05 11:56:52,201 epoch 90 - iter 28/280 - loss 0.01639187 - time (sec): 1.96 - samples/sec: 10840.92 - lr: 0.050000
2023-04-05 11:56:54,245 epoch 90 - iter 56/280 - loss 0.01439273 - time (sec): 4.00 - samples/sec: 10726.45 - lr: 0.050000
2023-04-05 11:56:56,222 epoch 90 - iter 84/280 - loss 0.01506792 - time (sec): 5.98 - samples/sec: 10778.77 - lr: 0.050000
2023-04-05 11:56:58,189 epoch 90 - iter 112/280 - loss 0.01557248 - time (sec): 7.95 - samples/sec: 10781.41 - lr: 0.050000
2023-04-05 11:57:00,145 epoch 90 - iter 140/280 - loss 0.01486076 - time (sec): 9.90 - samples/sec: 10756.30 - lr: 0.050000
2023-04-05 11:57:02,081 epoch 90 - iter 168/280 - loss 0.01478498 - time (sec): 11.84 - samples/sec: 10775.50 - lr: 0.050000
2023-04-05 11:57:04,042 epoch 90 - iter 196/280 - loss 0.01510865 - time (sec): 13.80 - samples/sec: 10783.04 - lr: 0.050000
2023-04-05 11:57:05,994 epoch 90 - iter 224/280 - loss 0.01506781 - time (sec): 15.75 - samples/sec: 10800.62 - lr: 0.050000
2023-04-05 11:57:07,960 epoch 90 - iter 252/280 - loss 0.01507409 - time (sec): 17.72 - samples/sec: 10790.03 - lr: 0.050000
2023-04-05 11:57:09,918 epoch 90 - iter 280/280 - loss 0.01503079 - time (sec): 19.67 - samples/sec: 10759.71 - lr: 0.050000
2023-04-05 11:57:09,918 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:09,918 EPOCH 90 done: loss 0.0150 - lr 0.050000
2023-04-05 11:57:09,918 BAD EPOCHS (no improvement): 1
2023-04-05 11:57:09,921 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:11,910 epoch 91 - iter 28/280 - loss 0.01545410 - time (sec): 1.99 - samples/sec: 10541.42 - lr: 0.050000
2023-04-05 11:57:13,946 epoch 91 - iter 56/280 - loss 0.01494736 - time (sec): 4.02 - samples/sec: 10595.56 - lr: 0.050000
2023-04-05 11:57:15,829 epoch 91 - iter 84/280 - loss 0.01527115 - time (sec): 5.91 - samples/sec: 10722.58 - lr: 0.050000
2023-04-05 11:57:17,778 epoch 91 - iter 112/280 - loss 0.01516962 - time (sec): 7.86 - samples/sec: 10783.11 - lr: 0.050000
2023-04-05 11:57:19,786 epoch 91 - iter 140/280 - loss 0.01508720 - time (sec): 9.87 - samples/sec: 10710.04 - lr: 0.050000
2023-04-05 11:57:21,664 epoch 91 - iter 168/280 - loss 0.01472600 - time (sec): 11.74 - samples/sec: 10774.53 - lr: 0.050000
2023-04-05 11:57:23,631 epoch 91 - iter 196/280 - loss 0.01473321 - time (sec): 13.71 - samples/sec: 10800.70 - lr: 0.050000
2023-04-05 11:57:25,573 epoch 91 - iter 224/280 - loss 0.01502994 - time (sec): 15.65 - samples/sec: 10806.61 - lr: 0.050000
2023-04-05 11:57:27,667 epoch 91 - iter 252/280 - loss 0.01507856 - time (sec): 17.75 - samples/sec: 10752.31 - lr: 0.050000
2023-04-05 11:57:29,590 epoch 91 - iter 280/280 - loss 0.01523840 - time (sec): 19.67 - samples/sec: 10762.66 - lr: 0.050000
2023-04-05 11:57:29,591 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:29,591 EPOCH 91 done: loss 0.0152 - lr 0.050000
2023-04-05 11:57:29,591 BAD EPOCHS (no improvement): 2
2023-04-05 11:57:29,593 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:31,543 epoch 92 - iter 28/280 - loss 0.01484371 - time (sec): 1.95 - samples/sec: 10930.48 - lr: 0.050000
2023-04-05 11:57:33,482 epoch 92 - iter 56/280 - loss 0.01573479 - time (sec): 3.89 - samples/sec: 10983.19 - lr: 0.050000
2023-04-05 11:57:35,398 epoch 92 - iter 84/280 - loss 0.01527193 - time (sec): 5.80 - samples/sec: 10991.00 - lr: 0.050000
2023-04-05 11:57:37,293 epoch 92 - iter 112/280 - loss 0.01465186 - time (sec): 7.70 - samples/sec: 10931.73 - lr: 0.050000
2023-04-05 11:57:39,311 epoch 92 - iter 140/280 - loss 0.01509237 - time (sec): 9.72 - samples/sec: 10850.88 - lr: 0.050000
2023-04-05 11:57:41,291 epoch 92 - iter 168/280 - loss 0.01495476 - time (sec): 11.70 - samples/sec: 10842.87 - lr: 0.050000
2023-04-05 11:57:43,263 epoch 92 - iter 196/280 - loss 0.01502795 - time (sec): 13.67 - samples/sec: 10866.17 - lr: 0.050000
2023-04-05 11:57:45,210 epoch 92 - iter 224/280 - loss 0.01485677 - time (sec): 15.62 - samples/sec: 10888.76 - lr: 0.050000
2023-04-05 11:57:47,185 epoch 92 - iter 252/280 - loss 0.01480522 - time (sec): 17.59 - samples/sec: 10861.36 - lr: 0.050000
2023-04-05 11:57:49,044 epoch 92 - iter 280/280 - loss 0.01521416 - time (sec): 19.45 - samples/sec: 10883.50 - lr: 0.050000
2023-04-05 11:57:49,044 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:49,044 EPOCH 92 done: loss 0.0152 - lr 0.050000
2023-04-05 11:57:49,045 BAD EPOCHS (no improvement): 3
2023-04-05 11:57:49,047 ----------------------------------------------------------------------------------------------------
2023-04-05 11:57:50,913 epoch 93 - iter 28/280 - loss 0.01198411 - time (sec): 1.87 - samples/sec: 11271.93 - lr: 0.050000
2023-04-05 11:57:52,826 epoch 93 - iter 56/280 - loss 0.01311257 - time (sec): 3.78 - samples/sec: 11258.88 - lr: 0.050000
2023-04-05 11:57:54,656 epoch 93 - iter 84/280 - loss 0.01376303 - time (sec): 5.61 - samples/sec: 11374.13 - lr: 0.050000
2023-04-05 11:57:56,552 epoch 93 - iter 112/280 - loss 0.01393217 - time (sec): 7.51 - samples/sec: 11336.61 - lr: 0.050000
2023-04-05 11:57:58,438 epoch 93 - iter 140/280 - loss 0.01453267 - time (sec): 9.39 - samples/sec: 11292.28 - lr: 0.050000
2023-04-05 11:58:00,413 epoch 93 - iter 168/280 - loss 0.01456068 - time (sec): 11.37 - samples/sec: 11197.02 - lr: 0.050000
2023-04-05 11:58:02,342 epoch 93 - iter 196/280 - loss 0.01474101 - time (sec): 13.29 - samples/sec: 11154.83 - lr: 0.050000
2023-04-05 11:58:04,199 epoch 93 - iter 224/280 - loss 0.01502533 - time (sec): 15.15 - samples/sec: 11195.78 - lr: 0.050000
2023-04-05 11:58:06,042 epoch 93 - iter 252/280 - loss 0.01511770 - time (sec): 16.99 - samples/sec: 11222.52 - lr: 0.050000
2023-04-05 11:58:07,915 epoch 93 - iter 280/280 - loss 0.01525482 - time (sec): 18.87 - samples/sec: 11220.00 - lr: 0.050000
2023-04-05 11:58:07,915 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:07,915 EPOCH 93 done: loss 0.0153 - lr 0.050000
2023-04-05 11:58:07,915 Epoch 93: reducing learning rate of group 0 to 2.5000e-02.
2023-04-05 11:58:07,915 BAD EPOCHS (no improvement): 4
2023-04-05 11:58:07,917 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:09,867 epoch 94 - iter 28/280 - loss 0.01152935 - time (sec): 1.95 - samples/sec: 10934.11 - lr: 0.025000
2023-04-05 11:58:11,771 epoch 94 - iter 56/280 - loss 0.01260573 - time (sec): 3.85 - samples/sec: 10933.71 - lr: 0.025000
2023-04-05 11:58:13,657 epoch 94 - iter 84/280 - loss 0.01333640 - time (sec): 5.74 - samples/sec: 11040.50 - lr: 0.025000
2023-04-05 11:58:15,549 epoch 94 - iter 112/280 - loss 0.01282413 - time (sec): 7.63 - samples/sec: 11117.60 - lr: 0.025000
2023-04-05 11:58:17,347 epoch 94 - iter 140/280 - loss 0.01297793 - time (sec): 9.43 - samples/sec: 11212.54 - lr: 0.025000
2023-04-05 11:58:19,191 epoch 94 - iter 168/280 - loss 0.01303816 - time (sec): 11.27 - samples/sec: 11264.98 - lr: 0.025000
2023-04-05 11:58:21,055 epoch 94 - iter 196/280 - loss 0.01326301 - time (sec): 13.14 - samples/sec: 11299.05 - lr: 0.025000
2023-04-05 11:58:22,991 epoch 94 - iter 224/280 - loss 0.01367185 - time (sec): 15.07 - samples/sec: 11277.29 - lr: 0.025000
2023-04-05 11:58:24,881 epoch 94 - iter 252/280 - loss 0.01370797 - time (sec): 16.96 - samples/sec: 11266.85 - lr: 0.025000
2023-04-05 11:58:26,725 epoch 94 - iter 280/280 - loss 0.01350361 - time (sec): 18.81 - samples/sec: 11255.38 - lr: 0.025000
2023-04-05 11:58:26,726 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:26,726 EPOCH 94 done: loss 0.0135 - lr 0.025000
2023-04-05 11:58:26,726 BAD EPOCHS (no improvement): 0
2023-04-05 11:58:26,729 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:28,651 epoch 95 - iter 28/280 - loss 0.01333991 - time (sec): 1.92 - samples/sec: 11174.31 - lr: 0.025000
2023-04-05 11:58:30,517 epoch 95 - iter 56/280 - loss 0.01371795 - time (sec): 3.79 - samples/sec: 11189.97 - lr: 0.025000
2023-04-05 11:58:32,365 epoch 95 - iter 84/280 - loss 0.01394390 - time (sec): 5.64 - samples/sec: 11316.15 - lr: 0.025000
2023-04-05 11:58:34,261 epoch 95 - iter 112/280 - loss 0.01372520 - time (sec): 7.53 - samples/sec: 11331.88 - lr: 0.025000
2023-04-05 11:58:36,106 epoch 95 - iter 140/280 - loss 0.01357480 - time (sec): 9.38 - samples/sec: 11350.16 - lr: 0.025000
2023-04-05 11:58:37,884 epoch 95 - iter 168/280 - loss 0.01370638 - time (sec): 11.16 - samples/sec: 11384.27 - lr: 0.025000
2023-04-05 11:58:39,810 epoch 95 - iter 196/280 - loss 0.01359010 - time (sec): 13.08 - samples/sec: 11363.40 - lr: 0.025000
2023-04-05 11:58:41,746 epoch 95 - iter 224/280 - loss 0.01379960 - time (sec): 15.02 - samples/sec: 11325.32 - lr: 0.025000
2023-04-05 11:58:43,663 epoch 95 - iter 252/280 - loss 0.01394541 - time (sec): 16.93 - samples/sec: 11283.73 - lr: 0.025000
2023-04-05 11:58:45,557 epoch 95 - iter 280/280 - loss 0.01404544 - time (sec): 18.83 - samples/sec: 11243.30 - lr: 0.025000
2023-04-05 11:58:45,557 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:45,557 EPOCH 95 done: loss 0.0140 - lr 0.025000
2023-04-05 11:58:45,557 BAD EPOCHS (no improvement): 1
2023-04-05 11:58:45,560 ----------------------------------------------------------------------------------------------------
2023-04-05 11:58:47,485 epoch 96 - iter 28/280 - loss 0.01093249 - time (sec): 1.92 - samples/sec: 11007.12 - lr: 0.025000
2023-04-05 11:58:49,362 epoch 96 - iter 56/280 - loss 0.01288285 - time (sec): 3.80 - samples/sec: 11085.50 - lr: 0.025000
2023-04-05 11:58:51,221 epoch 96 - iter 84/280 - loss 0.01249340 - time (sec): 5.66 - samples/sec: 11153.55 - lr: 0.025000
2023-04-05 11:58:53,066 epoch 96 - iter 112/280 - loss 0.01254522 - time (sec): 7.51 - samples/sec: 11226.66 - lr: 0.025000
2023-04-05 11:58:54,946 epoch 96 - iter 140/280 - loss 0.01274062 - time (sec): 9.39 - samples/sec: 11259.23 - lr: 0.025000
2023-04-05 11:58:56,853 epoch 96 - iter 168/280 - loss 0.01297879 - time (sec): 11.29 - samples/sec: 11251.11 - lr: 0.025000
2023-04-05 11:58:58,748 epoch 96 - iter 196/280 - loss 0.01343345 - time (sec): 13.19 - samples/sec: 11268.37 - lr: 0.025000
2023-04-05 11:59:00,616 epoch 96 - iter 224/280 - loss 0.01345790 - time (sec): 15.06 - samples/sec: 11284.82 - lr: 0.025000
2023-04-05 11:59:02,505 epoch 96 - iter 252/280 - loss 0.01328369 - time (sec): 16.95 - samples/sec: 11261.90 - lr: 0.025000
2023-04-05 11:59:04,423 epoch 96 - iter 280/280 - loss 0.01317795 - time (sec): 18.86 - samples/sec: 11222.67 - lr: 0.025000
2023-04-05 11:59:04,423 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:04,423 EPOCH 96 done: loss 0.0132 - lr 0.025000
2023-04-05 11:59:04,423 BAD EPOCHS (no improvement): 0
2023-04-05 11:59:04,426 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:06,265 epoch 97 - iter 28/280 - loss 0.01330318 - time (sec): 1.84 - samples/sec: 11575.41 - lr: 0.025000
2023-04-05 11:59:08,164 epoch 97 - iter 56/280 - loss 0.01407034 - time (sec): 3.74 - samples/sec: 11318.57 - lr: 0.025000
2023-04-05 11:59:10,020 epoch 97 - iter 84/280 - loss 0.01411762 - time (sec): 5.59 - samples/sec: 11340.86 - lr: 0.025000
2023-04-05 11:59:11,913 epoch 97 - iter 112/280 - loss 0.01408308 - time (sec): 7.49 - samples/sec: 11333.11 - lr: 0.025000
2023-04-05 11:59:13,823 epoch 97 - iter 140/280 - loss 0.01385214 - time (sec): 9.40 - samples/sec: 11323.61 - lr: 0.025000
2023-04-05 11:59:15,692 epoch 97 - iter 168/280 - loss 0.01382052 - time (sec): 11.27 - samples/sec: 11309.38 - lr: 0.025000
2023-04-05 11:59:17,579 epoch 97 - iter 196/280 - loss 0.01370190 - time (sec): 13.15 - samples/sec: 11286.36 - lr: 0.025000
2023-04-05 11:59:19,483 epoch 97 - iter 224/280 - loss 0.01343923 - time (sec): 15.06 - samples/sec: 11259.86 - lr: 0.025000
2023-04-05 11:59:21,324 epoch 97 - iter 252/280 - loss 0.01328980 - time (sec): 16.90 - samples/sec: 11300.17 - lr: 0.025000
2023-04-05 11:59:23,212 epoch 97 - iter 280/280 - loss 0.01327418 - time (sec): 18.79 - samples/sec: 11268.46 - lr: 0.025000
2023-04-05 11:59:23,212 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:23,212 EPOCH 97 done: loss 0.0133 - lr 0.025000
2023-04-05 11:59:23,213 BAD EPOCHS (no improvement): 1
2023-04-05 11:59:23,218 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:25,046 epoch 98 - iter 28/280 - loss 0.01357833 - time (sec): 1.83 - samples/sec: 11420.87 - lr: 0.025000
2023-04-05 11:59:26,905 epoch 98 - iter 56/280 - loss 0.01228311 - time (sec): 3.69 - samples/sec: 11355.57 - lr: 0.025000
2023-04-05 11:59:28,803 epoch 98 - iter 84/280 - loss 0.01301699 - time (sec): 5.59 - samples/sec: 11322.19 - lr: 0.025000
2023-04-05 11:59:30,693 epoch 98 - iter 112/280 - loss 0.01352615 - time (sec): 7.48 - samples/sec: 11312.11 - lr: 0.025000
2023-04-05 11:59:32,541 epoch 98 - iter 140/280 - loss 0.01315249 - time (sec): 9.32 - samples/sec: 11308.89 - lr: 0.025000
2023-04-05 11:59:34,398 epoch 98 - iter 168/280 - loss 0.01308830 - time (sec): 11.18 - samples/sec: 11351.06 - lr: 0.025000
2023-04-05 11:59:36,281 epoch 98 - iter 196/280 - loss 0.01339365 - time (sec): 13.06 - samples/sec: 11348.20 - lr: 0.025000
2023-04-05 11:59:38,107 epoch 98 - iter 224/280 - loss 0.01310229 - time (sec): 14.89 - samples/sec: 11392.91 - lr: 0.025000
2023-04-05 11:59:40,030 epoch 98 - iter 252/280 - loss 0.01302237 - time (sec): 16.81 - samples/sec: 11360.19 - lr: 0.025000
2023-04-05 11:59:41,885 epoch 98 - iter 280/280 - loss 0.01313041 - time (sec): 18.67 - samples/sec: 11340.59 - lr: 0.025000
2023-04-05 11:59:41,885 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:41,885 EPOCH 98 done: loss 0.0131 - lr 0.025000
2023-04-05 11:59:41,885 BAD EPOCHS (no improvement): 0
2023-04-05 11:59:41,888 ----------------------------------------------------------------------------------------------------
2023-04-05 11:59:43,880 epoch 99 - iter 28/280 - loss 0.01176522 - time (sec): 1.99 - samples/sec: 10856.36 - lr: 0.025000
2023-04-05 11:59:45,761 epoch 99 - iter 56/280 - loss 0.01315236 - time (sec): 3.87 - samples/sec: 11139.64 - lr: 0.025000
2023-04-05 11:59:47,624 epoch 99 - iter 84/280 - loss 0.01235075 - time (sec): 5.74 - samples/sec: 11247.26 - lr: 0.025000
2023-04-05 11:59:49,515 epoch 99 - iter 112/280 - loss 0.01212767 - time (sec): 7.63 - samples/sec: 11259.55 - lr: 0.025000
2023-04-05 11:59:51,353 epoch 99 - iter 140/280 - loss 0.01228047 - time (sec): 9.47 - samples/sec: 11299.51 - lr: 0.025000
2023-04-05 11:59:53,274 epoch 99 - iter 168/280 - loss 0.01242161 - time (sec): 11.39 - samples/sec: 11274.86 - lr: 0.025000
2023-04-05 11:59:55,189 epoch 99 - iter 196/280 - loss 0.01266913 - time (sec): 13.30 - samples/sec: 11248.91 - lr: 0.025000
2023-04-05 11:59:56,965 epoch 99 - iter 224/280 - loss 0.01254593 - time (sec): 15.08 - samples/sec: 11301.78 - lr: 0.025000
2023-04-05 11:59:58,855 epoch 99 - iter 252/280 - loss 0.01243269 - time (sec): 16.97 - samples/sec: 11271.37 - lr: 0.025000
2023-04-05 12:00:00,671 epoch 99 - iter 280/280 - loss 0.01232332 - time (sec): 18.78 - samples/sec: 11270.19 - lr: 0.025000
2023-04-05 12:00:00,671 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:00,671 EPOCH 99 done: loss 0.0123 - lr 0.025000
2023-04-05 12:00:00,671 BAD EPOCHS (no improvement): 0
2023-04-05 12:00:00,674 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:02,532 epoch 100 - iter 28/280 - loss 0.01143486 - time (sec): 1.86 - samples/sec: 11545.19 - lr: 0.025000
2023-04-05 12:00:04,338 epoch 100 - iter 56/280 - loss 0.01152210 - time (sec): 3.66 - samples/sec: 11645.44 - lr: 0.025000
2023-04-05 12:00:06,075 epoch 100 - iter 84/280 - loss 0.01132415 - time (sec): 5.40 - samples/sec: 11682.82 - lr: 0.025000
2023-04-05 12:00:07,898 epoch 100 - iter 112/280 - loss 0.01208818 - time (sec): 7.22 - samples/sec: 11643.74 - lr: 0.025000
2023-04-05 12:00:09,729 epoch 100 - iter 140/280 - loss 0.01216301 - time (sec): 9.06 - samples/sec: 11663.72 - lr: 0.025000
2023-04-05 12:00:11,524 epoch 100 - iter 168/280 - loss 0.01227385 - time (sec): 10.85 - samples/sec: 11689.04 - lr: 0.025000
2023-04-05 12:00:13,346 epoch 100 - iter 196/280 - loss 0.01225736 - time (sec): 12.67 - samples/sec: 11694.77 - lr: 0.025000
2023-04-05 12:00:15,216 epoch 100 - iter 224/280 - loss 0.01244240 - time (sec): 14.54 - samples/sec: 11652.84 - lr: 0.025000
2023-04-05 12:00:17,039 epoch 100 - iter 252/280 - loss 0.01243366 - time (sec): 16.36 - samples/sec: 11649.45 - lr: 0.025000
2023-04-05 12:00:18,857 epoch 100 - iter 280/280 - loss 0.01273108 - time (sec): 18.18 - samples/sec: 11642.16 - lr: 0.025000
2023-04-05 12:00:18,857 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:18,857 EPOCH 100 done: loss 0.0127 - lr 0.025000
2023-04-05 12:00:18,857 BAD EPOCHS (no improvement): 1
2023-04-05 12:00:18,860 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:20,726 epoch 101 - iter 28/280 - loss 0.01064416 - time (sec): 1.87 - samples/sec: 11505.15 - lr: 0.025000
2023-04-05 12:00:22,561 epoch 101 - iter 56/280 - loss 0.01216237 - time (sec): 3.70 - samples/sec: 11553.91 - lr: 0.025000
2023-04-05 12:00:24,399 epoch 101 - iter 84/280 - loss 0.01223580 - time (sec): 5.54 - samples/sec: 11592.08 - lr: 0.025000
2023-04-05 12:00:26,214 epoch 101 - iter 112/280 - loss 0.01261770 - time (sec): 7.35 - samples/sec: 11645.73 - lr: 0.025000
2023-04-05 12:00:28,062 epoch 101 - iter 140/280 - loss 0.01236011 - time (sec): 9.20 - samples/sec: 11589.76 - lr: 0.025000
2023-04-05 12:00:29,927 epoch 101 - iter 168/280 - loss 0.01186516 - time (sec): 11.07 - samples/sec: 11567.81 - lr: 0.025000
2023-04-05 12:00:31,731 epoch 101 - iter 196/280 - loss 0.01207753 - time (sec): 12.87 - samples/sec: 11571.43 - lr: 0.025000
2023-04-05 12:00:33,524 epoch 101 - iter 224/280 - loss 0.01211180 - time (sec): 14.66 - samples/sec: 11589.93 - lr: 0.025000
2023-04-05 12:00:35,330 epoch 101 - iter 252/280 - loss 0.01234716 - time (sec): 16.47 - samples/sec: 11601.29 - lr: 0.025000
2023-04-05 12:00:37,148 epoch 101 - iter 280/280 - loss 0.01246501 - time (sec): 18.29 - samples/sec: 11575.50 - lr: 0.025000
2023-04-05 12:00:37,148 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:37,148 EPOCH 101 done: loss 0.0125 - lr 0.025000
2023-04-05 12:00:37,148 BAD EPOCHS (no improvement): 2
2023-04-05 12:00:37,150 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:38,907 epoch 102 - iter 28/280 - loss 0.01175589 - time (sec): 1.76 - samples/sec: 11839.45 - lr: 0.025000
2023-04-05 12:00:40,738 epoch 102 - iter 56/280 - loss 0.01227038 - time (sec): 3.59 - samples/sec: 11906.64 - lr: 0.025000
2023-04-05 12:00:42,542 epoch 102 - iter 84/280 - loss 0.01149028 - time (sec): 5.39 - samples/sec: 11840.73 - lr: 0.025000
2023-04-05 12:00:44,382 epoch 102 - iter 112/280 - loss 0.01199075 - time (sec): 7.23 - samples/sec: 11806.54 - lr: 0.025000
2023-04-05 12:00:46,169 epoch 102 - iter 140/280 - loss 0.01196033 - time (sec): 9.02 - samples/sec: 11829.64 - lr: 0.025000
2023-04-05 12:00:47,998 epoch 102 - iter 168/280 - loss 0.01231761 - time (sec): 10.85 - samples/sec: 11816.82 - lr: 0.025000
2023-04-05 12:00:49,848 epoch 102 - iter 196/280 - loss 0.01233558 - time (sec): 12.70 - samples/sec: 11737.45 - lr: 0.025000
2023-04-05 12:00:51,696 epoch 102 - iter 224/280 - loss 0.01242845 - time (sec): 14.55 - samples/sec: 11704.63 - lr: 0.025000
2023-04-05 12:00:53,499 epoch 102 - iter 252/280 - loss 0.01275479 - time (sec): 16.35 - samples/sec: 11674.27 - lr: 0.025000
2023-04-05 12:00:55,317 epoch 102 - iter 280/280 - loss 0.01253303 - time (sec): 18.17 - samples/sec: 11653.01 - lr: 0.025000
2023-04-05 12:00:55,317 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:55,317 EPOCH 102 done: loss 0.0125 - lr 0.025000
2023-04-05 12:00:55,317 BAD EPOCHS (no improvement): 3
2023-04-05 12:00:55,319 ----------------------------------------------------------------------------------------------------
2023-04-05 12:00:57,196 epoch 103 - iter 28/280 - loss 0.01312249 - time (sec): 1.88 - samples/sec: 11709.39 - lr: 0.025000
2023-04-05 12:00:58,987 epoch 103 - iter 56/280 - loss 0.01392855 - time (sec): 3.67 - samples/sec: 11736.36 - lr: 0.025000
2023-04-05 12:01:00,816 epoch 103 - iter 84/280 - loss 0.01279326 - time (sec): 5.50 - samples/sec: 11721.00 - lr: 0.025000
2023-04-05 12:01:02,626 epoch 103 - iter 112/280 - loss 0.01272329 - time (sec): 7.31 - samples/sec: 11726.97 - lr: 0.025000
2023-04-05 12:01:04,446 epoch 103 - iter 140/280 - loss 0.01266934 - time (sec): 9.13 - samples/sec: 11702.48 - lr: 0.025000
2023-04-05 12:01:06,268 epoch 103 - iter 168/280 - loss 0.01252231 - time (sec): 10.95 - samples/sec: 11701.97 - lr: 0.025000
2023-04-05 12:01:08,054 epoch 103 - iter 196/280 - loss 0.01260058 - time (sec): 12.73 - samples/sec: 11727.38 - lr: 0.025000
2023-04-05 12:01:09,852 epoch 103 - iter 224/280 - loss 0.01247411 - time (sec): 14.53 - samples/sec: 11735.64 - lr: 0.025000
2023-04-05 12:01:11,633 epoch 103 - iter 252/280 - loss 0.01245813 - time (sec): 16.31 - samples/sec: 11710.52 - lr: 0.025000
2023-04-05 12:01:13,363 epoch 103 - iter 280/280 - loss 0.01242916 - time (sec): 18.04 - samples/sec: 11731.72 - lr: 0.025000
2023-04-05 12:01:13,364 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:13,364 EPOCH 103 done: loss 0.0124 - lr 0.025000
2023-04-05 12:01:13,364 Epoch 103: reducing learning rate of group 0 to 1.2500e-02.
2023-04-05 12:01:13,364 BAD EPOCHS (no improvement): 4
2023-04-05 12:01:13,367 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:15,219 epoch 104 - iter 28/280 - loss 0.01325120 - time (sec): 1.85 - samples/sec: 11664.70 - lr: 0.012500
2023-04-05 12:01:16,990 epoch 104 - iter 56/280 - loss 0.01314208 - time (sec): 3.62 - samples/sec: 11896.00 - lr: 0.012500
2023-04-05 12:01:18,736 epoch 104 - iter 84/280 - loss 0.01341299 - time (sec): 5.37 - samples/sec: 11952.69 - lr: 0.012500
2023-04-05 12:01:20,566 epoch 104 - iter 112/280 - loss 0.01338248 - time (sec): 7.20 - samples/sec: 11862.63 - lr: 0.012500
2023-04-05 12:01:23,736 epoch 104 - iter 140/280 - loss 0.01333953 - time (sec): 10.37 - samples/sec: 10305.11 - lr: 0.012500
2023-04-05 12:01:25,519 epoch 104 - iter 168/280 - loss 0.01330268 - time (sec): 12.15 - samples/sec: 10544.37 - lr: 0.012500
2023-04-05 12:01:27,325 epoch 104 - iter 196/280 - loss 0.01334608 - time (sec): 13.96 - samples/sec: 10707.07 - lr: 0.012500
2023-04-05 12:01:29,127 epoch 104 - iter 224/280 - loss 0.01333539 - time (sec): 15.76 - samples/sec: 10811.34 - lr: 0.012500
2023-04-05 12:01:30,920 epoch 104 - iter 252/280 - loss 0.01331231 - time (sec): 17.55 - samples/sec: 10890.04 - lr: 0.012500
2023-04-05 12:01:32,684 epoch 104 - iter 280/280 - loss 0.01321725 - time (sec): 19.32 - samples/sec: 10959.28 - lr: 0.012500
2023-04-05 12:01:32,684 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:32,684 EPOCH 104 done: loss 0.0132 - lr 0.012500
2023-04-05 12:01:32,684 BAD EPOCHS (no improvement): 1
2023-04-05 12:01:32,688 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:34,470 epoch 105 - iter 28/280 - loss 0.01184693 - time (sec): 1.78 - samples/sec: 11911.85 - lr: 0.012500
2023-04-05 12:01:36,318 epoch 105 - iter 56/280 - loss 0.01250167 - time (sec): 3.63 - samples/sec: 11722.62 - lr: 0.012500
2023-04-05 12:01:38,114 epoch 105 - iter 84/280 - loss 0.01274954 - time (sec): 5.43 - samples/sec: 11721.60 - lr: 0.012500
2023-04-05 12:01:39,879 epoch 105 - iter 112/280 - loss 0.01257985 - time (sec): 7.19 - samples/sec: 11736.39 - lr: 0.012500
2023-04-05 12:01:41,701 epoch 105 - iter 140/280 - loss 0.01271745 - time (sec): 9.01 - samples/sec: 11707.65 - lr: 0.012500
2023-04-05 12:01:43,496 epoch 105 - iter 168/280 - loss 0.01254130 - time (sec): 10.81 - samples/sec: 11745.81 - lr: 0.012500
2023-04-05 12:01:45,222 epoch 105 - iter 196/280 - loss 0.01260218 - time (sec): 12.53 - samples/sec: 11767.51 - lr: 0.012500
2023-04-05 12:01:47,005 epoch 105 - iter 224/280 - loss 0.01237941 - time (sec): 14.32 - samples/sec: 11787.04 - lr: 0.012500
2023-04-05 12:01:48,892 epoch 105 - iter 252/280 - loss 0.01213090 - time (sec): 16.20 - samples/sec: 11778.57 - lr: 0.012500
2023-04-05 12:01:50,670 epoch 105 - iter 280/280 - loss 0.01227421 - time (sec): 17.98 - samples/sec: 11772.11 - lr: 0.012500
2023-04-05 12:01:50,670 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:50,670 EPOCH 105 done: loss 0.0123 - lr 0.012500
2023-04-05 12:01:50,670 BAD EPOCHS (no improvement): 0
2023-04-05 12:01:50,673 ----------------------------------------------------------------------------------------------------
2023-04-05 12:01:52,499 epoch 106 - iter 28/280 - loss 0.01243735 - time (sec): 1.83 - samples/sec: 11736.66 - lr: 0.012500
2023-04-05 12:01:54,325 epoch 106 - iter 56/280 - loss 0.01150349 - time (sec): 3.65 - samples/sec: 11705.56 - lr: 0.012500
2023-04-05 12:01:56,092 epoch 106 - iter 84/280 - loss 0.01135112 - time (sec): 5.42 - samples/sec: 11713.03 - lr: 0.012500
2023-04-05 12:01:57,822 epoch 106 - iter 112/280 - loss 0.01181898 - time (sec): 7.15 - samples/sec: 11767.41 - lr: 0.012500
2023-04-05 12:01:59,637 epoch 106 - iter 140/280 - loss 0.01195970 - time (sec): 8.96 - samples/sec: 11727.78 - lr: 0.012500
2023-04-05 12:02:01,489 epoch 106 - iter 168/280 - loss 0.01234897 - time (sec): 10.82 - samples/sec: 11699.64 - lr: 0.012500
2023-04-05 12:02:03,298 epoch 106 - iter 196/280 - loss 0.01206787 - time (sec): 12.62 - samples/sec: 11699.56 - lr: 0.012500
2023-04-05 12:02:05,105 epoch 106 - iter 224/280 - loss 0.01223198 - time (sec): 14.43 - samples/sec: 11730.95 - lr: 0.012500
2023-04-05 12:02:06,937 epoch 106 - iter 252/280 - loss 0.01218783 - time (sec): 16.26 - samples/sec: 11738.87 - lr: 0.012500
2023-04-05 12:02:08,730 epoch 106 - iter 280/280 - loss 0.01217398 - time (sec): 18.06 - samples/sec: 11723.78 - lr: 0.012500
2023-04-05 12:02:08,730 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:08,730 EPOCH 106 done: loss 0.0122 - lr 0.012500
2023-04-05 12:02:08,730 BAD EPOCHS (no improvement): 0
2023-04-05 12:02:08,733 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:10,544 epoch 107 - iter 28/280 - loss 0.00966760 - time (sec): 1.81 - samples/sec: 11610.81 - lr: 0.012500
2023-04-05 12:02:12,352 epoch 107 - iter 56/280 - loss 0.01036859 - time (sec): 3.62 - samples/sec: 11627.53 - lr: 0.012500
2023-04-05 12:02:14,211 epoch 107 - iter 84/280 - loss 0.01102592 - time (sec): 5.48 - samples/sec: 11639.72 - lr: 0.012500
2023-04-05 12:02:16,087 epoch 107 - iter 112/280 - loss 0.01157287 - time (sec): 7.35 - samples/sec: 11600.81 - lr: 0.012500
2023-04-05 12:02:17,921 epoch 107 - iter 140/280 - loss 0.01170176 - time (sec): 9.19 - samples/sec: 11582.30 - lr: 0.012500
2023-04-05 12:02:19,711 epoch 107 - iter 168/280 - loss 0.01196695 - time (sec): 10.98 - samples/sec: 11625.94 - lr: 0.012500
2023-04-05 12:02:21,455 epoch 107 - iter 196/280 - loss 0.01171626 - time (sec): 12.72 - samples/sec: 11693.30 - lr: 0.012500
2023-04-05 12:02:23,255 epoch 107 - iter 224/280 - loss 0.01159026 - time (sec): 14.52 - samples/sec: 11733.14 - lr: 0.012500
2023-04-05 12:02:25,037 epoch 107 - iter 252/280 - loss 0.01166948 - time (sec): 16.30 - samples/sec: 11748.86 - lr: 0.012500
2023-04-05 12:02:26,747 epoch 107 - iter 280/280 - loss 0.01169413 - time (sec): 18.01 - samples/sec: 11751.37 - lr: 0.012500
2023-04-05 12:02:26,747 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:26,748 EPOCH 107 done: loss 0.0117 - lr 0.012500
2023-04-05 12:02:26,748 BAD EPOCHS (no improvement): 0
2023-04-05 12:02:26,751 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:28,513 epoch 108 - iter 28/280 - loss 0.01332731 - time (sec): 1.76 - samples/sec: 11800.29 - lr: 0.012500
2023-04-05 12:02:30,356 epoch 108 - iter 56/280 - loss 0.01368120 - time (sec): 3.61 - samples/sec: 11732.28 - lr: 0.012500
2023-04-05 12:02:32,145 epoch 108 - iter 84/280 - loss 0.01348220 - time (sec): 5.39 - samples/sec: 11826.82 - lr: 0.012500
2023-04-05 12:02:33,909 epoch 108 - iter 112/280 - loss 0.01343601 - time (sec): 7.16 - samples/sec: 11904.02 - lr: 0.012500
2023-04-05 12:02:35,627 epoch 108 - iter 140/280 - loss 0.01299514 - time (sec): 8.88 - samples/sec: 11952.62 - lr: 0.012500
2023-04-05 12:02:37,472 epoch 108 - iter 168/280 - loss 0.01273404 - time (sec): 10.72 - samples/sec: 11866.41 - lr: 0.012500
2023-04-05 12:02:39,256 epoch 108 - iter 196/280 - loss 0.01275609 - time (sec): 12.51 - samples/sec: 11847.86 - lr: 0.012500
2023-04-05 12:02:41,058 epoch 108 - iter 224/280 - loss 0.01288186 - time (sec): 14.31 - samples/sec: 11859.81 - lr: 0.012500
2023-04-05 12:02:42,853 epoch 108 - iter 252/280 - loss 0.01292018 - time (sec): 16.10 - samples/sec: 11839.18 - lr: 0.012500
2023-04-05 12:02:44,713 epoch 108 - iter 280/280 - loss 0.01281842 - time (sec): 17.96 - samples/sec: 11785.46 - lr: 0.012500
2023-04-05 12:02:44,713 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:44,713 EPOCH 108 done: loss 0.0128 - lr 0.012500
2023-04-05 12:02:44,713 BAD EPOCHS (no improvement): 1
2023-04-05 12:02:44,716 ----------------------------------------------------------------------------------------------------
2023-04-05 12:02:46,526 epoch 109 - iter 28/280 - loss 0.01221772 - time (sec): 1.81 - samples/sec: 11715.75 - lr: 0.012500
2023-04-05 12:02:48,293 epoch 109 - iter 56/280 - loss 0.01213670 - time (sec): 3.58 - samples/sec: 11852.56 - lr: 0.012500
2023-04-05 12:02:50,083 epoch 109 - iter 84/280 - loss 0.01232148 - time (sec): 5.37 - samples/sec: 11813.92 - lr: 0.012500
2023-04-05 12:02:51,907 epoch 109 - iter 112/280 - loss 0.01273374 - time (sec): 7.19 - samples/sec: 11798.62 - lr: 0.012500
2023-04-05 12:02:53,672 epoch 109 - iter 140/280 - loss 0.01257894 - time (sec): 8.96 - samples/sec: 11793.12 - lr: 0.012500
2023-04-05 12:02:55,528 epoch 109 - iter 168/280 - loss 0.01228648 - time (sec): 10.81 - samples/sec: 11728.52 - lr: 0.012500
2023-04-05 12:02:57,385 epoch 109 - iter 196/280 - loss 0.01235073 - time (sec): 12.67 - samples/sec: 11704.66 - lr: 0.012500
2023-04-05 12:02:59,165 epoch 109 - iter 224/280 - loss 0.01212374 - time (sec): 14.45 - samples/sec: 11721.36 - lr: 0.012500
2023-04-05 12:03:00,962 epoch 109 - iter 252/280 - loss 0.01239836 - time (sec): 16.25 - samples/sec: 11748.10 - lr: 0.012500
2023-04-05 12:03:02,740 epoch 109 - iter 280/280 - loss 0.01249306 - time (sec): 18.02 - samples/sec: 11745.09 - lr: 0.012500
2023-04-05 12:03:02,740 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:02,740 EPOCH 109 done: loss 0.0125 - lr 0.012500
2023-04-05 12:03:02,740 BAD EPOCHS (no improvement): 2
2023-04-05 12:03:02,743 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:04,521 epoch 110 - iter 28/280 - loss 0.01119783 - time (sec): 1.78 - samples/sec: 12026.51 - lr: 0.012500
2023-04-05 12:03:06,399 epoch 110 - iter 56/280 - loss 0.01246821 - time (sec): 3.66 - samples/sec: 11706.71 - lr: 0.012500
2023-04-05 12:03:08,167 epoch 110 - iter 84/280 - loss 0.01210950 - time (sec): 5.42 - samples/sec: 11769.24 - lr: 0.012500
2023-04-05 12:03:10,048 epoch 110 - iter 112/280 - loss 0.01180829 - time (sec): 7.30 - samples/sec: 11766.28 - lr: 0.012500
2023-04-05 12:03:11,816 epoch 110 - iter 140/280 - loss 0.01164647 - time (sec): 9.07 - samples/sec: 11753.01 - lr: 0.012500
2023-04-05 12:03:13,571 epoch 110 - iter 168/280 - loss 0.01159105 - time (sec): 10.83 - samples/sec: 11785.45 - lr: 0.012500
2023-04-05 12:03:15,379 epoch 110 - iter 196/280 - loss 0.01157746 - time (sec): 12.64 - samples/sec: 11772.06 - lr: 0.012500
2023-04-05 12:03:17,182 epoch 110 - iter 224/280 - loss 0.01159648 - time (sec): 14.44 - samples/sec: 11731.97 - lr: 0.012500
2023-04-05 12:03:19,001 epoch 110 - iter 252/280 - loss 0.01175475 - time (sec): 16.26 - samples/sec: 11746.31 - lr: 0.012500
2023-04-05 12:03:20,782 epoch 110 - iter 280/280 - loss 0.01185925 - time (sec): 18.04 - samples/sec: 11735.04 - lr: 0.012500
2023-04-05 12:03:20,783 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:20,783 EPOCH 110 done: loss 0.0119 - lr 0.012500
2023-04-05 12:03:20,783 BAD EPOCHS (no improvement): 3
2023-04-05 12:03:20,786 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:22,562 epoch 111 - iter 28/280 - loss 0.00932374 - time (sec): 1.78 - samples/sec: 11883.94 - lr: 0.012500
2023-04-05 12:03:24,337 epoch 111 - iter 56/280 - loss 0.00998230 - time (sec): 3.55 - samples/sec: 11864.13 - lr: 0.012500
2023-04-05 12:03:26,183 epoch 111 - iter 84/280 - loss 0.01051739 - time (sec): 5.40 - samples/sec: 11747.17 - lr: 0.012500
2023-04-05 12:03:27,950 epoch 111 - iter 112/280 - loss 0.01113727 - time (sec): 7.16 - samples/sec: 11767.04 - lr: 0.012500
2023-04-05 12:03:29,760 epoch 111 - iter 140/280 - loss 0.01114099 - time (sec): 8.97 - samples/sec: 11735.88 - lr: 0.012500
2023-04-05 12:03:31,581 epoch 111 - iter 168/280 - loss 0.01113536 - time (sec): 10.79 - samples/sec: 11706.10 - lr: 0.012500
2023-04-05 12:03:33,425 epoch 111 - iter 196/280 - loss 0.01127911 - time (sec): 12.64 - samples/sec: 11711.74 - lr: 0.012500
2023-04-05 12:03:35,241 epoch 111 - iter 224/280 - loss 0.01115847 - time (sec): 14.45 - samples/sec: 11714.40 - lr: 0.012500
2023-04-05 12:03:37,039 epoch 111 - iter 252/280 - loss 0.01120779 - time (sec): 16.25 - samples/sec: 11722.32 - lr: 0.012500
2023-04-05 12:03:38,838 epoch 111 - iter 280/280 - loss 0.01119183 - time (sec): 18.05 - samples/sec: 11727.09 - lr: 0.012500
2023-04-05 12:03:38,838 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:38,838 EPOCH 111 done: loss 0.0112 - lr 0.012500
2023-04-05 12:03:38,838 BAD EPOCHS (no improvement): 0
2023-04-05 12:03:38,841 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:40,614 epoch 112 - iter 28/280 - loss 0.01096795 - time (sec): 1.77 - samples/sec: 11807.19 - lr: 0.012500
2023-04-05 12:03:42,418 epoch 112 - iter 56/280 - loss 0.01120031 - time (sec): 3.58 - samples/sec: 11774.51 - lr: 0.012500
2023-04-05 12:03:44,209 epoch 112 - iter 84/280 - loss 0.01132304 - time (sec): 5.37 - samples/sec: 11784.56 - lr: 0.012500
2023-04-05 12:03:46,047 epoch 112 - iter 112/280 - loss 0.01107989 - time (sec): 7.21 - samples/sec: 11809.03 - lr: 0.012500
2023-04-05 12:03:47,805 epoch 112 - iter 140/280 - loss 0.01158773 - time (sec): 8.96 - samples/sec: 11835.47 - lr: 0.012500
2023-04-05 12:03:49,563 epoch 112 - iter 168/280 - loss 0.01209611 - time (sec): 10.72 - samples/sec: 11872.48 - lr: 0.012500
2023-04-05 12:03:51,368 epoch 112 - iter 196/280 - loss 0.01185674 - time (sec): 12.53 - samples/sec: 11864.36 - lr: 0.012500
2023-04-05 12:03:53,140 epoch 112 - iter 224/280 - loss 0.01193868 - time (sec): 14.30 - samples/sec: 11866.13 - lr: 0.012500
2023-04-05 12:03:54,969 epoch 112 - iter 252/280 - loss 0.01196546 - time (sec): 16.13 - samples/sec: 11844.08 - lr: 0.012500
2023-04-05 12:03:56,716 epoch 112 - iter 280/280 - loss 0.01195998 - time (sec): 17.88 - samples/sec: 11842.70 - lr: 0.012500
2023-04-05 12:03:56,716 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:56,716 EPOCH 112 done: loss 0.0120 - lr 0.012500
2023-04-05 12:03:56,716 BAD EPOCHS (no improvement): 1
2023-04-05 12:03:56,719 ----------------------------------------------------------------------------------------------------
2023-04-05 12:03:58,460 epoch 113 - iter 28/280 - loss 0.01157594 - time (sec): 1.74 - samples/sec: 12012.46 - lr: 0.012500
2023-04-05 12:04:00,317 epoch 113 - iter 56/280 - loss 0.01179186 - time (sec): 3.60 - samples/sec: 11724.88 - lr: 0.012500
2023-04-05 12:04:02,111 epoch 113 - iter 84/280 - loss 0.01195041 - time (sec): 5.39 - samples/sec: 11740.98 - lr: 0.012500
2023-04-05 12:04:03,887 epoch 113 - iter 112/280 - loss 0.01163289 - time (sec): 7.17 - samples/sec: 11831.13 - lr: 0.012500
2023-04-05 12:04:05,668 epoch 113 - iter 140/280 - loss 0.01114858 - time (sec): 8.95 - samples/sec: 11783.27 - lr: 0.012500
2023-04-05 12:04:07,514 epoch 113 - iter 168/280 - loss 0.01094912 - time (sec): 10.79 - samples/sec: 11724.88 - lr: 0.012500
2023-04-05 12:04:09,322 epoch 113 - iter 196/280 - loss 0.01091043 - time (sec): 12.60 - samples/sec: 11738.78 - lr: 0.012500
2023-04-05 12:04:11,122 epoch 113 - iter 224/280 - loss 0.01115677 - time (sec): 14.40 - samples/sec: 11732.08 - lr: 0.012500
2023-04-05 12:04:12,977 epoch 113 - iter 252/280 - loss 0.01122948 - time (sec): 16.26 - samples/sec: 11740.58 - lr: 0.012500
2023-04-05 12:04:14,777 epoch 113 - iter 280/280 - loss 0.01120865 - time (sec): 18.06 - samples/sec: 11723.11 - lr: 0.012500
2023-04-05 12:04:14,777 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:14,777 EPOCH 113 done: loss 0.0112 - lr 0.012500
2023-04-05 12:04:14,777 BAD EPOCHS (no improvement): 2
2023-04-05 12:04:14,781 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:16,556 epoch 114 - iter 28/280 - loss 0.01050594 - time (sec): 1.77 - samples/sec: 11936.15 - lr: 0.012500
2023-04-05 12:04:18,396 epoch 114 - iter 56/280 - loss 0.01080374 - time (sec): 3.61 - samples/sec: 11894.31 - lr: 0.012500
2023-04-05 12:04:20,215 epoch 114 - iter 84/280 - loss 0.01074294 - time (sec): 5.43 - samples/sec: 11904.68 - lr: 0.012500
2023-04-05 12:04:22,026 epoch 114 - iter 112/280 - loss 0.01079174 - time (sec): 7.24 - samples/sec: 11831.46 - lr: 0.012500
2023-04-05 12:04:23,814 epoch 114 - iter 140/280 - loss 0.01113253 - time (sec): 9.03 - samples/sec: 11809.01 - lr: 0.012500
2023-04-05 12:04:25,572 epoch 114 - iter 168/280 - loss 0.01105838 - time (sec): 10.79 - samples/sec: 11863.87 - lr: 0.012500
2023-04-05 12:04:27,329 epoch 114 - iter 196/280 - loss 0.01093990 - time (sec): 12.55 - samples/sec: 11869.24 - lr: 0.012500
2023-04-05 12:04:29,128 epoch 114 - iter 224/280 - loss 0.01105410 - time (sec): 14.35 - samples/sec: 11884.77 - lr: 0.012500
2023-04-05 12:04:30,948 epoch 114 - iter 252/280 - loss 0.01113445 - time (sec): 16.17 - samples/sec: 11833.35 - lr: 0.012500
2023-04-05 12:04:32,699 epoch 114 - iter 280/280 - loss 0.01098837 - time (sec): 17.92 - samples/sec: 11814.63 - lr: 0.012500
2023-04-05 12:04:32,699 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:32,699 EPOCH 114 done: loss 0.0110 - lr 0.012500
2023-04-05 12:04:32,699 BAD EPOCHS (no improvement): 0
2023-04-05 12:04:32,702 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:34,476 epoch 115 - iter 28/280 - loss 0.01180769 - time (sec): 1.77 - samples/sec: 11863.89 - lr: 0.012500
2023-04-05 12:04:36,332 epoch 115 - iter 56/280 - loss 0.01208287 - time (sec): 3.63 - samples/sec: 11723.32 - lr: 0.012500
2023-04-05 12:04:38,187 epoch 115 - iter 84/280 - loss 0.01125099 - time (sec): 5.48 - samples/sec: 11680.61 - lr: 0.012500
2023-04-05 12:04:39,973 epoch 115 - iter 112/280 - loss 0.01111443 - time (sec): 7.27 - samples/sec: 11671.26 - lr: 0.012500
2023-04-05 12:04:41,843 epoch 115 - iter 140/280 - loss 0.01119981 - time (sec): 9.14 - samples/sec: 11643.05 - lr: 0.012500
2023-04-05 12:04:43,616 epoch 115 - iter 168/280 - loss 0.01097438 - time (sec): 10.91 - samples/sec: 11677.93 - lr: 0.012500
2023-04-05 12:04:45,372 epoch 115 - iter 196/280 - loss 0.01117566 - time (sec): 12.67 - samples/sec: 11708.73 - lr: 0.012500
2023-04-05 12:04:47,136 epoch 115 - iter 224/280 - loss 0.01101021 - time (sec): 14.43 - samples/sec: 11766.71 - lr: 0.012500
2023-04-05 12:04:48,926 epoch 115 - iter 252/280 - loss 0.01106010 - time (sec): 16.22 - samples/sec: 11763.58 - lr: 0.012500
2023-04-05 12:04:50,722 epoch 115 - iter 280/280 - loss 0.01128993 - time (sec): 18.02 - samples/sec: 11747.32 - lr: 0.012500
2023-04-05 12:04:50,723 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:50,723 EPOCH 115 done: loss 0.0113 - lr 0.012500
2023-04-05 12:04:50,723 BAD EPOCHS (no improvement): 1
2023-04-05 12:04:50,726 ----------------------------------------------------------------------------------------------------
2023-04-05 12:04:52,524 epoch 116 - iter 28/280 - loss 0.01201711 - time (sec): 1.80 - samples/sec: 11838.44 - lr: 0.012500
2023-04-05 12:04:54,348 epoch 116 - iter 56/280 - loss 0.01195113 - time (sec): 3.62 - samples/sec: 11888.07 - lr: 0.012500
2023-04-05 12:04:56,120 epoch 116 - iter 84/280 - loss 0.01229700 - time (sec): 5.39 - samples/sec: 11754.77 - lr: 0.012500
2023-04-05 12:04:57,929 epoch 116 - iter 112/280 - loss 0.01266103 - time (sec): 7.20 - samples/sec: 11757.47 - lr: 0.012500
2023-04-05 12:04:59,673 epoch 116 - iter 140/280 - loss 0.01228128 - time (sec): 8.95 - samples/sec: 11792.36 - lr: 0.012500
2023-04-05 12:05:01,368 epoch 116 - iter 168/280 - loss 0.01205380 - time (sec): 10.64 - samples/sec: 11874.68 - lr: 0.012500
2023-04-05 12:05:03,142 epoch 116 - iter 196/280 - loss 0.01178919 - time (sec): 12.42 - samples/sec: 11865.73 - lr: 0.012500
2023-04-05 12:05:05,005 epoch 116 - iter 224/280 - loss 0.01191985 - time (sec): 14.28 - samples/sec: 11829.08 - lr: 0.012500
2023-04-05 12:05:06,859 epoch 116 - iter 252/280 - loss 0.01167624 - time (sec): 16.13 - samples/sec: 11845.23 - lr: 0.012500
2023-04-05 12:05:08,617 epoch 116 - iter 280/280 - loss 0.01177646 - time (sec): 17.89 - samples/sec: 11832.00 - lr: 0.012500
2023-04-05 12:05:08,617 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:08,617 EPOCH 116 done: loss 0.0118 - lr 0.012500
2023-04-05 12:05:08,617 BAD EPOCHS (no improvement): 2
2023-04-05 12:05:08,621 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:10,388 epoch 117 - iter 28/280 - loss 0.00996882 - time (sec): 1.77 - samples/sec: 11712.94 - lr: 0.012500
2023-04-05 12:05:12,170 epoch 117 - iter 56/280 - loss 0.00930017 - time (sec): 3.55 - samples/sec: 11788.39 - lr: 0.012500
2023-04-05 12:05:13,982 epoch 117 - iter 84/280 - loss 0.00931808 - time (sec): 5.36 - samples/sec: 11779.83 - lr: 0.012500
2023-04-05 12:05:15,838 epoch 117 - iter 112/280 - loss 0.00992919 - time (sec): 7.22 - samples/sec: 11745.63 - lr: 0.012500
2023-04-05 12:05:17,643 epoch 117 - iter 140/280 - loss 0.01002179 - time (sec): 9.02 - samples/sec: 11740.48 - lr: 0.012500
2023-04-05 12:05:19,466 epoch 117 - iter 168/280 - loss 0.01037592 - time (sec): 10.85 - samples/sec: 11721.72 - lr: 0.012500
2023-04-05 12:05:21,261 epoch 117 - iter 196/280 - loss 0.01042152 - time (sec): 12.64 - samples/sec: 11714.94 - lr: 0.012500
2023-04-05 12:05:23,089 epoch 117 - iter 224/280 - loss 0.01069902 - time (sec): 14.47 - samples/sec: 11711.95 - lr: 0.012500
2023-04-05 12:05:24,888 epoch 117 - iter 252/280 - loss 0.01090005 - time (sec): 16.27 - samples/sec: 11738.69 - lr: 0.012500
2023-04-05 12:05:26,630 epoch 117 - iter 280/280 - loss 0.01106367 - time (sec): 18.01 - samples/sec: 11754.58 - lr: 0.012500
2023-04-05 12:05:26,630 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:26,630 EPOCH 117 done: loss 0.0111 - lr 0.012500
2023-04-05 12:05:26,631 BAD EPOCHS (no improvement): 3
2023-04-05 12:05:26,633 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:28,473 epoch 118 - iter 28/280 - loss 0.01142009 - time (sec): 1.84 - samples/sec: 11795.93 - lr: 0.012500
2023-04-05 12:05:30,265 epoch 118 - iter 56/280 - loss 0.01209766 - time (sec): 3.63 - samples/sec: 11783.50 - lr: 0.012500
2023-04-05 12:05:32,084 epoch 118 - iter 84/280 - loss 0.01230989 - time (sec): 5.45 - samples/sec: 11715.80 - lr: 0.012500
2023-04-05 12:05:33,866 epoch 118 - iter 112/280 - loss 0.01210889 - time (sec): 7.23 - samples/sec: 11736.72 - lr: 0.012500
2023-04-05 12:05:35,684 epoch 118 - iter 140/280 - loss 0.01195205 - time (sec): 9.05 - samples/sec: 11758.87 - lr: 0.012500
2023-04-05 12:05:37,470 epoch 118 - iter 168/280 - loss 0.01186907 - time (sec): 10.84 - samples/sec: 11774.50 - lr: 0.012500
2023-04-05 12:05:39,221 epoch 118 - iter 196/280 - loss 0.01163592 - time (sec): 12.59 - samples/sec: 11827.94 - lr: 0.012500
2023-04-05 12:05:41,063 epoch 118 - iter 224/280 - loss 0.01144130 - time (sec): 14.43 - samples/sec: 11797.27 - lr: 0.012500
2023-04-05 12:05:42,865 epoch 118 - iter 252/280 - loss 0.01156138 - time (sec): 16.23 - samples/sec: 11776.38 - lr: 0.012500
2023-04-05 12:05:44,645 epoch 118 - iter 280/280 - loss 0.01160797 - time (sec): 18.01 - samples/sec: 11752.96 - lr: 0.012500
2023-04-05 12:05:44,645 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:44,645 EPOCH 118 done: loss 0.0116 - lr 0.012500
2023-04-05 12:05:44,645 Epoch 118: reducing learning rate of group 0 to 6.2500e-03.
2023-04-05 12:05:44,645 BAD EPOCHS (no improvement): 4
2023-04-05 12:05:44,649 ----------------------------------------------------------------------------------------------------
2023-04-05 12:05:46,437 epoch 119 - iter 28/280 - loss 0.01072948 - time (sec): 1.79 - samples/sec: 11858.91 - lr: 0.006250
2023-04-05 12:05:48,233 epoch 119 - iter 56/280 - loss 0.01086085 - time (sec): 3.58 - samples/sec: 11821.70 - lr: 0.006250
2023-04-05 12:05:50,070 epoch 119 - iter 84/280 - loss 0.01109623 - time (sec): 5.42 - samples/sec: 11686.65 - lr: 0.006250
2023-04-05 12:05:51,881 epoch 119 - iter 112/280 - loss 0.01119167 - time (sec): 7.23 - samples/sec: 11744.85 - lr: 0.006250
2023-04-05 12:05:53,684 epoch 119 - iter 140/280 - loss 0.01120795 - time (sec): 9.03 - samples/sec: 11743.84 - lr: 0.006250
2023-04-05 12:05:55,480 epoch 119 - iter 168/280 - loss 0.01147289 - time (sec): 10.83 - samples/sec: 11728.88 - lr: 0.006250
2023-04-05 12:05:57,342 epoch 119 - iter 196/280 - loss 0.01152869 - time (sec): 12.69 - samples/sec: 11701.64 - lr: 0.006250
2023-04-05 12:05:59,165 epoch 119 - iter 224/280 - loss 0.01130786 - time (sec): 14.52 - samples/sec: 11715.94 - lr: 0.006250
2023-04-05 12:06:01,002 epoch 119 - iter 252/280 - loss 0.01141347 - time (sec): 16.35 - samples/sec: 11704.26 - lr: 0.006250
2023-04-05 12:06:02,781 epoch 119 - iter 280/280 - loss 0.01141699 - time (sec): 18.13 - samples/sec: 11674.90 - lr: 0.006250
2023-04-05 12:06:02,781 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:02,781 EPOCH 119 done: loss 0.0114 - lr 0.006250
2023-04-05 12:06:02,781 BAD EPOCHS (no improvement): 1
2023-04-05 12:06:02,784 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:04,560 epoch 120 - iter 28/280 - loss 0.00945488 - time (sec): 1.78 - samples/sec: 11898.13 - lr: 0.006250
2023-04-05 12:06:06,323 epoch 120 - iter 56/280 - loss 0.00971431 - time (sec): 3.54 - samples/sec: 11829.85 - lr: 0.006250
2023-04-05 12:06:08,141 epoch 120 - iter 84/280 - loss 0.00981638 - time (sec): 5.36 - samples/sec: 11822.16 - lr: 0.006250
2023-04-05 12:06:09,946 epoch 120 - iter 112/280 - loss 0.01005684 - time (sec): 7.16 - samples/sec: 11788.18 - lr: 0.006250
2023-04-05 12:06:11,698 epoch 120 - iter 140/280 - loss 0.01074333 - time (sec): 8.91 - samples/sec: 11814.19 - lr: 0.006250
2023-04-05 12:06:13,505 epoch 120 - iter 168/280 - loss 0.01100882 - time (sec): 10.72 - samples/sec: 11799.01 - lr: 0.006250
2023-04-05 12:06:15,288 epoch 120 - iter 196/280 - loss 0.01140791 - time (sec): 12.50 - samples/sec: 11812.91 - lr: 0.006250
2023-04-05 12:06:17,122 epoch 120 - iter 224/280 - loss 0.01124203 - time (sec): 14.34 - samples/sec: 11800.92 - lr: 0.006250
2023-04-05 12:06:18,947 epoch 120 - iter 252/280 - loss 0.01122156 - time (sec): 16.16 - samples/sec: 11811.79 - lr: 0.006250
2023-04-05 12:06:20,737 epoch 120 - iter 280/280 - loss 0.01119354 - time (sec): 17.95 - samples/sec: 11791.53 - lr: 0.006250
2023-04-05 12:06:20,737 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:20,737 EPOCH 120 done: loss 0.0112 - lr 0.006250
2023-04-05 12:06:20,737 BAD EPOCHS (no improvement): 2
2023-04-05 12:06:20,739 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:22,522 epoch 121 - iter 28/280 - loss 0.01033663 - time (sec): 1.78 - samples/sec: 11819.15 - lr: 0.006250
2023-04-05 12:06:24,293 epoch 121 - iter 56/280 - loss 0.01057722 - time (sec): 3.55 - samples/sec: 11783.26 - lr: 0.006250
2023-04-05 12:06:26,140 epoch 121 - iter 84/280 - loss 0.01008745 - time (sec): 5.40 - samples/sec: 11687.21 - lr: 0.006250
2023-04-05 12:06:27,936 epoch 121 - iter 112/280 - loss 0.01089627 - time (sec): 7.20 - samples/sec: 11737.02 - lr: 0.006250
2023-04-05 12:06:29,772 epoch 121 - iter 140/280 - loss 0.01118474 - time (sec): 9.03 - samples/sec: 11653.18 - lr: 0.006250
2023-04-05 12:06:31,570 epoch 121 - iter 168/280 - loss 0.01108994 - time (sec): 10.83 - samples/sec: 11688.94 - lr: 0.006250
2023-04-05 12:06:33,414 epoch 121 - iter 196/280 - loss 0.01100477 - time (sec): 12.67 - samples/sec: 11700.45 - lr: 0.006250
2023-04-05 12:06:35,260 epoch 121 - iter 224/280 - loss 0.01093386 - time (sec): 14.52 - samples/sec: 11692.20 - lr: 0.006250
2023-04-05 12:06:37,050 epoch 121 - iter 252/280 - loss 0.01093211 - time (sec): 16.31 - samples/sec: 11691.14 - lr: 0.006250
2023-04-05 12:06:38,865 epoch 121 - iter 280/280 - loss 0.01094855 - time (sec): 18.13 - samples/sec: 11679.37 - lr: 0.006250
2023-04-05 12:06:38,865 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:38,865 EPOCH 121 done: loss 0.0109 - lr 0.006250
2023-04-05 12:06:38,865 BAD EPOCHS (no improvement): 0
2023-04-05 12:06:38,868 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:40,669 epoch 122 - iter 28/280 - loss 0.01129554 - time (sec): 1.80 - samples/sec: 11761.16 - lr: 0.006250
2023-04-05 12:06:42,416 epoch 122 - iter 56/280 - loss 0.01067775 - time (sec): 3.55 - samples/sec: 11844.17 - lr: 0.006250
2023-04-05 12:06:44,213 epoch 122 - iter 84/280 - loss 0.01070966 - time (sec): 5.35 - samples/sec: 11890.69 - lr: 0.006250
2023-04-05 12:06:46,030 epoch 122 - iter 112/280 - loss 0.01083069 - time (sec): 7.16 - samples/sec: 11858.14 - lr: 0.006250
2023-04-05 12:06:47,781 epoch 122 - iter 140/280 - loss 0.01059356 - time (sec): 8.91 - samples/sec: 11870.82 - lr: 0.006250
2023-04-05 12:06:49,601 epoch 122 - iter 168/280 - loss 0.01064965 - time (sec): 10.73 - samples/sec: 11847.89 - lr: 0.006250
2023-04-05 12:06:51,369 epoch 122 - iter 196/280 - loss 0.01045740 - time (sec): 12.50 - samples/sec: 11844.57 - lr: 0.006250
2023-04-05 12:06:53,204 epoch 122 - iter 224/280 - loss 0.01055529 - time (sec): 14.34 - samples/sec: 11860.11 - lr: 0.006250
2023-04-05 12:06:54,998 epoch 122 - iter 252/280 - loss 0.01048694 - time (sec): 16.13 - samples/sec: 11837.60 - lr: 0.006250
2023-04-05 12:06:56,771 epoch 122 - iter 280/280 - loss 0.01055719 - time (sec): 17.90 - samples/sec: 11824.56 - lr: 0.006250
2023-04-05 12:06:56,771 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:56,771 EPOCH 122 done: loss 0.0106 - lr 0.006250
2023-04-05 12:06:56,771 BAD EPOCHS (no improvement): 0
2023-04-05 12:06:56,773 ----------------------------------------------------------------------------------------------------
2023-04-05 12:06:58,561 epoch 123 - iter 28/280 - loss 0.01270939 - time (sec): 1.79 - samples/sec: 11945.11 - lr: 0.006250
2023-04-05 12:07:00,407 epoch 123 - iter 56/280 - loss 0.01133282 - time (sec): 3.63 - samples/sec: 11820.25 - lr: 0.006250
2023-04-05 12:07:02,244 epoch 123 - iter 84/280 - loss 0.01121898 - time (sec): 5.47 - samples/sec: 11727.54 - lr: 0.006250
2023-04-05 12:07:04,085 epoch 123 - iter 112/280 - loss 0.01178266 - time (sec): 7.31 - samples/sec: 11705.65 - lr: 0.006250
2023-04-05 12:07:05,890 epoch 123 - iter 140/280 - loss 0.01141382 - time (sec): 9.12 - samples/sec: 11711.09 - lr: 0.006250
2023-04-05 12:07:07,696 epoch 123 - iter 168/280 - loss 0.01127287 - time (sec): 10.92 - samples/sec: 11742.17 - lr: 0.006250
2023-04-05 12:07:09,498 epoch 123 - iter 196/280 - loss 0.01110444 - time (sec): 12.72 - samples/sec: 11713.17 - lr: 0.006250
2023-04-05 12:07:11,320 epoch 123 - iter 224/280 - loss 0.01101400 - time (sec): 14.55 - samples/sec: 11689.55 - lr: 0.006250
2023-04-05 12:07:13,119 epoch 123 - iter 252/280 - loss 0.01096720 - time (sec): 16.35 - samples/sec: 11687.01 - lr: 0.006250
2023-04-05 12:07:14,939 epoch 123 - iter 280/280 - loss 0.01107961 - time (sec): 18.17 - samples/sec: 11653.42 - lr: 0.006250
2023-04-05 12:07:14,939 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:14,939 EPOCH 123 done: loss 0.0111 - lr 0.006250
2023-04-05 12:07:14,939 BAD EPOCHS (no improvement): 1
2023-04-05 12:07:14,941 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:16,682 epoch 124 - iter 28/280 - loss 0.01243923 - time (sec): 1.74 - samples/sec: 12054.38 - lr: 0.006250
2023-04-05 12:07:18,482 epoch 124 - iter 56/280 - loss 0.01128348 - time (sec): 3.54 - samples/sec: 11887.96 - lr: 0.006250
2023-04-05 12:07:20,259 epoch 124 - iter 84/280 - loss 0.01049447 - time (sec): 5.32 - samples/sec: 11877.55 - lr: 0.006250
2023-04-05 12:07:22,079 epoch 124 - iter 112/280 - loss 0.01031175 - time (sec): 7.14 - samples/sec: 11815.06 - lr: 0.006250
2023-04-05 12:07:23,904 epoch 124 - iter 140/280 - loss 0.01028150 - time (sec): 8.96 - samples/sec: 11769.32 - lr: 0.006250
2023-04-05 12:07:25,688 epoch 124 - iter 168/280 - loss 0.01037011 - time (sec): 10.75 - samples/sec: 11833.37 - lr: 0.006250
2023-04-05 12:07:27,570 epoch 124 - iter 196/280 - loss 0.01047649 - time (sec): 12.63 - samples/sec: 11803.01 - lr: 0.006250
2023-04-05 12:07:29,378 epoch 124 - iter 224/280 - loss 0.01045159 - time (sec): 14.44 - samples/sec: 11799.64 - lr: 0.006250
2023-04-05 12:07:31,150 epoch 124 - iter 252/280 - loss 0.01054015 - time (sec): 16.21 - samples/sec: 11788.30 - lr: 0.006250
2023-04-05 12:07:32,930 epoch 124 - iter 280/280 - loss 0.01087892 - time (sec): 17.99 - samples/sec: 11768.33 - lr: 0.006250
2023-04-05 12:07:32,930 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:32,930 EPOCH 124 done: loss 0.0109 - lr 0.006250
2023-04-05 12:07:32,930 BAD EPOCHS (no improvement): 2
2023-04-05 12:07:32,932 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:34,736 epoch 125 - iter 28/280 - loss 0.01188909 - time (sec): 1.80 - samples/sec: 11815.06 - lr: 0.006250
2023-04-05 12:07:36,498 epoch 125 - iter 56/280 - loss 0.01194583 - time (sec): 3.57 - samples/sec: 11882.14 - lr: 0.006250
2023-04-05 12:07:38,268 epoch 125 - iter 84/280 - loss 0.01154589 - time (sec): 5.34 - samples/sec: 11868.19 - lr: 0.006250
2023-04-05 12:07:40,105 epoch 125 - iter 112/280 - loss 0.01142385 - time (sec): 7.17 - samples/sec: 11761.57 - lr: 0.006250
2023-04-05 12:07:41,871 epoch 125 - iter 140/280 - loss 0.01104290 - time (sec): 8.94 - samples/sec: 11770.61 - lr: 0.006250
2023-04-05 12:07:43,628 epoch 125 - iter 168/280 - loss 0.01102127 - time (sec): 10.70 - samples/sec: 11814.85 - lr: 0.006250
2023-04-05 12:07:45,488 epoch 125 - iter 196/280 - loss 0.01077312 - time (sec): 12.56 - samples/sec: 11788.28 - lr: 0.006250
2023-04-05 12:07:47,289 epoch 125 - iter 224/280 - loss 0.01078319 - time (sec): 14.36 - samples/sec: 11796.27 - lr: 0.006250
2023-04-05 12:07:49,158 epoch 125 - iter 252/280 - loss 0.01088515 - time (sec): 16.23 - samples/sec: 11783.05 - lr: 0.006250
2023-04-05 12:07:50,926 epoch 125 - iter 280/280 - loss 0.01080579 - time (sec): 17.99 - samples/sec: 11764.59 - lr: 0.006250
2023-04-05 12:07:50,927 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:50,927 EPOCH 125 done: loss 0.0108 - lr 0.006250
2023-04-05 12:07:50,927 BAD EPOCHS (no improvement): 3
2023-04-05 12:07:50,929 ----------------------------------------------------------------------------------------------------
2023-04-05 12:07:52,764 epoch 126 - iter 28/280 - loss 0.01145382 - time (sec): 1.83 - samples/sec: 11547.67 - lr: 0.006250
2023-04-05 12:07:54,543 epoch 126 - iter 56/280 - loss 0.01033521 - time (sec): 3.61 - samples/sec: 11659.67 - lr: 0.006250
2023-04-05 12:07:56,342 epoch 126 - iter 84/280 - loss 0.01060870 - time (sec): 5.41 - samples/sec: 11789.53 - lr: 0.006250
2023-04-05 12:07:58,114 epoch 126 - iter 112/280 - loss 0.01068080 - time (sec): 7.18 - samples/sec: 11822.28 - lr: 0.006250
2023-04-05 12:07:59,948 epoch 126 - iter 140/280 - loss 0.01013108 - time (sec): 9.02 - samples/sec: 11813.76 - lr: 0.006250
2023-04-05 12:08:01,720 epoch 126 - iter 168/280 - loss 0.01064802 - time (sec): 10.79 - samples/sec: 11799.91 - lr: 0.006250
2023-04-05 12:08:03,517 epoch 126 - iter 196/280 - loss 0.01073286 - time (sec): 12.59 - samples/sec: 11789.11 - lr: 0.006250
2023-04-05 12:08:05,317 epoch 126 - iter 224/280 - loss 0.01056839 - time (sec): 14.39 - samples/sec: 11806.15 - lr: 0.006250
2023-04-05 12:08:07,121 epoch 126 - iter 252/280 - loss 0.01080325 - time (sec): 16.19 - samples/sec: 11781.05 - lr: 0.006250
2023-04-05 12:08:08,887 epoch 126 - iter 280/280 - loss 0.01071723 - time (sec): 17.96 - samples/sec: 11788.67 - lr: 0.006250
2023-04-05 12:08:08,887 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:08,887 EPOCH 126 done: loss 0.0107 - lr 0.006250
2023-04-05 12:08:08,887 Epoch 126: reducing learning rate of group 0 to 3.1250e-03.
2023-04-05 12:08:08,887 BAD EPOCHS (no improvement): 4
2023-04-05 12:08:08,889 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:10,659 epoch 127 - iter 28/280 - loss 0.01096951 - time (sec): 1.77 - samples/sec: 11948.09 - lr: 0.003125
2023-04-05 12:08:12,444 epoch 127 - iter 56/280 - loss 0.01132439 - time (sec): 3.55 - samples/sec: 11913.84 - lr: 0.003125
2023-04-05 12:08:14,247 epoch 127 - iter 84/280 - loss 0.01073329 - time (sec): 5.36 - samples/sec: 11825.17 - lr: 0.003125
2023-04-05 12:08:16,141 epoch 127 - iter 112/280 - loss 0.01077826 - time (sec): 7.25 - samples/sec: 11719.21 - lr: 0.003125
2023-04-05 12:08:17,911 epoch 127 - iter 140/280 - loss 0.01072616 - time (sec): 9.02 - samples/sec: 11727.39 - lr: 0.003125
2023-04-05 12:08:19,754 epoch 127 - iter 168/280 - loss 0.01064664 - time (sec): 10.86 - samples/sec: 11716.51 - lr: 0.003125
2023-04-05 12:08:21,583 epoch 127 - iter 196/280 - loss 0.01049034 - time (sec): 12.69 - samples/sec: 11683.88 - lr: 0.003125
2023-04-05 12:08:24,830 epoch 127 - iter 224/280 - loss 0.01039444 - time (sec): 15.94 - samples/sec: 10651.48 - lr: 0.003125
2023-04-05 12:08:26,661 epoch 127 - iter 252/280 - loss 0.01036164 - time (sec): 17.77 - samples/sec: 10764.89 - lr: 0.003125
2023-04-05 12:08:28,395 epoch 127 - iter 280/280 - loss 0.01047828 - time (sec): 19.51 - samples/sec: 10853.01 - lr: 0.003125
2023-04-05 12:08:28,395 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:28,395 EPOCH 127 done: loss 0.0105 - lr 0.003125
2023-04-05 12:08:28,395 BAD EPOCHS (no improvement): 0
2023-04-05 12:08:28,397 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:30,159 epoch 128 - iter 28/280 - loss 0.01152725 - time (sec): 1.76 - samples/sec: 11866.73 - lr: 0.003125
2023-04-05 12:08:31,957 epoch 128 - iter 56/280 - loss 0.01114723 - time (sec): 3.56 - samples/sec: 11831.14 - lr: 0.003125
2023-04-05 12:08:33,729 epoch 128 - iter 84/280 - loss 0.01110665 - time (sec): 5.33 - samples/sec: 11855.60 - lr: 0.003125
2023-04-05 12:08:35,500 epoch 128 - iter 112/280 - loss 0.01139838 - time (sec): 7.10 - samples/sec: 11873.57 - lr: 0.003125
2023-04-05 12:08:37,244 epoch 128 - iter 140/280 - loss 0.01118654 - time (sec): 8.85 - samples/sec: 11891.05 - lr: 0.003125
2023-04-05 12:08:39,063 epoch 128 - iter 168/280 - loss 0.01120441 - time (sec): 10.67 - samples/sec: 11859.54 - lr: 0.003125
2023-04-05 12:08:40,856 epoch 128 - iter 196/280 - loss 0.01100440 - time (sec): 12.46 - samples/sec: 11855.85 - lr: 0.003125
2023-04-05 12:08:42,713 epoch 128 - iter 224/280 - loss 0.01118472 - time (sec): 14.32 - samples/sec: 11846.22 - lr: 0.003125
2023-04-05 12:08:44,525 epoch 128 - iter 252/280 - loss 0.01128943 - time (sec): 16.13 - samples/sec: 11843.55 - lr: 0.003125
2023-04-05 12:08:46,293 epoch 128 - iter 280/280 - loss 0.01129446 - time (sec): 17.90 - samples/sec: 11829.52 - lr: 0.003125
2023-04-05 12:08:46,293 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:46,293 EPOCH 128 done: loss 0.0113 - lr 0.003125
2023-04-05 12:08:46,293 BAD EPOCHS (no improvement): 1
2023-04-05 12:08:46,296 ----------------------------------------------------------------------------------------------------
2023-04-05 12:08:48,078 epoch 129 - iter 28/280 - loss 0.01070158 - time (sec): 1.78 - samples/sec: 11630.10 - lr: 0.003125
2023-04-05 12:08:49,871 epoch 129 - iter 56/280 - loss 0.01145810 - time (sec): 3.58 - samples/sec: 11711.22 - lr: 0.003125
2023-04-05 12:08:51,684 epoch 129 - iter 84/280 - loss 0.01160917 - time (sec): 5.39 - samples/sec: 11685.24 - lr: 0.003125
2023-04-05 12:08:53,564 epoch 129 - iter 112/280 - loss 0.01163926 - time (sec): 7.27 - samples/sec: 11623.54 - lr: 0.003125
2023-04-05 12:08:55,380 epoch 129 - iter 140/280 - loss 0.01157989 - time (sec): 9.08 - samples/sec: 11677.40 - lr: 0.003125
2023-04-05 12:08:57,190 epoch 129 - iter 168/280 - loss 0.01142378 - time (sec): 10.89 - samples/sec: 11692.53 - lr: 0.003125
2023-04-05 12:08:59,047 epoch 129 - iter 196/280 - loss 0.01123575 - time (sec): 12.75 - samples/sec: 11686.76 - lr: 0.003125
2023-04-05 12:09:00,856 epoch 129 - iter 224/280 - loss 0.01114607 - time (sec): 14.56 - samples/sec: 11684.40 - lr: 0.003125
2023-04-05 12:09:02,665 epoch 129 - iter 252/280 - loss 0.01111714 - time (sec): 16.37 - samples/sec: 11683.62 - lr: 0.003125
2023-04-05 12:09:04,399 epoch 129 - iter 280/280 - loss 0.01119902 - time (sec): 18.10 - samples/sec: 11693.17 - lr: 0.003125
2023-04-05 12:09:04,400 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:04,400 EPOCH 129 done: loss 0.0112 - lr 0.003125
2023-04-05 12:09:04,400 BAD EPOCHS (no improvement): 2
2023-04-05 12:09:04,403 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:06,156 epoch 130 - iter 28/280 - loss 0.01159306 - time (sec): 1.75 - samples/sec: 12016.95 - lr: 0.003125
2023-04-05 12:09:07,986 epoch 130 - iter 56/280 - loss 0.01042453 - time (sec): 3.58 - samples/sec: 11828.27 - lr: 0.003125
2023-04-05 12:09:09,806 epoch 130 - iter 84/280 - loss 0.01032958 - time (sec): 5.40 - samples/sec: 11759.52 - lr: 0.003125
2023-04-05 12:09:11,653 epoch 130 - iter 112/280 - loss 0.01015716 - time (sec): 7.25 - samples/sec: 11788.63 - lr: 0.003125
2023-04-05 12:09:13,448 epoch 130 - iter 140/280 - loss 0.01064559 - time (sec): 9.05 - samples/sec: 11793.99 - lr: 0.003125
2023-04-05 12:09:15,257 epoch 130 - iter 168/280 - loss 0.01101038 - time (sec): 10.85 - samples/sec: 11798.32 - lr: 0.003125
2023-04-05 12:09:17,075 epoch 130 - iter 196/280 - loss 0.01096947 - time (sec): 12.67 - samples/sec: 11771.87 - lr: 0.003125
2023-04-05 12:09:18,816 epoch 130 - iter 224/280 - loss 0.01129876 - time (sec): 14.41 - samples/sec: 11773.27 - lr: 0.003125
2023-04-05 12:09:20,626 epoch 130 - iter 252/280 - loss 0.01117386 - time (sec): 16.22 - samples/sec: 11781.39 - lr: 0.003125
2023-04-05 12:09:22,355 epoch 130 - iter 280/280 - loss 0.01124787 - time (sec): 17.95 - samples/sec: 11792.03 - lr: 0.003125
2023-04-05 12:09:22,355 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:22,355 EPOCH 130 done: loss 0.0112 - lr 0.003125
2023-04-05 12:09:22,355 BAD EPOCHS (no improvement): 3
2023-04-05 12:09:22,357 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:24,098 epoch 131 - iter 28/280 - loss 0.01274766 - time (sec): 1.74 - samples/sec: 11732.26 - lr: 0.003125
2023-04-05 12:09:25,897 epoch 131 - iter 56/280 - loss 0.01297943 - time (sec): 3.54 - samples/sec: 11670.09 - lr: 0.003125
2023-04-05 12:09:27,746 epoch 131 - iter 84/280 - loss 0.01253925 - time (sec): 5.39 - samples/sec: 11597.76 - lr: 0.003125
2023-04-05 12:09:29,594 epoch 131 - iter 112/280 - loss 0.01193371 - time (sec): 7.24 - samples/sec: 11602.38 - lr: 0.003125
2023-04-05 12:09:31,404 epoch 131 - iter 140/280 - loss 0.01191074 - time (sec): 9.05 - samples/sec: 11628.14 - lr: 0.003125
2023-04-05 12:09:33,216 epoch 131 - iter 168/280 - loss 0.01164349 - time (sec): 10.86 - samples/sec: 11634.36 - lr: 0.003125
2023-04-05 12:09:35,012 epoch 131 - iter 196/280 - loss 0.01139492 - time (sec): 12.65 - samples/sec: 11674.63 - lr: 0.003125
2023-04-05 12:09:36,831 epoch 131 - iter 224/280 - loss 0.01118010 - time (sec): 14.47 - samples/sec: 11670.40 - lr: 0.003125
2023-04-05 12:09:38,696 epoch 131 - iter 252/280 - loss 0.01118353 - time (sec): 16.34 - samples/sec: 11675.20 - lr: 0.003125
2023-04-05 12:09:40,452 epoch 131 - iter 280/280 - loss 0.01105305 - time (sec): 18.10 - samples/sec: 11698.77 - lr: 0.003125
2023-04-05 12:09:40,453 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:40,453 EPOCH 131 done: loss 0.0111 - lr 0.003125
2023-04-05 12:09:40,453 Epoch 131: reducing learning rate of group 0 to 1.5625e-03.
2023-04-05 12:09:40,453 BAD EPOCHS (no improvement): 4
2023-04-05 12:09:40,458 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:42,228 epoch 132 - iter 28/280 - loss 0.00925874 - time (sec): 1.77 - samples/sec: 11817.55 - lr: 0.001563
2023-04-05 12:09:44,037 epoch 132 - iter 56/280 - loss 0.00938656 - time (sec): 3.58 - samples/sec: 11873.20 - lr: 0.001563
2023-04-05 12:09:45,822 epoch 132 - iter 84/280 - loss 0.00937389 - time (sec): 5.36 - samples/sec: 11856.89 - lr: 0.001563
2023-04-05 12:09:47,637 epoch 132 - iter 112/280 - loss 0.00983262 - time (sec): 7.18 - samples/sec: 11802.86 - lr: 0.001563
2023-04-05 12:09:49,484 epoch 132 - iter 140/280 - loss 0.00979822 - time (sec): 9.03 - samples/sec: 11726.72 - lr: 0.001563
2023-04-05 12:09:51,219 epoch 132 - iter 168/280 - loss 0.00966243 - time (sec): 10.76 - samples/sec: 11753.10 - lr: 0.001563
2023-04-05 12:09:53,028 epoch 132 - iter 196/280 - loss 0.01001616 - time (sec): 12.57 - samples/sec: 11783.12 - lr: 0.001563
2023-04-05 12:09:54,851 epoch 132 - iter 224/280 - loss 0.00998480 - time (sec): 14.39 - samples/sec: 11758.14 - lr: 0.001563
2023-04-05 12:09:56,666 epoch 132 - iter 252/280 - loss 0.01020045 - time (sec): 16.21 - samples/sec: 11783.30 - lr: 0.001563
2023-04-05 12:09:58,477 epoch 132 - iter 280/280 - loss 0.01028833 - time (sec): 18.02 - samples/sec: 11748.35 - lr: 0.001563
2023-04-05 12:09:58,477 ----------------------------------------------------------------------------------------------------
2023-04-05 12:09:58,477 EPOCH 132 done: loss 0.0103 - lr 0.001563
2023-04-05 12:09:58,477 BAD EPOCHS (no improvement): 0
2023-04-05 12:09:58,480 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:00,275 epoch 133 - iter 28/280 - loss 0.01116906 - time (sec): 1.80 - samples/sec: 11661.94 - lr: 0.001563
2023-04-05 12:10:02,094 epoch 133 - iter 56/280 - loss 0.01068663 - time (sec): 3.61 - samples/sec: 11637.17 - lr: 0.001563
2023-04-05 12:10:03,896 epoch 133 - iter 84/280 - loss 0.01087141 - time (sec): 5.42 - samples/sec: 11664.15 - lr: 0.001563
2023-04-05 12:10:05,714 epoch 133 - iter 112/280 - loss 0.01074603 - time (sec): 7.23 - samples/sec: 11690.49 - lr: 0.001563
2023-04-05 12:10:07,518 epoch 133 - iter 140/280 - loss 0.01085783 - time (sec): 9.04 - samples/sec: 11673.04 - lr: 0.001563
2023-04-05 12:10:09,280 epoch 133 - iter 168/280 - loss 0.01118264 - time (sec): 10.80 - samples/sec: 11706.96 - lr: 0.001563
2023-04-05 12:10:11,137 epoch 133 - iter 196/280 - loss 0.01105545 - time (sec): 12.66 - samples/sec: 11659.11 - lr: 0.001563
2023-04-05 12:10:13,012 epoch 133 - iter 224/280 - loss 0.01101671 - time (sec): 14.53 - samples/sec: 11690.15 - lr: 0.001563
2023-04-05 12:10:14,865 epoch 133 - iter 252/280 - loss 0.01071504 - time (sec): 16.38 - samples/sec: 11681.95 - lr: 0.001563
2023-04-05 12:10:16,610 epoch 133 - iter 280/280 - loss 0.01080132 - time (sec): 18.13 - samples/sec: 11676.19 - lr: 0.001563
2023-04-05 12:10:16,610 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:16,610 EPOCH 133 done: loss 0.0108 - lr 0.001563
2023-04-05 12:10:16,610 BAD EPOCHS (no improvement): 1
2023-04-05 12:10:16,613 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:18,441 epoch 134 - iter 28/280 - loss 0.01256331 - time (sec): 1.83 - samples/sec: 11730.61 - lr: 0.001563
2023-04-05 12:10:20,299 epoch 134 - iter 56/280 - loss 0.01177924 - time (sec): 3.69 - samples/sec: 11673.17 - lr: 0.001563
2023-04-05 12:10:22,095 epoch 134 - iter 84/280 - loss 0.01130821 - time (sec): 5.48 - samples/sec: 11696.07 - lr: 0.001563
2023-04-05 12:10:23,839 epoch 134 - iter 112/280 - loss 0.01116989 - time (sec): 7.23 - samples/sec: 11725.82 - lr: 0.001563
2023-04-05 12:10:25,652 epoch 134 - iter 140/280 - loss 0.01115525 - time (sec): 9.04 - samples/sec: 11688.71 - lr: 0.001563
2023-04-05 12:10:27,458 epoch 134 - iter 168/280 - loss 0.01134369 - time (sec): 10.84 - samples/sec: 11720.49 - lr: 0.001563
2023-04-05 12:10:29,235 epoch 134 - iter 196/280 - loss 0.01102286 - time (sec): 12.62 - samples/sec: 11703.48 - lr: 0.001563
2023-04-05 12:10:31,002 epoch 134 - iter 224/280 - loss 0.01081519 - time (sec): 14.39 - samples/sec: 11757.46 - lr: 0.001563
2023-04-05 12:10:32,820 epoch 134 - iter 252/280 - loss 0.01085078 - time (sec): 16.21 - samples/sec: 11777.45 - lr: 0.001563
2023-04-05 12:10:34,590 epoch 134 - iter 280/280 - loss 0.01078023 - time (sec): 17.98 - samples/sec: 11775.52 - lr: 0.001563
2023-04-05 12:10:34,591 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:34,591 EPOCH 134 done: loss 0.0108 - lr 0.001563
2023-04-05 12:10:34,591 BAD EPOCHS (no improvement): 2
2023-04-05 12:10:34,593 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:36,336 epoch 135 - iter 28/280 - loss 0.00972761 - time (sec): 1.74 - samples/sec: 12023.34 - lr: 0.001563
2023-04-05 12:10:38,135 epoch 135 - iter 56/280 - loss 0.00962745 - time (sec): 3.54 - samples/sec: 11873.25 - lr: 0.001563
2023-04-05 12:10:39,931 epoch 135 - iter 84/280 - loss 0.01074129 - time (sec): 5.34 - samples/sec: 11832.45 - lr: 0.001563
2023-04-05 12:10:41,739 epoch 135 - iter 112/280 - loss 0.01078364 - time (sec): 7.15 - samples/sec: 11812.60 - lr: 0.001563
2023-04-05 12:10:43,600 epoch 135 - iter 140/280 - loss 0.01101098 - time (sec): 9.01 - samples/sec: 11785.15 - lr: 0.001563
2023-04-05 12:10:45,350 epoch 135 - iter 168/280 - loss 0.01097219 - time (sec): 10.76 - samples/sec: 11777.43 - lr: 0.001563
2023-04-05 12:10:47,230 epoch 135 - iter 196/280 - loss 0.01070514 - time (sec): 12.64 - samples/sec: 11758.67 - lr: 0.001563
2023-04-05 12:10:49,034 epoch 135 - iter 224/280 - loss 0.01082599 - time (sec): 14.44 - samples/sec: 11770.89 - lr: 0.001563
2023-04-05 12:10:50,914 epoch 135 - iter 252/280 - loss 0.01092360 - time (sec): 16.32 - samples/sec: 11714.36 - lr: 0.001563
2023-04-05 12:10:52,671 epoch 135 - iter 280/280 - loss 0.01072125 - time (sec): 18.08 - samples/sec: 11709.46 - lr: 0.001563
2023-04-05 12:10:52,672 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:52,672 EPOCH 135 done: loss 0.0107 - lr 0.001563
2023-04-05 12:10:52,672 BAD EPOCHS (no improvement): 3
2023-04-05 12:10:52,674 ----------------------------------------------------------------------------------------------------
2023-04-05 12:10:54,467 epoch 136 - iter 28/280 - loss 0.01094650 - time (sec): 1.79 - samples/sec: 11686.32 - lr: 0.001563
2023-04-05 12:10:56,267 epoch 136 - iter 56/280 - loss 0.01005064 - time (sec): 3.59 - samples/sec: 11738.90 - lr: 0.001563
2023-04-05 12:10:58,060 epoch 136 - iter 84/280 - loss 0.01025726 - time (sec): 5.39 - samples/sec: 11799.17 - lr: 0.001563
2023-04-05 12:10:59,871 epoch 136 - iter 112/280 - loss 0.01065586 - time (sec): 7.20 - samples/sec: 11827.42 - lr: 0.001563
2023-04-05 12:11:01,678 epoch 136 - iter 140/280 - loss 0.01055461 - time (sec): 9.00 - samples/sec: 11803.89 - lr: 0.001563
2023-04-05 12:11:03,408 epoch 136 - iter 168/280 - loss 0.01069580 - time (sec): 10.73 - samples/sec: 11858.91 - lr: 0.001563
2023-04-05 12:11:05,227 epoch 136 - iter 196/280 - loss 0.01054740 - time (sec): 12.55 - samples/sec: 11805.86 - lr: 0.001563
2023-04-05 12:11:07,023 epoch 136 - iter 224/280 - loss 0.01031011 - time (sec): 14.35 - samples/sec: 11814.10 - lr: 0.001563
2023-04-05 12:11:08,820 epoch 136 - iter 252/280 - loss 0.01034674 - time (sec): 16.15 - samples/sec: 11830.00 - lr: 0.001563
2023-04-05 12:11:10,582 epoch 136 - iter 280/280 - loss 0.01036827 - time (sec): 17.91 - samples/sec: 11821.31 - lr: 0.001563
2023-04-05 12:11:10,582 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:10,582 EPOCH 136 done: loss 0.0104 - lr 0.001563
2023-04-05 12:11:10,582 Epoch 136: reducing learning rate of group 0 to 7.8125e-04.
2023-04-05 12:11:10,582 BAD EPOCHS (no improvement): 4
2023-04-05 12:11:10,585 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:12,345 epoch 137 - iter 28/280 - loss 0.01045206 - time (sec): 1.76 - samples/sec: 12024.67 - lr: 0.000781
2023-04-05 12:11:14,122 epoch 137 - iter 56/280 - loss 0.01010636 - time (sec): 3.54 - samples/sec: 12038.35 - lr: 0.000781
2023-04-05 12:11:15,977 epoch 137 - iter 84/280 - loss 0.01048397 - time (sec): 5.39 - samples/sec: 11884.62 - lr: 0.000781
2023-04-05 12:11:17,762 epoch 137 - iter 112/280 - loss 0.01078085 - time (sec): 7.18 - samples/sec: 11861.36 - lr: 0.000781
2023-04-05 12:11:19,548 epoch 137 - iter 140/280 - loss 0.01062931 - time (sec): 8.96 - samples/sec: 11867.66 - lr: 0.000781
2023-04-05 12:11:21,394 epoch 137 - iter 168/280 - loss 0.01044636 - time (sec): 10.81 - samples/sec: 11809.44 - lr: 0.000781
2023-04-05 12:11:23,173 epoch 137 - iter 196/280 - loss 0.01053905 - time (sec): 12.59 - samples/sec: 11782.60 - lr: 0.000781
2023-04-05 12:11:25,005 epoch 137 - iter 224/280 - loss 0.01034119 - time (sec): 14.42 - samples/sec: 11777.53 - lr: 0.000781
2023-04-05 12:11:26,804 epoch 137 - iter 252/280 - loss 0.01045793 - time (sec): 16.22 - samples/sec: 11781.42 - lr: 0.000781
2023-04-05 12:11:28,580 epoch 137 - iter 280/280 - loss 0.01028058 - time (sec): 18.00 - samples/sec: 11763.82 - lr: 0.000781
2023-04-05 12:11:28,581 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:28,581 EPOCH 137 done: loss 0.0103 - lr 0.000781
2023-04-05 12:11:28,581 BAD EPOCHS (no improvement): 0
2023-04-05 12:11:28,584 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:30,396 epoch 138 - iter 28/280 - loss 0.01084612 - time (sec): 1.81 - samples/sec: 11636.98 - lr: 0.000781
2023-04-05 12:11:32,201 epoch 138 - iter 56/280 - loss 0.01159855 - time (sec): 3.62 - samples/sec: 11659.29 - lr: 0.000781
2023-04-05 12:11:34,013 epoch 138 - iter 84/280 - loss 0.01204322 - time (sec): 5.43 - samples/sec: 11658.68 - lr: 0.000781
2023-04-05 12:11:35,813 epoch 138 - iter 112/280 - loss 0.01142015 - time (sec): 7.23 - samples/sec: 11642.86 - lr: 0.000781
2023-04-05 12:11:37,607 epoch 138 - iter 140/280 - loss 0.01136237 - time (sec): 9.02 - samples/sec: 11652.33 - lr: 0.000781
2023-04-05 12:11:39,366 epoch 138 - iter 168/280 - loss 0.01105023 - time (sec): 10.78 - samples/sec: 11731.09 - lr: 0.000781
2023-04-05 12:11:41,193 epoch 138 - iter 196/280 - loss 0.01119620 - time (sec): 12.61 - samples/sec: 11749.25 - lr: 0.000781
2023-04-05 12:11:42,983 epoch 138 - iter 224/280 - loss 0.01100213 - time (sec): 14.40 - samples/sec: 11791.58 - lr: 0.000781
2023-04-05 12:11:44,716 epoch 138 - iter 252/280 - loss 0.01097296 - time (sec): 16.13 - samples/sec: 11838.45 - lr: 0.000781
2023-04-05 12:11:46,456 epoch 138 - iter 280/280 - loss 0.01090239 - time (sec): 17.87 - samples/sec: 11845.03 - lr: 0.000781
2023-04-05 12:11:46,456 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:46,456 EPOCH 138 done: loss 0.0109 - lr 0.000781
2023-04-05 12:11:46,456 BAD EPOCHS (no improvement): 1
2023-04-05 12:11:46,458 ----------------------------------------------------------------------------------------------------
2023-04-05 12:11:48,230 epoch 139 - iter 28/280 - loss 0.00960729 - time (sec): 1.77 - samples/sec: 12200.58 - lr: 0.000781
2023-04-05 12:11:49,988 epoch 139 - iter 56/280 - loss 0.00982174 - time (sec): 3.53 - samples/sec: 12125.24 - lr: 0.000781
2023-04-05 12:11:51,812 epoch 139 - iter 84/280 - loss 0.01052495 - time (sec): 5.35 - samples/sec: 11985.15 - lr: 0.000781
2023-04-05 12:11:53,623 epoch 139 - iter 112/280 - loss 0.01039308 - time (sec): 7.16 - samples/sec: 11855.74 - lr: 0.000781
2023-04-05 12:11:55,416 epoch 139 - iter 140/280 - loss 0.01038677 - time (sec): 8.96 - samples/sec: 11816.64 - lr: 0.000781
2023-04-05 12:11:57,196 epoch 139 - iter 168/280 - loss 0.01008153 - time (sec): 10.74 - samples/sec: 11788.76 - lr: 0.000781
2023-04-05 12:11:58,957 epoch 139 - iter 196/280 - loss 0.00987411 - time (sec): 12.50 - samples/sec: 11810.43 - lr: 0.000781
2023-04-05 12:12:00,771 epoch 139 - iter 224/280 - loss 0.00989098 - time (sec): 14.31 - samples/sec: 11842.11 - lr: 0.000781
2023-04-05 12:12:02,633 epoch 139 - iter 252/280 - loss 0.00990100 - time (sec): 16.17 - samples/sec: 11812.85 - lr: 0.000781
2023-04-05 12:12:04,444 epoch 139 - iter 280/280 - loss 0.00999831 - time (sec): 17.99 - samples/sec: 11770.27 - lr: 0.000781
2023-04-05 12:12:04,444 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:04,444 EPOCH 139 done: loss 0.0100 - lr 0.000781
2023-04-05 12:12:04,444 BAD EPOCHS (no improvement): 0
2023-04-05 12:12:04,447 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:06,208 epoch 140 - iter 28/280 - loss 0.00909391 - time (sec): 1.76 - samples/sec: 11787.57 - lr: 0.000781
2023-04-05 12:12:07,977 epoch 140 - iter 56/280 - loss 0.00860290 - time (sec): 3.53 - samples/sec: 11857.21 - lr: 0.000781
2023-04-05 12:12:09,702 epoch 140 - iter 84/280 - loss 0.00902457 - time (sec): 5.26 - samples/sec: 11911.23 - lr: 0.000781
2023-04-05 12:12:11,526 epoch 140 - iter 112/280 - loss 0.00901790 - time (sec): 7.08 - samples/sec: 11870.37 - lr: 0.000781
2023-04-05 12:12:13,309 epoch 140 - iter 140/280 - loss 0.00961332 - time (sec): 8.86 - samples/sec: 11857.70 - lr: 0.000781
2023-04-05 12:12:15,110 epoch 140 - iter 168/280 - loss 0.00958585 - time (sec): 10.66 - samples/sec: 11885.90 - lr: 0.000781
2023-04-05 12:12:16,906 epoch 140 - iter 196/280 - loss 0.00973194 - time (sec): 12.46 - samples/sec: 11913.09 - lr: 0.000781
2023-04-05 12:12:18,671 epoch 140 - iter 224/280 - loss 0.01007258 - time (sec): 14.22 - samples/sec: 11922.65 - lr: 0.000781
2023-04-05 12:12:20,519 epoch 140 - iter 252/280 - loss 0.01018922 - time (sec): 16.07 - samples/sec: 11869.39 - lr: 0.000781
2023-04-05 12:12:22,307 epoch 140 - iter 280/280 - loss 0.01021125 - time (sec): 17.86 - samples/sec: 11852.94 - lr: 0.000781
2023-04-05 12:12:22,307 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:22,307 EPOCH 140 done: loss 0.0102 - lr 0.000781
2023-04-05 12:12:22,307 BAD EPOCHS (no improvement): 1
2023-04-05 12:12:22,309 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:24,035 epoch 141 - iter 28/280 - loss 0.01073215 - time (sec): 1.73 - samples/sec: 12004.33 - lr: 0.000781
2023-04-05 12:12:25,851 epoch 141 - iter 56/280 - loss 0.01000618 - time (sec): 3.54 - samples/sec: 11890.97 - lr: 0.000781
2023-04-05 12:12:27,636 epoch 141 - iter 84/280 - loss 0.00969786 - time (sec): 5.33 - samples/sec: 11873.27 - lr: 0.000781
2023-04-05 12:12:29,466 epoch 141 - iter 112/280 - loss 0.00987680 - time (sec): 7.16 - samples/sec: 11836.51 - lr: 0.000781
2023-04-05 12:12:31,312 epoch 141 - iter 140/280 - loss 0.00952684 - time (sec): 9.00 - samples/sec: 11825.34 - lr: 0.000781
2023-04-05 12:12:33,160 epoch 141 - iter 168/280 - loss 0.00988177 - time (sec): 10.85 - samples/sec: 11767.49 - lr: 0.000781
2023-04-05 12:12:35,024 epoch 141 - iter 196/280 - loss 0.01014547 - time (sec): 12.71 - samples/sec: 11735.81 - lr: 0.000781
2023-04-05 12:12:36,829 epoch 141 - iter 224/280 - loss 0.01039188 - time (sec): 14.52 - samples/sec: 11730.31 - lr: 0.000781
2023-04-05 12:12:38,605 epoch 141 - iter 252/280 - loss 0.01026791 - time (sec): 16.30 - samples/sec: 11726.45 - lr: 0.000781
2023-04-05 12:12:40,337 epoch 141 - iter 280/280 - loss 0.01022648 - time (sec): 18.03 - samples/sec: 11742.75 - lr: 0.000781
2023-04-05 12:12:40,337 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:40,337 EPOCH 141 done: loss 0.0102 - lr 0.000781
2023-04-05 12:12:40,337 BAD EPOCHS (no improvement): 2
2023-04-05 12:12:40,340 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:42,162 epoch 142 - iter 28/280 - loss 0.01213985 - time (sec): 1.82 - samples/sec: 11752.28 - lr: 0.000781
2023-04-05 12:12:43,935 epoch 142 - iter 56/280 - loss 0.01074658 - time (sec): 3.60 - samples/sec: 11757.81 - lr: 0.000781
2023-04-05 12:12:45,761 epoch 142 - iter 84/280 - loss 0.01102786 - time (sec): 5.42 - samples/sec: 11702.15 - lr: 0.000781
2023-04-05 12:12:47,579 epoch 142 - iter 112/280 - loss 0.01064194 - time (sec): 7.24 - samples/sec: 11733.84 - lr: 0.000781
2023-04-05 12:12:49,405 epoch 142 - iter 140/280 - loss 0.01066783 - time (sec): 9.07 - samples/sec: 11744.35 - lr: 0.000781
2023-04-05 12:12:51,161 epoch 142 - iter 168/280 - loss 0.01059697 - time (sec): 10.82 - samples/sec: 11788.87 - lr: 0.000781
2023-04-05 12:12:52,896 epoch 142 - iter 196/280 - loss 0.01059307 - time (sec): 12.56 - samples/sec: 11847.02 - lr: 0.000781
2023-04-05 12:12:54,721 epoch 142 - iter 224/280 - loss 0.01085592 - time (sec): 14.38 - samples/sec: 11829.15 - lr: 0.000781
2023-04-05 12:12:56,472 epoch 142 - iter 252/280 - loss 0.01093214 - time (sec): 16.13 - samples/sec: 11827.21 - lr: 0.000781
2023-04-05 12:12:58,278 epoch 142 - iter 280/280 - loss 0.01083253 - time (sec): 17.94 - samples/sec: 11801.29 - lr: 0.000781
2023-04-05 12:12:58,278 ----------------------------------------------------------------------------------------------------
2023-04-05 12:12:58,278 EPOCH 142 done: loss 0.0108 - lr 0.000781
2023-04-05 12:12:58,278 BAD EPOCHS (no improvement): 3
2023-04-05 12:12:58,281 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:00,123 epoch 143 - iter 28/280 - loss 0.01267777 - time (sec): 1.84 - samples/sec: 11608.54 - lr: 0.000781
2023-04-05 12:13:01,903 epoch 143 - iter 56/280 - loss 0.01178169 - time (sec): 3.62 - samples/sec: 11745.25 - lr: 0.000781
2023-04-05 12:13:03,730 epoch 143 - iter 84/280 - loss 0.01165349 - time (sec): 5.45 - samples/sec: 11810.74 - lr: 0.000781
2023-04-05 12:13:05,494 epoch 143 - iter 112/280 - loss 0.01065898 - time (sec): 7.21 - samples/sec: 11878.49 - lr: 0.000781
2023-04-05 12:13:07,299 epoch 143 - iter 140/280 - loss 0.01064630 - time (sec): 9.02 - samples/sec: 11866.61 - lr: 0.000781
2023-04-05 12:13:09,088 epoch 143 - iter 168/280 - loss 0.01063665 - time (sec): 10.81 - samples/sec: 11821.23 - lr: 0.000781
2023-04-05 12:13:10,855 epoch 143 - iter 196/280 - loss 0.01071972 - time (sec): 12.57 - samples/sec: 11816.67 - lr: 0.000781
2023-04-05 12:13:12,708 epoch 143 - iter 224/280 - loss 0.01059566 - time (sec): 14.43 - samples/sec: 11810.31 - lr: 0.000781
2023-04-05 12:13:14,537 epoch 143 - iter 252/280 - loss 0.01065342 - time (sec): 16.26 - samples/sec: 11776.92 - lr: 0.000781
2023-04-05 12:13:16,271 epoch 143 - iter 280/280 - loss 0.01066816 - time (sec): 17.99 - samples/sec: 11767.23 - lr: 0.000781
2023-04-05 12:13:16,271 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:16,271 EPOCH 143 done: loss 0.0107 - lr 0.000781
2023-04-05 12:13:16,271 Epoch 143: reducing learning rate of group 0 to 3.9063e-04.
2023-04-05 12:13:16,271 BAD EPOCHS (no improvement): 4
2023-04-05 12:13:16,274 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:18,126 epoch 144 - iter 28/280 - loss 0.01245578 - time (sec): 1.85 - samples/sec: 11673.38 - lr: 0.000391
2023-04-05 12:13:19,913 epoch 144 - iter 56/280 - loss 0.01096762 - time (sec): 3.64 - samples/sec: 11746.34 - lr: 0.000391
2023-04-05 12:13:21,717 epoch 144 - iter 84/280 - loss 0.01102028 - time (sec): 5.44 - samples/sec: 11778.04 - lr: 0.000391
2023-04-05 12:13:23,514 epoch 144 - iter 112/280 - loss 0.01081096 - time (sec): 7.24 - samples/sec: 11787.26 - lr: 0.000391
2023-04-05 12:13:25,308 epoch 144 - iter 140/280 - loss 0.01092085 - time (sec): 9.03 - samples/sec: 11757.57 - lr: 0.000391
2023-04-05 12:13:27,104 epoch 144 - iter 168/280 - loss 0.01081241 - time (sec): 10.83 - samples/sec: 11769.31 - lr: 0.000391
2023-04-05 12:13:28,872 epoch 144 - iter 196/280 - loss 0.01064821 - time (sec): 12.60 - samples/sec: 11784.91 - lr: 0.000391
2023-04-05 12:13:30,674 epoch 144 - iter 224/280 - loss 0.01064948 - time (sec): 14.40 - samples/sec: 11801.91 - lr: 0.000391
2023-04-05 12:13:32,473 epoch 144 - iter 252/280 - loss 0.01080856 - time (sec): 16.20 - samples/sec: 11782.90 - lr: 0.000391
2023-04-05 12:13:34,214 epoch 144 - iter 280/280 - loss 0.01081265 - time (sec): 17.94 - samples/sec: 11799.68 - lr: 0.000391
2023-04-05 12:13:34,215 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:34,215 EPOCH 144 done: loss 0.0108 - lr 0.000391
2023-04-05 12:13:34,215 BAD EPOCHS (no improvement): 1
2023-04-05 12:13:34,217 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:36,042 epoch 145 - iter 28/280 - loss 0.01026302 - time (sec): 1.82 - samples/sec: 11564.35 - lr: 0.000391
2023-04-05 12:13:37,829 epoch 145 - iter 56/280 - loss 0.01016126 - time (sec): 3.61 - samples/sec: 11710.48 - lr: 0.000391
2023-04-05 12:13:39,553 epoch 145 - iter 84/280 - loss 0.01030744 - time (sec): 5.34 - samples/sec: 11808.22 - lr: 0.000391
2023-04-05 12:13:41,333 epoch 145 - iter 112/280 - loss 0.01021951 - time (sec): 7.12 - samples/sec: 11848.26 - lr: 0.000391
2023-04-05 12:13:43,137 epoch 145 - iter 140/280 - loss 0.01010803 - time (sec): 8.92 - samples/sec: 11837.10 - lr: 0.000391
2023-04-05 12:13:44,965 epoch 145 - iter 168/280 - loss 0.01026575 - time (sec): 10.75 - samples/sec: 11791.27 - lr: 0.000391
2023-04-05 12:13:46,788 epoch 145 - iter 196/280 - loss 0.01036926 - time (sec): 12.57 - samples/sec: 11755.39 - lr: 0.000391
2023-04-05 12:13:48,580 epoch 145 - iter 224/280 - loss 0.01050502 - time (sec): 14.36 - samples/sec: 11787.43 - lr: 0.000391
2023-04-05 12:13:50,375 epoch 145 - iter 252/280 - loss 0.01034817 - time (sec): 16.16 - samples/sec: 11775.85 - lr: 0.000391
2023-04-05 12:13:52,216 epoch 145 - iter 280/280 - loss 0.01032713 - time (sec): 18.00 - samples/sec: 11761.27 - lr: 0.000391
2023-04-05 12:13:52,216 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:52,216 EPOCH 145 done: loss 0.0103 - lr 0.000391
2023-04-05 12:13:52,216 BAD EPOCHS (no improvement): 2
2023-04-05 12:13:52,219 ----------------------------------------------------------------------------------------------------
2023-04-05 12:13:54,040 epoch 146 - iter 28/280 - loss 0.01250359 - time (sec): 1.82 - samples/sec: 11528.75 - lr: 0.000391
2023-04-05 12:13:55,850 epoch 146 - iter 56/280 - loss 0.01095527 - time (sec): 3.63 - samples/sec: 11754.23 - lr: 0.000391
2023-04-05 12:13:57,619 epoch 146 - iter 84/280 - loss 0.01084596 - time (sec): 5.40 - samples/sec: 11811.85 - lr: 0.000391
2023-04-05 12:13:59,439 epoch 146 - iter 112/280 - loss 0.01055029 - time (sec): 7.22 - samples/sec: 11827.54 - lr: 0.000391
2023-04-05 12:14:01,251 epoch 146 - iter 140/280 - loss 0.01046470 - time (sec): 9.03 - samples/sec: 11788.31 - lr: 0.000391
2023-04-05 12:14:03,103 epoch 146 - iter 168/280 - loss 0.01049046 - time (sec): 10.88 - samples/sec: 11727.81 - lr: 0.000391
2023-04-05 12:14:04,854 epoch 146 - iter 196/280 - loss 0.01039761 - time (sec): 12.64 - samples/sec: 11776.26 - lr: 0.000391
2023-04-05 12:14:06,612 epoch 146 - iter 224/280 - loss 0.01050378 - time (sec): 14.39 - samples/sec: 11773.26 - lr: 0.000391
2023-04-05 12:14:08,410 epoch 146 - iter 252/280 - loss 0.01050673 - time (sec): 16.19 - samples/sec: 11779.91 - lr: 0.000391
2023-04-05 12:14:10,174 epoch 146 - iter 280/280 - loss 0.01049592 - time (sec): 17.95 - samples/sec: 11790.35 - lr: 0.000391
2023-04-05 12:14:10,174 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:10,174 EPOCH 146 done: loss 0.0105 - lr 0.000391
2023-04-05 12:14:10,174 BAD EPOCHS (no improvement): 3
2023-04-05 12:14:10,177 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:11,964 epoch 147 - iter 28/280 - loss 0.01157791 - time (sec): 1.79 - samples/sec: 11865.70 - lr: 0.000391
2023-04-05 12:14:13,676 epoch 147 - iter 56/280 - loss 0.01138951 - time (sec): 3.50 - samples/sec: 11862.77 - lr: 0.000391
2023-04-05 12:14:15,451 epoch 147 - iter 84/280 - loss 0.01136762 - time (sec): 5.27 - samples/sec: 11856.88 - lr: 0.000391
2023-04-05 12:14:17,212 epoch 147 - iter 112/280 - loss 0.01112186 - time (sec): 7.04 - samples/sec: 11922.89 - lr: 0.000391
2023-04-05 12:14:19,010 epoch 147 - iter 140/280 - loss 0.01106003 - time (sec): 8.83 - samples/sec: 11938.49 - lr: 0.000391
2023-04-05 12:14:20,838 epoch 147 - iter 168/280 - loss 0.01063220 - time (sec): 10.66 - samples/sec: 11889.00 - lr: 0.000391
2023-04-05 12:14:22,633 epoch 147 - iter 196/280 - loss 0.01074291 - time (sec): 12.46 - samples/sec: 11907.22 - lr: 0.000391
2023-04-05 12:14:24,456 epoch 147 - iter 224/280 - loss 0.01055046 - time (sec): 14.28 - samples/sec: 11893.95 - lr: 0.000391
2023-04-05 12:14:26,284 epoch 147 - iter 252/280 - loss 0.01051517 - time (sec): 16.11 - samples/sec: 11851.17 - lr: 0.000391
2023-04-05 12:14:28,116 epoch 147 - iter 280/280 - loss 0.01035595 - time (sec): 17.94 - samples/sec: 11800.58 - lr: 0.000391
2023-04-05 12:14:28,116 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:28,116 EPOCH 147 done: loss 0.0104 - lr 0.000391
2023-04-05 12:14:28,116 Epoch 147: reducing learning rate of group 0 to 1.9531e-04.
2023-04-05 12:14:28,116 BAD EPOCHS (no improvement): 4
2023-04-05 12:14:28,119 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:29,968 epoch 148 - iter 28/280 - loss 0.01297738 - time (sec): 1.85 - samples/sec: 11690.09 - lr: 0.000195
2023-04-05 12:14:31,795 epoch 148 - iter 56/280 - loss 0.01176461 - time (sec): 3.68 - samples/sec: 11643.62 - lr: 0.000195
2023-04-05 12:14:33,617 epoch 148 - iter 84/280 - loss 0.01069930 - time (sec): 5.50 - samples/sec: 11613.13 - lr: 0.000195
2023-04-05 12:14:35,330 epoch 148 - iter 112/280 - loss 0.01032601 - time (sec): 7.21 - samples/sec: 11727.87 - lr: 0.000195
2023-04-05 12:14:37,096 epoch 148 - iter 140/280 - loss 0.01041431 - time (sec): 8.98 - samples/sec: 11750.46 - lr: 0.000195
2023-04-05 12:14:38,866 epoch 148 - iter 168/280 - loss 0.01027550 - time (sec): 10.75 - samples/sec: 11801.32 - lr: 0.000195
2023-04-05 12:14:40,655 epoch 148 - iter 196/280 - loss 0.01055545 - time (sec): 12.54 - samples/sec: 11803.11 - lr: 0.000195
2023-04-05 12:14:42,483 epoch 148 - iter 224/280 - loss 0.01045086 - time (sec): 14.36 - samples/sec: 11812.36 - lr: 0.000195
2023-04-05 12:14:44,302 epoch 148 - iter 252/280 - loss 0.01041031 - time (sec): 16.18 - samples/sec: 11801.98 - lr: 0.000195
2023-04-05 12:14:46,062 epoch 148 - iter 280/280 - loss 0.01036047 - time (sec): 17.94 - samples/sec: 11798.00 - lr: 0.000195
2023-04-05 12:14:46,062 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:46,062 EPOCH 148 done: loss 0.0104 - lr 0.000195
2023-04-05 12:14:46,062 BAD EPOCHS (no improvement): 1
2023-04-05 12:14:46,065 ----------------------------------------------------------------------------------------------------
2023-04-05 12:14:47,836 epoch 149 - iter 28/280 - loss 0.01148945 - time (sec): 1.77 - samples/sec: 12126.88 - lr: 0.000195
2023-04-05 12:14:49,636 epoch 149 - iter 56/280 - loss 0.01007240 - time (sec): 3.57 - samples/sec: 11983.05 - lr: 0.000195
2023-04-05 12:14:51,423 epoch 149 - iter 84/280 - loss 0.01100695 - time (sec): 5.36 - samples/sec: 11949.38 - lr: 0.000195
2023-04-05 12:14:53,231 epoch 149 - iter 112/280 - loss 0.01096823 - time (sec): 7.17 - samples/sec: 11962.80 - lr: 0.000195
2023-04-05 12:14:55,038 epoch 149 - iter 140/280 - loss 0.01088771 - time (sec): 8.97 - samples/sec: 11930.03 - lr: 0.000195
2023-04-05 12:14:56,868 epoch 149 - iter 168/280 - loss 0.01070884 - time (sec): 10.80 - samples/sec: 11840.10 - lr: 0.000195
2023-04-05 12:14:58,709 epoch 149 - iter 196/280 - loss 0.01078719 - time (sec): 12.64 - samples/sec: 11788.73 - lr: 0.000195
2023-04-05 12:15:00,460 epoch 149 - iter 224/280 - loss 0.01081691 - time (sec): 14.39 - samples/sec: 11782.86 - lr: 0.000195
2023-04-05 12:15:02,316 epoch 149 - iter 252/280 - loss 0.01083639 - time (sec): 16.25 - samples/sec: 11752.66 - lr: 0.000195
2023-04-05 12:15:04,061 epoch 149 - iter 280/280 - loss 0.01075966 - time (sec): 18.00 - samples/sec: 11763.32 - lr: 0.000195
2023-04-05 12:15:04,061 ----------------------------------------------------------------------------------------------------
2023-04-05 12:15:04,061 EPOCH 149 done: loss 0.0108 - lr 0.000195
2023-04-05 12:15:04,061 BAD EPOCHS (no improvement): 2
2023-04-05 12:15:04,064 ----------------------------------------------------------------------------------------------------
2023-04-05 12:15:05,829 epoch 150 - iter 28/280 - loss 0.01103959 - time (sec): 1.76 - samples/sec: 11907.88 - lr: 0.000195
2023-04-05 12:15:07,702 epoch 150 - iter 56/280 - loss 0.01115773 - time (sec): 3.64 - samples/sec: 11648.54 - lr: 0.000195
2023-04-05 12:15:09,525 epoch 150 - iter 84/280 - loss 0.01086519 - time (sec): 5.46 - samples/sec: 11743.26 - lr: 0.000195
2023-04-05 12:15:11,349 epoch 150 - iter 112/280 - loss 0.01100287 - time (sec): 7.28 - samples/sec: 11737.32 - lr: 0.000195
2023-04-05 12:15:13,149 epoch 150 - iter 140/280 - loss 0.01119393 - time (sec): 9.08 - samples/sec: 11751.70 - lr: 0.000195
2023-04-05 12:15:14,894 epoch 150 - iter 168/280 - loss 0.01122796 - time (sec): 10.83 - samples/sec: 11812.41 - lr: 0.000195
2023-04-05 12:15:16,670 epoch 150 - iter 196/280 - loss 0.01098057 - time (sec): 12.61 - samples/sec: 11798.01 - lr: 0.000195
2023-04-05 12:15:18,448 epoch 150 - iter 224/280 - loss 0.01097500 - time (sec): 14.38 - samples/sec: 11810.44 - lr: 0.000195
2023-04-05 12:15:20,345 epoch 150 - iter 252/280 - loss 0.01104126 - time (sec): 16.28 - samples/sec: 11749.38 - lr: 0.000195
2023-04-05 12:15:22,124 epoch 150 - iter 280/280 - loss 0.01096389 - time (sec): 18.06 - samples/sec: 11721.30 - lr: 0.000195
2023-04-05 12:15:22,125 ----------------------------------------------------------------------------------------------------
2023-04-05 12:15:22,125 EPOCH 150 done: loss 0.0110 - lr 0.000195
2023-04-05 12:15:22,125 BAD EPOCHS (no improvement): 3
2023-04-05 12:15:23,401 ----------------------------------------------------------------------------------------------------
2023-04-05 12:15:23,402 Testing using last state of model ...
2023-04-05 12:15:32,233 Evaluating as a multi-label problem: False
2023-04-05 12:15:32,332 0.9642 0.964 0.9641 0.937
2023-04-05 12:15:32,332
Results:
- F-score (micro) 0.9641
- F-score (macro) 0.8041
- Accuracy 0.937
By class:
precision recall f1-score support
NP 0.9707 0.9678 0.9692 12422
PP 0.9837 0.9890 0.9863 4811
VP 0.9641 0.9674 0.9657 4658
ADVP 0.8685 0.8614 0.8649 866
SBAR 0.9402 0.9402 0.9402 535
ADJP 0.8500 0.8151 0.8322 438
PRT 0.7623 0.8774 0.8158 106
CONJP 0.5833 0.7778 0.6667 9
LST 0.0000 0.0000 0.0000 5
INTJ 1.0000 1.0000 1.0000 2
micro avg 0.9642 0.9640 0.9641 23852
macro avg 0.7923 0.8196 0.8041 23852
weighted avg 0.9641 0.9640 0.9640 23852
2023-04-05 12:15:32,332 ----------------------------------------------------------------------------------------------------