ner-german / training.log
alanakbik's picture
Update model for torch 2.0
4e3f3d1
2023-03-29 16:42:30,589 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,589 Model: "SequenceTagger(
(embeddings): StackedEmbeddings(
(list_embedding_0): WordEmbeddings(
'de'
(embedding): Embedding(1000000, 300)
)
(list_embedding_1): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.25, inplace=False)
(encoder): Embedding(275, 100)
(rnn): LSTM(100, 2048)
)
)
(list_embedding_2): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.25, inplace=False)
(encoder): Embedding(275, 100)
(rnn): LSTM(100, 2048)
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(embedding2nn): Linear(in_features=4396, out_features=4396, bias=True)
(rnn): LSTM(4396, 256, batch_first=True, bidirectional=True)
(linear): Linear(in_features=512, out_features=19, bias=True)
(loss_function): ViterbiLoss()
(crf): CRF()
)"
2023-03-29 16:42:30,589 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,589 Corpus: "Corpus: 12705 train + 3068 dev + 3160 test sentences"
2023-03-29 16:42:30,589 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,590 Parameters:
2023-03-29 16:42:30,590 - learning_rate: "0.100000"
2023-03-29 16:42:30,590 - mini_batch_size: "32"
2023-03-29 16:42:30,590 - patience: "3"
2023-03-29 16:42:30,590 - anneal_factor: "0.5"
2023-03-29 16:42:30,590 - max_epochs: "150"
2023-03-29 16:42:30,590 - shuffle: "True"
2023-03-29 16:42:30,590 - train_with_dev: "True"
2023-03-29 16:42:30,590 - batch_growth_annealing: "False"
2023-03-29 16:42:30,590 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,590 Model training base path: "resources/taggers/release-de-ner-0"
2023-03-29 16:42:30,590 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,590 Device: cuda:2
2023-03-29 16:42:30,590 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:30,590 Embeddings storage mode: cpu
2023-03-29 16:42:30,590 ----------------------------------------------------------------------------------------------------
2023-03-29 16:42:39,764 epoch 1 - iter 49/493 - loss 0.46644716 - time (sec): 9.17 - samples/sec: 3034.05 - lr: 0.100000
2023-03-29 16:42:48,338 epoch 1 - iter 98/493 - loss 0.31988353 - time (sec): 17.75 - samples/sec: 3117.17 - lr: 0.100000
2023-03-29 16:42:56,178 epoch 1 - iter 147/493 - loss 0.27195175 - time (sec): 25.59 - samples/sec: 3102.09 - lr: 0.100000
2023-03-29 16:43:06,551 epoch 1 - iter 196/493 - loss 0.23366763 - time (sec): 35.96 - samples/sec: 2905.85 - lr: 0.100000
2023-03-29 16:43:14,061 epoch 1 - iter 245/493 - loss 0.21486776 - time (sec): 43.47 - samples/sec: 2968.67 - lr: 0.100000
2023-03-29 16:43:21,787 epoch 1 - iter 294/493 - loss 0.20025894 - time (sec): 51.20 - samples/sec: 2991.22 - lr: 0.100000
2023-03-29 16:43:29,873 epoch 1 - iter 343/493 - loss 0.18706718 - time (sec): 59.28 - samples/sec: 3016.39 - lr: 0.100000
2023-03-29 16:43:38,046 epoch 1 - iter 392/493 - loss 0.17935330 - time (sec): 67.46 - samples/sec: 3044.55 - lr: 0.100000
2023-03-29 16:43:46,005 epoch 1 - iter 441/493 - loss 0.17112302 - time (sec): 75.42 - samples/sec: 3063.40 - lr: 0.100000
2023-03-29 16:43:55,198 epoch 1 - iter 490/493 - loss 0.16739534 - time (sec): 84.61 - samples/sec: 3046.95 - lr: 0.100000
2023-03-29 16:43:55,603 ----------------------------------------------------------------------------------------------------
2023-03-29 16:43:55,603 EPOCH 1 done: loss 0.1671 - lr 0.100000
2023-03-29 16:43:55,603 BAD EPOCHS (no improvement): 0
2023-03-29 16:43:55,607 ----------------------------------------------------------------------------------------------------
2023-03-29 16:43:59,136 epoch 2 - iter 49/493 - loss 0.09655865 - time (sec): 3.53 - samples/sec: 7203.04 - lr: 0.100000
2023-03-29 16:44:02,516 epoch 2 - iter 98/493 - loss 0.09332598 - time (sec): 6.91 - samples/sec: 7379.31 - lr: 0.100000
2023-03-29 16:44:05,867 epoch 2 - iter 147/493 - loss 0.08847197 - time (sec): 10.26 - samples/sec: 7473.16 - lr: 0.100000
2023-03-29 16:44:09,403 epoch 2 - iter 196/493 - loss 0.08720627 - time (sec): 13.80 - samples/sec: 7464.19 - lr: 0.100000
2023-03-29 16:44:12,849 epoch 2 - iter 245/493 - loss 0.08579958 - time (sec): 17.24 - samples/sec: 7429.85 - lr: 0.100000
2023-03-29 16:44:16,401 epoch 2 - iter 294/493 - loss 0.08543270 - time (sec): 20.79 - samples/sec: 7423.51 - lr: 0.100000
2023-03-29 16:44:19,885 epoch 2 - iter 343/493 - loss 0.08456374 - time (sec): 24.28 - samples/sec: 7417.79 - lr: 0.100000
2023-03-29 16:44:23,379 epoch 2 - iter 392/493 - loss 0.08342429 - time (sec): 27.77 - samples/sec: 7414.44 - lr: 0.100000
2023-03-29 16:44:26,982 epoch 2 - iter 441/493 - loss 0.08165096 - time (sec): 31.38 - samples/sec: 7388.68 - lr: 0.100000
2023-03-29 16:44:30,537 epoch 2 - iter 490/493 - loss 0.08070827 - time (sec): 34.93 - samples/sec: 7373.67 - lr: 0.100000
2023-03-29 16:44:30,760 ----------------------------------------------------------------------------------------------------
2023-03-29 16:44:30,760 EPOCH 2 done: loss 0.0806 - lr 0.100000
2023-03-29 16:44:30,760 BAD EPOCHS (no improvement): 0
2023-03-29 16:44:30,763 ----------------------------------------------------------------------------------------------------
2023-03-29 16:44:34,387 epoch 3 - iter 49/493 - loss 0.07044696 - time (sec): 3.62 - samples/sec: 7085.11 - lr: 0.100000
2023-03-29 16:44:37,948 epoch 3 - iter 98/493 - loss 0.07021930 - time (sec): 7.18 - samples/sec: 7193.38 - lr: 0.100000
2023-03-29 16:44:41,435 epoch 3 - iter 147/493 - loss 0.06980087 - time (sec): 10.67 - samples/sec: 7252.82 - lr: 0.100000
2023-03-29 16:44:44,806 epoch 3 - iter 196/493 - loss 0.06875732 - time (sec): 14.04 - samples/sec: 7274.11 - lr: 0.100000
2023-03-29 16:44:48,514 epoch 3 - iter 245/493 - loss 0.06766544 - time (sec): 17.75 - samples/sec: 7267.36 - lr: 0.100000
2023-03-29 16:44:52,022 epoch 3 - iter 294/493 - loss 0.06729169 - time (sec): 21.26 - samples/sec: 7303.83 - lr: 0.100000
2023-03-29 16:44:55,573 epoch 3 - iter 343/493 - loss 0.06677841 - time (sec): 24.81 - samples/sec: 7284.11 - lr: 0.100000
2023-03-29 16:44:59,021 epoch 3 - iter 392/493 - loss 0.06648263 - time (sec): 28.26 - samples/sec: 7285.31 - lr: 0.100000
2023-03-29 16:45:02,393 epoch 3 - iter 441/493 - loss 0.06542096 - time (sec): 31.63 - samples/sec: 7318.28 - lr: 0.100000
2023-03-29 16:45:06,092 epoch 3 - iter 490/493 - loss 0.06462579 - time (sec): 35.33 - samples/sec: 7292.72 - lr: 0.100000
2023-03-29 16:45:06,314 ----------------------------------------------------------------------------------------------------
2023-03-29 16:45:06,314 EPOCH 3 done: loss 0.0645 - lr 0.100000
2023-03-29 16:45:06,314 BAD EPOCHS (no improvement): 0
2023-03-29 16:45:06,317 ----------------------------------------------------------------------------------------------------
2023-03-29 16:45:09,880 epoch 4 - iter 49/493 - loss 0.05399821 - time (sec): 3.56 - samples/sec: 7237.97 - lr: 0.100000
2023-03-29 16:45:13,503 epoch 4 - iter 98/493 - loss 0.05873254 - time (sec): 7.19 - samples/sec: 7293.58 - lr: 0.100000
2023-03-29 16:45:17,064 epoch 4 - iter 147/493 - loss 0.05794216 - time (sec): 10.75 - samples/sec: 7232.18 - lr: 0.100000
2023-03-29 16:45:20,625 epoch 4 - iter 196/493 - loss 0.05804724 - time (sec): 14.31 - samples/sec: 7255.24 - lr: 0.100000
2023-03-29 16:45:24,173 epoch 4 - iter 245/493 - loss 0.05661678 - time (sec): 17.86 - samples/sec: 7238.34 - lr: 0.100000
2023-03-29 16:45:27,805 epoch 4 - iter 294/493 - loss 0.05627032 - time (sec): 21.49 - samples/sec: 7234.24 - lr: 0.100000
2023-03-29 16:45:31,363 epoch 4 - iter 343/493 - loss 0.05755638 - time (sec): 25.05 - samples/sec: 7221.15 - lr: 0.100000
2023-03-29 16:45:34,810 epoch 4 - iter 392/493 - loss 0.05756938 - time (sec): 28.49 - samples/sec: 7233.02 - lr: 0.100000
2023-03-29 16:45:38,266 epoch 4 - iter 441/493 - loss 0.05668179 - time (sec): 31.95 - samples/sec: 7252.68 - lr: 0.100000
2023-03-29 16:45:41,729 epoch 4 - iter 490/493 - loss 0.05688996 - time (sec): 35.41 - samples/sec: 7277.98 - lr: 0.100000
2023-03-29 16:45:41,927 ----------------------------------------------------------------------------------------------------
2023-03-29 16:45:41,927 EPOCH 4 done: loss 0.0568 - lr 0.100000
2023-03-29 16:45:41,927 BAD EPOCHS (no improvement): 0
2023-03-29 16:45:41,930 ----------------------------------------------------------------------------------------------------
2023-03-29 16:45:45,411 epoch 5 - iter 49/493 - loss 0.05633686 - time (sec): 3.48 - samples/sec: 7345.05 - lr: 0.100000
2023-03-29 16:45:48,905 epoch 5 - iter 98/493 - loss 0.05432266 - time (sec): 6.98 - samples/sec: 7381.72 - lr: 0.100000
2023-03-29 16:45:52,377 epoch 5 - iter 147/493 - loss 0.05132033 - time (sec): 10.45 - samples/sec: 7362.57 - lr: 0.100000
2023-03-29 16:45:56,158 epoch 5 - iter 196/493 - loss 0.05227944 - time (sec): 14.23 - samples/sec: 7264.72 - lr: 0.100000
2023-03-29 16:45:59,673 epoch 5 - iter 245/493 - loss 0.05224815 - time (sec): 17.74 - samples/sec: 7290.39 - lr: 0.100000
2023-03-29 16:46:03,123 epoch 5 - iter 294/493 - loss 0.05241316 - time (sec): 21.19 - samples/sec: 7286.62 - lr: 0.100000
2023-03-29 16:46:06,533 epoch 5 - iter 343/493 - loss 0.05160962 - time (sec): 24.60 - samples/sec: 7294.67 - lr: 0.100000
2023-03-29 16:46:10,050 epoch 5 - iter 392/493 - loss 0.05166800 - time (sec): 28.12 - samples/sec: 7309.76 - lr: 0.100000
2023-03-29 16:46:13,499 epoch 5 - iter 441/493 - loss 0.05105173 - time (sec): 31.57 - samples/sec: 7325.58 - lr: 0.100000
2023-03-29 16:46:17,066 epoch 5 - iter 490/493 - loss 0.05112971 - time (sec): 35.14 - samples/sec: 7330.55 - lr: 0.100000
2023-03-29 16:46:17,299 ----------------------------------------------------------------------------------------------------
2023-03-29 16:46:17,299 EPOCH 5 done: loss 0.0511 - lr 0.100000
2023-03-29 16:46:17,300 BAD EPOCHS (no improvement): 0
2023-03-29 16:46:17,302 ----------------------------------------------------------------------------------------------------
2023-03-29 16:46:20,810 epoch 6 - iter 49/493 - loss 0.05209740 - time (sec): 3.51 - samples/sec: 7243.72 - lr: 0.100000
2023-03-29 16:46:24,419 epoch 6 - iter 98/493 - loss 0.04942847 - time (sec): 7.12 - samples/sec: 7217.24 - lr: 0.100000
2023-03-29 16:46:27,996 epoch 6 - iter 147/493 - loss 0.04744082 - time (sec): 10.69 - samples/sec: 7219.87 - lr: 0.100000
2023-03-29 16:46:31,549 epoch 6 - iter 196/493 - loss 0.04695821 - time (sec): 14.25 - samples/sec: 7231.42 - lr: 0.100000
2023-03-29 16:46:35,001 epoch 6 - iter 245/493 - loss 0.04703050 - time (sec): 17.70 - samples/sec: 7278.84 - lr: 0.100000
2023-03-29 16:46:38,512 epoch 6 - iter 294/493 - loss 0.04711416 - time (sec): 21.21 - samples/sec: 7284.29 - lr: 0.100000
2023-03-29 16:46:41,958 epoch 6 - iter 343/493 - loss 0.04731643 - time (sec): 24.66 - samples/sec: 7309.44 - lr: 0.100000
2023-03-29 16:46:45,554 epoch 6 - iter 392/493 - loss 0.04712845 - time (sec): 28.25 - samples/sec: 7292.92 - lr: 0.100000
2023-03-29 16:46:49,021 epoch 6 - iter 441/493 - loss 0.04714741 - time (sec): 31.72 - samples/sec: 7295.85 - lr: 0.100000
2023-03-29 16:46:52,535 epoch 6 - iter 490/493 - loss 0.04727371 - time (sec): 35.23 - samples/sec: 7310.68 - lr: 0.100000
2023-03-29 16:46:52,737 ----------------------------------------------------------------------------------------------------
2023-03-29 16:46:52,737 EPOCH 6 done: loss 0.0472 - lr 0.100000
2023-03-29 16:46:52,737 BAD EPOCHS (no improvement): 0
2023-03-29 16:46:52,740 ----------------------------------------------------------------------------------------------------
2023-03-29 16:46:56,160 epoch 7 - iter 49/493 - loss 0.04490630 - time (sec): 3.42 - samples/sec: 7473.27 - lr: 0.100000
2023-03-29 16:46:59,809 epoch 7 - iter 98/493 - loss 0.04517921 - time (sec): 7.07 - samples/sec: 7257.92 - lr: 0.100000
2023-03-29 16:47:03,343 epoch 7 - iter 147/493 - loss 0.04423338 - time (sec): 10.60 - samples/sec: 7298.80 - lr: 0.100000
2023-03-29 16:47:06,805 epoch 7 - iter 196/493 - loss 0.04484448 - time (sec): 14.07 - samples/sec: 7357.24 - lr: 0.100000
2023-03-29 16:47:10,248 epoch 7 - iter 245/493 - loss 0.04447620 - time (sec): 17.51 - samples/sec: 7371.12 - lr: 0.100000
2023-03-29 16:47:13,563 epoch 7 - iter 294/493 - loss 0.04512531 - time (sec): 20.82 - samples/sec: 7405.23 - lr: 0.100000
2023-03-29 16:47:17,032 epoch 7 - iter 343/493 - loss 0.04506370 - time (sec): 24.29 - samples/sec: 7421.62 - lr: 0.100000
2023-03-29 16:47:20,518 epoch 7 - iter 392/493 - loss 0.04479532 - time (sec): 27.78 - samples/sec: 7415.90 - lr: 0.100000
2023-03-29 16:47:23,841 epoch 7 - iter 441/493 - loss 0.04451346 - time (sec): 31.10 - samples/sec: 7444.63 - lr: 0.100000
2023-03-29 16:47:27,177 epoch 7 - iter 490/493 - loss 0.04423305 - time (sec): 34.44 - samples/sec: 7476.12 - lr: 0.100000
2023-03-29 16:47:27,386 ----------------------------------------------------------------------------------------------------
2023-03-29 16:47:27,386 EPOCH 7 done: loss 0.0443 - lr 0.100000
2023-03-29 16:47:27,386 BAD EPOCHS (no improvement): 0
2023-03-29 16:47:27,389 ----------------------------------------------------------------------------------------------------
2023-03-29 16:47:30,790 epoch 8 - iter 49/493 - loss 0.04066354 - time (sec): 3.40 - samples/sec: 7515.74 - lr: 0.100000
2023-03-29 16:47:34,240 epoch 8 - iter 98/493 - loss 0.03882795 - time (sec): 6.85 - samples/sec: 7489.75 - lr: 0.100000
2023-03-29 16:47:37,791 epoch 8 - iter 147/493 - loss 0.04099944 - time (sec): 10.40 - samples/sec: 7454.65 - lr: 0.100000
2023-03-29 16:47:41,245 epoch 8 - iter 196/493 - loss 0.03977522 - time (sec): 13.86 - samples/sec: 7447.01 - lr: 0.100000
2023-03-29 16:47:44,658 epoch 8 - iter 245/493 - loss 0.04034347 - time (sec): 17.27 - samples/sec: 7468.39 - lr: 0.100000
2023-03-29 16:47:48,216 epoch 8 - iter 294/493 - loss 0.04126713 - time (sec): 20.83 - samples/sec: 7431.95 - lr: 0.100000
2023-03-29 16:47:51,764 epoch 8 - iter 343/493 - loss 0.04131202 - time (sec): 24.37 - samples/sec: 7404.65 - lr: 0.100000
2023-03-29 16:47:55,253 epoch 8 - iter 392/493 - loss 0.04137829 - time (sec): 27.86 - samples/sec: 7401.41 - lr: 0.100000
2023-03-29 16:47:58,769 epoch 8 - iter 441/493 - loss 0.04110908 - time (sec): 31.38 - samples/sec: 7388.98 - lr: 0.100000
2023-03-29 16:48:02,337 epoch 8 - iter 490/493 - loss 0.04130897 - time (sec): 34.95 - samples/sec: 7370.69 - lr: 0.100000
2023-03-29 16:48:02,556 ----------------------------------------------------------------------------------------------------
2023-03-29 16:48:02,556 EPOCH 8 done: loss 0.0413 - lr 0.100000
2023-03-29 16:48:02,556 BAD EPOCHS (no improvement): 0
2023-03-29 16:48:02,559 ----------------------------------------------------------------------------------------------------
2023-03-29 16:48:06,058 epoch 9 - iter 49/493 - loss 0.03553756 - time (sec): 3.50 - samples/sec: 7473.85 - lr: 0.100000
2023-03-29 16:48:09,597 epoch 9 - iter 98/493 - loss 0.03648757 - time (sec): 7.04 - samples/sec: 7394.93 - lr: 0.100000
2023-03-29 16:48:13,214 epoch 9 - iter 147/493 - loss 0.03650184 - time (sec): 10.66 - samples/sec: 7324.75 - lr: 0.100000
2023-03-29 16:48:16,770 epoch 9 - iter 196/493 - loss 0.03747618 - time (sec): 14.21 - samples/sec: 7308.40 - lr: 0.100000
2023-03-29 16:48:20,177 epoch 9 - iter 245/493 - loss 0.03841574 - time (sec): 17.62 - samples/sec: 7311.52 - lr: 0.100000
2023-03-29 16:48:23,540 epoch 9 - iter 294/493 - loss 0.03813335 - time (sec): 20.98 - samples/sec: 7325.15 - lr: 0.100000
2023-03-29 16:48:26,998 epoch 9 - iter 343/493 - loss 0.03850934 - time (sec): 24.44 - samples/sec: 7343.88 - lr: 0.100000
2023-03-29 16:48:30,551 epoch 9 - iter 392/493 - loss 0.03817715 - time (sec): 27.99 - samples/sec: 7342.64 - lr: 0.100000
2023-03-29 16:48:34,191 epoch 9 - iter 441/493 - loss 0.03798437 - time (sec): 31.63 - samples/sec: 7318.14 - lr: 0.100000
2023-03-29 16:48:37,761 epoch 9 - iter 490/493 - loss 0.03837003 - time (sec): 35.20 - samples/sec: 7316.20 - lr: 0.100000
2023-03-29 16:48:37,979 ----------------------------------------------------------------------------------------------------
2023-03-29 16:48:37,979 EPOCH 9 done: loss 0.0384 - lr 0.100000
2023-03-29 16:48:37,979 BAD EPOCHS (no improvement): 0
2023-03-29 16:48:37,983 ----------------------------------------------------------------------------------------------------
2023-03-29 16:48:41,533 epoch 10 - iter 49/493 - loss 0.03833640 - time (sec): 3.55 - samples/sec: 7325.14 - lr: 0.100000
2023-03-29 16:48:45,057 epoch 10 - iter 98/493 - loss 0.03736996 - time (sec): 7.07 - samples/sec: 7339.41 - lr: 0.100000
2023-03-29 16:48:48,540 epoch 10 - iter 147/493 - loss 0.03792437 - time (sec): 10.56 - samples/sec: 7342.35 - lr: 0.100000
2023-03-29 16:48:52,017 epoch 10 - iter 196/493 - loss 0.03777501 - time (sec): 14.03 - samples/sec: 7347.24 - lr: 0.100000
2023-03-29 16:48:55,567 epoch 10 - iter 245/493 - loss 0.03717360 - time (sec): 17.58 - samples/sec: 7350.60 - lr: 0.100000
2023-03-29 16:48:59,084 epoch 10 - iter 294/493 - loss 0.03729877 - time (sec): 21.10 - samples/sec: 7332.27 - lr: 0.100000
2023-03-29 16:49:02,599 epoch 10 - iter 343/493 - loss 0.03714881 - time (sec): 24.62 - samples/sec: 7344.72 - lr: 0.100000
2023-03-29 16:49:06,176 epoch 10 - iter 392/493 - loss 0.03692179 - time (sec): 28.19 - samples/sec: 7327.47 - lr: 0.100000
2023-03-29 16:49:09,708 epoch 10 - iter 441/493 - loss 0.03705621 - time (sec): 31.73 - samples/sec: 7324.63 - lr: 0.100000
2023-03-29 16:49:13,187 epoch 10 - iter 490/493 - loss 0.03696067 - time (sec): 35.20 - samples/sec: 7317.72 - lr: 0.100000
2023-03-29 16:49:13,405 ----------------------------------------------------------------------------------------------------
2023-03-29 16:49:13,405 EPOCH 10 done: loss 0.0370 - lr 0.100000
2023-03-29 16:49:13,405 BAD EPOCHS (no improvement): 0
2023-03-29 16:49:13,408 ----------------------------------------------------------------------------------------------------
2023-03-29 16:49:16,859 epoch 11 - iter 49/493 - loss 0.03358704 - time (sec): 3.45 - samples/sec: 7366.50 - lr: 0.100000
2023-03-29 16:49:20,414 epoch 11 - iter 98/493 - loss 0.03487343 - time (sec): 7.01 - samples/sec: 7328.15 - lr: 0.100000
2023-03-29 16:49:24,007 epoch 11 - iter 147/493 - loss 0.03544229 - time (sec): 10.60 - samples/sec: 7304.00 - lr: 0.100000
2023-03-29 16:49:27,731 epoch 11 - iter 196/493 - loss 0.03582510 - time (sec): 14.32 - samples/sec: 7262.77 - lr: 0.100000
2023-03-29 16:49:31,302 epoch 11 - iter 245/493 - loss 0.03594562 - time (sec): 17.89 - samples/sec: 7234.66 - lr: 0.100000
2023-03-29 16:49:34,722 epoch 11 - iter 294/493 - loss 0.03626975 - time (sec): 21.31 - samples/sec: 7257.21 - lr: 0.100000
2023-03-29 16:49:38,208 epoch 11 - iter 343/493 - loss 0.03596812 - time (sec): 24.80 - samples/sec: 7271.58 - lr: 0.100000
2023-03-29 16:49:44,560 epoch 11 - iter 392/493 - loss 0.03562583 - time (sec): 31.15 - samples/sec: 6615.04 - lr: 0.100000
2023-03-29 16:49:48,180 epoch 11 - iter 441/493 - loss 0.03555375 - time (sec): 34.77 - samples/sec: 6673.95 - lr: 0.100000
2023-03-29 16:49:51,555 epoch 11 - iter 490/493 - loss 0.03555316 - time (sec): 38.15 - samples/sec: 6751.87 - lr: 0.100000
2023-03-29 16:49:51,751 ----------------------------------------------------------------------------------------------------
2023-03-29 16:49:51,751 EPOCH 11 done: loss 0.0356 - lr 0.100000
2023-03-29 16:49:51,751 BAD EPOCHS (no improvement): 0
2023-03-29 16:49:51,754 ----------------------------------------------------------------------------------------------------
2023-03-29 16:49:55,217 epoch 12 - iter 49/493 - loss 0.03491700 - time (sec): 3.46 - samples/sec: 7415.38 - lr: 0.100000
2023-03-29 16:49:58,947 epoch 12 - iter 98/493 - loss 0.03448655 - time (sec): 7.19 - samples/sec: 7195.86 - lr: 0.100000
2023-03-29 16:50:02,185 epoch 12 - iter 147/493 - loss 0.03407943 - time (sec): 10.43 - samples/sec: 7325.52 - lr: 0.100000
2023-03-29 16:50:05,726 epoch 12 - iter 196/493 - loss 0.03345478 - time (sec): 13.97 - samples/sec: 7345.91 - lr: 0.100000
2023-03-29 16:50:09,187 epoch 12 - iter 245/493 - loss 0.03372026 - time (sec): 17.43 - samples/sec: 7356.45 - lr: 0.100000
2023-03-29 16:50:12,547 epoch 12 - iter 294/493 - loss 0.03358878 - time (sec): 20.79 - samples/sec: 7387.20 - lr: 0.100000
2023-03-29 16:50:15,920 epoch 12 - iter 343/493 - loss 0.03394292 - time (sec): 24.17 - samples/sec: 7434.85 - lr: 0.100000
2023-03-29 16:50:19,576 epoch 12 - iter 392/493 - loss 0.03407674 - time (sec): 27.82 - samples/sec: 7385.66 - lr: 0.100000
2023-03-29 16:50:23,092 epoch 12 - iter 441/493 - loss 0.03392460 - time (sec): 31.34 - samples/sec: 7387.42 - lr: 0.100000
2023-03-29 16:50:26,631 epoch 12 - iter 490/493 - loss 0.03411242 - time (sec): 34.88 - samples/sec: 7384.04 - lr: 0.100000
2023-03-29 16:50:26,852 ----------------------------------------------------------------------------------------------------
2023-03-29 16:50:26,852 EPOCH 12 done: loss 0.0340 - lr 0.100000
2023-03-29 16:50:26,852 BAD EPOCHS (no improvement): 0
2023-03-29 16:50:26,855 ----------------------------------------------------------------------------------------------------
2023-03-29 16:50:30,525 epoch 13 - iter 49/493 - loss 0.03286744 - time (sec): 3.67 - samples/sec: 7186.84 - lr: 0.100000
2023-03-29 16:50:34,045 epoch 13 - iter 98/493 - loss 0.03406802 - time (sec): 7.19 - samples/sec: 7255.69 - lr: 0.100000
2023-03-29 16:50:37,643 epoch 13 - iter 147/493 - loss 0.03504269 - time (sec): 10.79 - samples/sec: 7267.80 - lr: 0.100000
2023-03-29 16:50:41,176 epoch 13 - iter 196/493 - loss 0.03368493 - time (sec): 14.32 - samples/sec: 7238.02 - lr: 0.100000
2023-03-29 16:50:44,549 epoch 13 - iter 245/493 - loss 0.03403303 - time (sec): 17.69 - samples/sec: 7286.09 - lr: 0.100000
2023-03-29 16:50:48,076 epoch 13 - iter 294/493 - loss 0.03351105 - time (sec): 21.22 - samples/sec: 7317.20 - lr: 0.100000
2023-03-29 16:50:51,477 epoch 13 - iter 343/493 - loss 0.03355732 - time (sec): 24.62 - samples/sec: 7337.05 - lr: 0.100000
2023-03-29 16:50:55,117 epoch 13 - iter 392/493 - loss 0.03308972 - time (sec): 28.26 - samples/sec: 7319.27 - lr: 0.100000
2023-03-29 16:50:58,441 epoch 13 - iter 441/493 - loss 0.03303461 - time (sec): 31.59 - samples/sec: 7339.40 - lr: 0.100000
2023-03-29 16:51:02,113 epoch 13 - iter 490/493 - loss 0.03317976 - time (sec): 35.26 - samples/sec: 7306.18 - lr: 0.100000
2023-03-29 16:51:02,313 ----------------------------------------------------------------------------------------------------
2023-03-29 16:51:02,313 EPOCH 13 done: loss 0.0332 - lr 0.100000
2023-03-29 16:51:02,313 BAD EPOCHS (no improvement): 0
2023-03-29 16:51:02,316 ----------------------------------------------------------------------------------------------------
2023-03-29 16:51:06,005 epoch 14 - iter 49/493 - loss 0.02607393 - time (sec): 3.69 - samples/sec: 7078.16 - lr: 0.100000
2023-03-29 16:51:09,637 epoch 14 - iter 98/493 - loss 0.02998247 - time (sec): 7.32 - samples/sec: 7198.45 - lr: 0.100000
2023-03-29 16:51:13,083 epoch 14 - iter 147/493 - loss 0.03053717 - time (sec): 10.77 - samples/sec: 7234.39 - lr: 0.100000
2023-03-29 16:51:16,555 epoch 14 - iter 196/493 - loss 0.03118994 - time (sec): 14.24 - samples/sec: 7255.24 - lr: 0.100000
2023-03-29 16:51:20,008 epoch 14 - iter 245/493 - loss 0.03121169 - time (sec): 17.69 - samples/sec: 7274.30 - lr: 0.100000
2023-03-29 16:51:23,499 epoch 14 - iter 294/493 - loss 0.03151520 - time (sec): 21.18 - samples/sec: 7288.50 - lr: 0.100000
2023-03-29 16:51:26,894 epoch 14 - iter 343/493 - loss 0.03136935 - time (sec): 24.58 - samples/sec: 7304.39 - lr: 0.100000
2023-03-29 16:51:30,450 epoch 14 - iter 392/493 - loss 0.03147462 - time (sec): 28.13 - samples/sec: 7307.28 - lr: 0.100000
2023-03-29 16:51:33,891 epoch 14 - iter 441/493 - loss 0.03181244 - time (sec): 31.58 - samples/sec: 7340.58 - lr: 0.100000
2023-03-29 16:51:37,309 epoch 14 - iter 490/493 - loss 0.03192350 - time (sec): 34.99 - samples/sec: 7364.55 - lr: 0.100000
2023-03-29 16:51:37,520 ----------------------------------------------------------------------------------------------------
2023-03-29 16:51:37,521 EPOCH 14 done: loss 0.0319 - lr 0.100000
2023-03-29 16:51:37,521 BAD EPOCHS (no improvement): 0
2023-03-29 16:51:37,523 ----------------------------------------------------------------------------------------------------
2023-03-29 16:51:40,987 epoch 15 - iter 49/493 - loss 0.02819409 - time (sec): 3.46 - samples/sec: 7526.26 - lr: 0.100000
2023-03-29 16:51:44,515 epoch 15 - iter 98/493 - loss 0.02975221 - time (sec): 6.99 - samples/sec: 7532.35 - lr: 0.100000
2023-03-29 16:51:47,886 epoch 15 - iter 147/493 - loss 0.02896187 - time (sec): 10.36 - samples/sec: 7563.21 - lr: 0.100000
2023-03-29 16:51:51,243 epoch 15 - iter 196/493 - loss 0.02871311 - time (sec): 13.72 - samples/sec: 7602.57 - lr: 0.100000
2023-03-29 16:51:54,604 epoch 15 - iter 245/493 - loss 0.02948830 - time (sec): 17.08 - samples/sec: 7601.25 - lr: 0.100000
2023-03-29 16:51:58,096 epoch 15 - iter 294/493 - loss 0.02948580 - time (sec): 20.57 - samples/sec: 7526.29 - lr: 0.100000
2023-03-29 16:52:01,798 epoch 15 - iter 343/493 - loss 0.02958343 - time (sec): 24.27 - samples/sec: 7453.85 - lr: 0.100000
2023-03-29 16:52:05,344 epoch 15 - iter 392/493 - loss 0.02970103 - time (sec): 27.82 - samples/sec: 7432.83 - lr: 0.100000
2023-03-29 16:52:08,761 epoch 15 - iter 441/493 - loss 0.02973647 - time (sec): 31.24 - samples/sec: 7421.93 - lr: 0.100000
2023-03-29 16:52:12,289 epoch 15 - iter 490/493 - loss 0.03001027 - time (sec): 34.77 - samples/sec: 7410.79 - lr: 0.100000
2023-03-29 16:52:12,503 ----------------------------------------------------------------------------------------------------
2023-03-29 16:52:12,503 EPOCH 15 done: loss 0.0301 - lr 0.100000
2023-03-29 16:52:12,503 BAD EPOCHS (no improvement): 0
2023-03-29 16:52:12,506 ----------------------------------------------------------------------------------------------------
2023-03-29 16:52:16,022 epoch 16 - iter 49/493 - loss 0.02885649 - time (sec): 3.52 - samples/sec: 7218.64 - lr: 0.100000
2023-03-29 16:52:19,583 epoch 16 - iter 98/493 - loss 0.02956793 - time (sec): 7.08 - samples/sec: 7233.33 - lr: 0.100000
2023-03-29 16:52:22,864 epoch 16 - iter 147/493 - loss 0.02855421 - time (sec): 10.36 - samples/sec: 7311.61 - lr: 0.100000
2023-03-29 16:52:26,386 epoch 16 - iter 196/493 - loss 0.02881925 - time (sec): 13.88 - samples/sec: 7340.35 - lr: 0.100000
2023-03-29 16:52:29,973 epoch 16 - iter 245/493 - loss 0.02917363 - time (sec): 17.47 - samples/sec: 7357.81 - lr: 0.100000
2023-03-29 16:52:33,303 epoch 16 - iter 294/493 - loss 0.02905890 - time (sec): 20.80 - samples/sec: 7415.52 - lr: 0.100000
2023-03-29 16:52:36,687 epoch 16 - iter 343/493 - loss 0.02902118 - time (sec): 24.18 - samples/sec: 7450.31 - lr: 0.100000
2023-03-29 16:52:40,244 epoch 16 - iter 392/493 - loss 0.02911782 - time (sec): 27.74 - samples/sec: 7447.17 - lr: 0.100000
2023-03-29 16:52:43,519 epoch 16 - iter 441/493 - loss 0.02917781 - time (sec): 31.01 - samples/sec: 7460.22 - lr: 0.100000
2023-03-29 16:52:47,048 epoch 16 - iter 490/493 - loss 0.02902898 - time (sec): 34.54 - samples/sec: 7458.98 - lr: 0.100000
2023-03-29 16:52:47,253 ----------------------------------------------------------------------------------------------------
2023-03-29 16:52:47,253 EPOCH 16 done: loss 0.0290 - lr 0.100000
2023-03-29 16:52:47,253 BAD EPOCHS (no improvement): 0
2023-03-29 16:52:47,255 ----------------------------------------------------------------------------------------------------
2023-03-29 16:52:50,689 epoch 17 - iter 49/493 - loss 0.02809275 - time (sec): 3.43 - samples/sec: 7421.70 - lr: 0.100000
2023-03-29 16:52:53,987 epoch 17 - iter 98/493 - loss 0.02817160 - time (sec): 6.73 - samples/sec: 7476.99 - lr: 0.100000
2023-03-29 16:52:57,338 epoch 17 - iter 147/493 - loss 0.02799345 - time (sec): 10.08 - samples/sec: 7548.19 - lr: 0.100000
2023-03-29 16:53:00,763 epoch 17 - iter 196/493 - loss 0.02827564 - time (sec): 13.51 - samples/sec: 7513.88 - lr: 0.100000
2023-03-29 16:53:04,239 epoch 17 - iter 245/493 - loss 0.02817585 - time (sec): 16.98 - samples/sec: 7503.70 - lr: 0.100000
2023-03-29 16:53:07,856 epoch 17 - iter 294/493 - loss 0.02844140 - time (sec): 20.60 - samples/sec: 7453.22 - lr: 0.100000
2023-03-29 16:53:11,147 epoch 17 - iter 343/493 - loss 0.02840434 - time (sec): 23.89 - samples/sec: 7490.65 - lr: 0.100000
2023-03-29 16:53:14,716 epoch 17 - iter 392/493 - loss 0.02814949 - time (sec): 27.46 - samples/sec: 7492.98 - lr: 0.100000
2023-03-29 16:53:18,290 epoch 17 - iter 441/493 - loss 0.02821183 - time (sec): 31.03 - samples/sec: 7476.49 - lr: 0.100000
2023-03-29 16:53:21,733 epoch 17 - iter 490/493 - loss 0.02861115 - time (sec): 34.48 - samples/sec: 7472.44 - lr: 0.100000
2023-03-29 16:53:21,956 ----------------------------------------------------------------------------------------------------
2023-03-29 16:53:21,956 EPOCH 17 done: loss 0.0287 - lr 0.100000
2023-03-29 16:53:21,956 BAD EPOCHS (no improvement): 0
2023-03-29 16:53:21,959 ----------------------------------------------------------------------------------------------------
2023-03-29 16:53:25,361 epoch 18 - iter 49/493 - loss 0.02505381 - time (sec): 3.40 - samples/sec: 7421.34 - lr: 0.100000
2023-03-29 16:53:28,992 epoch 18 - iter 98/493 - loss 0.02566057 - time (sec): 7.03 - samples/sec: 7292.07 - lr: 0.100000
2023-03-29 16:53:32,582 epoch 18 - iter 147/493 - loss 0.02717920 - time (sec): 10.62 - samples/sec: 7293.06 - lr: 0.100000
2023-03-29 16:53:36,137 epoch 18 - iter 196/493 - loss 0.02619533 - time (sec): 14.18 - samples/sec: 7291.12 - lr: 0.100000
2023-03-29 16:53:39,540 epoch 18 - iter 245/493 - loss 0.02697691 - time (sec): 17.58 - samples/sec: 7334.68 - lr: 0.100000
2023-03-29 16:53:42,916 epoch 18 - iter 294/493 - loss 0.02737061 - time (sec): 20.96 - samples/sec: 7370.69 - lr: 0.100000
2023-03-29 16:53:46,411 epoch 18 - iter 343/493 - loss 0.02737739 - time (sec): 24.45 - samples/sec: 7381.99 - lr: 0.100000
2023-03-29 16:53:49,774 epoch 18 - iter 392/493 - loss 0.02733425 - time (sec): 27.82 - samples/sec: 7412.24 - lr: 0.100000
2023-03-29 16:53:53,175 epoch 18 - iter 441/493 - loss 0.02719115 - time (sec): 31.22 - samples/sec: 7412.58 - lr: 0.100000
2023-03-29 16:53:56,764 epoch 18 - iter 490/493 - loss 0.02743921 - time (sec): 34.80 - samples/sec: 7397.17 - lr: 0.100000
2023-03-29 16:53:56,976 ----------------------------------------------------------------------------------------------------
2023-03-29 16:53:56,976 EPOCH 18 done: loss 0.0275 - lr 0.100000
2023-03-29 16:53:56,976 BAD EPOCHS (no improvement): 0
2023-03-29 16:53:56,979 ----------------------------------------------------------------------------------------------------
2023-03-29 16:54:00,442 epoch 19 - iter 49/493 - loss 0.02522647 - time (sec): 3.46 - samples/sec: 7383.88 - lr: 0.100000
2023-03-29 16:54:03,946 epoch 19 - iter 98/493 - loss 0.02666554 - time (sec): 6.97 - samples/sec: 7298.43 - lr: 0.100000
2023-03-29 16:54:07,635 epoch 19 - iter 147/493 - loss 0.02635048 - time (sec): 10.66 - samples/sec: 7248.31 - lr: 0.100000
2023-03-29 16:54:10,989 epoch 19 - iter 196/493 - loss 0.02605426 - time (sec): 14.01 - samples/sec: 7336.96 - lr: 0.100000
2023-03-29 16:54:14,426 epoch 19 - iter 245/493 - loss 0.02609494 - time (sec): 17.45 - samples/sec: 7346.52 - lr: 0.100000
2023-03-29 16:54:17,931 epoch 19 - iter 294/493 - loss 0.02540040 - time (sec): 20.95 - samples/sec: 7366.71 - lr: 0.100000
2023-03-29 16:54:21,374 epoch 19 - iter 343/493 - loss 0.02600550 - time (sec): 24.39 - samples/sec: 7370.70 - lr: 0.100000
2023-03-29 16:54:24,781 epoch 19 - iter 392/493 - loss 0.02636907 - time (sec): 27.80 - samples/sec: 7416.99 - lr: 0.100000
2023-03-29 16:54:28,203 epoch 19 - iter 441/493 - loss 0.02621604 - time (sec): 31.22 - samples/sec: 7431.68 - lr: 0.100000
2023-03-29 16:54:31,587 epoch 19 - iter 490/493 - loss 0.02622509 - time (sec): 34.61 - samples/sec: 7443.55 - lr: 0.100000
2023-03-29 16:54:31,803 ----------------------------------------------------------------------------------------------------
2023-03-29 16:54:31,803 EPOCH 19 done: loss 0.0261 - lr 0.100000
2023-03-29 16:54:31,803 BAD EPOCHS (no improvement): 0
2023-03-29 16:54:31,806 ----------------------------------------------------------------------------------------------------
2023-03-29 16:54:35,299 epoch 20 - iter 49/493 - loss 0.02261473 - time (sec): 3.49 - samples/sec: 7428.57 - lr: 0.100000
2023-03-29 16:54:38,759 epoch 20 - iter 98/493 - loss 0.02338803 - time (sec): 6.95 - samples/sec: 7473.40 - lr: 0.100000
2023-03-29 16:54:42,116 epoch 20 - iter 147/493 - loss 0.02413707 - time (sec): 10.31 - samples/sec: 7505.11 - lr: 0.100000
2023-03-29 16:54:45,539 epoch 20 - iter 196/493 - loss 0.02438812 - time (sec): 13.73 - samples/sec: 7498.12 - lr: 0.100000
2023-03-29 16:54:48,952 epoch 20 - iter 245/493 - loss 0.02509863 - time (sec): 17.15 - samples/sec: 7449.20 - lr: 0.100000
2023-03-29 16:54:52,544 epoch 20 - iter 294/493 - loss 0.02548981 - time (sec): 20.74 - samples/sec: 7424.67 - lr: 0.100000
2023-03-29 16:54:56,087 epoch 20 - iter 343/493 - loss 0.02576187 - time (sec): 24.28 - samples/sec: 7424.90 - lr: 0.100000
2023-03-29 16:54:59,659 epoch 20 - iter 392/493 - loss 0.02583905 - time (sec): 27.85 - samples/sec: 7383.33 - lr: 0.100000
2023-03-29 16:55:03,133 epoch 20 - iter 441/493 - loss 0.02555222 - time (sec): 31.33 - samples/sec: 7390.61 - lr: 0.100000
2023-03-29 16:55:06,579 epoch 20 - iter 490/493 - loss 0.02572386 - time (sec): 34.77 - samples/sec: 7407.18 - lr: 0.100000
2023-03-29 16:55:06,779 ----------------------------------------------------------------------------------------------------
2023-03-29 16:55:06,779 EPOCH 20 done: loss 0.0257 - lr 0.100000
2023-03-29 16:55:06,779 BAD EPOCHS (no improvement): 0
2023-03-29 16:55:06,782 ----------------------------------------------------------------------------------------------------
2023-03-29 16:55:10,358 epoch 21 - iter 49/493 - loss 0.02230234 - time (sec): 3.58 - samples/sec: 7170.68 - lr: 0.100000
2023-03-29 16:55:13,782 epoch 21 - iter 98/493 - loss 0.02296165 - time (sec): 7.00 - samples/sec: 7308.87 - lr: 0.100000
2023-03-29 16:55:17,342 epoch 21 - iter 147/493 - loss 0.02381138 - time (sec): 10.56 - samples/sec: 7309.12 - lr: 0.100000
2023-03-29 16:55:20,799 epoch 21 - iter 196/493 - loss 0.02360520 - time (sec): 14.02 - samples/sec: 7354.02 - lr: 0.100000
2023-03-29 16:55:24,247 epoch 21 - iter 245/493 - loss 0.02404954 - time (sec): 17.46 - samples/sec: 7367.70 - lr: 0.100000
2023-03-29 16:55:27,625 epoch 21 - iter 294/493 - loss 0.02464552 - time (sec): 20.84 - samples/sec: 7397.59 - lr: 0.100000
2023-03-29 16:55:30,915 epoch 21 - iter 343/493 - loss 0.02498145 - time (sec): 24.13 - samples/sec: 7445.29 - lr: 0.100000
2023-03-29 16:55:34,648 epoch 21 - iter 392/493 - loss 0.02466062 - time (sec): 27.87 - samples/sec: 7407.81 - lr: 0.100000
2023-03-29 16:55:38,090 epoch 21 - iter 441/493 - loss 0.02464145 - time (sec): 31.31 - samples/sec: 7417.13 - lr: 0.100000
2023-03-29 16:55:41,514 epoch 21 - iter 490/493 - loss 0.02471447 - time (sec): 34.73 - samples/sec: 7419.10 - lr: 0.100000
2023-03-29 16:55:41,719 ----------------------------------------------------------------------------------------------------
2023-03-29 16:55:41,719 EPOCH 21 done: loss 0.0247 - lr 0.100000
2023-03-29 16:55:41,720 BAD EPOCHS (no improvement): 0
2023-03-29 16:55:41,722 ----------------------------------------------------------------------------------------------------
2023-03-29 16:55:45,122 epoch 22 - iter 49/493 - loss 0.02427077 - time (sec): 3.40 - samples/sec: 7657.38 - lr: 0.100000
2023-03-29 16:55:48,633 epoch 22 - iter 98/493 - loss 0.02580996 - time (sec): 6.91 - samples/sec: 7513.27 - lr: 0.100000
2023-03-29 16:55:51,990 epoch 22 - iter 147/493 - loss 0.02482537 - time (sec): 10.27 - samples/sec: 7497.12 - lr: 0.100000
2023-03-29 16:55:55,426 epoch 22 - iter 196/493 - loss 0.02461447 - time (sec): 13.70 - samples/sec: 7535.37 - lr: 0.100000
2023-03-29 16:55:58,951 epoch 22 - iter 245/493 - loss 0.02492944 - time (sec): 17.23 - samples/sec: 7520.11 - lr: 0.100000
2023-03-29 16:56:02,486 epoch 22 - iter 294/493 - loss 0.02466471 - time (sec): 20.76 - samples/sec: 7473.86 - lr: 0.100000
2023-03-29 16:56:05,822 epoch 22 - iter 343/493 - loss 0.02423040 - time (sec): 24.10 - samples/sec: 7484.40 - lr: 0.100000
2023-03-29 16:56:09,396 epoch 22 - iter 392/493 - loss 0.02433423 - time (sec): 27.67 - samples/sec: 7456.88 - lr: 0.100000
2023-03-29 16:56:12,803 epoch 22 - iter 441/493 - loss 0.02423754 - time (sec): 31.08 - samples/sec: 7438.74 - lr: 0.100000
2023-03-29 16:56:16,336 epoch 22 - iter 490/493 - loss 0.02434931 - time (sec): 34.61 - samples/sec: 7439.05 - lr: 0.100000
2023-03-29 16:56:16,578 ----------------------------------------------------------------------------------------------------
2023-03-29 16:56:16,578 EPOCH 22 done: loss 0.0243 - lr 0.100000
2023-03-29 16:56:16,578 BAD EPOCHS (no improvement): 0
2023-03-29 16:56:16,581 ----------------------------------------------------------------------------------------------------
2023-03-29 16:56:20,162 epoch 23 - iter 49/493 - loss 0.02359272 - time (sec): 3.58 - samples/sec: 7301.46 - lr: 0.100000
2023-03-29 16:56:23,514 epoch 23 - iter 98/493 - loss 0.02420099 - time (sec): 6.93 - samples/sec: 7350.27 - lr: 0.100000
2023-03-29 16:56:27,111 epoch 23 - iter 147/493 - loss 0.02390837 - time (sec): 10.53 - samples/sec: 7295.33 - lr: 0.100000
2023-03-29 16:56:30,803 epoch 23 - iter 196/493 - loss 0.02386080 - time (sec): 14.22 - samples/sec: 7235.51 - lr: 0.100000
2023-03-29 16:56:34,331 epoch 23 - iter 245/493 - loss 0.02349786 - time (sec): 17.75 - samples/sec: 7240.32 - lr: 0.100000
2023-03-29 16:56:37,963 epoch 23 - iter 294/493 - loss 0.02318388 - time (sec): 21.38 - samples/sec: 7232.17 - lr: 0.100000
2023-03-29 16:56:41,545 epoch 23 - iter 343/493 - loss 0.02338028 - time (sec): 24.96 - samples/sec: 7240.44 - lr: 0.100000
2023-03-29 16:56:44,985 epoch 23 - iter 392/493 - loss 0.02360155 - time (sec): 28.40 - samples/sec: 7266.07 - lr: 0.100000
2023-03-29 16:56:48,448 epoch 23 - iter 441/493 - loss 0.02397330 - time (sec): 31.87 - samples/sec: 7279.46 - lr: 0.100000
2023-03-29 16:56:51,903 epoch 23 - iter 490/493 - loss 0.02395066 - time (sec): 35.32 - samples/sec: 7291.49 - lr: 0.100000
2023-03-29 16:56:52,130 ----------------------------------------------------------------------------------------------------
2023-03-29 16:56:52,131 EPOCH 23 done: loss 0.0239 - lr 0.100000
2023-03-29 16:56:52,131 BAD EPOCHS (no improvement): 0
2023-03-29 16:56:52,133 ----------------------------------------------------------------------------------------------------
2023-03-29 16:56:55,518 epoch 24 - iter 49/493 - loss 0.02095970 - time (sec): 3.39 - samples/sec: 7656.77 - lr: 0.100000
2023-03-29 16:56:59,044 epoch 24 - iter 98/493 - loss 0.02328984 - time (sec): 6.91 - samples/sec: 7518.07 - lr: 0.100000
2023-03-29 16:57:02,592 epoch 24 - iter 147/493 - loss 0.02424203 - time (sec): 10.46 - samples/sec: 7458.15 - lr: 0.100000
2023-03-29 16:57:06,016 epoch 24 - iter 196/493 - loss 0.02367765 - time (sec): 13.88 - samples/sec: 7490.98 - lr: 0.100000
2023-03-29 16:57:09,380 epoch 24 - iter 245/493 - loss 0.02314913 - time (sec): 17.25 - samples/sec: 7506.28 - lr: 0.100000
2023-03-29 16:57:12,843 epoch 24 - iter 294/493 - loss 0.02319669 - time (sec): 20.71 - samples/sec: 7480.45 - lr: 0.100000
2023-03-29 16:57:16,329 epoch 24 - iter 343/493 - loss 0.02329273 - time (sec): 24.20 - samples/sec: 7457.53 - lr: 0.100000
2023-03-29 16:57:19,746 epoch 24 - iter 392/493 - loss 0.02327041 - time (sec): 27.61 - samples/sec: 7462.46 - lr: 0.100000
2023-03-29 16:57:23,072 epoch 24 - iter 441/493 - loss 0.02335046 - time (sec): 30.94 - samples/sec: 7484.59 - lr: 0.100000
2023-03-29 16:57:26,462 epoch 24 - iter 490/493 - loss 0.02332618 - time (sec): 34.33 - samples/sec: 7498.66 - lr: 0.100000
2023-03-29 16:57:26,711 ----------------------------------------------------------------------------------------------------
2023-03-29 16:57:26,711 EPOCH 24 done: loss 0.0233 - lr 0.100000
2023-03-29 16:57:26,712 BAD EPOCHS (no improvement): 0
2023-03-29 16:57:26,714 ----------------------------------------------------------------------------------------------------
2023-03-29 16:57:30,266 epoch 25 - iter 49/493 - loss 0.02248101 - time (sec): 3.55 - samples/sec: 7347.62 - lr: 0.100000
2023-03-29 16:57:33,724 epoch 25 - iter 98/493 - loss 0.02274761 - time (sec): 7.01 - samples/sec: 7456.50 - lr: 0.100000
2023-03-29 16:57:37,115 epoch 25 - iter 147/493 - loss 0.02235646 - time (sec): 10.40 - samples/sec: 7508.82 - lr: 0.100000
2023-03-29 16:57:40,615 epoch 25 - iter 196/493 - loss 0.02197934 - time (sec): 13.90 - samples/sec: 7474.03 - lr: 0.100000
2023-03-29 16:57:44,057 epoch 25 - iter 245/493 - loss 0.02217488 - time (sec): 17.34 - samples/sec: 7471.17 - lr: 0.100000
2023-03-29 16:57:47,552 epoch 25 - iter 294/493 - loss 0.02251446 - time (sec): 20.84 - samples/sec: 7443.73 - lr: 0.100000
2023-03-29 16:57:50,919 epoch 25 - iter 343/493 - loss 0.02266783 - time (sec): 24.21 - samples/sec: 7447.12 - lr: 0.100000
2023-03-29 16:57:54,388 epoch 25 - iter 392/493 - loss 0.02276777 - time (sec): 27.67 - samples/sec: 7457.66 - lr: 0.100000
2023-03-29 16:57:57,701 epoch 25 - iter 441/493 - loss 0.02291707 - time (sec): 30.99 - samples/sec: 7493.77 - lr: 0.100000
2023-03-29 16:58:01,002 epoch 25 - iter 490/493 - loss 0.02290020 - time (sec): 34.29 - samples/sec: 7522.17 - lr: 0.100000
2023-03-29 16:58:01,154 ----------------------------------------------------------------------------------------------------
2023-03-29 16:58:01,155 EPOCH 25 done: loss 0.0229 - lr 0.100000
2023-03-29 16:58:01,155 BAD EPOCHS (no improvement): 0
2023-03-29 16:58:01,157 ----------------------------------------------------------------------------------------------------
2023-03-29 16:58:04,610 epoch 26 - iter 49/493 - loss 0.02121337 - time (sec): 3.45 - samples/sec: 7602.00 - lr: 0.100000
2023-03-29 16:58:08,034 epoch 26 - iter 98/493 - loss 0.02081900 - time (sec): 6.88 - samples/sec: 7537.43 - lr: 0.100000
2023-03-29 16:58:11,496 epoch 26 - iter 147/493 - loss 0.02158772 - time (sec): 10.34 - samples/sec: 7492.35 - lr: 0.100000
2023-03-29 16:58:15,045 epoch 26 - iter 196/493 - loss 0.02148317 - time (sec): 13.89 - samples/sec: 7482.44 - lr: 0.100000
2023-03-29 16:58:18,392 epoch 26 - iter 245/493 - loss 0.02160603 - time (sec): 17.23 - samples/sec: 7487.59 - lr: 0.100000
2023-03-29 16:58:21,821 epoch 26 - iter 294/493 - loss 0.02170775 - time (sec): 20.66 - samples/sec: 7483.18 - lr: 0.100000
2023-03-29 16:58:25,264 epoch 26 - iter 343/493 - loss 0.02175861 - time (sec): 24.11 - samples/sec: 7498.01 - lr: 0.100000
2023-03-29 16:58:28,677 epoch 26 - iter 392/493 - loss 0.02189150 - time (sec): 27.52 - samples/sec: 7496.63 - lr: 0.100000
2023-03-29 16:58:32,113 epoch 26 - iter 441/493 - loss 0.02204473 - time (sec): 30.96 - samples/sec: 7489.15 - lr: 0.100000
2023-03-29 16:58:35,573 epoch 26 - iter 490/493 - loss 0.02232022 - time (sec): 34.42 - samples/sec: 7486.86 - lr: 0.100000
2023-03-29 16:58:35,785 ----------------------------------------------------------------------------------------------------
2023-03-29 16:58:35,786 EPOCH 26 done: loss 0.0223 - lr 0.100000
2023-03-29 16:58:35,786 BAD EPOCHS (no improvement): 0
2023-03-29 16:58:35,789 ----------------------------------------------------------------------------------------------------
2023-03-29 16:58:39,265 epoch 27 - iter 49/493 - loss 0.01936595 - time (sec): 3.48 - samples/sec: 7545.22 - lr: 0.100000
2023-03-29 16:58:42,893 epoch 27 - iter 98/493 - loss 0.02046637 - time (sec): 7.10 - samples/sec: 7351.79 - lr: 0.100000
2023-03-29 16:58:46,341 epoch 27 - iter 147/493 - loss 0.02126493 - time (sec): 10.55 - samples/sec: 7379.64 - lr: 0.100000
2023-03-29 16:58:49,889 epoch 27 - iter 196/493 - loss 0.02156718 - time (sec): 14.10 - samples/sec: 7382.85 - lr: 0.100000
2023-03-29 16:58:53,286 epoch 27 - iter 245/493 - loss 0.02159603 - time (sec): 17.50 - samples/sec: 7437.47 - lr: 0.100000
2023-03-29 16:58:56,638 epoch 27 - iter 294/493 - loss 0.02162616 - time (sec): 20.85 - samples/sec: 7473.92 - lr: 0.100000
2023-03-29 16:59:00,021 epoch 27 - iter 343/493 - loss 0.02169039 - time (sec): 24.23 - samples/sec: 7472.82 - lr: 0.100000
2023-03-29 16:59:03,381 epoch 27 - iter 392/493 - loss 0.02196524 - time (sec): 27.59 - samples/sec: 7484.73 - lr: 0.100000
2023-03-29 16:59:06,783 epoch 27 - iter 441/493 - loss 0.02198872 - time (sec): 30.99 - samples/sec: 7487.22 - lr: 0.100000
2023-03-29 16:59:10,224 epoch 27 - iter 490/493 - loss 0.02197725 - time (sec): 34.44 - samples/sec: 7486.01 - lr: 0.100000
2023-03-29 16:59:10,417 ----------------------------------------------------------------------------------------------------
2023-03-29 16:59:10,417 EPOCH 27 done: loss 0.0220 - lr 0.100000
2023-03-29 16:59:10,417 BAD EPOCHS (no improvement): 0
2023-03-29 16:59:10,420 ----------------------------------------------------------------------------------------------------
2023-03-29 16:59:13,795 epoch 28 - iter 49/493 - loss 0.01817396 - time (sec): 3.37 - samples/sec: 7569.99 - lr: 0.100000
2023-03-29 16:59:17,035 epoch 28 - iter 98/493 - loss 0.01993294 - time (sec): 6.62 - samples/sec: 7728.02 - lr: 0.100000
2023-03-29 16:59:20,543 epoch 28 - iter 147/493 - loss 0.02037421 - time (sec): 10.12 - samples/sec: 7620.04 - lr: 0.100000
2023-03-29 16:59:23,832 epoch 28 - iter 196/493 - loss 0.02027088 - time (sec): 13.41 - samples/sec: 7618.38 - lr: 0.100000
2023-03-29 16:59:27,228 epoch 28 - iter 245/493 - loss 0.02043651 - time (sec): 16.81 - samples/sec: 7630.34 - lr: 0.100000
2023-03-29 16:59:30,799 epoch 28 - iter 294/493 - loss 0.02062145 - time (sec): 20.38 - samples/sec: 7603.02 - lr: 0.100000
2023-03-29 16:59:34,193 epoch 28 - iter 343/493 - loss 0.02057760 - time (sec): 23.77 - samples/sec: 7592.12 - lr: 0.100000
2023-03-29 16:59:37,670 epoch 28 - iter 392/493 - loss 0.02107826 - time (sec): 27.25 - samples/sec: 7559.59 - lr: 0.100000
2023-03-29 16:59:41,308 epoch 28 - iter 441/493 - loss 0.02149576 - time (sec): 30.89 - samples/sec: 7519.09 - lr: 0.100000
2023-03-29 16:59:44,575 epoch 28 - iter 490/493 - loss 0.02140158 - time (sec): 34.15 - samples/sec: 7544.17 - lr: 0.100000
2023-03-29 16:59:44,756 ----------------------------------------------------------------------------------------------------
2023-03-29 16:59:44,756 EPOCH 28 done: loss 0.0214 - lr 0.100000
2023-03-29 16:59:44,756 BAD EPOCHS (no improvement): 0
2023-03-29 16:59:44,759 ----------------------------------------------------------------------------------------------------
2023-03-29 16:59:48,463 epoch 29 - iter 49/493 - loss 0.02004433 - time (sec): 3.70 - samples/sec: 7020.39 - lr: 0.100000
2023-03-29 16:59:51,927 epoch 29 - iter 98/493 - loss 0.02018283 - time (sec): 7.17 - samples/sec: 7248.82 - lr: 0.100000
2023-03-29 16:59:55,475 epoch 29 - iter 147/493 - loss 0.01976671 - time (sec): 10.72 - samples/sec: 7370.52 - lr: 0.100000
2023-03-29 16:59:58,896 epoch 29 - iter 196/493 - loss 0.01972188 - time (sec): 14.14 - samples/sec: 7376.56 - lr: 0.100000
2023-03-29 17:00:02,459 epoch 29 - iter 245/493 - loss 0.02013960 - time (sec): 17.70 - samples/sec: 7345.55 - lr: 0.100000
2023-03-29 17:00:05,916 epoch 29 - iter 294/493 - loss 0.02049491 - time (sec): 21.16 - samples/sec: 7352.49 - lr: 0.100000
2023-03-29 17:00:09,470 epoch 29 - iter 343/493 - loss 0.02100287 - time (sec): 24.71 - samples/sec: 7339.05 - lr: 0.100000
2023-03-29 17:00:13,005 epoch 29 - iter 392/493 - loss 0.02139835 - time (sec): 28.25 - samples/sec: 7328.32 - lr: 0.100000
2023-03-29 17:00:16,365 epoch 29 - iter 441/493 - loss 0.02136569 - time (sec): 31.61 - samples/sec: 7344.73 - lr: 0.100000
2023-03-29 17:00:19,731 epoch 29 - iter 490/493 - loss 0.02103539 - time (sec): 34.97 - samples/sec: 7366.77 - lr: 0.100000
2023-03-29 17:00:19,919 ----------------------------------------------------------------------------------------------------
2023-03-29 17:00:19,919 EPOCH 29 done: loss 0.0211 - lr 0.100000
2023-03-29 17:00:19,919 BAD EPOCHS (no improvement): 0
2023-03-29 17:00:19,922 ----------------------------------------------------------------------------------------------------
2023-03-29 17:00:23,334 epoch 30 - iter 49/493 - loss 0.02147030 - time (sec): 3.41 - samples/sec: 7513.04 - lr: 0.100000
2023-03-29 17:00:26,692 epoch 30 - iter 98/493 - loss 0.02071065 - time (sec): 6.77 - samples/sec: 7543.61 - lr: 0.100000
2023-03-29 17:00:30,244 epoch 30 - iter 147/493 - loss 0.02038991 - time (sec): 10.32 - samples/sec: 7443.01 - lr: 0.100000
2023-03-29 17:00:33,696 epoch 30 - iter 196/493 - loss 0.01993747 - time (sec): 13.77 - samples/sec: 7465.51 - lr: 0.100000
2023-03-29 17:00:37,202 epoch 30 - iter 245/493 - loss 0.02010334 - time (sec): 17.28 - samples/sec: 7460.56 - lr: 0.100000
2023-03-29 17:00:40,707 epoch 30 - iter 294/493 - loss 0.02037618 - time (sec): 20.79 - samples/sec: 7444.31 - lr: 0.100000
2023-03-29 17:00:44,109 epoch 30 - iter 343/493 - loss 0.02047890 - time (sec): 24.19 - samples/sec: 7448.45 - lr: 0.100000
2023-03-29 17:00:47,506 epoch 30 - iter 392/493 - loss 0.02095414 - time (sec): 27.58 - samples/sec: 7451.52 - lr: 0.100000
2023-03-29 17:00:50,851 epoch 30 - iter 441/493 - loss 0.02134298 - time (sec): 30.93 - samples/sec: 7497.46 - lr: 0.100000
2023-03-29 17:00:54,243 epoch 30 - iter 490/493 - loss 0.02140982 - time (sec): 34.32 - samples/sec: 7504.63 - lr: 0.100000
2023-03-29 17:00:54,449 ----------------------------------------------------------------------------------------------------
2023-03-29 17:00:54,449 EPOCH 30 done: loss 0.0214 - lr 0.100000
2023-03-29 17:00:54,449 BAD EPOCHS (no improvement): 1
2023-03-29 17:00:54,452 ----------------------------------------------------------------------------------------------------
2023-03-29 17:00:57,878 epoch 31 - iter 49/493 - loss 0.01921930 - time (sec): 3.43 - samples/sec: 7534.61 - lr: 0.100000
2023-03-29 17:01:01,238 epoch 31 - iter 98/493 - loss 0.01979540 - time (sec): 6.79 - samples/sec: 7593.91 - lr: 0.100000
2023-03-29 17:01:04,533 epoch 31 - iter 147/493 - loss 0.02032389 - time (sec): 10.08 - samples/sec: 7615.78 - lr: 0.100000
2023-03-29 17:01:08,052 epoch 31 - iter 196/493 - loss 0.02106022 - time (sec): 13.60 - samples/sec: 7588.18 - lr: 0.100000
2023-03-29 17:01:11,341 epoch 31 - iter 245/493 - loss 0.02059598 - time (sec): 16.89 - samples/sec: 7576.95 - lr: 0.100000
2023-03-29 17:01:14,726 epoch 31 - iter 294/493 - loss 0.02049102 - time (sec): 20.27 - samples/sec: 7599.15 - lr: 0.100000
2023-03-29 17:01:18,305 epoch 31 - iter 343/493 - loss 0.02002229 - time (sec): 23.85 - samples/sec: 7556.16 - lr: 0.100000
2023-03-29 17:01:21,704 epoch 31 - iter 392/493 - loss 0.01990785 - time (sec): 27.25 - samples/sec: 7565.72 - lr: 0.100000
2023-03-29 17:01:25,211 epoch 31 - iter 441/493 - loss 0.01990999 - time (sec): 30.76 - samples/sec: 7552.65 - lr: 0.100000
2023-03-29 17:01:28,617 epoch 31 - iter 490/493 - loss 0.01977638 - time (sec): 34.17 - samples/sec: 7544.21 - lr: 0.100000
2023-03-29 17:01:28,792 ----------------------------------------------------------------------------------------------------
2023-03-29 17:01:28,793 EPOCH 31 done: loss 0.0199 - lr 0.100000
2023-03-29 17:01:28,793 BAD EPOCHS (no improvement): 0
2023-03-29 17:01:28,796 ----------------------------------------------------------------------------------------------------
2023-03-29 17:01:32,196 epoch 32 - iter 49/493 - loss 0.01670713 - time (sec): 3.40 - samples/sec: 7328.94 - lr: 0.100000
2023-03-29 17:01:35,665 epoch 32 - iter 98/493 - loss 0.01803757 - time (sec): 6.87 - samples/sec: 7377.19 - lr: 0.100000
2023-03-29 17:01:39,079 epoch 32 - iter 147/493 - loss 0.01853837 - time (sec): 10.28 - samples/sec: 7435.13 - lr: 0.100000
2023-03-29 17:01:42,619 epoch 32 - iter 196/493 - loss 0.01865148 - time (sec): 13.82 - samples/sec: 7399.52 - lr: 0.100000
2023-03-29 17:01:46,006 epoch 32 - iter 245/493 - loss 0.01941646 - time (sec): 17.21 - samples/sec: 7447.13 - lr: 0.100000
2023-03-29 17:01:49,405 epoch 32 - iter 294/493 - loss 0.01942109 - time (sec): 20.61 - samples/sec: 7466.68 - lr: 0.100000
2023-03-29 17:01:52,741 epoch 32 - iter 343/493 - loss 0.01914671 - time (sec): 23.94 - samples/sec: 7491.61 - lr: 0.100000
2023-03-29 17:01:56,241 epoch 32 - iter 392/493 - loss 0.01956232 - time (sec): 27.45 - samples/sec: 7484.30 - lr: 0.100000
2023-03-29 17:01:59,739 epoch 32 - iter 441/493 - loss 0.01963566 - time (sec): 30.94 - samples/sec: 7481.46 - lr: 0.100000
2023-03-29 17:02:03,255 epoch 32 - iter 490/493 - loss 0.01958624 - time (sec): 34.46 - samples/sec: 7467.47 - lr: 0.100000
2023-03-29 17:02:03,511 ----------------------------------------------------------------------------------------------------
2023-03-29 17:02:03,511 EPOCH 32 done: loss 0.0195 - lr 0.100000
2023-03-29 17:02:03,511 BAD EPOCHS (no improvement): 0
2023-03-29 17:02:03,515 ----------------------------------------------------------------------------------------------------
2023-03-29 17:02:09,836 epoch 33 - iter 49/493 - loss 0.01773546 - time (sec): 6.32 - samples/sec: 4065.61 - lr: 0.100000
2023-03-29 17:02:13,367 epoch 33 - iter 98/493 - loss 0.01758205 - time (sec): 9.85 - samples/sec: 5233.97 - lr: 0.100000
2023-03-29 17:02:16,801 epoch 33 - iter 147/493 - loss 0.01691064 - time (sec): 13.29 - samples/sec: 5817.72 - lr: 0.100000
2023-03-29 17:02:20,291 epoch 33 - iter 196/493 - loss 0.01741224 - time (sec): 16.78 - samples/sec: 6144.58 - lr: 0.100000
2023-03-29 17:02:23,634 epoch 33 - iter 245/493 - loss 0.01742488 - time (sec): 20.12 - samples/sec: 6395.04 - lr: 0.100000
2023-03-29 17:02:27,006 epoch 33 - iter 294/493 - loss 0.01779106 - time (sec): 23.49 - samples/sec: 6591.64 - lr: 0.100000
2023-03-29 17:02:30,475 epoch 33 - iter 343/493 - loss 0.01811343 - time (sec): 26.96 - samples/sec: 6699.48 - lr: 0.100000
2023-03-29 17:02:33,920 epoch 33 - iter 392/493 - loss 0.01867143 - time (sec): 30.41 - samples/sec: 6782.42 - lr: 0.100000
2023-03-29 17:02:37,339 epoch 33 - iter 441/493 - loss 0.01895394 - time (sec): 33.82 - samples/sec: 6867.85 - lr: 0.100000
2023-03-29 17:02:40,718 epoch 33 - iter 490/493 - loss 0.01911883 - time (sec): 37.20 - samples/sec: 6924.32 - lr: 0.100000
2023-03-29 17:02:40,918 ----------------------------------------------------------------------------------------------------
2023-03-29 17:02:40,918 EPOCH 33 done: loss 0.0191 - lr 0.100000
2023-03-29 17:02:40,918 BAD EPOCHS (no improvement): 0
2023-03-29 17:02:40,922 ----------------------------------------------------------------------------------------------------
2023-03-29 17:02:44,318 epoch 34 - iter 49/493 - loss 0.01734115 - time (sec): 3.40 - samples/sec: 7628.31 - lr: 0.100000
2023-03-29 17:02:47,604 epoch 34 - iter 98/493 - loss 0.01733570 - time (sec): 6.68 - samples/sec: 7677.96 - lr: 0.100000
2023-03-29 17:02:51,019 epoch 34 - iter 147/493 - loss 0.01795239 - time (sec): 10.10 - samples/sec: 7644.00 - lr: 0.100000
2023-03-29 17:02:54,361 epoch 34 - iter 196/493 - loss 0.01844653 - time (sec): 13.44 - samples/sec: 7649.58 - lr: 0.100000
2023-03-29 17:02:57,812 epoch 34 - iter 245/493 - loss 0.01867821 - time (sec): 16.89 - samples/sec: 7619.66 - lr: 0.100000
2023-03-29 17:03:01,199 epoch 34 - iter 294/493 - loss 0.01873024 - time (sec): 20.28 - samples/sec: 7593.65 - lr: 0.100000
2023-03-29 17:03:04,606 epoch 34 - iter 343/493 - loss 0.01869788 - time (sec): 23.68 - samples/sec: 7592.07 - lr: 0.100000
2023-03-29 17:03:07,923 epoch 34 - iter 392/493 - loss 0.01864921 - time (sec): 27.00 - samples/sec: 7600.98 - lr: 0.100000
2023-03-29 17:03:11,464 epoch 34 - iter 441/493 - loss 0.01868923 - time (sec): 30.54 - samples/sec: 7581.79 - lr: 0.100000
2023-03-29 17:03:14,963 epoch 34 - iter 490/493 - loss 0.01919747 - time (sec): 34.04 - samples/sec: 7561.04 - lr: 0.100000
2023-03-29 17:03:15,264 ----------------------------------------------------------------------------------------------------
2023-03-29 17:03:15,264 EPOCH 34 done: loss 0.0192 - lr 0.100000
2023-03-29 17:03:15,264 BAD EPOCHS (no improvement): 1
2023-03-29 17:03:15,270 ----------------------------------------------------------------------------------------------------
2023-03-29 17:03:18,716 epoch 35 - iter 49/493 - loss 0.01656590 - time (sec): 3.45 - samples/sec: 7486.19 - lr: 0.100000
2023-03-29 17:03:22,275 epoch 35 - iter 98/493 - loss 0.01727986 - time (sec): 7.00 - samples/sec: 7454.43 - lr: 0.100000
2023-03-29 17:03:25,834 epoch 35 - iter 147/493 - loss 0.01749116 - time (sec): 10.56 - samples/sec: 7386.99 - lr: 0.100000
2023-03-29 17:03:29,340 epoch 35 - iter 196/493 - loss 0.01760123 - time (sec): 14.07 - samples/sec: 7359.82 - lr: 0.100000
2023-03-29 17:03:32,947 epoch 35 - iter 245/493 - loss 0.01797448 - time (sec): 17.68 - samples/sec: 7344.10 - lr: 0.100000
2023-03-29 17:03:36,459 epoch 35 - iter 294/493 - loss 0.01793659 - time (sec): 21.19 - samples/sec: 7320.86 - lr: 0.100000
2023-03-29 17:03:39,860 epoch 35 - iter 343/493 - loss 0.01818851 - time (sec): 24.59 - samples/sec: 7360.13 - lr: 0.100000
2023-03-29 17:03:43,242 epoch 35 - iter 392/493 - loss 0.01832636 - time (sec): 27.97 - samples/sec: 7378.54 - lr: 0.100000
2023-03-29 17:03:46,775 epoch 35 - iter 441/493 - loss 0.01858242 - time (sec): 31.50 - samples/sec: 7361.57 - lr: 0.100000
2023-03-29 17:03:50,179 epoch 35 - iter 490/493 - loss 0.01874364 - time (sec): 34.91 - samples/sec: 7379.04 - lr: 0.100000
2023-03-29 17:03:50,390 ----------------------------------------------------------------------------------------------------
2023-03-29 17:03:50,391 EPOCH 35 done: loss 0.0187 - lr 0.100000
2023-03-29 17:03:50,391 BAD EPOCHS (no improvement): 0
2023-03-29 17:03:50,394 ----------------------------------------------------------------------------------------------------
2023-03-29 17:03:53,778 epoch 36 - iter 49/493 - loss 0.01421262 - time (sec): 3.38 - samples/sec: 7337.27 - lr: 0.100000
2023-03-29 17:03:57,124 epoch 36 - iter 98/493 - loss 0.01543496 - time (sec): 6.73 - samples/sec: 7490.82 - lr: 0.100000
2023-03-29 17:04:00,583 epoch 36 - iter 147/493 - loss 0.01703673 - time (sec): 10.19 - samples/sec: 7550.41 - lr: 0.100000
2023-03-29 17:04:03,871 epoch 36 - iter 196/493 - loss 0.01655657 - time (sec): 13.48 - samples/sec: 7605.83 - lr: 0.100000
2023-03-29 17:04:07,355 epoch 36 - iter 245/493 - loss 0.01745942 - time (sec): 16.96 - samples/sec: 7583.79 - lr: 0.100000
2023-03-29 17:04:10,887 epoch 36 - iter 294/493 - loss 0.01805801 - time (sec): 20.49 - samples/sec: 7520.81 - lr: 0.100000
2023-03-29 17:04:14,384 epoch 36 - iter 343/493 - loss 0.01826545 - time (sec): 23.99 - samples/sec: 7496.38 - lr: 0.100000
2023-03-29 17:04:17,886 epoch 36 - iter 392/493 - loss 0.01839494 - time (sec): 27.49 - samples/sec: 7507.28 - lr: 0.100000
2023-03-29 17:04:21,345 epoch 36 - iter 441/493 - loss 0.01843839 - time (sec): 30.95 - samples/sec: 7494.31 - lr: 0.100000
2023-03-29 17:04:24,801 epoch 36 - iter 490/493 - loss 0.01846872 - time (sec): 34.41 - samples/sec: 7485.02 - lr: 0.100000
2023-03-29 17:04:25,017 ----------------------------------------------------------------------------------------------------
2023-03-29 17:04:25,017 EPOCH 36 done: loss 0.0184 - lr 0.100000
2023-03-29 17:04:25,017 BAD EPOCHS (no improvement): 0
2023-03-29 17:04:25,020 ----------------------------------------------------------------------------------------------------
2023-03-29 17:04:28,416 epoch 37 - iter 49/493 - loss 0.01785955 - time (sec): 3.40 - samples/sec: 7514.73 - lr: 0.100000
2023-03-29 17:04:31,669 epoch 37 - iter 98/493 - loss 0.01847271 - time (sec): 6.65 - samples/sec: 7584.10 - lr: 0.100000
2023-03-29 17:04:35,108 epoch 37 - iter 147/493 - loss 0.01884187 - time (sec): 10.09 - samples/sec: 7578.35 - lr: 0.100000
2023-03-29 17:04:38,489 epoch 37 - iter 196/493 - loss 0.01874920 - time (sec): 13.47 - samples/sec: 7620.98 - lr: 0.100000
2023-03-29 17:04:41,905 epoch 37 - iter 245/493 - loss 0.01854140 - time (sec): 16.89 - samples/sec: 7595.70 - lr: 0.100000
2023-03-29 17:04:45,388 epoch 37 - iter 294/493 - loss 0.01816475 - time (sec): 20.37 - samples/sec: 7557.46 - lr: 0.100000
2023-03-29 17:04:48,833 epoch 37 - iter 343/493 - loss 0.01818780 - time (sec): 23.81 - samples/sec: 7554.96 - lr: 0.100000
2023-03-29 17:04:52,327 epoch 37 - iter 392/493 - loss 0.01838789 - time (sec): 27.31 - samples/sec: 7556.49 - lr: 0.100000
2023-03-29 17:04:55,765 epoch 37 - iter 441/493 - loss 0.01844340 - time (sec): 30.75 - samples/sec: 7537.68 - lr: 0.100000
2023-03-29 17:04:59,311 epoch 37 - iter 490/493 - loss 0.01886309 - time (sec): 34.29 - samples/sec: 7513.43 - lr: 0.100000
2023-03-29 17:04:59,553 ----------------------------------------------------------------------------------------------------
2023-03-29 17:04:59,554 EPOCH 37 done: loss 0.0189 - lr 0.100000
2023-03-29 17:04:59,554 BAD EPOCHS (no improvement): 1
2023-03-29 17:04:59,557 ----------------------------------------------------------------------------------------------------
2023-03-29 17:05:02,868 epoch 38 - iter 49/493 - loss 0.01747937 - time (sec): 3.31 - samples/sec: 7738.36 - lr: 0.100000
2023-03-29 17:05:06,183 epoch 38 - iter 98/493 - loss 0.01749155 - time (sec): 6.63 - samples/sec: 7712.70 - lr: 0.100000
2023-03-29 17:05:09,842 epoch 38 - iter 147/493 - loss 0.01740220 - time (sec): 10.28 - samples/sec: 7520.64 - lr: 0.100000
2023-03-29 17:05:13,358 epoch 38 - iter 196/493 - loss 0.01688770 - time (sec): 13.80 - samples/sec: 7454.68 - lr: 0.100000
2023-03-29 17:05:16,863 epoch 38 - iter 245/493 - loss 0.01737584 - time (sec): 17.31 - samples/sec: 7448.11 - lr: 0.100000
2023-03-29 17:05:20,231 epoch 38 - iter 294/493 - loss 0.01739911 - time (sec): 20.67 - samples/sec: 7464.11 - lr: 0.100000
2023-03-29 17:05:23,501 epoch 38 - iter 343/493 - loss 0.01745142 - time (sec): 23.94 - samples/sec: 7507.98 - lr: 0.100000
2023-03-29 17:05:26,947 epoch 38 - iter 392/493 - loss 0.01756866 - time (sec): 27.39 - samples/sec: 7505.09 - lr: 0.100000
2023-03-29 17:05:30,360 epoch 38 - iter 441/493 - loss 0.01756450 - time (sec): 30.80 - samples/sec: 7513.29 - lr: 0.100000
2023-03-29 17:05:33,771 epoch 38 - iter 490/493 - loss 0.01759899 - time (sec): 34.21 - samples/sec: 7525.44 - lr: 0.100000
2023-03-29 17:05:33,983 ----------------------------------------------------------------------------------------------------
2023-03-29 17:05:33,983 EPOCH 38 done: loss 0.0177 - lr 0.100000
2023-03-29 17:05:33,983 BAD EPOCHS (no improvement): 0
2023-03-29 17:05:33,987 ----------------------------------------------------------------------------------------------------
2023-03-29 17:05:37,312 epoch 39 - iter 49/493 - loss 0.01780322 - time (sec): 3.33 - samples/sec: 7463.39 - lr: 0.100000
2023-03-29 17:05:40,838 epoch 39 - iter 98/493 - loss 0.01709588 - time (sec): 6.85 - samples/sec: 7441.15 - lr: 0.100000
2023-03-29 17:05:44,367 epoch 39 - iter 147/493 - loss 0.01675546 - time (sec): 10.38 - samples/sec: 7382.39 - lr: 0.100000
2023-03-29 17:05:47,830 epoch 39 - iter 196/493 - loss 0.01693559 - time (sec): 13.84 - samples/sec: 7394.50 - lr: 0.100000
2023-03-29 17:05:51,460 epoch 39 - iter 245/493 - loss 0.01699721 - time (sec): 17.47 - samples/sec: 7365.81 - lr: 0.100000
2023-03-29 17:05:55,143 epoch 39 - iter 294/493 - loss 0.01717201 - time (sec): 21.16 - samples/sec: 7297.92 - lr: 0.100000
2023-03-29 17:05:58,676 epoch 39 - iter 343/493 - loss 0.01759266 - time (sec): 24.69 - samples/sec: 7317.66 - lr: 0.100000
2023-03-29 17:06:02,247 epoch 39 - iter 392/493 - loss 0.01771966 - time (sec): 28.26 - samples/sec: 7306.37 - lr: 0.100000
2023-03-29 17:06:05,776 epoch 39 - iter 441/493 - loss 0.01791377 - time (sec): 31.79 - samples/sec: 7293.79 - lr: 0.100000
2023-03-29 17:06:09,131 epoch 39 - iter 490/493 - loss 0.01813105 - time (sec): 35.14 - samples/sec: 7328.41 - lr: 0.100000
2023-03-29 17:06:09,334 ----------------------------------------------------------------------------------------------------
2023-03-29 17:06:09,334 EPOCH 39 done: loss 0.0181 - lr 0.100000
2023-03-29 17:06:09,334 BAD EPOCHS (no improvement): 1
2023-03-29 17:06:09,337 ----------------------------------------------------------------------------------------------------
2023-03-29 17:06:12,756 epoch 40 - iter 49/493 - loss 0.01830086 - time (sec): 3.42 - samples/sec: 7577.95 - lr: 0.100000
2023-03-29 17:06:16,173 epoch 40 - iter 98/493 - loss 0.01851355 - time (sec): 6.84 - samples/sec: 7594.57 - lr: 0.100000
2023-03-29 17:06:19,703 epoch 40 - iter 147/493 - loss 0.01696150 - time (sec): 10.37 - samples/sec: 7516.09 - lr: 0.100000
2023-03-29 17:06:23,146 epoch 40 - iter 196/493 - loss 0.01668594 - time (sec): 13.81 - samples/sec: 7495.96 - lr: 0.100000
2023-03-29 17:06:26,689 epoch 40 - iter 245/493 - loss 0.01686581 - time (sec): 17.35 - samples/sec: 7460.42 - lr: 0.100000
2023-03-29 17:06:30,079 epoch 40 - iter 294/493 - loss 0.01684896 - time (sec): 20.74 - samples/sec: 7472.84 - lr: 0.100000
2023-03-29 17:06:33,464 epoch 40 - iter 343/493 - loss 0.01693061 - time (sec): 24.13 - samples/sec: 7507.11 - lr: 0.100000
2023-03-29 17:06:36,930 epoch 40 - iter 392/493 - loss 0.01716048 - time (sec): 27.59 - samples/sec: 7485.28 - lr: 0.100000
2023-03-29 17:06:40,272 epoch 40 - iter 441/493 - loss 0.01701427 - time (sec): 30.93 - samples/sec: 7497.06 - lr: 0.100000
2023-03-29 17:06:43,733 epoch 40 - iter 490/493 - loss 0.01710322 - time (sec): 34.40 - samples/sec: 7487.30 - lr: 0.100000
2023-03-29 17:06:43,938 ----------------------------------------------------------------------------------------------------
2023-03-29 17:06:43,938 EPOCH 40 done: loss 0.0171 - lr 0.100000
2023-03-29 17:06:43,939 BAD EPOCHS (no improvement): 0
2023-03-29 17:06:43,942 ----------------------------------------------------------------------------------------------------
2023-03-29 17:06:47,471 epoch 41 - iter 49/493 - loss 0.01867754 - time (sec): 3.53 - samples/sec: 7351.89 - lr: 0.100000
2023-03-29 17:06:50,983 epoch 41 - iter 98/493 - loss 0.01669905 - time (sec): 7.04 - samples/sec: 7336.00 - lr: 0.100000
2023-03-29 17:06:54,471 epoch 41 - iter 147/493 - loss 0.01580668 - time (sec): 10.53 - samples/sec: 7373.61 - lr: 0.100000
2023-03-29 17:06:57,875 epoch 41 - iter 196/493 - loss 0.01592062 - time (sec): 13.93 - samples/sec: 7379.45 - lr: 0.100000
2023-03-29 17:07:01,457 epoch 41 - iter 245/493 - loss 0.01631036 - time (sec): 17.52 - samples/sec: 7304.83 - lr: 0.100000
2023-03-29 17:07:04,856 epoch 41 - iter 294/493 - loss 0.01668790 - time (sec): 20.91 - samples/sec: 7339.41 - lr: 0.100000
2023-03-29 17:07:08,292 epoch 41 - iter 343/493 - loss 0.01710882 - time (sec): 24.35 - samples/sec: 7358.00 - lr: 0.100000
2023-03-29 17:07:11,829 epoch 41 - iter 392/493 - loss 0.01717882 - time (sec): 27.89 - samples/sec: 7372.24 - lr: 0.100000
2023-03-29 17:07:15,357 epoch 41 - iter 441/493 - loss 0.01727225 - time (sec): 31.42 - samples/sec: 7372.63 - lr: 0.100000
2023-03-29 17:07:18,925 epoch 41 - iter 490/493 - loss 0.01738310 - time (sec): 34.98 - samples/sec: 7363.71 - lr: 0.100000
2023-03-29 17:07:19,116 ----------------------------------------------------------------------------------------------------
2023-03-29 17:07:19,116 EPOCH 41 done: loss 0.0173 - lr 0.100000
2023-03-29 17:07:19,116 BAD EPOCHS (no improvement): 1
2023-03-29 17:07:19,119 ----------------------------------------------------------------------------------------------------
2023-03-29 17:07:22,608 epoch 42 - iter 49/493 - loss 0.01486363 - time (sec): 3.49 - samples/sec: 7269.55 - lr: 0.100000
2023-03-29 17:07:26,037 epoch 42 - iter 98/493 - loss 0.01657675 - time (sec): 6.92 - samples/sec: 7393.63 - lr: 0.100000
2023-03-29 17:07:29,447 epoch 42 - iter 147/493 - loss 0.01674186 - time (sec): 10.33 - samples/sec: 7430.30 - lr: 0.100000
2023-03-29 17:07:33,045 epoch 42 - iter 196/493 - loss 0.01680212 - time (sec): 13.93 - samples/sec: 7382.38 - lr: 0.100000
2023-03-29 17:07:36,624 epoch 42 - iter 245/493 - loss 0.01735195 - time (sec): 17.50 - samples/sec: 7356.70 - lr: 0.100000
2023-03-29 17:07:40,050 epoch 42 - iter 294/493 - loss 0.01740284 - time (sec): 20.93 - samples/sec: 7373.11 - lr: 0.100000
2023-03-29 17:07:43,719 epoch 42 - iter 343/493 - loss 0.01731150 - time (sec): 24.60 - samples/sec: 7324.29 - lr: 0.100000
2023-03-29 17:07:47,176 epoch 42 - iter 392/493 - loss 0.01747284 - time (sec): 28.06 - samples/sec: 7329.64 - lr: 0.100000
2023-03-29 17:07:50,692 epoch 42 - iter 441/493 - loss 0.01732007 - time (sec): 31.57 - samples/sec: 7334.41 - lr: 0.100000
2023-03-29 17:07:54,356 epoch 42 - iter 490/493 - loss 0.01756081 - time (sec): 35.24 - samples/sec: 7309.94 - lr: 0.100000
2023-03-29 17:07:54,561 ----------------------------------------------------------------------------------------------------
2023-03-29 17:07:54,561 EPOCH 42 done: loss 0.0176 - lr 0.100000
2023-03-29 17:07:54,561 BAD EPOCHS (no improvement): 2
2023-03-29 17:07:54,564 ----------------------------------------------------------------------------------------------------
2023-03-29 17:07:58,156 epoch 43 - iter 49/493 - loss 0.01346854 - time (sec): 3.59 - samples/sec: 7275.30 - lr: 0.100000
2023-03-29 17:08:01,672 epoch 43 - iter 98/493 - loss 0.01535669 - time (sec): 7.11 - samples/sec: 7289.49 - lr: 0.100000
2023-03-29 17:08:05,178 epoch 43 - iter 147/493 - loss 0.01530354 - time (sec): 10.61 - samples/sec: 7363.62 - lr: 0.100000
2023-03-29 17:08:08,657 epoch 43 - iter 196/493 - loss 0.01612927 - time (sec): 14.09 - samples/sec: 7368.90 - lr: 0.100000
2023-03-29 17:08:11,998 epoch 43 - iter 245/493 - loss 0.01648459 - time (sec): 17.43 - samples/sec: 7376.62 - lr: 0.100000
2023-03-29 17:08:15,661 epoch 43 - iter 294/493 - loss 0.01620351 - time (sec): 21.10 - samples/sec: 7318.49 - lr: 0.100000
2023-03-29 17:08:19,132 epoch 43 - iter 343/493 - loss 0.01615823 - time (sec): 24.57 - samples/sec: 7329.19 - lr: 0.100000
2023-03-29 17:08:22,617 epoch 43 - iter 392/493 - loss 0.01646610 - time (sec): 28.05 - samples/sec: 7334.92 - lr: 0.100000
2023-03-29 17:08:26,271 epoch 43 - iter 441/493 - loss 0.01659449 - time (sec): 31.71 - samples/sec: 7312.24 - lr: 0.100000
2023-03-29 17:08:29,889 epoch 43 - iter 490/493 - loss 0.01682178 - time (sec): 35.33 - samples/sec: 7291.49 - lr: 0.100000
2023-03-29 17:08:30,120 ----------------------------------------------------------------------------------------------------
2023-03-29 17:08:30,120 EPOCH 43 done: loss 0.0168 - lr 0.100000
2023-03-29 17:08:30,120 BAD EPOCHS (no improvement): 0
2023-03-29 17:08:30,133 ----------------------------------------------------------------------------------------------------
2023-03-29 17:08:33,653 epoch 44 - iter 49/493 - loss 0.01396551 - time (sec): 3.52 - samples/sec: 7254.02 - lr: 0.100000
2023-03-29 17:08:36,928 epoch 44 - iter 98/493 - loss 0.01531589 - time (sec): 6.80 - samples/sec: 7522.60 - lr: 0.100000
2023-03-29 17:08:40,572 epoch 44 - iter 147/493 - loss 0.01637416 - time (sec): 10.44 - samples/sec: 7451.59 - lr: 0.100000
2023-03-29 17:08:44,243 epoch 44 - iter 196/493 - loss 0.01580264 - time (sec): 14.11 - samples/sec: 7352.49 - lr: 0.100000
2023-03-29 17:08:47,695 epoch 44 - iter 245/493 - loss 0.01585910 - time (sec): 17.56 - samples/sec: 7297.39 - lr: 0.100000
2023-03-29 17:08:51,180 epoch 44 - iter 294/493 - loss 0.01616521 - time (sec): 21.05 - samples/sec: 7321.38 - lr: 0.100000
2023-03-29 17:08:54,659 epoch 44 - iter 343/493 - loss 0.01602245 - time (sec): 24.53 - samples/sec: 7327.82 - lr: 0.100000
2023-03-29 17:08:58,053 epoch 44 - iter 392/493 - loss 0.01592255 - time (sec): 27.92 - samples/sec: 7354.05 - lr: 0.100000
2023-03-29 17:09:01,516 epoch 44 - iter 441/493 - loss 0.01603362 - time (sec): 31.38 - samples/sec: 7362.04 - lr: 0.100000
2023-03-29 17:09:05,240 epoch 44 - iter 490/493 - loss 0.01606192 - time (sec): 35.11 - samples/sec: 7339.68 - lr: 0.100000
2023-03-29 17:09:05,434 ----------------------------------------------------------------------------------------------------
2023-03-29 17:09:05,434 EPOCH 44 done: loss 0.0160 - lr 0.100000
2023-03-29 17:09:05,434 BAD EPOCHS (no improvement): 0
2023-03-29 17:09:05,437 ----------------------------------------------------------------------------------------------------
2023-03-29 17:09:09,094 epoch 45 - iter 49/493 - loss 0.01512284 - time (sec): 3.66 - samples/sec: 7270.94 - lr: 0.100000
2023-03-29 17:09:12,591 epoch 45 - iter 98/493 - loss 0.01586746 - time (sec): 7.15 - samples/sec: 7257.78 - lr: 0.100000
2023-03-29 17:09:16,026 epoch 45 - iter 147/493 - loss 0.01544188 - time (sec): 10.59 - samples/sec: 7282.31 - lr: 0.100000
2023-03-29 17:09:19,453 epoch 45 - iter 196/493 - loss 0.01610986 - time (sec): 14.02 - samples/sec: 7331.93 - lr: 0.100000
2023-03-29 17:09:23,038 epoch 45 - iter 245/493 - loss 0.01588432 - time (sec): 17.60 - samples/sec: 7323.57 - lr: 0.100000
2023-03-29 17:09:26,600 epoch 45 - iter 294/493 - loss 0.01610278 - time (sec): 21.16 - samples/sec: 7308.80 - lr: 0.100000
2023-03-29 17:09:29,868 epoch 45 - iter 343/493 - loss 0.01617301 - time (sec): 24.43 - samples/sec: 7362.46 - lr: 0.100000
2023-03-29 17:09:33,379 epoch 45 - iter 392/493 - loss 0.01632700 - time (sec): 27.94 - samples/sec: 7351.71 - lr: 0.100000
2023-03-29 17:09:36,945 epoch 45 - iter 441/493 - loss 0.01680040 - time (sec): 31.51 - samples/sec: 7341.96 - lr: 0.100000
2023-03-29 17:09:40,513 epoch 45 - iter 490/493 - loss 0.01696391 - time (sec): 35.08 - samples/sec: 7343.49 - lr: 0.100000
2023-03-29 17:09:40,735 ----------------------------------------------------------------------------------------------------
2023-03-29 17:09:40,735 EPOCH 45 done: loss 0.0170 - lr 0.100000
2023-03-29 17:09:40,735 BAD EPOCHS (no improvement): 1
2023-03-29 17:09:40,738 ----------------------------------------------------------------------------------------------------
2023-03-29 17:09:44,300 epoch 46 - iter 49/493 - loss 0.01467726 - time (sec): 3.56 - samples/sec: 7324.75 - lr: 0.100000
2023-03-29 17:09:47,742 epoch 46 - iter 98/493 - loss 0.01515751 - time (sec): 7.00 - samples/sec: 7388.86 - lr: 0.100000
2023-03-29 17:09:51,347 epoch 46 - iter 147/493 - loss 0.01583287 - time (sec): 10.61 - samples/sec: 7364.21 - lr: 0.100000
2023-03-29 17:09:54,814 epoch 46 - iter 196/493 - loss 0.01586639 - time (sec): 14.08 - samples/sec: 7380.87 - lr: 0.100000
2023-03-29 17:09:58,222 epoch 46 - iter 245/493 - loss 0.01642692 - time (sec): 17.48 - samples/sec: 7360.54 - lr: 0.100000
2023-03-29 17:10:01,954 epoch 46 - iter 294/493 - loss 0.01669223 - time (sec): 21.22 - samples/sec: 7323.34 - lr: 0.100000
2023-03-29 17:10:05,450 epoch 46 - iter 343/493 - loss 0.01656987 - time (sec): 24.71 - samples/sec: 7340.76 - lr: 0.100000
2023-03-29 17:10:08,759 epoch 46 - iter 392/493 - loss 0.01670286 - time (sec): 28.02 - samples/sec: 7372.90 - lr: 0.100000
2023-03-29 17:10:12,155 epoch 46 - iter 441/493 - loss 0.01683924 - time (sec): 31.42 - samples/sec: 7387.09 - lr: 0.100000
2023-03-29 17:10:15,540 epoch 46 - iter 490/493 - loss 0.01687354 - time (sec): 34.80 - samples/sec: 7403.20 - lr: 0.100000
2023-03-29 17:10:15,755 ----------------------------------------------------------------------------------------------------
2023-03-29 17:10:15,755 EPOCH 46 done: loss 0.0169 - lr 0.100000
2023-03-29 17:10:15,755 BAD EPOCHS (no improvement): 2
2023-03-29 17:10:15,758 ----------------------------------------------------------------------------------------------------
2023-03-29 17:10:19,258 epoch 47 - iter 49/493 - loss 0.01523513 - time (sec): 3.50 - samples/sec: 7517.34 - lr: 0.100000
2023-03-29 17:10:22,879 epoch 47 - iter 98/493 - loss 0.01596035 - time (sec): 7.12 - samples/sec: 7296.77 - lr: 0.100000
2023-03-29 17:10:26,473 epoch 47 - iter 147/493 - loss 0.01680429 - time (sec): 10.71 - samples/sec: 7289.03 - lr: 0.100000
2023-03-29 17:10:30,109 epoch 47 - iter 196/493 - loss 0.01626073 - time (sec): 14.35 - samples/sec: 7281.34 - lr: 0.100000
2023-03-29 17:10:33,497 epoch 47 - iter 245/493 - loss 0.01580049 - time (sec): 17.74 - samples/sec: 7277.35 - lr: 0.100000
2023-03-29 17:10:37,212 epoch 47 - iter 294/493 - loss 0.01578821 - time (sec): 21.45 - samples/sec: 7225.98 - lr: 0.100000
2023-03-29 17:10:40,710 epoch 47 - iter 343/493 - loss 0.01535653 - time (sec): 24.95 - samples/sec: 7276.39 - lr: 0.100000
2023-03-29 17:10:44,216 epoch 47 - iter 392/493 - loss 0.01563372 - time (sec): 28.46 - samples/sec: 7267.90 - lr: 0.100000
2023-03-29 17:10:47,786 epoch 47 - iter 441/493 - loss 0.01555640 - time (sec): 32.03 - samples/sec: 7274.36 - lr: 0.100000
2023-03-29 17:10:51,090 epoch 47 - iter 490/493 - loss 0.01558427 - time (sec): 35.33 - samples/sec: 7293.56 - lr: 0.100000
2023-03-29 17:10:51,271 ----------------------------------------------------------------------------------------------------
2023-03-29 17:10:51,271 EPOCH 47 done: loss 0.0156 - lr 0.100000
2023-03-29 17:10:51,271 BAD EPOCHS (no improvement): 0
2023-03-29 17:10:51,274 ----------------------------------------------------------------------------------------------------
2023-03-29 17:10:54,764 epoch 48 - iter 49/493 - loss 0.01426575 - time (sec): 3.49 - samples/sec: 7580.23 - lr: 0.100000
2023-03-29 17:10:58,224 epoch 48 - iter 98/493 - loss 0.01373443 - time (sec): 6.95 - samples/sec: 7438.39 - lr: 0.100000
2023-03-29 17:11:01,806 epoch 48 - iter 147/493 - loss 0.01420001 - time (sec): 10.53 - samples/sec: 7385.08 - lr: 0.100000
2023-03-29 17:11:05,274 epoch 48 - iter 196/493 - loss 0.01435123 - time (sec): 14.00 - samples/sec: 7406.07 - lr: 0.100000
2023-03-29 17:11:08,687 epoch 48 - iter 245/493 - loss 0.01508124 - time (sec): 17.41 - samples/sec: 7434.05 - lr: 0.100000
2023-03-29 17:11:12,079 epoch 48 - iter 294/493 - loss 0.01530754 - time (sec): 20.80 - samples/sec: 7435.97 - lr: 0.100000
2023-03-29 17:11:15,509 epoch 48 - iter 343/493 - loss 0.01553116 - time (sec): 24.23 - samples/sec: 7429.86 - lr: 0.100000
2023-03-29 17:11:19,133 epoch 48 - iter 392/493 - loss 0.01572504 - time (sec): 27.86 - samples/sec: 7410.02 - lr: 0.100000
2023-03-29 17:11:22,654 epoch 48 - iter 441/493 - loss 0.01583564 - time (sec): 31.38 - samples/sec: 7414.97 - lr: 0.100000
2023-03-29 17:11:25,941 epoch 48 - iter 490/493 - loss 0.01578621 - time (sec): 34.67 - samples/sec: 7435.91 - lr: 0.100000
2023-03-29 17:11:26,142 ----------------------------------------------------------------------------------------------------
2023-03-29 17:11:26,142 EPOCH 48 done: loss 0.0158 - lr 0.100000
2023-03-29 17:11:26,142 BAD EPOCHS (no improvement): 1
2023-03-29 17:11:26,145 ----------------------------------------------------------------------------------------------------
2023-03-29 17:11:29,541 epoch 49 - iter 49/493 - loss 0.01388802 - time (sec): 3.40 - samples/sec: 7467.75 - lr: 0.100000
2023-03-29 17:11:32,922 epoch 49 - iter 98/493 - loss 0.01400908 - time (sec): 6.78 - samples/sec: 7479.04 - lr: 0.100000
2023-03-29 17:11:36,313 epoch 49 - iter 147/493 - loss 0.01493476 - time (sec): 10.17 - samples/sec: 7519.48 - lr: 0.100000
2023-03-29 17:11:39,616 epoch 49 - iter 196/493 - loss 0.01474928 - time (sec): 13.47 - samples/sec: 7601.20 - lr: 0.100000
2023-03-29 17:11:43,028 epoch 49 - iter 245/493 - loss 0.01495729 - time (sec): 16.88 - samples/sec: 7614.56 - lr: 0.100000
2023-03-29 17:11:46,433 epoch 49 - iter 294/493 - loss 0.01496143 - time (sec): 20.29 - samples/sec: 7607.41 - lr: 0.100000
2023-03-29 17:11:49,860 epoch 49 - iter 343/493 - loss 0.01536235 - time (sec): 23.71 - samples/sec: 7588.99 - lr: 0.100000
2023-03-29 17:11:53,438 epoch 49 - iter 392/493 - loss 0.01543578 - time (sec): 27.29 - samples/sec: 7565.70 - lr: 0.100000
2023-03-29 17:11:56,900 epoch 49 - iter 441/493 - loss 0.01562429 - time (sec): 30.76 - samples/sec: 7548.76 - lr: 0.100000
2023-03-29 17:12:00,230 epoch 49 - iter 490/493 - loss 0.01585238 - time (sec): 34.08 - samples/sec: 7556.50 - lr: 0.100000
2023-03-29 17:12:00,444 ----------------------------------------------------------------------------------------------------
2023-03-29 17:12:00,444 EPOCH 49 done: loss 0.0158 - lr 0.100000
2023-03-29 17:12:00,444 BAD EPOCHS (no improvement): 2
2023-03-29 17:12:00,447 ----------------------------------------------------------------------------------------------------
2023-03-29 17:12:03,836 epoch 50 - iter 49/493 - loss 0.01489813 - time (sec): 3.39 - samples/sec: 7396.68 - lr: 0.100000
2023-03-29 17:12:07,301 epoch 50 - iter 98/493 - loss 0.01582275 - time (sec): 6.85 - samples/sec: 7443.36 - lr: 0.100000
2023-03-29 17:12:10,781 epoch 50 - iter 147/493 - loss 0.01563354 - time (sec): 10.33 - samples/sec: 7401.89 - lr: 0.100000
2023-03-29 17:12:14,268 epoch 50 - iter 196/493 - loss 0.01588996 - time (sec): 13.82 - samples/sec: 7410.19 - lr: 0.100000
2023-03-29 17:12:17,623 epoch 50 - iter 245/493 - loss 0.01566313 - time (sec): 17.18 - samples/sec: 7454.41 - lr: 0.100000
2023-03-29 17:12:21,151 epoch 50 - iter 294/493 - loss 0.01582972 - time (sec): 20.70 - samples/sec: 7429.94 - lr: 0.100000
2023-03-29 17:12:24,891 epoch 50 - iter 343/493 - loss 0.01550919 - time (sec): 24.44 - samples/sec: 7368.52 - lr: 0.100000
2023-03-29 17:12:28,362 epoch 50 - iter 392/493 - loss 0.01544892 - time (sec): 27.92 - samples/sec: 7361.22 - lr: 0.100000
2023-03-29 17:12:31,892 epoch 50 - iter 441/493 - loss 0.01551870 - time (sec): 31.45 - samples/sec: 7362.98 - lr: 0.100000
2023-03-29 17:12:35,314 epoch 50 - iter 490/493 - loss 0.01538672 - time (sec): 34.87 - samples/sec: 7386.56 - lr: 0.100000
2023-03-29 17:12:35,521 ----------------------------------------------------------------------------------------------------
2023-03-29 17:12:35,521 EPOCH 50 done: loss 0.0154 - lr 0.100000
2023-03-29 17:12:35,521 BAD EPOCHS (no improvement): 0
2023-03-29 17:12:35,523 ----------------------------------------------------------------------------------------------------
2023-03-29 17:12:39,011 epoch 51 - iter 49/493 - loss 0.01504737 - time (sec): 3.49 - samples/sec: 7373.00 - lr: 0.100000
2023-03-29 17:12:42,281 epoch 51 - iter 98/493 - loss 0.01582277 - time (sec): 6.76 - samples/sec: 7499.47 - lr: 0.100000
2023-03-29 17:12:45,704 epoch 51 - iter 147/493 - loss 0.01596518 - time (sec): 10.18 - samples/sec: 7586.79 - lr: 0.100000
2023-03-29 17:12:49,205 epoch 51 - iter 196/493 - loss 0.01640200 - time (sec): 13.68 - samples/sec: 7560.52 - lr: 0.100000
2023-03-29 17:12:52,639 epoch 51 - iter 245/493 - loss 0.01607979 - time (sec): 17.12 - samples/sec: 7539.78 - lr: 0.100000
2023-03-29 17:12:56,135 epoch 51 - iter 294/493 - loss 0.01603384 - time (sec): 20.61 - samples/sec: 7512.51 - lr: 0.100000
2023-03-29 17:12:59,690 epoch 51 - iter 343/493 - loss 0.01598721 - time (sec): 24.17 - samples/sec: 7448.72 - lr: 0.100000
2023-03-29 17:13:03,110 epoch 51 - iter 392/493 - loss 0.01597553 - time (sec): 27.59 - samples/sec: 7442.02 - lr: 0.100000
2023-03-29 17:13:06,698 epoch 51 - iter 441/493 - loss 0.01601232 - time (sec): 31.17 - samples/sec: 7409.08 - lr: 0.100000
2023-03-29 17:13:10,262 epoch 51 - iter 490/493 - loss 0.01592414 - time (sec): 34.74 - samples/sec: 7405.78 - lr: 0.100000
2023-03-29 17:13:10,554 ----------------------------------------------------------------------------------------------------
2023-03-29 17:13:10,554 EPOCH 51 done: loss 0.0159 - lr 0.100000
2023-03-29 17:13:10,554 BAD EPOCHS (no improvement): 1
2023-03-29 17:13:10,557 ----------------------------------------------------------------------------------------------------
2023-03-29 17:13:14,226 epoch 52 - iter 49/493 - loss 0.01157104 - time (sec): 3.67 - samples/sec: 6988.30 - lr: 0.100000
2023-03-29 17:13:17,678 epoch 52 - iter 98/493 - loss 0.01271535 - time (sec): 7.12 - samples/sec: 7219.43 - lr: 0.100000
2023-03-29 17:13:21,176 epoch 52 - iter 147/493 - loss 0.01338717 - time (sec): 10.62 - samples/sec: 7221.57 - lr: 0.100000
2023-03-29 17:13:24,762 epoch 52 - iter 196/493 - loss 0.01385390 - time (sec): 14.21 - samples/sec: 7250.32 - lr: 0.100000
2023-03-29 17:13:28,346 epoch 52 - iter 245/493 - loss 0.01444630 - time (sec): 17.79 - samples/sec: 7264.74 - lr: 0.100000
2023-03-29 17:13:31,831 epoch 52 - iter 294/493 - loss 0.01446241 - time (sec): 21.27 - samples/sec: 7279.51 - lr: 0.100000
2023-03-29 17:13:35,424 epoch 52 - iter 343/493 - loss 0.01459279 - time (sec): 24.87 - samples/sec: 7261.43 - lr: 0.100000
2023-03-29 17:13:39,010 epoch 52 - iter 392/493 - loss 0.01459994 - time (sec): 28.45 - samples/sec: 7265.59 - lr: 0.100000
2023-03-29 17:13:42,349 epoch 52 - iter 441/493 - loss 0.01463644 - time (sec): 31.79 - samples/sec: 7291.75 - lr: 0.100000
2023-03-29 17:13:45,762 epoch 52 - iter 490/493 - loss 0.01509526 - time (sec): 35.20 - samples/sec: 7315.32 - lr: 0.100000
2023-03-29 17:13:45,963 ----------------------------------------------------------------------------------------------------
2023-03-29 17:13:45,963 EPOCH 52 done: loss 0.0152 - lr 0.100000
2023-03-29 17:13:45,963 BAD EPOCHS (no improvement): 0
2023-03-29 17:13:45,966 ----------------------------------------------------------------------------------------------------
2023-03-29 17:13:49,648 epoch 53 - iter 49/493 - loss 0.01232584 - time (sec): 3.68 - samples/sec: 7195.24 - lr: 0.100000
2023-03-29 17:13:53,152 epoch 53 - iter 98/493 - loss 0.01337726 - time (sec): 7.19 - samples/sec: 7282.12 - lr: 0.100000
2023-03-29 17:13:56,752 epoch 53 - iter 147/493 - loss 0.01417300 - time (sec): 10.79 - samples/sec: 7251.37 - lr: 0.100000
2023-03-29 17:14:00,229 epoch 53 - iter 196/493 - loss 0.01354577 - time (sec): 14.26 - samples/sec: 7289.05 - lr: 0.100000
2023-03-29 17:14:03,820 epoch 53 - iter 245/493 - loss 0.01402281 - time (sec): 17.85 - samples/sec: 7256.52 - lr: 0.100000
2023-03-29 17:14:06,998 epoch 53 - iter 294/493 - loss 0.01411532 - time (sec): 21.03 - samples/sec: 7346.46 - lr: 0.100000
2023-03-29 17:14:10,500 epoch 53 - iter 343/493 - loss 0.01441897 - time (sec): 24.53 - samples/sec: 7344.16 - lr: 0.100000
2023-03-29 17:14:13,886 epoch 53 - iter 392/493 - loss 0.01427549 - time (sec): 27.92 - samples/sec: 7376.28 - lr: 0.100000
2023-03-29 17:14:17,126 epoch 53 - iter 441/493 - loss 0.01451250 - time (sec): 31.16 - samples/sec: 7416.63 - lr: 0.100000
2023-03-29 17:14:20,659 epoch 53 - iter 490/493 - loss 0.01451116 - time (sec): 34.69 - samples/sec: 7431.49 - lr: 0.100000
2023-03-29 17:14:20,824 ----------------------------------------------------------------------------------------------------
2023-03-29 17:14:20,824 EPOCH 53 done: loss 0.0145 - lr 0.100000
2023-03-29 17:14:20,824 BAD EPOCHS (no improvement): 0
2023-03-29 17:14:20,827 ----------------------------------------------------------------------------------------------------
2023-03-29 17:14:27,323 epoch 54 - iter 49/493 - loss 0.01274126 - time (sec): 6.50 - samples/sec: 4015.51 - lr: 0.100000
2023-03-29 17:14:30,717 epoch 54 - iter 98/493 - loss 0.01311452 - time (sec): 9.89 - samples/sec: 5236.80 - lr: 0.100000
2023-03-29 17:14:34,067 epoch 54 - iter 147/493 - loss 0.01453920 - time (sec): 13.24 - samples/sec: 5799.34 - lr: 0.100000
2023-03-29 17:14:37,465 epoch 54 - iter 196/493 - loss 0.01526810 - time (sec): 16.64 - samples/sec: 6151.35 - lr: 0.100000
2023-03-29 17:14:40,899 epoch 54 - iter 245/493 - loss 0.01525681 - time (sec): 20.07 - samples/sec: 6379.84 - lr: 0.100000
2023-03-29 17:14:44,293 epoch 54 - iter 294/493 - loss 0.01483662 - time (sec): 23.47 - samples/sec: 6539.74 - lr: 0.100000
2023-03-29 17:14:47,832 epoch 54 - iter 343/493 - loss 0.01485919 - time (sec): 27.00 - samples/sec: 6649.56 - lr: 0.100000
2023-03-29 17:14:51,277 epoch 54 - iter 392/493 - loss 0.01481153 - time (sec): 30.45 - samples/sec: 6746.23 - lr: 0.100000
2023-03-29 17:14:54,807 epoch 54 - iter 441/493 - loss 0.01483988 - time (sec): 33.98 - samples/sec: 6800.71 - lr: 0.100000
2023-03-29 17:14:58,587 epoch 54 - iter 490/493 - loss 0.01495454 - time (sec): 37.76 - samples/sec: 6820.78 - lr: 0.100000
2023-03-29 17:14:58,821 ----------------------------------------------------------------------------------------------------
2023-03-29 17:14:58,821 EPOCH 54 done: loss 0.0149 - lr 0.100000
2023-03-29 17:14:58,821 BAD EPOCHS (no improvement): 1
2023-03-29 17:14:58,824 ----------------------------------------------------------------------------------------------------
2023-03-29 17:15:02,438 epoch 55 - iter 49/493 - loss 0.01231345 - time (sec): 3.61 - samples/sec: 7087.92 - lr: 0.100000
2023-03-29 17:15:05,946 epoch 55 - iter 98/493 - loss 0.01333611 - time (sec): 7.12 - samples/sec: 7269.53 - lr: 0.100000
2023-03-29 17:15:09,411 epoch 55 - iter 147/493 - loss 0.01361445 - time (sec): 10.59 - samples/sec: 7281.80 - lr: 0.100000
2023-03-29 17:15:13,034 epoch 55 - iter 196/493 - loss 0.01408134 - time (sec): 14.21 - samples/sec: 7251.37 - lr: 0.100000
2023-03-29 17:15:16,574 epoch 55 - iter 245/493 - loss 0.01438197 - time (sec): 17.75 - samples/sec: 7275.99 - lr: 0.100000
2023-03-29 17:15:19,985 epoch 55 - iter 294/493 - loss 0.01430433 - time (sec): 21.16 - samples/sec: 7292.72 - lr: 0.100000
2023-03-29 17:15:23,465 epoch 55 - iter 343/493 - loss 0.01458900 - time (sec): 24.64 - samples/sec: 7305.88 - lr: 0.100000
2023-03-29 17:15:26,999 epoch 55 - iter 392/493 - loss 0.01457322 - time (sec): 28.17 - samples/sec: 7322.37 - lr: 0.100000
2023-03-29 17:15:30,506 epoch 55 - iter 441/493 - loss 0.01445627 - time (sec): 31.68 - samples/sec: 7329.84 - lr: 0.100000
2023-03-29 17:15:33,976 epoch 55 - iter 490/493 - loss 0.01437347 - time (sec): 35.15 - samples/sec: 7327.24 - lr: 0.100000
2023-03-29 17:15:34,193 ----------------------------------------------------------------------------------------------------
2023-03-29 17:15:34,193 EPOCH 55 done: loss 0.0144 - lr 0.100000
2023-03-29 17:15:34,193 BAD EPOCHS (no improvement): 0
2023-03-29 17:15:34,196 ----------------------------------------------------------------------------------------------------
2023-03-29 17:15:37,666 epoch 56 - iter 49/493 - loss 0.01333028 - time (sec): 3.47 - samples/sec: 7393.28 - lr: 0.100000
2023-03-29 17:15:41,119 epoch 56 - iter 98/493 - loss 0.01410583 - time (sec): 6.92 - samples/sec: 7476.29 - lr: 0.100000
2023-03-29 17:15:44,611 epoch 56 - iter 147/493 - loss 0.01424667 - time (sec): 10.42 - samples/sec: 7406.96 - lr: 0.100000
2023-03-29 17:15:48,118 epoch 56 - iter 196/493 - loss 0.01495167 - time (sec): 13.92 - samples/sec: 7390.75 - lr: 0.100000
2023-03-29 17:15:51,762 epoch 56 - iter 245/493 - loss 0.01479072 - time (sec): 17.57 - samples/sec: 7335.50 - lr: 0.100000
2023-03-29 17:15:55,183 epoch 56 - iter 294/493 - loss 0.01461522 - time (sec): 20.99 - samples/sec: 7398.52 - lr: 0.100000
2023-03-29 17:15:58,585 epoch 56 - iter 343/493 - loss 0.01469628 - time (sec): 24.39 - samples/sec: 7408.50 - lr: 0.100000
2023-03-29 17:16:02,229 epoch 56 - iter 392/493 - loss 0.01453457 - time (sec): 28.03 - samples/sec: 7376.82 - lr: 0.100000
2023-03-29 17:16:06,163 epoch 56 - iter 441/493 - loss 0.01462831 - time (sec): 31.97 - samples/sec: 7263.25 - lr: 0.100000
2023-03-29 17:16:09,549 epoch 56 - iter 490/493 - loss 0.01470445 - time (sec): 35.35 - samples/sec: 7289.39 - lr: 0.100000
2023-03-29 17:16:09,727 ----------------------------------------------------------------------------------------------------
2023-03-29 17:16:09,727 EPOCH 56 done: loss 0.0147 - lr 0.100000
2023-03-29 17:16:09,727 BAD EPOCHS (no improvement): 1
2023-03-29 17:16:09,730 ----------------------------------------------------------------------------------------------------
2023-03-29 17:16:13,364 epoch 57 - iter 49/493 - loss 0.01370354 - time (sec): 3.63 - samples/sec: 7164.86 - lr: 0.100000
2023-03-29 17:16:16,936 epoch 57 - iter 98/493 - loss 0.01383830 - time (sec): 7.21 - samples/sec: 7214.32 - lr: 0.100000
2023-03-29 17:16:20,294 epoch 57 - iter 147/493 - loss 0.01434544 - time (sec): 10.56 - samples/sec: 7302.54 - lr: 0.100000
2023-03-29 17:16:23,716 epoch 57 - iter 196/493 - loss 0.01454230 - time (sec): 13.99 - samples/sec: 7332.73 - lr: 0.100000
2023-03-29 17:16:27,303 epoch 57 - iter 245/493 - loss 0.01405052 - time (sec): 17.57 - samples/sec: 7345.16 - lr: 0.100000
2023-03-29 17:16:30,711 epoch 57 - iter 294/493 - loss 0.01393116 - time (sec): 20.98 - samples/sec: 7356.20 - lr: 0.100000
2023-03-29 17:16:34,257 epoch 57 - iter 343/493 - loss 0.01394941 - time (sec): 24.53 - samples/sec: 7356.79 - lr: 0.100000
2023-03-29 17:16:37,870 epoch 57 - iter 392/493 - loss 0.01406392 - time (sec): 28.14 - samples/sec: 7334.48 - lr: 0.100000
2023-03-29 17:16:41,258 epoch 57 - iter 441/493 - loss 0.01416258 - time (sec): 31.53 - samples/sec: 7371.77 - lr: 0.100000
2023-03-29 17:16:44,707 epoch 57 - iter 490/493 - loss 0.01414036 - time (sec): 34.98 - samples/sec: 7361.88 - lr: 0.100000
2023-03-29 17:16:44,920 ----------------------------------------------------------------------------------------------------
2023-03-29 17:16:44,920 EPOCH 57 done: loss 0.0142 - lr 0.100000
2023-03-29 17:16:44,920 BAD EPOCHS (no improvement): 0
2023-03-29 17:16:44,923 ----------------------------------------------------------------------------------------------------
2023-03-29 17:16:48,418 epoch 58 - iter 49/493 - loss 0.01618956 - time (sec): 3.49 - samples/sec: 7414.98 - lr: 0.100000
2023-03-29 17:16:51,868 epoch 58 - iter 98/493 - loss 0.01550140 - time (sec): 6.95 - samples/sec: 7481.45 - lr: 0.100000
2023-03-29 17:16:55,468 epoch 58 - iter 147/493 - loss 0.01440295 - time (sec): 10.54 - samples/sec: 7367.02 - lr: 0.100000
2023-03-29 17:16:59,051 epoch 58 - iter 196/493 - loss 0.01425204 - time (sec): 14.13 - samples/sec: 7320.16 - lr: 0.100000
2023-03-29 17:17:02,536 epoch 58 - iter 245/493 - loss 0.01408594 - time (sec): 17.61 - samples/sec: 7323.14 - lr: 0.100000
2023-03-29 17:17:06,191 epoch 58 - iter 294/493 - loss 0.01431825 - time (sec): 21.27 - samples/sec: 7327.83 - lr: 0.100000
2023-03-29 17:17:09,617 epoch 58 - iter 343/493 - loss 0.01430148 - time (sec): 24.69 - samples/sec: 7326.86 - lr: 0.100000
2023-03-29 17:17:13,254 epoch 58 - iter 392/493 - loss 0.01406795 - time (sec): 28.33 - samples/sec: 7302.85 - lr: 0.100000
2023-03-29 17:17:16,695 epoch 58 - iter 441/493 - loss 0.01417236 - time (sec): 31.77 - samples/sec: 7306.84 - lr: 0.100000
2023-03-29 17:17:20,145 epoch 58 - iter 490/493 - loss 0.01412735 - time (sec): 35.22 - samples/sec: 7312.81 - lr: 0.100000
2023-03-29 17:17:20,378 ----------------------------------------------------------------------------------------------------
2023-03-29 17:17:20,378 EPOCH 58 done: loss 0.0141 - lr 0.100000
2023-03-29 17:17:20,378 BAD EPOCHS (no improvement): 0
2023-03-29 17:17:20,386 ----------------------------------------------------------------------------------------------------
2023-03-29 17:17:23,875 epoch 59 - iter 49/493 - loss 0.01377288 - time (sec): 3.49 - samples/sec: 7211.38 - lr: 0.100000
2023-03-29 17:17:27,275 epoch 59 - iter 98/493 - loss 0.01330625 - time (sec): 6.89 - samples/sec: 7309.50 - lr: 0.100000
2023-03-29 17:17:30,852 epoch 59 - iter 147/493 - loss 0.01386733 - time (sec): 10.47 - samples/sec: 7292.69 - lr: 0.100000
2023-03-29 17:17:34,329 epoch 59 - iter 196/493 - loss 0.01408587 - time (sec): 13.94 - samples/sec: 7314.80 - lr: 0.100000
2023-03-29 17:17:37,987 epoch 59 - iter 245/493 - loss 0.01466598 - time (sec): 17.60 - samples/sec: 7230.92 - lr: 0.100000
2023-03-29 17:17:41,534 epoch 59 - iter 294/493 - loss 0.01429410 - time (sec): 21.15 - samples/sec: 7269.33 - lr: 0.100000
2023-03-29 17:17:45,015 epoch 59 - iter 343/493 - loss 0.01454364 - time (sec): 24.63 - samples/sec: 7269.88 - lr: 0.100000
2023-03-29 17:17:48,608 epoch 59 - iter 392/493 - loss 0.01475087 - time (sec): 28.22 - samples/sec: 7257.90 - lr: 0.100000
2023-03-29 17:17:52,234 epoch 59 - iter 441/493 - loss 0.01465414 - time (sec): 31.85 - samples/sec: 7250.19 - lr: 0.100000
2023-03-29 17:17:55,885 epoch 59 - iter 490/493 - loss 0.01470073 - time (sec): 35.50 - samples/sec: 7254.77 - lr: 0.100000
2023-03-29 17:17:56,134 ----------------------------------------------------------------------------------------------------
2023-03-29 17:17:56,134 EPOCH 59 done: loss 0.0147 - lr 0.100000
2023-03-29 17:17:56,134 BAD EPOCHS (no improvement): 1
2023-03-29 17:17:56,146 ----------------------------------------------------------------------------------------------------
2023-03-29 17:17:59,581 epoch 60 - iter 49/493 - loss 0.01503901 - time (sec): 3.43 - samples/sec: 7267.53 - lr: 0.100000
2023-03-29 17:18:03,303 epoch 60 - iter 98/493 - loss 0.01396733 - time (sec): 7.16 - samples/sec: 7179.73 - lr: 0.100000
2023-03-29 17:18:06,892 epoch 60 - iter 147/493 - loss 0.01415840 - time (sec): 10.75 - samples/sec: 7208.88 - lr: 0.100000
2023-03-29 17:18:10,267 epoch 60 - iter 196/493 - loss 0.01490000 - time (sec): 14.12 - samples/sec: 7306.92 - lr: 0.100000
2023-03-29 17:18:13,712 epoch 60 - iter 245/493 - loss 0.01452413 - time (sec): 17.57 - samples/sec: 7330.84 - lr: 0.100000
2023-03-29 17:18:17,154 epoch 60 - iter 294/493 - loss 0.01425252 - time (sec): 21.01 - samples/sec: 7338.44 - lr: 0.100000
2023-03-29 17:18:20,640 epoch 60 - iter 343/493 - loss 0.01439855 - time (sec): 24.49 - samples/sec: 7344.73 - lr: 0.100000
2023-03-29 17:18:24,186 epoch 60 - iter 392/493 - loss 0.01426844 - time (sec): 28.04 - samples/sec: 7333.47 - lr: 0.100000
2023-03-29 17:18:27,755 epoch 60 - iter 441/493 - loss 0.01395254 - time (sec): 31.61 - samples/sec: 7343.02 - lr: 0.100000
2023-03-29 17:18:31,321 epoch 60 - iter 490/493 - loss 0.01391507 - time (sec): 35.17 - samples/sec: 7324.65 - lr: 0.100000
2023-03-29 17:18:31,543 ----------------------------------------------------------------------------------------------------
2023-03-29 17:18:31,543 EPOCH 60 done: loss 0.0140 - lr 0.100000
2023-03-29 17:18:31,543 BAD EPOCHS (no improvement): 0
2023-03-29 17:18:31,546 ----------------------------------------------------------------------------------------------------
2023-03-29 17:18:35,171 epoch 61 - iter 49/493 - loss 0.01249832 - time (sec): 3.62 - samples/sec: 7222.68 - lr: 0.100000
2023-03-29 17:18:38,757 epoch 61 - iter 98/493 - loss 0.01301925 - time (sec): 7.21 - samples/sec: 7147.14 - lr: 0.100000
2023-03-29 17:18:42,191 epoch 61 - iter 147/493 - loss 0.01335370 - time (sec): 10.64 - samples/sec: 7191.03 - lr: 0.100000
2023-03-29 17:18:45,757 epoch 61 - iter 196/493 - loss 0.01356842 - time (sec): 14.21 - samples/sec: 7216.53 - lr: 0.100000
2023-03-29 17:18:49,281 epoch 61 - iter 245/493 - loss 0.01353358 - time (sec): 17.73 - samples/sec: 7232.75 - lr: 0.100000
2023-03-29 17:18:52,895 epoch 61 - iter 294/493 - loss 0.01350559 - time (sec): 21.35 - samples/sec: 7206.19 - lr: 0.100000
2023-03-29 17:18:56,356 epoch 61 - iter 343/493 - loss 0.01330506 - time (sec): 24.81 - samples/sec: 7231.95 - lr: 0.100000
2023-03-29 17:18:59,875 epoch 61 - iter 392/493 - loss 0.01356860 - time (sec): 28.33 - samples/sec: 7265.07 - lr: 0.100000
2023-03-29 17:19:03,344 epoch 61 - iter 441/493 - loss 0.01393315 - time (sec): 31.80 - samples/sec: 7278.70 - lr: 0.100000
2023-03-29 17:19:06,737 epoch 61 - iter 490/493 - loss 0.01404745 - time (sec): 35.19 - samples/sec: 7316.47 - lr: 0.100000
2023-03-29 17:19:06,955 ----------------------------------------------------------------------------------------------------
2023-03-29 17:19:06,955 EPOCH 61 done: loss 0.0141 - lr 0.100000
2023-03-29 17:19:06,955 BAD EPOCHS (no improvement): 1
2023-03-29 17:19:06,958 ----------------------------------------------------------------------------------------------------
2023-03-29 17:19:10,421 epoch 62 - iter 49/493 - loss 0.01347008 - time (sec): 3.46 - samples/sec: 7281.19 - lr: 0.100000
2023-03-29 17:19:13,930 epoch 62 - iter 98/493 - loss 0.01371521 - time (sec): 6.97 - samples/sec: 7362.18 - lr: 0.100000
2023-03-29 17:19:17,430 epoch 62 - iter 147/493 - loss 0.01392313 - time (sec): 10.47 - samples/sec: 7402.23 - lr: 0.100000
2023-03-29 17:19:20,820 epoch 62 - iter 196/493 - loss 0.01348139 - time (sec): 13.86 - samples/sec: 7482.85 - lr: 0.100000
2023-03-29 17:19:24,205 epoch 62 - iter 245/493 - loss 0.01348751 - time (sec): 17.25 - samples/sec: 7461.67 - lr: 0.100000
2023-03-29 17:19:27,672 epoch 62 - iter 294/493 - loss 0.01354501 - time (sec): 20.71 - samples/sec: 7452.19 - lr: 0.100000
2023-03-29 17:19:31,240 epoch 62 - iter 343/493 - loss 0.01367531 - time (sec): 24.28 - samples/sec: 7418.46 - lr: 0.100000
2023-03-29 17:19:34,931 epoch 62 - iter 392/493 - loss 0.01373421 - time (sec): 27.97 - samples/sec: 7363.29 - lr: 0.100000
2023-03-29 17:19:38,406 epoch 62 - iter 441/493 - loss 0.01388546 - time (sec): 31.45 - samples/sec: 7363.08 - lr: 0.100000
2023-03-29 17:19:41,793 epoch 62 - iter 490/493 - loss 0.01386271 - time (sec): 34.84 - samples/sec: 7395.62 - lr: 0.100000
2023-03-29 17:19:42,008 ----------------------------------------------------------------------------------------------------
2023-03-29 17:19:42,008 EPOCH 62 done: loss 0.0139 - lr 0.100000
2023-03-29 17:19:42,008 BAD EPOCHS (no improvement): 0
2023-03-29 17:19:42,011 ----------------------------------------------------------------------------------------------------
2023-03-29 17:19:45,531 epoch 63 - iter 49/493 - loss 0.01380628 - time (sec): 3.52 - samples/sec: 7353.07 - lr: 0.100000
2023-03-29 17:19:49,009 epoch 63 - iter 98/493 - loss 0.01336162 - time (sec): 7.00 - samples/sec: 7314.26 - lr: 0.100000
2023-03-29 17:19:52,700 epoch 63 - iter 147/493 - loss 0.01358568 - time (sec): 10.69 - samples/sec: 7268.56 - lr: 0.100000
2023-03-29 17:19:56,192 epoch 63 - iter 196/493 - loss 0.01391087 - time (sec): 14.18 - samples/sec: 7339.24 - lr: 0.100000
2023-03-29 17:19:59,508 epoch 63 - iter 245/493 - loss 0.01394779 - time (sec): 17.50 - samples/sec: 7360.64 - lr: 0.100000
2023-03-29 17:20:03,040 epoch 63 - iter 294/493 - loss 0.01382026 - time (sec): 21.03 - samples/sec: 7378.82 - lr: 0.100000
2023-03-29 17:20:06,645 epoch 63 - iter 343/493 - loss 0.01367075 - time (sec): 24.63 - samples/sec: 7334.23 - lr: 0.100000
2023-03-29 17:20:10,112 epoch 63 - iter 392/493 - loss 0.01370568 - time (sec): 28.10 - samples/sec: 7341.12 - lr: 0.100000
2023-03-29 17:20:13,476 epoch 63 - iter 441/493 - loss 0.01398788 - time (sec): 31.46 - samples/sec: 7355.34 - lr: 0.100000
2023-03-29 17:20:17,188 epoch 63 - iter 490/493 - loss 0.01412362 - time (sec): 35.18 - samples/sec: 7323.53 - lr: 0.100000
2023-03-29 17:20:17,495 ----------------------------------------------------------------------------------------------------
2023-03-29 17:20:17,495 EPOCH 63 done: loss 0.0141 - lr 0.100000
2023-03-29 17:20:17,495 BAD EPOCHS (no improvement): 1
2023-03-29 17:20:17,507 ----------------------------------------------------------------------------------------------------
2023-03-29 17:20:21,242 epoch 64 - iter 49/493 - loss 0.01181352 - time (sec): 3.74 - samples/sec: 7016.45 - lr: 0.100000
2023-03-29 17:20:24,810 epoch 64 - iter 98/493 - loss 0.01236484 - time (sec): 7.30 - samples/sec: 7113.45 - lr: 0.100000
2023-03-29 17:20:28,402 epoch 64 - iter 147/493 - loss 0.01220007 - time (sec): 10.89 - samples/sec: 7104.63 - lr: 0.100000
2023-03-29 17:20:31,939 epoch 64 - iter 196/493 - loss 0.01250486 - time (sec): 14.43 - samples/sec: 7158.82 - lr: 0.100000
2023-03-29 17:20:35,614 epoch 64 - iter 245/493 - loss 0.01269158 - time (sec): 18.11 - samples/sec: 7150.88 - lr: 0.100000
2023-03-29 17:20:39,178 epoch 64 - iter 294/493 - loss 0.01276626 - time (sec): 21.67 - samples/sec: 7171.04 - lr: 0.100000
2023-03-29 17:20:42,662 epoch 64 - iter 343/493 - loss 0.01288358 - time (sec): 25.15 - samples/sec: 7216.20 - lr: 0.100000
2023-03-29 17:20:45,983 epoch 64 - iter 392/493 - loss 0.01267778 - time (sec): 28.48 - samples/sec: 7267.96 - lr: 0.100000
2023-03-29 17:20:49,532 epoch 64 - iter 441/493 - loss 0.01272635 - time (sec): 32.03 - samples/sec: 7259.67 - lr: 0.100000
2023-03-29 17:20:52,945 epoch 64 - iter 490/493 - loss 0.01282229 - time (sec): 35.44 - samples/sec: 7273.10 - lr: 0.100000
2023-03-29 17:20:53,133 ----------------------------------------------------------------------------------------------------
2023-03-29 17:20:53,133 EPOCH 64 done: loss 0.0128 - lr 0.100000
2023-03-29 17:20:53,133 BAD EPOCHS (no improvement): 0
2023-03-29 17:20:53,146 ----------------------------------------------------------------------------------------------------
2023-03-29 17:20:56,767 epoch 65 - iter 49/493 - loss 0.01289008 - time (sec): 3.62 - samples/sec: 7071.46 - lr: 0.100000
2023-03-29 17:21:00,204 epoch 65 - iter 98/493 - loss 0.01295738 - time (sec): 7.06 - samples/sec: 7222.68 - lr: 0.100000
2023-03-29 17:21:03,757 epoch 65 - iter 147/493 - loss 0.01383996 - time (sec): 10.61 - samples/sec: 7250.18 - lr: 0.100000
2023-03-29 17:21:07,261 epoch 65 - iter 196/493 - loss 0.01311985 - time (sec): 14.11 - samples/sec: 7275.79 - lr: 0.100000
2023-03-29 17:21:10,796 epoch 65 - iter 245/493 - loss 0.01332136 - time (sec): 17.65 - samples/sec: 7277.64 - lr: 0.100000
2023-03-29 17:21:14,365 epoch 65 - iter 294/493 - loss 0.01329845 - time (sec): 21.22 - samples/sec: 7289.78 - lr: 0.100000
2023-03-29 17:21:17,863 epoch 65 - iter 343/493 - loss 0.01329281 - time (sec): 24.72 - samples/sec: 7300.47 - lr: 0.100000
2023-03-29 17:21:21,499 epoch 65 - iter 392/493 - loss 0.01344102 - time (sec): 28.35 - samples/sec: 7271.27 - lr: 0.100000
2023-03-29 17:21:25,108 epoch 65 - iter 441/493 - loss 0.01343916 - time (sec): 31.96 - samples/sec: 7249.00 - lr: 0.100000
2023-03-29 17:21:28,612 epoch 65 - iter 490/493 - loss 0.01367235 - time (sec): 35.47 - samples/sec: 7263.28 - lr: 0.100000
2023-03-29 17:21:28,837 ----------------------------------------------------------------------------------------------------
2023-03-29 17:21:28,837 EPOCH 65 done: loss 0.0136 - lr 0.100000
2023-03-29 17:21:28,837 BAD EPOCHS (no improvement): 1
2023-03-29 17:21:28,840 ----------------------------------------------------------------------------------------------------
2023-03-29 17:21:32,413 epoch 66 - iter 49/493 - loss 0.01304500 - time (sec): 3.57 - samples/sec: 7303.52 - lr: 0.100000
2023-03-29 17:21:35,815 epoch 66 - iter 98/493 - loss 0.01305723 - time (sec): 6.98 - samples/sec: 7457.14 - lr: 0.100000
2023-03-29 17:21:39,224 epoch 66 - iter 147/493 - loss 0.01325008 - time (sec): 10.38 - samples/sec: 7450.67 - lr: 0.100000
2023-03-29 17:21:42,739 epoch 66 - iter 196/493 - loss 0.01299578 - time (sec): 13.90 - samples/sec: 7404.83 - lr: 0.100000
2023-03-29 17:21:46,271 epoch 66 - iter 245/493 - loss 0.01303427 - time (sec): 17.43 - samples/sec: 7385.38 - lr: 0.100000
2023-03-29 17:21:49,708 epoch 66 - iter 294/493 - loss 0.01337153 - time (sec): 20.87 - samples/sec: 7395.20 - lr: 0.100000
2023-03-29 17:21:53,184 epoch 66 - iter 343/493 - loss 0.01343721 - time (sec): 24.34 - samples/sec: 7412.15 - lr: 0.100000
2023-03-29 17:21:56,527 epoch 66 - iter 392/493 - loss 0.01337333 - time (sec): 27.69 - samples/sec: 7420.45 - lr: 0.100000
2023-03-29 17:21:59,944 epoch 66 - iter 441/493 - loss 0.01357385 - time (sec): 31.10 - samples/sec: 7430.71 - lr: 0.100000
2023-03-29 17:22:03,381 epoch 66 - iter 490/493 - loss 0.01388323 - time (sec): 34.54 - samples/sec: 7460.54 - lr: 0.100000
2023-03-29 17:22:03,563 ----------------------------------------------------------------------------------------------------
2023-03-29 17:22:03,563 EPOCH 66 done: loss 0.0139 - lr 0.100000
2023-03-29 17:22:03,563 BAD EPOCHS (no improvement): 2
2023-03-29 17:22:03,566 ----------------------------------------------------------------------------------------------------
2023-03-29 17:22:06,943 epoch 67 - iter 49/493 - loss 0.01114057 - time (sec): 3.38 - samples/sec: 7645.56 - lr: 0.100000
2023-03-29 17:22:10,328 epoch 67 - iter 98/493 - loss 0.01239925 - time (sec): 6.76 - samples/sec: 7632.21 - lr: 0.100000
2023-03-29 17:22:13,617 epoch 67 - iter 147/493 - loss 0.01175981 - time (sec): 10.05 - samples/sec: 7635.40 - lr: 0.100000
2023-03-29 17:22:17,075 epoch 67 - iter 196/493 - loss 0.01204963 - time (sec): 13.51 - samples/sec: 7587.78 - lr: 0.100000
2023-03-29 17:22:20,334 epoch 67 - iter 245/493 - loss 0.01210831 - time (sec): 16.77 - samples/sec: 7635.00 - lr: 0.100000
2023-03-29 17:22:23,641 epoch 67 - iter 294/493 - loss 0.01254705 - time (sec): 20.07 - samples/sec: 7654.92 - lr: 0.100000
2023-03-29 17:22:27,147 epoch 67 - iter 343/493 - loss 0.01288148 - time (sec): 23.58 - samples/sec: 7619.76 - lr: 0.100000
2023-03-29 17:22:30,620 epoch 67 - iter 392/493 - loss 0.01301038 - time (sec): 27.05 - samples/sec: 7598.98 - lr: 0.100000
2023-03-29 17:22:34,152 epoch 67 - iter 441/493 - loss 0.01319562 - time (sec): 30.59 - samples/sec: 7572.64 - lr: 0.100000
2023-03-29 17:22:37,715 epoch 67 - iter 490/493 - loss 0.01319560 - time (sec): 34.15 - samples/sec: 7544.13 - lr: 0.100000
2023-03-29 17:22:37,923 ----------------------------------------------------------------------------------------------------
2023-03-29 17:22:37,923 EPOCH 67 done: loss 0.0132 - lr 0.100000
2023-03-29 17:22:37,923 BAD EPOCHS (no improvement): 3
2023-03-29 17:22:37,926 ----------------------------------------------------------------------------------------------------
2023-03-29 17:22:41,499 epoch 68 - iter 49/493 - loss 0.01013715 - time (sec): 3.57 - samples/sec: 7250.98 - lr: 0.100000
2023-03-29 17:22:44,766 epoch 68 - iter 98/493 - loss 0.01095767 - time (sec): 6.84 - samples/sec: 7509.90 - lr: 0.100000
2023-03-29 17:22:48,175 epoch 68 - iter 147/493 - loss 0.01186890 - time (sec): 10.25 - samples/sec: 7559.05 - lr: 0.100000
2023-03-29 17:22:51,512 epoch 68 - iter 196/493 - loss 0.01211961 - time (sec): 13.59 - samples/sec: 7561.57 - lr: 0.100000
2023-03-29 17:22:54,785 epoch 68 - iter 245/493 - loss 0.01266951 - time (sec): 16.86 - samples/sec: 7589.12 - lr: 0.100000
2023-03-29 17:22:58,145 epoch 68 - iter 294/493 - loss 0.01270952 - time (sec): 20.22 - samples/sec: 7591.24 - lr: 0.100000
2023-03-29 17:23:01,498 epoch 68 - iter 343/493 - loss 0.01315991 - time (sec): 23.57 - samples/sec: 7603.24 - lr: 0.100000
2023-03-29 17:23:04,980 epoch 68 - iter 392/493 - loss 0.01328441 - time (sec): 27.05 - samples/sec: 7583.58 - lr: 0.100000
2023-03-29 17:23:08,405 epoch 68 - iter 441/493 - loss 0.01355643 - time (sec): 30.48 - samples/sec: 7579.13 - lr: 0.100000
2023-03-29 17:23:11,948 epoch 68 - iter 490/493 - loss 0.01352761 - time (sec): 34.02 - samples/sec: 7569.81 - lr: 0.100000
2023-03-29 17:23:12,144 ----------------------------------------------------------------------------------------------------
2023-03-29 17:23:12,145 EPOCH 68 done: loss 0.0135 - lr 0.100000
2023-03-29 17:23:12,145 Epoch 68: reducing learning rate of group 0 to 5.0000e-02.
2023-03-29 17:23:12,145 BAD EPOCHS (no improvement): 4
2023-03-29 17:23:12,148 ----------------------------------------------------------------------------------------------------
2023-03-29 17:23:15,497 epoch 69 - iter 49/493 - loss 0.01171368 - time (sec): 3.35 - samples/sec: 7622.08 - lr: 0.050000
2023-03-29 17:23:18,799 epoch 69 - iter 98/493 - loss 0.01117632 - time (sec): 6.65 - samples/sec: 7592.76 - lr: 0.050000
2023-03-29 17:23:22,192 epoch 69 - iter 147/493 - loss 0.01098222 - time (sec): 10.04 - samples/sec: 7596.17 - lr: 0.050000
2023-03-29 17:23:25,634 epoch 69 - iter 196/493 - loss 0.01094257 - time (sec): 13.49 - samples/sec: 7627.80 - lr: 0.050000
2023-03-29 17:23:29,021 epoch 69 - iter 245/493 - loss 0.01131774 - time (sec): 16.87 - samples/sec: 7605.78 - lr: 0.050000
2023-03-29 17:23:32,517 epoch 69 - iter 294/493 - loss 0.01116370 - time (sec): 20.37 - samples/sec: 7540.97 - lr: 0.050000
2023-03-29 17:23:35,829 epoch 69 - iter 343/493 - loss 0.01131542 - time (sec): 23.68 - samples/sec: 7586.10 - lr: 0.050000
2023-03-29 17:23:39,254 epoch 69 - iter 392/493 - loss 0.01132121 - time (sec): 27.11 - samples/sec: 7591.85 - lr: 0.050000
2023-03-29 17:23:42,670 epoch 69 - iter 441/493 - loss 0.01158834 - time (sec): 30.52 - samples/sec: 7580.55 - lr: 0.050000
2023-03-29 17:23:46,105 epoch 69 - iter 490/493 - loss 0.01148656 - time (sec): 33.96 - samples/sec: 7583.37 - lr: 0.050000
2023-03-29 17:23:46,363 ----------------------------------------------------------------------------------------------------
2023-03-29 17:23:46,364 EPOCH 69 done: loss 0.0115 - lr 0.050000
2023-03-29 17:23:46,364 BAD EPOCHS (no improvement): 0
2023-03-29 17:23:46,367 ----------------------------------------------------------------------------------------------------
2023-03-29 17:23:49,932 epoch 70 - iter 49/493 - loss 0.01105996 - time (sec): 3.57 - samples/sec: 7492.74 - lr: 0.050000
2023-03-29 17:23:53,230 epoch 70 - iter 98/493 - loss 0.01113480 - time (sec): 6.86 - samples/sec: 7609.16 - lr: 0.050000
2023-03-29 17:23:56,722 epoch 70 - iter 147/493 - loss 0.01170958 - time (sec): 10.36 - samples/sec: 7534.25 - lr: 0.050000
2023-03-29 17:24:00,321 epoch 70 - iter 196/493 - loss 0.01134969 - time (sec): 13.95 - samples/sec: 7483.63 - lr: 0.050000
2023-03-29 17:24:03,762 epoch 70 - iter 245/493 - loss 0.01156641 - time (sec): 17.40 - samples/sec: 7439.13 - lr: 0.050000
2023-03-29 17:24:07,055 epoch 70 - iter 294/493 - loss 0.01133544 - time (sec): 20.69 - samples/sec: 7470.67 - lr: 0.050000
2023-03-29 17:24:10,645 epoch 70 - iter 343/493 - loss 0.01128159 - time (sec): 24.28 - samples/sec: 7438.67 - lr: 0.050000
2023-03-29 17:24:14,225 epoch 70 - iter 392/493 - loss 0.01111996 - time (sec): 27.86 - samples/sec: 7434.02 - lr: 0.050000
2023-03-29 17:24:17,608 epoch 70 - iter 441/493 - loss 0.01093840 - time (sec): 31.24 - samples/sec: 7435.53 - lr: 0.050000
2023-03-29 17:24:21,059 epoch 70 - iter 490/493 - loss 0.01092195 - time (sec): 34.69 - samples/sec: 7427.28 - lr: 0.050000
2023-03-29 17:24:21,293 ----------------------------------------------------------------------------------------------------
2023-03-29 17:24:21,293 EPOCH 70 done: loss 0.0109 - lr 0.050000
2023-03-29 17:24:21,293 BAD EPOCHS (no improvement): 0
2023-03-29 17:24:21,296 ----------------------------------------------------------------------------------------------------
2023-03-29 17:24:24,867 epoch 71 - iter 49/493 - loss 0.01226585 - time (sec): 3.57 - samples/sec: 7188.35 - lr: 0.050000
2023-03-29 17:24:28,318 epoch 71 - iter 98/493 - loss 0.01132077 - time (sec): 7.02 - samples/sec: 7289.37 - lr: 0.050000
2023-03-29 17:24:31,838 epoch 71 - iter 147/493 - loss 0.01092955 - time (sec): 10.54 - samples/sec: 7239.33 - lr: 0.050000
2023-03-29 17:24:35,410 epoch 71 - iter 196/493 - loss 0.01112133 - time (sec): 14.11 - samples/sec: 7285.46 - lr: 0.050000
2023-03-29 17:24:38,779 epoch 71 - iter 245/493 - loss 0.01070353 - time (sec): 17.48 - samples/sec: 7330.41 - lr: 0.050000
2023-03-29 17:24:42,277 epoch 71 - iter 294/493 - loss 0.01074123 - time (sec): 20.98 - samples/sec: 7380.12 - lr: 0.050000
2023-03-29 17:24:45,728 epoch 71 - iter 343/493 - loss 0.01092731 - time (sec): 24.43 - samples/sec: 7399.83 - lr: 0.050000
2023-03-29 17:24:49,002 epoch 71 - iter 392/493 - loss 0.01083803 - time (sec): 27.71 - samples/sec: 7431.33 - lr: 0.050000
2023-03-29 17:24:52,365 epoch 71 - iter 441/493 - loss 0.01102854 - time (sec): 31.07 - samples/sec: 7464.33 - lr: 0.050000
2023-03-29 17:24:55,768 epoch 71 - iter 490/493 - loss 0.01079234 - time (sec): 34.47 - samples/sec: 7472.74 - lr: 0.050000
2023-03-29 17:24:55,976 ----------------------------------------------------------------------------------------------------
2023-03-29 17:24:55,976 EPOCH 71 done: loss 0.0108 - lr 0.050000
2023-03-29 17:24:55,976 BAD EPOCHS (no improvement): 0
2023-03-29 17:24:55,979 ----------------------------------------------------------------------------------------------------
2023-03-29 17:24:59,364 epoch 72 - iter 49/493 - loss 0.01048003 - time (sec): 3.39 - samples/sec: 7639.49 - lr: 0.050000
2023-03-29 17:25:02,802 epoch 72 - iter 98/493 - loss 0.01081559 - time (sec): 6.82 - samples/sec: 7595.59 - lr: 0.050000
2023-03-29 17:25:06,180 epoch 72 - iter 147/493 - loss 0.01120801 - time (sec): 10.20 - samples/sec: 7618.84 - lr: 0.050000
2023-03-29 17:25:09,799 epoch 72 - iter 196/493 - loss 0.01138571 - time (sec): 13.82 - samples/sec: 7474.17 - lr: 0.050000
2023-03-29 17:25:13,288 epoch 72 - iter 245/493 - loss 0.01129584 - time (sec): 17.31 - samples/sec: 7420.36 - lr: 0.050000
2023-03-29 17:25:16,781 epoch 72 - iter 294/493 - loss 0.01122859 - time (sec): 20.80 - samples/sec: 7417.37 - lr: 0.050000
2023-03-29 17:25:20,284 epoch 72 - iter 343/493 - loss 0.01136076 - time (sec): 24.31 - samples/sec: 7406.42 - lr: 0.050000
2023-03-29 17:25:23,758 epoch 72 - iter 392/493 - loss 0.01114565 - time (sec): 27.78 - samples/sec: 7409.50 - lr: 0.050000
2023-03-29 17:25:27,385 epoch 72 - iter 441/493 - loss 0.01097188 - time (sec): 31.41 - samples/sec: 7365.87 - lr: 0.050000
2023-03-29 17:25:30,896 epoch 72 - iter 490/493 - loss 0.01097012 - time (sec): 34.92 - samples/sec: 7379.41 - lr: 0.050000
2023-03-29 17:25:31,094 ----------------------------------------------------------------------------------------------------
2023-03-29 17:25:31,094 EPOCH 72 done: loss 0.0110 - lr 0.050000
2023-03-29 17:25:31,094 BAD EPOCHS (no improvement): 1
2023-03-29 17:25:31,097 ----------------------------------------------------------------------------------------------------
2023-03-29 17:25:34,663 epoch 73 - iter 49/493 - loss 0.01061080 - time (sec): 3.57 - samples/sec: 7324.84 - lr: 0.050000
2023-03-29 17:25:38,148 epoch 73 - iter 98/493 - loss 0.01112468 - time (sec): 7.05 - samples/sec: 7387.56 - lr: 0.050000
2023-03-29 17:25:41,604 epoch 73 - iter 147/493 - loss 0.01064969 - time (sec): 10.51 - samples/sec: 7336.15 - lr: 0.050000
2023-03-29 17:25:44,977 epoch 73 - iter 196/493 - loss 0.01092566 - time (sec): 13.88 - samples/sec: 7415.77 - lr: 0.050000
2023-03-29 17:25:48,368 epoch 73 - iter 245/493 - loss 0.01064025 - time (sec): 17.27 - samples/sec: 7434.77 - lr: 0.050000
2023-03-29 17:25:51,748 epoch 73 - iter 294/493 - loss 0.01078392 - time (sec): 20.65 - samples/sec: 7425.55 - lr: 0.050000
2023-03-29 17:25:55,142 epoch 73 - iter 343/493 - loss 0.01097633 - time (sec): 24.05 - samples/sec: 7461.26 - lr: 0.050000
2023-03-29 17:25:58,764 epoch 73 - iter 392/493 - loss 0.01081272 - time (sec): 27.67 - samples/sec: 7451.43 - lr: 0.050000
2023-03-29 17:26:02,035 epoch 73 - iter 441/493 - loss 0.01068652 - time (sec): 30.94 - samples/sec: 7480.04 - lr: 0.050000
2023-03-29 17:26:05,426 epoch 73 - iter 490/493 - loss 0.01072536 - time (sec): 34.33 - samples/sec: 7498.69 - lr: 0.050000
2023-03-29 17:26:05,647 ----------------------------------------------------------------------------------------------------
2023-03-29 17:26:05,647 EPOCH 73 done: loss 0.0107 - lr 0.050000
2023-03-29 17:26:05,647 BAD EPOCHS (no improvement): 0
2023-03-29 17:26:05,650 ----------------------------------------------------------------------------------------------------
2023-03-29 17:26:08,966 epoch 74 - iter 49/493 - loss 0.01202913 - time (sec): 3.32 - samples/sec: 7576.87 - lr: 0.050000
2023-03-29 17:26:12,345 epoch 74 - iter 98/493 - loss 0.01058554 - time (sec): 6.69 - samples/sec: 7621.67 - lr: 0.050000
2023-03-29 17:26:15,724 epoch 74 - iter 147/493 - loss 0.00976941 - time (sec): 10.07 - samples/sec: 7618.16 - lr: 0.050000
2023-03-29 17:26:19,161 epoch 74 - iter 196/493 - loss 0.00996838 - time (sec): 13.51 - samples/sec: 7608.96 - lr: 0.050000
2023-03-29 17:26:22,600 epoch 74 - iter 245/493 - loss 0.00990701 - time (sec): 16.95 - samples/sec: 7574.92 - lr: 0.050000
2023-03-29 17:26:26,042 epoch 74 - iter 294/493 - loss 0.00981314 - time (sec): 20.39 - samples/sec: 7590.99 - lr: 0.050000
2023-03-29 17:26:29,505 epoch 74 - iter 343/493 - loss 0.01015396 - time (sec): 23.85 - samples/sec: 7581.50 - lr: 0.050000
2023-03-29 17:26:32,922 epoch 74 - iter 392/493 - loss 0.01034269 - time (sec): 27.27 - samples/sec: 7573.68 - lr: 0.050000
2023-03-29 17:26:36,248 epoch 74 - iter 441/493 - loss 0.01033233 - time (sec): 30.60 - samples/sec: 7569.14 - lr: 0.050000
2023-03-29 17:26:39,728 epoch 74 - iter 490/493 - loss 0.01023915 - time (sec): 34.08 - samples/sec: 7556.70 - lr: 0.050000
2023-03-29 17:26:39,950 ----------------------------------------------------------------------------------------------------
2023-03-29 17:26:39,950 EPOCH 74 done: loss 0.0102 - lr 0.050000
2023-03-29 17:26:39,950 BAD EPOCHS (no improvement): 0
2023-03-29 17:26:39,953 ----------------------------------------------------------------------------------------------------
2023-03-29 17:26:43,307 epoch 75 - iter 49/493 - loss 0.00885348 - time (sec): 3.35 - samples/sec: 7494.50 - lr: 0.050000
2023-03-29 17:26:46,767 epoch 75 - iter 98/493 - loss 0.00988912 - time (sec): 6.81 - samples/sec: 7513.70 - lr: 0.050000
2023-03-29 17:26:50,131 epoch 75 - iter 147/493 - loss 0.00927253 - time (sec): 10.18 - samples/sec: 7618.39 - lr: 0.050000
2023-03-29 17:26:53,450 epoch 75 - iter 196/493 - loss 0.00963817 - time (sec): 13.50 - samples/sec: 7628.57 - lr: 0.050000
2023-03-29 17:26:56,853 epoch 75 - iter 245/493 - loss 0.00945055 - time (sec): 16.90 - samples/sec: 7606.94 - lr: 0.050000
2023-03-29 17:27:00,302 epoch 75 - iter 294/493 - loss 0.00925766 - time (sec): 20.35 - samples/sec: 7568.98 - lr: 0.050000
2023-03-29 17:27:06,603 epoch 75 - iter 343/493 - loss 0.00920292 - time (sec): 26.65 - samples/sec: 6740.72 - lr: 0.050000
2023-03-29 17:27:10,060 epoch 75 - iter 392/493 - loss 0.00910148 - time (sec): 30.11 - samples/sec: 6834.98 - lr: 0.050000
2023-03-29 17:27:13,535 epoch 75 - iter 441/493 - loss 0.00940079 - time (sec): 33.58 - samples/sec: 6913.37 - lr: 0.050000
2023-03-29 17:27:16,847 epoch 75 - iter 490/493 - loss 0.00953565 - time (sec): 36.89 - samples/sec: 6978.41 - lr: 0.050000
2023-03-29 17:27:17,107 ----------------------------------------------------------------------------------------------------
2023-03-29 17:27:17,108 EPOCH 75 done: loss 0.0095 - lr 0.050000
2023-03-29 17:27:17,108 BAD EPOCHS (no improvement): 0
2023-03-29 17:27:17,111 ----------------------------------------------------------------------------------------------------
2023-03-29 17:27:20,568 epoch 76 - iter 49/493 - loss 0.00981784 - time (sec): 3.46 - samples/sec: 7362.12 - lr: 0.050000
2023-03-29 17:27:24,117 epoch 76 - iter 98/493 - loss 0.01066915 - time (sec): 7.01 - samples/sec: 7379.81 - lr: 0.050000
2023-03-29 17:27:27,512 epoch 76 - iter 147/493 - loss 0.01098721 - time (sec): 10.40 - samples/sec: 7394.50 - lr: 0.050000
2023-03-29 17:27:31,106 epoch 76 - iter 196/493 - loss 0.01039730 - time (sec): 14.00 - samples/sec: 7387.07 - lr: 0.050000
2023-03-29 17:27:34,442 epoch 76 - iter 245/493 - loss 0.01030536 - time (sec): 17.33 - samples/sec: 7424.82 - lr: 0.050000
2023-03-29 17:27:37,794 epoch 76 - iter 294/493 - loss 0.01025668 - time (sec): 20.68 - samples/sec: 7467.47 - lr: 0.050000
2023-03-29 17:27:41,073 epoch 76 - iter 343/493 - loss 0.01048481 - time (sec): 23.96 - samples/sec: 7506.74 - lr: 0.050000
2023-03-29 17:27:44,653 epoch 76 - iter 392/493 - loss 0.01019815 - time (sec): 27.54 - samples/sec: 7486.25 - lr: 0.050000
2023-03-29 17:27:48,014 epoch 76 - iter 441/493 - loss 0.01018646 - time (sec): 30.90 - samples/sec: 7514.59 - lr: 0.050000
2023-03-29 17:27:51,307 epoch 76 - iter 490/493 - loss 0.01012295 - time (sec): 34.20 - samples/sec: 7536.74 - lr: 0.050000
2023-03-29 17:27:51,505 ----------------------------------------------------------------------------------------------------
2023-03-29 17:27:51,505 EPOCH 76 done: loss 0.0101 - lr 0.050000
2023-03-29 17:27:51,505 BAD EPOCHS (no improvement): 1
2023-03-29 17:27:51,508 ----------------------------------------------------------------------------------------------------
2023-03-29 17:27:54,747 epoch 77 - iter 49/493 - loss 0.00828988 - time (sec): 3.24 - samples/sec: 7803.56 - lr: 0.050000
2023-03-29 17:27:58,121 epoch 77 - iter 98/493 - loss 0.00979376 - time (sec): 6.61 - samples/sec: 7672.96 - lr: 0.050000
2023-03-29 17:28:01,728 epoch 77 - iter 147/493 - loss 0.00967213 - time (sec): 10.22 - samples/sec: 7594.07 - lr: 0.050000
2023-03-29 17:28:05,051 epoch 77 - iter 196/493 - loss 0.00943330 - time (sec): 13.54 - samples/sec: 7601.21 - lr: 0.050000
2023-03-29 17:28:08,476 epoch 77 - iter 245/493 - loss 0.00940306 - time (sec): 16.97 - samples/sec: 7562.10 - lr: 0.050000
2023-03-29 17:28:11,959 epoch 77 - iter 294/493 - loss 0.00942384 - time (sec): 20.45 - samples/sec: 7538.00 - lr: 0.050000
2023-03-29 17:28:15,487 epoch 77 - iter 343/493 - loss 0.00921174 - time (sec): 23.98 - samples/sec: 7521.36 - lr: 0.050000
2023-03-29 17:28:18,941 epoch 77 - iter 392/493 - loss 0.00924901 - time (sec): 27.43 - samples/sec: 7522.48 - lr: 0.050000
2023-03-29 17:28:22,389 epoch 77 - iter 441/493 - loss 0.00909774 - time (sec): 30.88 - samples/sec: 7514.47 - lr: 0.050000
2023-03-29 17:28:25,706 epoch 77 - iter 490/493 - loss 0.00927596 - time (sec): 34.20 - samples/sec: 7531.27 - lr: 0.050000
2023-03-29 17:28:25,920 ----------------------------------------------------------------------------------------------------
2023-03-29 17:28:25,920 EPOCH 77 done: loss 0.0093 - lr 0.050000
2023-03-29 17:28:25,920 BAD EPOCHS (no improvement): 0
2023-03-29 17:28:25,923 ----------------------------------------------------------------------------------------------------
2023-03-29 17:28:29,316 epoch 78 - iter 49/493 - loss 0.01051722 - time (sec): 3.39 - samples/sec: 7613.50 - lr: 0.050000
2023-03-29 17:28:32,790 epoch 78 - iter 98/493 - loss 0.00926310 - time (sec): 6.87 - samples/sec: 7610.89 - lr: 0.050000
2023-03-29 17:28:36,206 epoch 78 - iter 147/493 - loss 0.00921288 - time (sec): 10.28 - samples/sec: 7586.14 - lr: 0.050000
2023-03-29 17:28:39,631 epoch 78 - iter 196/493 - loss 0.00933609 - time (sec): 13.71 - samples/sec: 7595.57 - lr: 0.050000
2023-03-29 17:28:43,005 epoch 78 - iter 245/493 - loss 0.00927300 - time (sec): 17.08 - samples/sec: 7565.38 - lr: 0.050000
2023-03-29 17:28:46,356 epoch 78 - iter 294/493 - loss 0.00943744 - time (sec): 20.43 - samples/sec: 7565.25 - lr: 0.050000
2023-03-29 17:28:49,748 epoch 78 - iter 343/493 - loss 0.00939066 - time (sec): 23.82 - samples/sec: 7572.99 - lr: 0.050000
2023-03-29 17:28:53,229 epoch 78 - iter 392/493 - loss 0.00942446 - time (sec): 27.31 - samples/sec: 7542.32 - lr: 0.050000
2023-03-29 17:28:56,551 epoch 78 - iter 441/493 - loss 0.00962718 - time (sec): 30.63 - samples/sec: 7560.15 - lr: 0.050000
2023-03-29 17:29:00,053 epoch 78 - iter 490/493 - loss 0.00963655 - time (sec): 34.13 - samples/sec: 7548.98 - lr: 0.050000
2023-03-29 17:29:00,258 ----------------------------------------------------------------------------------------------------
2023-03-29 17:29:00,258 EPOCH 78 done: loss 0.0096 - lr 0.050000
2023-03-29 17:29:00,258 BAD EPOCHS (no improvement): 1
2023-03-29 17:29:00,262 ----------------------------------------------------------------------------------------------------
2023-03-29 17:29:03,767 epoch 79 - iter 49/493 - loss 0.01055823 - time (sec): 3.51 - samples/sec: 7529.80 - lr: 0.050000
2023-03-29 17:29:07,219 epoch 79 - iter 98/493 - loss 0.00952825 - time (sec): 6.96 - samples/sec: 7490.31 - lr: 0.050000
2023-03-29 17:29:10,590 epoch 79 - iter 147/493 - loss 0.00905265 - time (sec): 10.33 - samples/sec: 7533.85 - lr: 0.050000
2023-03-29 17:29:13,923 epoch 79 - iter 196/493 - loss 0.00910520 - time (sec): 13.66 - samples/sec: 7536.71 - lr: 0.050000
2023-03-29 17:29:17,404 epoch 79 - iter 245/493 - loss 0.00966195 - time (sec): 17.14 - samples/sec: 7536.00 - lr: 0.050000
2023-03-29 17:29:20,718 epoch 79 - iter 294/493 - loss 0.00972959 - time (sec): 20.46 - samples/sec: 7568.25 - lr: 0.050000
2023-03-29 17:29:24,267 epoch 79 - iter 343/493 - loss 0.01010607 - time (sec): 24.01 - samples/sec: 7555.83 - lr: 0.050000
2023-03-29 17:29:27,765 epoch 79 - iter 392/493 - loss 0.00988854 - time (sec): 27.50 - samples/sec: 7515.13 - lr: 0.050000
2023-03-29 17:29:31,125 epoch 79 - iter 441/493 - loss 0.00975348 - time (sec): 30.86 - samples/sec: 7527.60 - lr: 0.050000
2023-03-29 17:29:34,560 epoch 79 - iter 490/493 - loss 0.00982827 - time (sec): 34.30 - samples/sec: 7504.35 - lr: 0.050000
2023-03-29 17:29:34,806 ----------------------------------------------------------------------------------------------------
2023-03-29 17:29:34,806 EPOCH 79 done: loss 0.0098 - lr 0.050000
2023-03-29 17:29:34,806 BAD EPOCHS (no improvement): 2
2023-03-29 17:29:34,809 ----------------------------------------------------------------------------------------------------
2023-03-29 17:29:38,302 epoch 80 - iter 49/493 - loss 0.00955727 - time (sec): 3.49 - samples/sec: 7391.98 - lr: 0.050000
2023-03-29 17:29:41,748 epoch 80 - iter 98/493 - loss 0.01010763 - time (sec): 6.94 - samples/sec: 7374.58 - lr: 0.050000
2023-03-29 17:29:45,301 epoch 80 - iter 147/493 - loss 0.00991690 - time (sec): 10.49 - samples/sec: 7383.10 - lr: 0.050000
2023-03-29 17:29:48,822 epoch 80 - iter 196/493 - loss 0.00964989 - time (sec): 14.01 - samples/sec: 7381.68 - lr: 0.050000
2023-03-29 17:29:52,540 epoch 80 - iter 245/493 - loss 0.00940646 - time (sec): 17.73 - samples/sec: 7325.79 - lr: 0.050000
2023-03-29 17:29:56,155 epoch 80 - iter 294/493 - loss 0.00957563 - time (sec): 21.35 - samples/sec: 7290.71 - lr: 0.050000
2023-03-29 17:29:59,472 epoch 80 - iter 343/493 - loss 0.00952503 - time (sec): 24.66 - samples/sec: 7333.49 - lr: 0.050000
2023-03-29 17:30:02,934 epoch 80 - iter 392/493 - loss 0.00958252 - time (sec): 28.12 - samples/sec: 7347.70 - lr: 0.050000
2023-03-29 17:30:06,349 epoch 80 - iter 441/493 - loss 0.00952980 - time (sec): 31.54 - samples/sec: 7346.34 - lr: 0.050000
2023-03-29 17:30:09,834 epoch 80 - iter 490/493 - loss 0.00942324 - time (sec): 35.02 - samples/sec: 7354.60 - lr: 0.050000
2023-03-29 17:30:10,030 ----------------------------------------------------------------------------------------------------
2023-03-29 17:30:10,031 EPOCH 80 done: loss 0.0094 - lr 0.050000
2023-03-29 17:30:10,031 BAD EPOCHS (no improvement): 3
2023-03-29 17:30:10,033 ----------------------------------------------------------------------------------------------------
2023-03-29 17:30:13,598 epoch 81 - iter 49/493 - loss 0.01002106 - time (sec): 3.56 - samples/sec: 7190.54 - lr: 0.050000
2023-03-29 17:30:17,103 epoch 81 - iter 98/493 - loss 0.00985517 - time (sec): 7.07 - samples/sec: 7204.94 - lr: 0.050000
2023-03-29 17:30:20,529 epoch 81 - iter 147/493 - loss 0.01044884 - time (sec): 10.50 - samples/sec: 7318.60 - lr: 0.050000
2023-03-29 17:30:24,062 epoch 81 - iter 196/493 - loss 0.00955628 - time (sec): 14.03 - samples/sec: 7262.02 - lr: 0.050000
2023-03-29 17:30:27,549 epoch 81 - iter 245/493 - loss 0.00979656 - time (sec): 17.52 - samples/sec: 7298.53 - lr: 0.050000
2023-03-29 17:30:31,098 epoch 81 - iter 294/493 - loss 0.00971134 - time (sec): 21.06 - samples/sec: 7324.09 - lr: 0.050000
2023-03-29 17:30:34,526 epoch 81 - iter 343/493 - loss 0.00960326 - time (sec): 24.49 - samples/sec: 7352.22 - lr: 0.050000
2023-03-29 17:30:38,139 epoch 81 - iter 392/493 - loss 0.00971190 - time (sec): 28.11 - samples/sec: 7329.36 - lr: 0.050000
2023-03-29 17:30:41,417 epoch 81 - iter 441/493 - loss 0.00965209 - time (sec): 31.38 - samples/sec: 7364.74 - lr: 0.050000
2023-03-29 17:30:44,986 epoch 81 - iter 490/493 - loss 0.00996203 - time (sec): 34.95 - samples/sec: 7370.03 - lr: 0.050000
2023-03-29 17:30:45,209 ----------------------------------------------------------------------------------------------------
2023-03-29 17:30:45,209 EPOCH 81 done: loss 0.0100 - lr 0.050000
2023-03-29 17:30:45,210 Epoch 81: reducing learning rate of group 0 to 2.5000e-02.
2023-03-29 17:30:45,210 BAD EPOCHS (no improvement): 4
2023-03-29 17:30:45,213 ----------------------------------------------------------------------------------------------------
2023-03-29 17:30:48,752 epoch 82 - iter 49/493 - loss 0.01074600 - time (sec): 3.54 - samples/sec: 7203.20 - lr: 0.025000
2023-03-29 17:30:52,210 epoch 82 - iter 98/493 - loss 0.01073206 - time (sec): 7.00 - samples/sec: 7330.66 - lr: 0.025000
2023-03-29 17:30:55,832 epoch 82 - iter 147/493 - loss 0.00974743 - time (sec): 10.62 - samples/sec: 7243.69 - lr: 0.025000
2023-03-29 17:30:59,220 epoch 82 - iter 196/493 - loss 0.00909511 - time (sec): 14.01 - samples/sec: 7344.79 - lr: 0.025000
2023-03-29 17:31:02,647 epoch 82 - iter 245/493 - loss 0.00898577 - time (sec): 17.43 - samples/sec: 7372.98 - lr: 0.025000
2023-03-29 17:31:06,045 epoch 82 - iter 294/493 - loss 0.00890555 - time (sec): 20.83 - samples/sec: 7407.49 - lr: 0.025000
2023-03-29 17:31:09,501 epoch 82 - iter 343/493 - loss 0.00886367 - time (sec): 24.29 - samples/sec: 7432.85 - lr: 0.025000
2023-03-29 17:31:12,807 epoch 82 - iter 392/493 - loss 0.00886122 - time (sec): 27.59 - samples/sec: 7431.87 - lr: 0.025000
2023-03-29 17:31:16,265 epoch 82 - iter 441/493 - loss 0.00891728 - time (sec): 31.05 - samples/sec: 7441.66 - lr: 0.025000
2023-03-29 17:31:19,651 epoch 82 - iter 490/493 - loss 0.00882848 - time (sec): 34.44 - samples/sec: 7479.92 - lr: 0.025000
2023-03-29 17:31:19,872 ----------------------------------------------------------------------------------------------------
2023-03-29 17:31:19,872 EPOCH 82 done: loss 0.0088 - lr 0.025000
2023-03-29 17:31:19,872 BAD EPOCHS (no improvement): 0
2023-03-29 17:31:19,875 ----------------------------------------------------------------------------------------------------
2023-03-29 17:31:23,528 epoch 83 - iter 49/493 - loss 0.00639402 - time (sec): 3.65 - samples/sec: 7304.73 - lr: 0.025000
2023-03-29 17:31:26,864 epoch 83 - iter 98/493 - loss 0.00685855 - time (sec): 6.99 - samples/sec: 7496.75 - lr: 0.025000
2023-03-29 17:31:30,176 epoch 83 - iter 147/493 - loss 0.00743186 - time (sec): 10.30 - samples/sec: 7575.61 - lr: 0.025000
2023-03-29 17:31:33,646 epoch 83 - iter 196/493 - loss 0.00746254 - time (sec): 13.77 - samples/sec: 7520.50 - lr: 0.025000
2023-03-29 17:31:37,019 epoch 83 - iter 245/493 - loss 0.00747551 - time (sec): 17.14 - samples/sec: 7537.19 - lr: 0.025000
2023-03-29 17:31:40,315 epoch 83 - iter 294/493 - loss 0.00751471 - time (sec): 20.44 - samples/sec: 7580.86 - lr: 0.025000
2023-03-29 17:31:43,676 epoch 83 - iter 343/493 - loss 0.00753261 - time (sec): 23.80 - samples/sec: 7586.15 - lr: 0.025000
2023-03-29 17:31:47,046 epoch 83 - iter 392/493 - loss 0.00766587 - time (sec): 27.17 - samples/sec: 7572.96 - lr: 0.025000
2023-03-29 17:31:50,532 epoch 83 - iter 441/493 - loss 0.00777515 - time (sec): 30.66 - samples/sec: 7577.36 - lr: 0.025000
2023-03-29 17:31:53,781 epoch 83 - iter 490/493 - loss 0.00768110 - time (sec): 33.91 - samples/sec: 7590.31 - lr: 0.025000
2023-03-29 17:31:54,060 ----------------------------------------------------------------------------------------------------
2023-03-29 17:31:54,060 EPOCH 83 done: loss 0.0077 - lr 0.025000
2023-03-29 17:31:54,060 BAD EPOCHS (no improvement): 0
2023-03-29 17:31:54,063 ----------------------------------------------------------------------------------------------------
2023-03-29 17:31:57,669 epoch 84 - iter 49/493 - loss 0.00951597 - time (sec): 3.61 - samples/sec: 7237.85 - lr: 0.025000
2023-03-29 17:32:00,895 epoch 84 - iter 98/493 - loss 0.00926416 - time (sec): 6.83 - samples/sec: 7455.17 - lr: 0.025000
2023-03-29 17:32:04,371 epoch 84 - iter 147/493 - loss 0.00867070 - time (sec): 10.31 - samples/sec: 7485.51 - lr: 0.025000
2023-03-29 17:32:07,664 epoch 84 - iter 196/493 - loss 0.00837038 - time (sec): 13.60 - samples/sec: 7546.98 - lr: 0.025000
2023-03-29 17:32:11,078 epoch 84 - iter 245/493 - loss 0.00822513 - time (sec): 17.01 - samples/sec: 7585.11 - lr: 0.025000
2023-03-29 17:32:14,627 epoch 84 - iter 294/493 - loss 0.00807168 - time (sec): 20.56 - samples/sec: 7556.60 - lr: 0.025000
2023-03-29 17:32:18,000 epoch 84 - iter 343/493 - loss 0.00805656 - time (sec): 23.94 - samples/sec: 7570.48 - lr: 0.025000
2023-03-29 17:32:21,290 epoch 84 - iter 392/493 - loss 0.00813457 - time (sec): 27.23 - samples/sec: 7578.98 - lr: 0.025000
2023-03-29 17:32:24,768 epoch 84 - iter 441/493 - loss 0.00821600 - time (sec): 30.70 - samples/sec: 7549.98 - lr: 0.025000
2023-03-29 17:32:28,215 epoch 84 - iter 490/493 - loss 0.00825681 - time (sec): 34.15 - samples/sec: 7544.04 - lr: 0.025000
2023-03-29 17:32:28,449 ----------------------------------------------------------------------------------------------------
2023-03-29 17:32:28,449 EPOCH 84 done: loss 0.0083 - lr 0.025000
2023-03-29 17:32:28,449 BAD EPOCHS (no improvement): 1
2023-03-29 17:32:28,452 ----------------------------------------------------------------------------------------------------
2023-03-29 17:32:31,875 epoch 85 - iter 49/493 - loss 0.00888830 - time (sec): 3.42 - samples/sec: 7448.75 - lr: 0.025000
2023-03-29 17:32:35,427 epoch 85 - iter 98/493 - loss 0.00945619 - time (sec): 6.97 - samples/sec: 7417.30 - lr: 0.025000
2023-03-29 17:32:38,822 epoch 85 - iter 147/493 - loss 0.00933311 - time (sec): 10.37 - samples/sec: 7457.31 - lr: 0.025000
2023-03-29 17:32:42,259 epoch 85 - iter 196/493 - loss 0.00915426 - time (sec): 13.81 - samples/sec: 7462.61 - lr: 0.025000
2023-03-29 17:32:45,781 epoch 85 - iter 245/493 - loss 0.00873924 - time (sec): 17.33 - samples/sec: 7391.70 - lr: 0.025000
2023-03-29 17:32:49,309 epoch 85 - iter 294/493 - loss 0.00852341 - time (sec): 20.86 - samples/sec: 7371.96 - lr: 0.025000
2023-03-29 17:32:52,710 epoch 85 - iter 343/493 - loss 0.00870791 - time (sec): 24.26 - samples/sec: 7368.48 - lr: 0.025000
2023-03-29 17:32:56,234 epoch 85 - iter 392/493 - loss 0.00879625 - time (sec): 27.78 - samples/sec: 7370.33 - lr: 0.025000
2023-03-29 17:32:59,843 epoch 85 - iter 441/493 - loss 0.00868990 - time (sec): 31.39 - samples/sec: 7364.22 - lr: 0.025000
2023-03-29 17:33:03,313 epoch 85 - iter 490/493 - loss 0.00839087 - time (sec): 34.86 - samples/sec: 7388.63 - lr: 0.025000
2023-03-29 17:33:03,515 ----------------------------------------------------------------------------------------------------
2023-03-29 17:33:03,515 EPOCH 85 done: loss 0.0084 - lr 0.025000
2023-03-29 17:33:03,515 BAD EPOCHS (no improvement): 2
2023-03-29 17:33:03,518 ----------------------------------------------------------------------------------------------------
2023-03-29 17:33:07,132 epoch 86 - iter 49/493 - loss 0.00743107 - time (sec): 3.61 - samples/sec: 7513.78 - lr: 0.025000
2023-03-29 17:33:10,538 epoch 86 - iter 98/493 - loss 0.00884617 - time (sec): 7.02 - samples/sec: 7496.21 - lr: 0.025000
2023-03-29 17:33:13,991 epoch 86 - iter 147/493 - loss 0.00891430 - time (sec): 10.47 - samples/sec: 7533.97 - lr: 0.025000
2023-03-29 17:33:17,506 epoch 86 - iter 196/493 - loss 0.00853555 - time (sec): 13.99 - samples/sec: 7459.50 - lr: 0.025000
2023-03-29 17:33:21,165 epoch 86 - iter 245/493 - loss 0.00839808 - time (sec): 17.65 - samples/sec: 7380.52 - lr: 0.025000
2023-03-29 17:33:24,527 epoch 86 - iter 294/493 - loss 0.00839447 - time (sec): 21.01 - samples/sec: 7414.71 - lr: 0.025000
2023-03-29 17:33:27,885 epoch 86 - iter 343/493 - loss 0.00837283 - time (sec): 24.37 - samples/sec: 7429.72 - lr: 0.025000
2023-03-29 17:33:31,296 epoch 86 - iter 392/493 - loss 0.00822468 - time (sec): 27.78 - samples/sec: 7433.07 - lr: 0.025000
2023-03-29 17:33:34,816 epoch 86 - iter 441/493 - loss 0.00846475 - time (sec): 31.30 - samples/sec: 7418.93 - lr: 0.025000
2023-03-29 17:33:38,189 epoch 86 - iter 490/493 - loss 0.00841567 - time (sec): 34.67 - samples/sec: 7427.59 - lr: 0.025000
2023-03-29 17:33:38,422 ----------------------------------------------------------------------------------------------------
2023-03-29 17:33:38,422 EPOCH 86 done: loss 0.0084 - lr 0.025000
2023-03-29 17:33:38,423 BAD EPOCHS (no improvement): 3
2023-03-29 17:33:38,425 ----------------------------------------------------------------------------------------------------
2023-03-29 17:33:41,896 epoch 87 - iter 49/493 - loss 0.00822418 - time (sec): 3.47 - samples/sec: 7274.30 - lr: 0.025000
2023-03-29 17:33:45,457 epoch 87 - iter 98/493 - loss 0.00821659 - time (sec): 7.03 - samples/sec: 7376.07 - lr: 0.025000
2023-03-29 17:33:49,114 epoch 87 - iter 147/493 - loss 0.00783945 - time (sec): 10.69 - samples/sec: 7315.62 - lr: 0.025000
2023-03-29 17:33:52,550 epoch 87 - iter 196/493 - loss 0.00788863 - time (sec): 14.12 - samples/sec: 7303.96 - lr: 0.025000
2023-03-29 17:33:55,930 epoch 87 - iter 245/493 - loss 0.00772906 - time (sec): 17.50 - samples/sec: 7371.81 - lr: 0.025000
2023-03-29 17:33:59,572 epoch 87 - iter 294/493 - loss 0.00772945 - time (sec): 21.15 - samples/sec: 7372.27 - lr: 0.025000
2023-03-29 17:34:02,882 epoch 87 - iter 343/493 - loss 0.00749599 - time (sec): 24.46 - samples/sec: 7414.29 - lr: 0.025000
2023-03-29 17:34:06,200 epoch 87 - iter 392/493 - loss 0.00785828 - time (sec): 27.78 - samples/sec: 7427.03 - lr: 0.025000
2023-03-29 17:34:09,528 epoch 87 - iter 441/493 - loss 0.00807089 - time (sec): 31.10 - samples/sec: 7451.79 - lr: 0.025000
2023-03-29 17:34:12,858 epoch 87 - iter 490/493 - loss 0.00790619 - time (sec): 34.43 - samples/sec: 7475.50 - lr: 0.025000
2023-03-29 17:34:13,084 ----------------------------------------------------------------------------------------------------
2023-03-29 17:34:13,084 EPOCH 87 done: loss 0.0079 - lr 0.025000
2023-03-29 17:34:13,084 Epoch 87: reducing learning rate of group 0 to 1.2500e-02.
2023-03-29 17:34:13,084 BAD EPOCHS (no improvement): 4
2023-03-29 17:34:13,090 ----------------------------------------------------------------------------------------------------
2023-03-29 17:34:16,475 epoch 88 - iter 49/493 - loss 0.00717920 - time (sec): 3.38 - samples/sec: 7689.05 - lr: 0.012500
2023-03-29 17:34:19,796 epoch 88 - iter 98/493 - loss 0.00781184 - time (sec): 6.70 - samples/sec: 7717.25 - lr: 0.012500
2023-03-29 17:34:23,165 epoch 88 - iter 147/493 - loss 0.00803943 - time (sec): 10.07 - samples/sec: 7681.66 - lr: 0.012500
2023-03-29 17:34:26,634 epoch 88 - iter 196/493 - loss 0.00794215 - time (sec): 13.54 - samples/sec: 7614.91 - lr: 0.012500
2023-03-29 17:34:29,961 epoch 88 - iter 245/493 - loss 0.00814575 - time (sec): 16.87 - samples/sec: 7624.74 - lr: 0.012500
2023-03-29 17:34:33,218 epoch 88 - iter 294/493 - loss 0.00772997 - time (sec): 20.13 - samples/sec: 7654.91 - lr: 0.012500
2023-03-29 17:34:36,569 epoch 88 - iter 343/493 - loss 0.00787626 - time (sec): 23.48 - samples/sec: 7660.19 - lr: 0.012500
2023-03-29 17:34:39,956 epoch 88 - iter 392/493 - loss 0.00776030 - time (sec): 26.87 - samples/sec: 7651.91 - lr: 0.012500
2023-03-29 17:34:43,461 epoch 88 - iter 441/493 - loss 0.00782617 - time (sec): 30.37 - samples/sec: 7614.89 - lr: 0.012500
2023-03-29 17:34:46,957 epoch 88 - iter 490/493 - loss 0.00787161 - time (sec): 33.87 - samples/sec: 7602.74 - lr: 0.012500
2023-03-29 17:34:47,166 ----------------------------------------------------------------------------------------------------
2023-03-29 17:34:47,166 EPOCH 88 done: loss 0.0079 - lr 0.012500
2023-03-29 17:34:47,166 BAD EPOCHS (no improvement): 1
2023-03-29 17:34:47,169 ----------------------------------------------------------------------------------------------------
2023-03-29 17:34:50,428 epoch 89 - iter 49/493 - loss 0.00688935 - time (sec): 3.26 - samples/sec: 7831.22 - lr: 0.012500
2023-03-29 17:34:53,895 epoch 89 - iter 98/493 - loss 0.00681574 - time (sec): 6.73 - samples/sec: 7615.01 - lr: 0.012500
2023-03-29 17:34:57,293 epoch 89 - iter 147/493 - loss 0.00701717 - time (sec): 10.12 - samples/sec: 7604.71 - lr: 0.012500
2023-03-29 17:35:00,545 epoch 89 - iter 196/493 - loss 0.00719824 - time (sec): 13.38 - samples/sec: 7656.21 - lr: 0.012500
2023-03-29 17:35:04,063 epoch 89 - iter 245/493 - loss 0.00718949 - time (sec): 16.89 - samples/sec: 7606.75 - lr: 0.012500
2023-03-29 17:35:07,423 epoch 89 - iter 294/493 - loss 0.00732995 - time (sec): 20.25 - samples/sec: 7635.07 - lr: 0.012500
2023-03-29 17:35:10,960 epoch 89 - iter 343/493 - loss 0.00750596 - time (sec): 23.79 - samples/sec: 7589.27 - lr: 0.012500
2023-03-29 17:35:14,267 epoch 89 - iter 392/493 - loss 0.00764029 - time (sec): 27.10 - samples/sec: 7592.73 - lr: 0.012500
2023-03-29 17:35:17,512 epoch 89 - iter 441/493 - loss 0.00756291 - time (sec): 30.34 - samples/sec: 7621.12 - lr: 0.012500
2023-03-29 17:35:21,031 epoch 89 - iter 490/493 - loss 0.00762677 - time (sec): 33.86 - samples/sec: 7599.67 - lr: 0.012500
2023-03-29 17:35:21,268 ----------------------------------------------------------------------------------------------------
2023-03-29 17:35:21,268 EPOCH 89 done: loss 0.0077 - lr 0.012500
2023-03-29 17:35:21,268 BAD EPOCHS (no improvement): 0
2023-03-29 17:35:21,271 ----------------------------------------------------------------------------------------------------
2023-03-29 17:35:24,740 epoch 90 - iter 49/493 - loss 0.00774234 - time (sec): 3.47 - samples/sec: 7417.02 - lr: 0.012500
2023-03-29 17:35:28,111 epoch 90 - iter 98/493 - loss 0.00727610 - time (sec): 6.84 - samples/sec: 7453.36 - lr: 0.012500
2023-03-29 17:35:31,568 epoch 90 - iter 147/493 - loss 0.00725228 - time (sec): 10.30 - samples/sec: 7539.86 - lr: 0.012500
2023-03-29 17:35:34,926 epoch 90 - iter 196/493 - loss 0.00755444 - time (sec): 13.66 - samples/sec: 7567.09 - lr: 0.012500
2023-03-29 17:35:38,230 epoch 90 - iter 245/493 - loss 0.00749687 - time (sec): 16.96 - samples/sec: 7602.55 - lr: 0.012500
2023-03-29 17:35:41,589 epoch 90 - iter 294/493 - loss 0.00755391 - time (sec): 20.32 - samples/sec: 7609.74 - lr: 0.012500
2023-03-29 17:35:44,967 epoch 90 - iter 343/493 - loss 0.00738970 - time (sec): 23.70 - samples/sec: 7610.29 - lr: 0.012500
2023-03-29 17:35:48,479 epoch 90 - iter 392/493 - loss 0.00733041 - time (sec): 27.21 - samples/sec: 7596.38 - lr: 0.012500
2023-03-29 17:35:51,896 epoch 90 - iter 441/493 - loss 0.00743191 - time (sec): 30.62 - samples/sec: 7581.72 - lr: 0.012500
2023-03-29 17:35:55,233 epoch 90 - iter 490/493 - loss 0.00752115 - time (sec): 33.96 - samples/sec: 7583.58 - lr: 0.012500
2023-03-29 17:35:55,432 ----------------------------------------------------------------------------------------------------
2023-03-29 17:35:55,433 EPOCH 90 done: loss 0.0075 - lr 0.012500
2023-03-29 17:35:55,433 BAD EPOCHS (no improvement): 0
2023-03-29 17:35:55,436 ----------------------------------------------------------------------------------------------------
2023-03-29 17:35:59,068 epoch 91 - iter 49/493 - loss 0.00747239 - time (sec): 3.63 - samples/sec: 7191.34 - lr: 0.012500
2023-03-29 17:36:02,542 epoch 91 - iter 98/493 - loss 0.00753983 - time (sec): 7.11 - samples/sec: 7309.90 - lr: 0.012500
2023-03-29 17:36:05,998 epoch 91 - iter 147/493 - loss 0.00735989 - time (sec): 10.56 - samples/sec: 7355.56 - lr: 0.012500
2023-03-29 17:36:09,424 epoch 91 - iter 196/493 - loss 0.00738180 - time (sec): 13.99 - samples/sec: 7389.14 - lr: 0.012500
2023-03-29 17:36:12,933 epoch 91 - iter 245/493 - loss 0.00760846 - time (sec): 17.50 - samples/sec: 7409.76 - lr: 0.012500
2023-03-29 17:36:16,423 epoch 91 - iter 294/493 - loss 0.00762934 - time (sec): 20.99 - samples/sec: 7415.50 - lr: 0.012500
2023-03-29 17:36:19,828 epoch 91 - iter 343/493 - loss 0.00748198 - time (sec): 24.39 - samples/sec: 7423.25 - lr: 0.012500
2023-03-29 17:36:23,222 epoch 91 - iter 392/493 - loss 0.00756791 - time (sec): 27.79 - samples/sec: 7445.41 - lr: 0.012500
2023-03-29 17:36:26,662 epoch 91 - iter 441/493 - loss 0.00773975 - time (sec): 31.23 - samples/sec: 7441.74 - lr: 0.012500
2023-03-29 17:36:30,062 epoch 91 - iter 490/493 - loss 0.00756086 - time (sec): 34.63 - samples/sec: 7443.45 - lr: 0.012500
2023-03-29 17:36:30,250 ----------------------------------------------------------------------------------------------------
2023-03-29 17:36:30,250 EPOCH 91 done: loss 0.0076 - lr 0.012500
2023-03-29 17:36:30,250 BAD EPOCHS (no improvement): 1
2023-03-29 17:36:30,254 ----------------------------------------------------------------------------------------------------
2023-03-29 17:36:33,754 epoch 92 - iter 49/493 - loss 0.00778161 - time (sec): 3.50 - samples/sec: 7409.61 - lr: 0.012500
2023-03-29 17:36:37,234 epoch 92 - iter 98/493 - loss 0.00729927 - time (sec): 6.98 - samples/sec: 7361.59 - lr: 0.012500
2023-03-29 17:36:40,720 epoch 92 - iter 147/493 - loss 0.00701721 - time (sec): 10.47 - samples/sec: 7352.86 - lr: 0.012500
2023-03-29 17:36:44,333 epoch 92 - iter 196/493 - loss 0.00720800 - time (sec): 14.08 - samples/sec: 7300.57 - lr: 0.012500
2023-03-29 17:36:47,871 epoch 92 - iter 245/493 - loss 0.00683350 - time (sec): 17.62 - samples/sec: 7318.69 - lr: 0.012500
2023-03-29 17:36:51,272 epoch 92 - iter 294/493 - loss 0.00692472 - time (sec): 21.02 - samples/sec: 7326.94 - lr: 0.012500
2023-03-29 17:36:54,894 epoch 92 - iter 343/493 - loss 0.00686000 - time (sec): 24.64 - samples/sec: 7323.88 - lr: 0.012500
2023-03-29 17:36:58,339 epoch 92 - iter 392/493 - loss 0.00686942 - time (sec): 28.09 - samples/sec: 7353.28 - lr: 0.012500
2023-03-29 17:37:01,813 epoch 92 - iter 441/493 - loss 0.00694407 - time (sec): 31.56 - samples/sec: 7365.29 - lr: 0.012500
2023-03-29 17:37:05,262 epoch 92 - iter 490/493 - loss 0.00699090 - time (sec): 35.01 - samples/sec: 7364.37 - lr: 0.012500
2023-03-29 17:37:05,432 ----------------------------------------------------------------------------------------------------
2023-03-29 17:37:05,432 EPOCH 92 done: loss 0.0070 - lr 0.012500
2023-03-29 17:37:05,432 BAD EPOCHS (no improvement): 0
2023-03-29 17:37:05,435 ----------------------------------------------------------------------------------------------------
2023-03-29 17:37:09,032 epoch 93 - iter 49/493 - loss 0.00755886 - time (sec): 3.60 - samples/sec: 7279.21 - lr: 0.012500
2023-03-29 17:37:12,458 epoch 93 - iter 98/493 - loss 0.00737342 - time (sec): 7.02 - samples/sec: 7416.34 - lr: 0.012500
2023-03-29 17:37:15,866 epoch 93 - iter 147/493 - loss 0.00675790 - time (sec): 10.43 - samples/sec: 7428.82 - lr: 0.012500
2023-03-29 17:37:19,283 epoch 93 - iter 196/493 - loss 0.00696906 - time (sec): 13.85 - samples/sec: 7442.13 - lr: 0.012500
2023-03-29 17:37:22,760 epoch 93 - iter 245/493 - loss 0.00702522 - time (sec): 17.33 - samples/sec: 7443.06 - lr: 0.012500
2023-03-29 17:37:26,319 epoch 93 - iter 294/493 - loss 0.00717816 - time (sec): 20.88 - samples/sec: 7392.16 - lr: 0.012500
2023-03-29 17:37:29,840 epoch 93 - iter 343/493 - loss 0.00700690 - time (sec): 24.41 - samples/sec: 7389.55 - lr: 0.012500
2023-03-29 17:37:33,300 epoch 93 - iter 392/493 - loss 0.00705466 - time (sec): 27.86 - samples/sec: 7397.06 - lr: 0.012500
2023-03-29 17:37:36,925 epoch 93 - iter 441/493 - loss 0.00706977 - time (sec): 31.49 - samples/sec: 7361.43 - lr: 0.012500
2023-03-29 17:37:40,550 epoch 93 - iter 490/493 - loss 0.00711711 - time (sec): 35.11 - samples/sec: 7339.96 - lr: 0.012500
2023-03-29 17:37:40,748 ----------------------------------------------------------------------------------------------------
2023-03-29 17:37:40,748 EPOCH 93 done: loss 0.0071 - lr 0.012500
2023-03-29 17:37:40,748 BAD EPOCHS (no improvement): 1
2023-03-29 17:37:40,751 ----------------------------------------------------------------------------------------------------
2023-03-29 17:37:44,500 epoch 94 - iter 49/493 - loss 0.00637227 - time (sec): 3.75 - samples/sec: 7038.20 - lr: 0.012500
2023-03-29 17:37:47,898 epoch 94 - iter 98/493 - loss 0.00691832 - time (sec): 7.15 - samples/sec: 7224.41 - lr: 0.012500
2023-03-29 17:37:51,490 epoch 94 - iter 147/493 - loss 0.00703549 - time (sec): 10.74 - samples/sec: 7287.98 - lr: 0.012500
2023-03-29 17:37:54,995 epoch 94 - iter 196/493 - loss 0.00698354 - time (sec): 14.24 - samples/sec: 7337.39 - lr: 0.012500
2023-03-29 17:37:58,298 epoch 94 - iter 245/493 - loss 0.00693494 - time (sec): 17.55 - samples/sec: 7382.33 - lr: 0.012500
2023-03-29 17:38:01,639 epoch 94 - iter 294/493 - loss 0.00696120 - time (sec): 20.89 - samples/sec: 7421.69 - lr: 0.012500
2023-03-29 17:38:05,159 epoch 94 - iter 343/493 - loss 0.00712158 - time (sec): 24.41 - samples/sec: 7419.47 - lr: 0.012500
2023-03-29 17:38:08,564 epoch 94 - iter 392/493 - loss 0.00712961 - time (sec): 27.81 - samples/sec: 7438.78 - lr: 0.012500
2023-03-29 17:38:11,886 epoch 94 - iter 441/493 - loss 0.00733870 - time (sec): 31.13 - samples/sec: 7460.17 - lr: 0.012500
2023-03-29 17:38:15,313 epoch 94 - iter 490/493 - loss 0.00732635 - time (sec): 34.56 - samples/sec: 7454.42 - lr: 0.012500
2023-03-29 17:38:15,515 ----------------------------------------------------------------------------------------------------
2023-03-29 17:38:15,515 EPOCH 94 done: loss 0.0073 - lr 0.012500
2023-03-29 17:38:15,515 BAD EPOCHS (no improvement): 2
2023-03-29 17:38:15,518 ----------------------------------------------------------------------------------------------------
2023-03-29 17:38:18,890 epoch 95 - iter 49/493 - loss 0.00643454 - time (sec): 3.37 - samples/sec: 7805.73 - lr: 0.012500
2023-03-29 17:38:22,315 epoch 95 - iter 98/493 - loss 0.00585888 - time (sec): 6.80 - samples/sec: 7631.48 - lr: 0.012500
2023-03-29 17:38:25,733 epoch 95 - iter 147/493 - loss 0.00632071 - time (sec): 10.21 - samples/sec: 7586.67 - lr: 0.012500
2023-03-29 17:38:29,105 epoch 95 - iter 196/493 - loss 0.00626598 - time (sec): 13.59 - samples/sec: 7593.42 - lr: 0.012500
2023-03-29 17:38:32,614 epoch 95 - iter 245/493 - loss 0.00616908 - time (sec): 17.10 - samples/sec: 7550.33 - lr: 0.012500
2023-03-29 17:38:35,903 epoch 95 - iter 294/493 - loss 0.00641856 - time (sec): 20.38 - samples/sec: 7574.88 - lr: 0.012500
2023-03-29 17:38:39,322 epoch 95 - iter 343/493 - loss 0.00646827 - time (sec): 23.80 - samples/sec: 7567.71 - lr: 0.012500
2023-03-29 17:38:42,675 epoch 95 - iter 392/493 - loss 0.00657234 - time (sec): 27.16 - samples/sec: 7579.78 - lr: 0.012500
2023-03-29 17:38:46,017 epoch 95 - iter 441/493 - loss 0.00679228 - time (sec): 30.50 - samples/sec: 7591.70 - lr: 0.012500
2023-03-29 17:38:49,406 epoch 95 - iter 490/493 - loss 0.00655373 - time (sec): 33.89 - samples/sec: 7605.25 - lr: 0.012500
2023-03-29 17:38:49,613 ----------------------------------------------------------------------------------------------------
2023-03-29 17:38:49,613 EPOCH 95 done: loss 0.0065 - lr 0.012500
2023-03-29 17:38:49,613 BAD EPOCHS (no improvement): 0
2023-03-29 17:38:49,616 ----------------------------------------------------------------------------------------------------
2023-03-29 17:38:52,972 epoch 96 - iter 49/493 - loss 0.00591867 - time (sec): 3.36 - samples/sec: 7797.66 - lr: 0.012500
2023-03-29 17:38:56,413 epoch 96 - iter 98/493 - loss 0.00642648 - time (sec): 6.80 - samples/sec: 7694.51 - lr: 0.012500
2023-03-29 17:38:59,923 epoch 96 - iter 147/493 - loss 0.00631591 - time (sec): 10.31 - samples/sec: 7549.90 - lr: 0.012500
2023-03-29 17:39:03,391 epoch 96 - iter 196/493 - loss 0.00636280 - time (sec): 13.78 - samples/sec: 7544.03 - lr: 0.012500
2023-03-29 17:39:06,799 epoch 96 - iter 245/493 - loss 0.00663686 - time (sec): 17.18 - samples/sec: 7565.57 - lr: 0.012500
2023-03-29 17:39:10,104 epoch 96 - iter 294/493 - loss 0.00669715 - time (sec): 20.49 - samples/sec: 7582.58 - lr: 0.012500
2023-03-29 17:39:13,616 epoch 96 - iter 343/493 - loss 0.00671731 - time (sec): 24.00 - samples/sec: 7518.54 - lr: 0.012500
2023-03-29 17:39:19,911 epoch 96 - iter 392/493 - loss 0.00686078 - time (sec): 30.30 - samples/sec: 6804.79 - lr: 0.012500
2023-03-29 17:39:23,222 epoch 96 - iter 441/493 - loss 0.00683092 - time (sec): 33.61 - samples/sec: 6895.97 - lr: 0.012500
2023-03-29 17:39:26,674 epoch 96 - iter 490/493 - loss 0.00672148 - time (sec): 37.06 - samples/sec: 6949.59 - lr: 0.012500
2023-03-29 17:39:26,870 ----------------------------------------------------------------------------------------------------
2023-03-29 17:39:26,870 EPOCH 96 done: loss 0.0067 - lr 0.012500
2023-03-29 17:39:26,870 BAD EPOCHS (no improvement): 1
2023-03-29 17:39:26,873 ----------------------------------------------------------------------------------------------------
2023-03-29 17:39:30,409 epoch 97 - iter 49/493 - loss 0.00732336 - time (sec): 3.54 - samples/sec: 7387.14 - lr: 0.012500
2023-03-29 17:39:33,791 epoch 97 - iter 98/493 - loss 0.00626166 - time (sec): 6.92 - samples/sec: 7451.67 - lr: 0.012500
2023-03-29 17:39:37,128 epoch 97 - iter 147/493 - loss 0.00669875 - time (sec): 10.26 - samples/sec: 7522.30 - lr: 0.012500
2023-03-29 17:39:40,480 epoch 97 - iter 196/493 - loss 0.00652041 - time (sec): 13.61 - samples/sec: 7525.05 - lr: 0.012500
2023-03-29 17:39:43,787 epoch 97 - iter 245/493 - loss 0.00648784 - time (sec): 16.91 - samples/sec: 7566.76 - lr: 0.012500
2023-03-29 17:39:47,356 epoch 97 - iter 294/493 - loss 0.00683404 - time (sec): 20.48 - samples/sec: 7535.02 - lr: 0.012500
2023-03-29 17:39:50,780 epoch 97 - iter 343/493 - loss 0.00680856 - time (sec): 23.91 - samples/sec: 7535.76 - lr: 0.012500
2023-03-29 17:39:54,114 epoch 97 - iter 392/493 - loss 0.00681470 - time (sec): 27.24 - samples/sec: 7536.12 - lr: 0.012500
2023-03-29 17:39:57,598 epoch 97 - iter 441/493 - loss 0.00685807 - time (sec): 30.73 - samples/sec: 7529.57 - lr: 0.012500
2023-03-29 17:40:00,966 epoch 97 - iter 490/493 - loss 0.00684843 - time (sec): 34.09 - samples/sec: 7557.47 - lr: 0.012500
2023-03-29 17:40:01,159 ----------------------------------------------------------------------------------------------------
2023-03-29 17:40:01,159 EPOCH 97 done: loss 0.0068 - lr 0.012500
2023-03-29 17:40:01,159 BAD EPOCHS (no improvement): 2
2023-03-29 17:40:01,162 ----------------------------------------------------------------------------------------------------
2023-03-29 17:40:04,588 epoch 98 - iter 49/493 - loss 0.00736130 - time (sec): 3.43 - samples/sec: 7580.80 - lr: 0.012500
2023-03-29 17:40:08,102 epoch 98 - iter 98/493 - loss 0.00625809 - time (sec): 6.94 - samples/sec: 7532.20 - lr: 0.012500
2023-03-29 17:40:11,482 epoch 98 - iter 147/493 - loss 0.00647096 - time (sec): 10.32 - samples/sec: 7605.97 - lr: 0.012500
2023-03-29 17:40:14,763 epoch 98 - iter 196/493 - loss 0.00628648 - time (sec): 13.60 - samples/sec: 7601.24 - lr: 0.012500
2023-03-29 17:40:18,086 epoch 98 - iter 245/493 - loss 0.00633511 - time (sec): 16.92 - samples/sec: 7593.51 - lr: 0.012500
2023-03-29 17:40:21,649 epoch 98 - iter 294/493 - loss 0.00634420 - time (sec): 20.49 - samples/sec: 7568.09 - lr: 0.012500
2023-03-29 17:40:24,971 epoch 98 - iter 343/493 - loss 0.00642238 - time (sec): 23.81 - samples/sec: 7601.82 - lr: 0.012500
2023-03-29 17:40:28,428 epoch 98 - iter 392/493 - loss 0.00632552 - time (sec): 27.27 - samples/sec: 7563.43 - lr: 0.012500
2023-03-29 17:40:31,709 epoch 98 - iter 441/493 - loss 0.00655439 - time (sec): 30.55 - samples/sec: 7577.74 - lr: 0.012500
2023-03-29 17:40:35,101 epoch 98 - iter 490/493 - loss 0.00670011 - time (sec): 33.94 - samples/sec: 7585.75 - lr: 0.012500
2023-03-29 17:40:35,327 ----------------------------------------------------------------------------------------------------
2023-03-29 17:40:35,327 EPOCH 98 done: loss 0.0067 - lr 0.012500
2023-03-29 17:40:35,327 BAD EPOCHS (no improvement): 3
2023-03-29 17:40:35,330 ----------------------------------------------------------------------------------------------------
2023-03-29 17:40:38,615 epoch 99 - iter 49/493 - loss 0.00763632 - time (sec): 3.28 - samples/sec: 7642.33 - lr: 0.012500
2023-03-29 17:40:42,080 epoch 99 - iter 98/493 - loss 0.00661340 - time (sec): 6.75 - samples/sec: 7513.07 - lr: 0.012500
2023-03-29 17:40:45,702 epoch 99 - iter 147/493 - loss 0.00703313 - time (sec): 10.37 - samples/sec: 7395.55 - lr: 0.012500
2023-03-29 17:40:49,403 epoch 99 - iter 196/493 - loss 0.00703327 - time (sec): 14.07 - samples/sec: 7293.92 - lr: 0.012500
2023-03-29 17:40:52,885 epoch 99 - iter 245/493 - loss 0.00735015 - time (sec): 17.55 - samples/sec: 7306.54 - lr: 0.012500
2023-03-29 17:40:56,423 epoch 99 - iter 294/493 - loss 0.00725869 - time (sec): 21.09 - samples/sec: 7344.87 - lr: 0.012500
2023-03-29 17:40:59,998 epoch 99 - iter 343/493 - loss 0.00718158 - time (sec): 24.67 - samples/sec: 7329.30 - lr: 0.012500
2023-03-29 17:41:03,467 epoch 99 - iter 392/493 - loss 0.00709454 - time (sec): 28.14 - samples/sec: 7342.38 - lr: 0.012500
2023-03-29 17:41:06,937 epoch 99 - iter 441/493 - loss 0.00705312 - time (sec): 31.61 - samples/sec: 7337.12 - lr: 0.012500
2023-03-29 17:41:10,338 epoch 99 - iter 490/493 - loss 0.00702137 - time (sec): 35.01 - samples/sec: 7356.27 - lr: 0.012500
2023-03-29 17:41:10,543 ----------------------------------------------------------------------------------------------------
2023-03-29 17:41:10,543 EPOCH 99 done: loss 0.0070 - lr 0.012500
2023-03-29 17:41:10,543 Epoch 99: reducing learning rate of group 0 to 6.2500e-03.
2023-03-29 17:41:10,543 BAD EPOCHS (no improvement): 4
2023-03-29 17:41:10,546 ----------------------------------------------------------------------------------------------------
2023-03-29 17:41:13,927 epoch 100 - iter 49/493 - loss 0.00781292 - time (sec): 3.38 - samples/sec: 7607.63 - lr: 0.006250
2023-03-29 17:41:17,251 epoch 100 - iter 98/493 - loss 0.00777990 - time (sec): 6.70 - samples/sec: 7608.20 - lr: 0.006250
2023-03-29 17:41:20,575 epoch 100 - iter 147/493 - loss 0.00752571 - time (sec): 10.03 - samples/sec: 7707.53 - lr: 0.006250
2023-03-29 17:41:24,078 epoch 100 - iter 196/493 - loss 0.00775018 - time (sec): 13.53 - samples/sec: 7643.09 - lr: 0.006250
2023-03-29 17:41:27,397 epoch 100 - iter 245/493 - loss 0.00773860 - time (sec): 16.85 - samples/sec: 7627.85 - lr: 0.006250
2023-03-29 17:41:30,892 epoch 100 - iter 294/493 - loss 0.00752868 - time (sec): 20.35 - samples/sec: 7599.70 - lr: 0.006250
2023-03-29 17:41:34,240 epoch 100 - iter 343/493 - loss 0.00736977 - time (sec): 23.69 - samples/sec: 7613.83 - lr: 0.006250
2023-03-29 17:41:37,594 epoch 100 - iter 392/493 - loss 0.00737501 - time (sec): 27.05 - samples/sec: 7608.49 - lr: 0.006250
2023-03-29 17:41:40,951 epoch 100 - iter 441/493 - loss 0.00748740 - time (sec): 30.41 - samples/sec: 7617.68 - lr: 0.006250
2023-03-29 17:41:44,542 epoch 100 - iter 490/493 - loss 0.00726519 - time (sec): 34.00 - samples/sec: 7577.19 - lr: 0.006250
2023-03-29 17:41:44,738 ----------------------------------------------------------------------------------------------------
2023-03-29 17:41:44,738 EPOCH 100 done: loss 0.0072 - lr 0.006250
2023-03-29 17:41:44,738 BAD EPOCHS (no improvement): 1
2023-03-29 17:41:44,741 ----------------------------------------------------------------------------------------------------
2023-03-29 17:41:48,117 epoch 101 - iter 49/493 - loss 0.00679042 - time (sec): 3.38 - samples/sec: 7505.27 - lr: 0.006250
2023-03-29 17:41:51,564 epoch 101 - iter 98/493 - loss 0.00668759 - time (sec): 6.82 - samples/sec: 7456.05 - lr: 0.006250
2023-03-29 17:41:54,839 epoch 101 - iter 147/493 - loss 0.00682418 - time (sec): 10.10 - samples/sec: 7551.41 - lr: 0.006250
2023-03-29 17:41:58,130 epoch 101 - iter 196/493 - loss 0.00665905 - time (sec): 13.39 - samples/sec: 7590.33 - lr: 0.006250
2023-03-29 17:42:01,523 epoch 101 - iter 245/493 - loss 0.00699336 - time (sec): 16.78 - samples/sec: 7592.93 - lr: 0.006250
2023-03-29 17:42:04,963 epoch 101 - iter 294/493 - loss 0.00727522 - time (sec): 20.22 - samples/sec: 7561.06 - lr: 0.006250
2023-03-29 17:42:08,654 epoch 101 - iter 343/493 - loss 0.00720216 - time (sec): 23.91 - samples/sec: 7520.32 - lr: 0.006250
2023-03-29 17:42:12,046 epoch 101 - iter 392/493 - loss 0.00722994 - time (sec): 27.31 - samples/sec: 7532.23 - lr: 0.006250
2023-03-29 17:42:15,428 epoch 101 - iter 441/493 - loss 0.00715049 - time (sec): 30.69 - samples/sec: 7540.97 - lr: 0.006250
2023-03-29 17:42:18,860 epoch 101 - iter 490/493 - loss 0.00703315 - time (sec): 34.12 - samples/sec: 7550.95 - lr: 0.006250
2023-03-29 17:42:19,064 ----------------------------------------------------------------------------------------------------
2023-03-29 17:42:19,064 EPOCH 101 done: loss 0.0070 - lr 0.006250
2023-03-29 17:42:19,064 BAD EPOCHS (no improvement): 2
2023-03-29 17:42:19,067 ----------------------------------------------------------------------------------------------------
2023-03-29 17:42:22,621 epoch 102 - iter 49/493 - loss 0.00564790 - time (sec): 3.55 - samples/sec: 7258.22 - lr: 0.006250
2023-03-29 17:42:26,096 epoch 102 - iter 98/493 - loss 0.00634264 - time (sec): 7.03 - samples/sec: 7367.86 - lr: 0.006250
2023-03-29 17:42:29,523 epoch 102 - iter 147/493 - loss 0.00656381 - time (sec): 10.46 - samples/sec: 7406.53 - lr: 0.006250
2023-03-29 17:42:32,891 epoch 102 - iter 196/493 - loss 0.00663508 - time (sec): 13.82 - samples/sec: 7467.36 - lr: 0.006250
2023-03-29 17:42:36,296 epoch 102 - iter 245/493 - loss 0.00681001 - time (sec): 17.23 - samples/sec: 7486.78 - lr: 0.006250
2023-03-29 17:42:39,679 epoch 102 - iter 294/493 - loss 0.00688534 - time (sec): 20.61 - samples/sec: 7488.36 - lr: 0.006250
2023-03-29 17:42:43,074 epoch 102 - iter 343/493 - loss 0.00688321 - time (sec): 24.01 - samples/sec: 7517.16 - lr: 0.006250
2023-03-29 17:42:46,504 epoch 102 - iter 392/493 - loss 0.00687005 - time (sec): 27.44 - samples/sec: 7526.23 - lr: 0.006250
2023-03-29 17:42:49,861 epoch 102 - iter 441/493 - loss 0.00684483 - time (sec): 30.79 - samples/sec: 7550.09 - lr: 0.006250
2023-03-29 17:42:53,137 epoch 102 - iter 490/493 - loss 0.00687019 - time (sec): 34.07 - samples/sec: 7562.41 - lr: 0.006250
2023-03-29 17:42:53,336 ----------------------------------------------------------------------------------------------------
2023-03-29 17:42:53,336 EPOCH 102 done: loss 0.0069 - lr 0.006250
2023-03-29 17:42:53,336 BAD EPOCHS (no improvement): 3
2023-03-29 17:42:53,339 ----------------------------------------------------------------------------------------------------
2023-03-29 17:42:56,817 epoch 103 - iter 49/493 - loss 0.00625346 - time (sec): 3.48 - samples/sec: 7386.06 - lr: 0.006250
2023-03-29 17:43:00,238 epoch 103 - iter 98/493 - loss 0.00672863 - time (sec): 6.90 - samples/sec: 7507.57 - lr: 0.006250
2023-03-29 17:43:03,653 epoch 103 - iter 147/493 - loss 0.00688897 - time (sec): 10.31 - samples/sec: 7559.68 - lr: 0.006250
2023-03-29 17:43:07,032 epoch 103 - iter 196/493 - loss 0.00645936 - time (sec): 13.69 - samples/sec: 7584.93 - lr: 0.006250
2023-03-29 17:43:10,430 epoch 103 - iter 245/493 - loss 0.00644862 - time (sec): 17.09 - samples/sec: 7590.17 - lr: 0.006250
2023-03-29 17:43:13,817 epoch 103 - iter 294/493 - loss 0.00656614 - time (sec): 20.48 - samples/sec: 7574.17 - lr: 0.006250
2023-03-29 17:43:17,296 epoch 103 - iter 343/493 - loss 0.00661927 - time (sec): 23.96 - samples/sec: 7535.85 - lr: 0.006250
2023-03-29 17:43:20,637 epoch 103 - iter 392/493 - loss 0.00652321 - time (sec): 27.30 - samples/sec: 7568.08 - lr: 0.006250
2023-03-29 17:43:24,021 epoch 103 - iter 441/493 - loss 0.00646239 - time (sec): 30.68 - samples/sec: 7572.40 - lr: 0.006250
2023-03-29 17:43:27,432 epoch 103 - iter 490/493 - loss 0.00645975 - time (sec): 34.09 - samples/sec: 7558.57 - lr: 0.006250
2023-03-29 17:43:27,637 ----------------------------------------------------------------------------------------------------
2023-03-29 17:43:27,637 EPOCH 103 done: loss 0.0065 - lr 0.006250
2023-03-29 17:43:27,637 BAD EPOCHS (no improvement): 0
2023-03-29 17:43:27,656 ----------------------------------------------------------------------------------------------------
2023-03-29 17:43:31,159 epoch 104 - iter 49/493 - loss 0.00688949 - time (sec): 3.50 - samples/sec: 7648.84 - lr: 0.006250
2023-03-29 17:43:34,477 epoch 104 - iter 98/493 - loss 0.00658225 - time (sec): 6.82 - samples/sec: 7678.01 - lr: 0.006250
2023-03-29 17:43:37,926 epoch 104 - iter 147/493 - loss 0.00654253 - time (sec): 10.27 - samples/sec: 7611.14 - lr: 0.006250
2023-03-29 17:43:41,239 epoch 104 - iter 196/493 - loss 0.00637756 - time (sec): 13.58 - samples/sec: 7662.54 - lr: 0.006250
2023-03-29 17:43:44,755 epoch 104 - iter 245/493 - loss 0.00617179 - time (sec): 17.10 - samples/sec: 7625.36 - lr: 0.006250
2023-03-29 17:43:48,133 epoch 104 - iter 294/493 - loss 0.00634876 - time (sec): 20.48 - samples/sec: 7622.77 - lr: 0.006250
2023-03-29 17:43:51,441 epoch 104 - iter 343/493 - loss 0.00645310 - time (sec): 23.78 - samples/sec: 7605.03 - lr: 0.006250
2023-03-29 17:43:55,032 epoch 104 - iter 392/493 - loss 0.00649483 - time (sec): 27.38 - samples/sec: 7568.48 - lr: 0.006250
2023-03-29 17:43:58,369 epoch 104 - iter 441/493 - loss 0.00658586 - time (sec): 30.71 - samples/sec: 7568.96 - lr: 0.006250
2023-03-29 17:44:01,866 epoch 104 - iter 490/493 - loss 0.00669526 - time (sec): 34.21 - samples/sec: 7530.22 - lr: 0.006250
2023-03-29 17:44:02,051 ----------------------------------------------------------------------------------------------------
2023-03-29 17:44:02,051 EPOCH 104 done: loss 0.0067 - lr 0.006250
2023-03-29 17:44:02,051 BAD EPOCHS (no improvement): 1
2023-03-29 17:44:02,054 ----------------------------------------------------------------------------------------------------
2023-03-29 17:44:05,424 epoch 105 - iter 49/493 - loss 0.00696216 - time (sec): 3.37 - samples/sec: 7654.03 - lr: 0.006250
2023-03-29 17:44:09,056 epoch 105 - iter 98/493 - loss 0.00709603 - time (sec): 7.00 - samples/sec: 7450.78 - lr: 0.006250
2023-03-29 17:44:12,620 epoch 105 - iter 147/493 - loss 0.00660560 - time (sec): 10.57 - samples/sec: 7405.96 - lr: 0.006250
2023-03-29 17:44:16,055 epoch 105 - iter 196/493 - loss 0.00611341 - time (sec): 14.00 - samples/sec: 7409.07 - lr: 0.006250
2023-03-29 17:44:19,462 epoch 105 - iter 245/493 - loss 0.00586705 - time (sec): 17.41 - samples/sec: 7469.39 - lr: 0.006250
2023-03-29 17:44:22,753 epoch 105 - iter 294/493 - loss 0.00594734 - time (sec): 20.70 - samples/sec: 7496.14 - lr: 0.006250
2023-03-29 17:44:26,096 epoch 105 - iter 343/493 - loss 0.00600638 - time (sec): 24.04 - samples/sec: 7519.25 - lr: 0.006250
2023-03-29 17:44:29,429 epoch 105 - iter 392/493 - loss 0.00596648 - time (sec): 27.37 - samples/sec: 7520.20 - lr: 0.006250
2023-03-29 17:44:32,834 epoch 105 - iter 441/493 - loss 0.00586112 - time (sec): 30.78 - samples/sec: 7534.23 - lr: 0.006250
2023-03-29 17:44:36,246 epoch 105 - iter 490/493 - loss 0.00580261 - time (sec): 34.19 - samples/sec: 7536.27 - lr: 0.006250
2023-03-29 17:44:36,455 ----------------------------------------------------------------------------------------------------
2023-03-29 17:44:36,455 EPOCH 105 done: loss 0.0058 - lr 0.006250
2023-03-29 17:44:36,455 BAD EPOCHS (no improvement): 0
2023-03-29 17:44:36,462 ----------------------------------------------------------------------------------------------------
2023-03-29 17:44:39,961 epoch 106 - iter 49/493 - loss 0.00639123 - time (sec): 3.50 - samples/sec: 7328.57 - lr: 0.006250
2023-03-29 17:44:43,429 epoch 106 - iter 98/493 - loss 0.00581449 - time (sec): 6.97 - samples/sec: 7450.81 - lr: 0.006250
2023-03-29 17:44:47,041 epoch 106 - iter 147/493 - loss 0.00613041 - time (sec): 10.58 - samples/sec: 7381.59 - lr: 0.006250
2023-03-29 17:44:50,467 epoch 106 - iter 196/493 - loss 0.00628508 - time (sec): 14.01 - samples/sec: 7400.46 - lr: 0.006250
2023-03-29 17:44:53,841 epoch 106 - iter 245/493 - loss 0.00630604 - time (sec): 17.38 - samples/sec: 7463.03 - lr: 0.006250
2023-03-29 17:44:57,226 epoch 106 - iter 294/493 - loss 0.00642721 - time (sec): 20.76 - samples/sec: 7504.85 - lr: 0.006250
2023-03-29 17:45:00,660 epoch 106 - iter 343/493 - loss 0.00650604 - time (sec): 24.20 - samples/sec: 7514.05 - lr: 0.006250
2023-03-29 17:45:03,893 epoch 106 - iter 392/493 - loss 0.00668340 - time (sec): 27.43 - samples/sec: 7534.06 - lr: 0.006250
2023-03-29 17:45:07,228 epoch 106 - iter 441/493 - loss 0.00675751 - time (sec): 30.77 - samples/sec: 7547.52 - lr: 0.006250
2023-03-29 17:45:10,578 epoch 106 - iter 490/493 - loss 0.00669822 - time (sec): 34.12 - samples/sec: 7558.91 - lr: 0.006250
2023-03-29 17:45:10,773 ----------------------------------------------------------------------------------------------------
2023-03-29 17:45:10,773 EPOCH 106 done: loss 0.0067 - lr 0.006250
2023-03-29 17:45:10,773 BAD EPOCHS (no improvement): 1
2023-03-29 17:45:10,776 ----------------------------------------------------------------------------------------------------
2023-03-29 17:45:14,139 epoch 107 - iter 49/493 - loss 0.00683930 - time (sec): 3.36 - samples/sec: 7631.58 - lr: 0.006250
2023-03-29 17:45:17,494 epoch 107 - iter 98/493 - loss 0.00682668 - time (sec): 6.72 - samples/sec: 7693.71 - lr: 0.006250
2023-03-29 17:45:20,828 epoch 107 - iter 147/493 - loss 0.00676924 - time (sec): 10.05 - samples/sec: 7682.21 - lr: 0.006250
2023-03-29 17:45:24,233 epoch 107 - iter 196/493 - loss 0.00671740 - time (sec): 13.46 - samples/sec: 7635.77 - lr: 0.006250
2023-03-29 17:45:27,820 epoch 107 - iter 245/493 - loss 0.00693082 - time (sec): 17.04 - samples/sec: 7577.00 - lr: 0.006250
2023-03-29 17:45:31,295 epoch 107 - iter 294/493 - loss 0.00670085 - time (sec): 20.52 - samples/sec: 7548.87 - lr: 0.006250
2023-03-29 17:45:34,614 epoch 107 - iter 343/493 - loss 0.00668710 - time (sec): 23.84 - samples/sec: 7554.80 - lr: 0.006250
2023-03-29 17:45:38,192 epoch 107 - iter 392/493 - loss 0.00660513 - time (sec): 27.42 - samples/sec: 7530.21 - lr: 0.006250
2023-03-29 17:45:41,677 epoch 107 - iter 441/493 - loss 0.00659416 - time (sec): 30.90 - samples/sec: 7528.22 - lr: 0.006250
2023-03-29 17:45:44,879 epoch 107 - iter 490/493 - loss 0.00662348 - time (sec): 34.10 - samples/sec: 7555.36 - lr: 0.006250
2023-03-29 17:45:45,080 ----------------------------------------------------------------------------------------------------
2023-03-29 17:45:45,080 EPOCH 107 done: loss 0.0067 - lr 0.006250
2023-03-29 17:45:45,080 BAD EPOCHS (no improvement): 2
2023-03-29 17:45:45,083 ----------------------------------------------------------------------------------------------------
2023-03-29 17:45:48,625 epoch 108 - iter 49/493 - loss 0.00551575 - time (sec): 3.54 - samples/sec: 7268.45 - lr: 0.006250
2023-03-29 17:45:52,057 epoch 108 - iter 98/493 - loss 0.00552690 - time (sec): 6.97 - samples/sec: 7405.47 - lr: 0.006250
2023-03-29 17:45:55,471 epoch 108 - iter 147/493 - loss 0.00592047 - time (sec): 10.39 - samples/sec: 7434.61 - lr: 0.006250
2023-03-29 17:45:58,895 epoch 108 - iter 196/493 - loss 0.00594017 - time (sec): 13.81 - samples/sec: 7480.84 - lr: 0.006250
2023-03-29 17:46:02,244 epoch 108 - iter 245/493 - loss 0.00604263 - time (sec): 17.16 - samples/sec: 7457.55 - lr: 0.006250
2023-03-29 17:46:05,872 epoch 108 - iter 294/493 - loss 0.00612733 - time (sec): 20.79 - samples/sec: 7416.79 - lr: 0.006250
2023-03-29 17:46:09,225 epoch 108 - iter 343/493 - loss 0.00608618 - time (sec): 24.14 - samples/sec: 7465.94 - lr: 0.006250
2023-03-29 17:46:12,592 epoch 108 - iter 392/493 - loss 0.00601520 - time (sec): 27.51 - samples/sec: 7510.39 - lr: 0.006250
2023-03-29 17:46:16,006 epoch 108 - iter 441/493 - loss 0.00618919 - time (sec): 30.92 - samples/sec: 7517.98 - lr: 0.006250
2023-03-29 17:46:19,255 epoch 108 - iter 490/493 - loss 0.00612462 - time (sec): 34.17 - samples/sec: 7538.09 - lr: 0.006250
2023-03-29 17:46:19,471 ----------------------------------------------------------------------------------------------------
2023-03-29 17:46:19,471 EPOCH 108 done: loss 0.0061 - lr 0.006250
2023-03-29 17:46:19,471 BAD EPOCHS (no improvement): 3
2023-03-29 17:46:19,474 ----------------------------------------------------------------------------------------------------
2023-03-29 17:46:22,824 epoch 109 - iter 49/493 - loss 0.00903710 - time (sec): 3.35 - samples/sec: 7635.08 - lr: 0.006250
2023-03-29 17:46:26,242 epoch 109 - iter 98/493 - loss 0.00814505 - time (sec): 6.77 - samples/sec: 7515.80 - lr: 0.006250
2023-03-29 17:46:29,666 epoch 109 - iter 147/493 - loss 0.00746926 - time (sec): 10.19 - samples/sec: 7508.80 - lr: 0.006250
2023-03-29 17:46:33,062 epoch 109 - iter 196/493 - loss 0.00725585 - time (sec): 13.59 - samples/sec: 7571.22 - lr: 0.006250
2023-03-29 17:46:36,536 epoch 109 - iter 245/493 - loss 0.00703958 - time (sec): 17.06 - samples/sec: 7558.56 - lr: 0.006250
2023-03-29 17:46:39,840 epoch 109 - iter 294/493 - loss 0.00688267 - time (sec): 20.37 - samples/sec: 7582.88 - lr: 0.006250
2023-03-29 17:46:43,203 epoch 109 - iter 343/493 - loss 0.00681259 - time (sec): 23.73 - samples/sec: 7590.04 - lr: 0.006250
2023-03-29 17:46:46,658 epoch 109 - iter 392/493 - loss 0.00674094 - time (sec): 27.18 - samples/sec: 7576.79 - lr: 0.006250
2023-03-29 17:46:49,968 epoch 109 - iter 441/493 - loss 0.00661662 - time (sec): 30.49 - samples/sec: 7592.64 - lr: 0.006250
2023-03-29 17:46:53,484 epoch 109 - iter 490/493 - loss 0.00661883 - time (sec): 34.01 - samples/sec: 7574.34 - lr: 0.006250
2023-03-29 17:46:53,684 ----------------------------------------------------------------------------------------------------
2023-03-29 17:46:53,684 EPOCH 109 done: loss 0.0066 - lr 0.006250
2023-03-29 17:46:53,684 Epoch 109: reducing learning rate of group 0 to 3.1250e-03.
2023-03-29 17:46:53,684 BAD EPOCHS (no improvement): 4
2023-03-29 17:46:53,686 ----------------------------------------------------------------------------------------------------
2023-03-29 17:46:57,129 epoch 110 - iter 49/493 - loss 0.00797808 - time (sec): 3.44 - samples/sec: 7578.80 - lr: 0.003125
2023-03-29 17:47:00,647 epoch 110 - iter 98/493 - loss 0.00788657 - time (sec): 6.96 - samples/sec: 7490.44 - lr: 0.003125
2023-03-29 17:47:04,036 epoch 110 - iter 147/493 - loss 0.00761853 - time (sec): 10.35 - samples/sec: 7520.12 - lr: 0.003125
2023-03-29 17:47:07,485 epoch 110 - iter 196/493 - loss 0.00719395 - time (sec): 13.80 - samples/sec: 7469.20 - lr: 0.003125
2023-03-29 17:47:10,802 epoch 110 - iter 245/493 - loss 0.00706682 - time (sec): 17.12 - samples/sec: 7486.76 - lr: 0.003125
2023-03-29 17:47:14,192 epoch 110 - iter 294/493 - loss 0.00706757 - time (sec): 20.50 - samples/sec: 7515.01 - lr: 0.003125
2023-03-29 17:47:17,627 epoch 110 - iter 343/493 - loss 0.00680669 - time (sec): 23.94 - samples/sec: 7554.11 - lr: 0.003125
2023-03-29 17:47:20,987 epoch 110 - iter 392/493 - loss 0.00669291 - time (sec): 27.30 - samples/sec: 7566.27 - lr: 0.003125
2023-03-29 17:47:24,443 epoch 110 - iter 441/493 - loss 0.00663679 - time (sec): 30.76 - samples/sec: 7547.51 - lr: 0.003125
2023-03-29 17:47:27,836 epoch 110 - iter 490/493 - loss 0.00666335 - time (sec): 34.15 - samples/sec: 7540.72 - lr: 0.003125
2023-03-29 17:47:28,047 ----------------------------------------------------------------------------------------------------
2023-03-29 17:47:28,047 EPOCH 110 done: loss 0.0066 - lr 0.003125
2023-03-29 17:47:28,047 BAD EPOCHS (no improvement): 1
2023-03-29 17:47:28,050 ----------------------------------------------------------------------------------------------------
2023-03-29 17:47:31,485 epoch 111 - iter 49/493 - loss 0.00607921 - time (sec): 3.43 - samples/sec: 7504.04 - lr: 0.003125
2023-03-29 17:47:34,908 epoch 111 - iter 98/493 - loss 0.00554559 - time (sec): 6.86 - samples/sec: 7510.30 - lr: 0.003125
2023-03-29 17:47:38,226 epoch 111 - iter 147/493 - loss 0.00606643 - time (sec): 10.18 - samples/sec: 7616.09 - lr: 0.003125
2023-03-29 17:47:41,519 epoch 111 - iter 196/493 - loss 0.00581492 - time (sec): 13.47 - samples/sec: 7650.82 - lr: 0.003125
2023-03-29 17:47:44,811 epoch 111 - iter 245/493 - loss 0.00604291 - time (sec): 16.76 - samples/sec: 7677.78 - lr: 0.003125
2023-03-29 17:47:48,389 epoch 111 - iter 294/493 - loss 0.00605158 - time (sec): 20.34 - samples/sec: 7612.18 - lr: 0.003125
2023-03-29 17:47:51,867 epoch 111 - iter 343/493 - loss 0.00601472 - time (sec): 23.82 - samples/sec: 7589.31 - lr: 0.003125
2023-03-29 17:47:55,228 epoch 111 - iter 392/493 - loss 0.00616816 - time (sec): 27.18 - samples/sec: 7569.76 - lr: 0.003125
2023-03-29 17:47:58,691 epoch 111 - iter 441/493 - loss 0.00619059 - time (sec): 30.64 - samples/sec: 7570.77 - lr: 0.003125
2023-03-29 17:48:02,035 epoch 111 - iter 490/493 - loss 0.00625418 - time (sec): 33.98 - samples/sec: 7585.11 - lr: 0.003125
2023-03-29 17:48:02,211 ----------------------------------------------------------------------------------------------------
2023-03-29 17:48:02,211 EPOCH 111 done: loss 0.0063 - lr 0.003125
2023-03-29 17:48:02,211 BAD EPOCHS (no improvement): 2
2023-03-29 17:48:02,214 ----------------------------------------------------------------------------------------------------
2023-03-29 17:48:05,702 epoch 112 - iter 49/493 - loss 0.00570778 - time (sec): 3.49 - samples/sec: 7461.05 - lr: 0.003125
2023-03-29 17:48:09,138 epoch 112 - iter 98/493 - loss 0.00638859 - time (sec): 6.92 - samples/sec: 7504.59 - lr: 0.003125
2023-03-29 17:48:12,464 epoch 112 - iter 147/493 - loss 0.00623389 - time (sec): 10.25 - samples/sec: 7561.92 - lr: 0.003125
2023-03-29 17:48:15,822 epoch 112 - iter 196/493 - loss 0.00631565 - time (sec): 13.61 - samples/sec: 7559.53 - lr: 0.003125
2023-03-29 17:48:19,318 epoch 112 - iter 245/493 - loss 0.00637721 - time (sec): 17.10 - samples/sec: 7541.73 - lr: 0.003125
2023-03-29 17:48:22,610 epoch 112 - iter 294/493 - loss 0.00647482 - time (sec): 20.40 - samples/sec: 7562.90 - lr: 0.003125
2023-03-29 17:48:26,213 epoch 112 - iter 343/493 - loss 0.00629836 - time (sec): 24.00 - samples/sec: 7537.45 - lr: 0.003125
2023-03-29 17:48:29,518 epoch 112 - iter 392/493 - loss 0.00636500 - time (sec): 27.30 - samples/sec: 7569.61 - lr: 0.003125
2023-03-29 17:48:32,832 epoch 112 - iter 441/493 - loss 0.00630345 - time (sec): 30.62 - samples/sec: 7565.54 - lr: 0.003125
2023-03-29 17:48:36,184 epoch 112 - iter 490/493 - loss 0.00622378 - time (sec): 33.97 - samples/sec: 7576.11 - lr: 0.003125
2023-03-29 17:48:36,407 ----------------------------------------------------------------------------------------------------
2023-03-29 17:48:36,407 EPOCH 112 done: loss 0.0062 - lr 0.003125
2023-03-29 17:48:36,407 BAD EPOCHS (no improvement): 3
2023-03-29 17:48:36,409 ----------------------------------------------------------------------------------------------------
2023-03-29 17:48:39,983 epoch 113 - iter 49/493 - loss 0.00663710 - time (sec): 3.57 - samples/sec: 7271.01 - lr: 0.003125
2023-03-29 17:48:43,368 epoch 113 - iter 98/493 - loss 0.00679455 - time (sec): 6.96 - samples/sec: 7408.44 - lr: 0.003125
2023-03-29 17:48:46,864 epoch 113 - iter 147/493 - loss 0.00653552 - time (sec): 10.45 - samples/sec: 7411.12 - lr: 0.003125
2023-03-29 17:48:50,278 epoch 113 - iter 196/493 - loss 0.00639593 - time (sec): 13.87 - samples/sec: 7445.78 - lr: 0.003125
2023-03-29 17:48:53,720 epoch 113 - iter 245/493 - loss 0.00661250 - time (sec): 17.31 - samples/sec: 7425.43 - lr: 0.003125
2023-03-29 17:48:57,394 epoch 113 - iter 294/493 - loss 0.00678804 - time (sec): 20.98 - samples/sec: 7384.44 - lr: 0.003125
2023-03-29 17:49:00,931 epoch 113 - iter 343/493 - loss 0.00691133 - time (sec): 24.52 - samples/sec: 7365.59 - lr: 0.003125
2023-03-29 17:49:04,345 epoch 113 - iter 392/493 - loss 0.00679528 - time (sec): 27.94 - samples/sec: 7376.35 - lr: 0.003125
2023-03-29 17:49:07,816 epoch 113 - iter 441/493 - loss 0.00687754 - time (sec): 31.41 - samples/sec: 7380.89 - lr: 0.003125
2023-03-29 17:49:11,464 epoch 113 - iter 490/493 - loss 0.00661288 - time (sec): 35.06 - samples/sec: 7347.13 - lr: 0.003125
2023-03-29 17:49:11,666 ----------------------------------------------------------------------------------------------------
2023-03-29 17:49:11,666 EPOCH 113 done: loss 0.0066 - lr 0.003125
2023-03-29 17:49:11,666 Epoch 113: reducing learning rate of group 0 to 1.5625e-03.
2023-03-29 17:49:11,666 BAD EPOCHS (no improvement): 4
2023-03-29 17:49:11,669 ----------------------------------------------------------------------------------------------------
2023-03-29 17:49:15,144 epoch 114 - iter 49/493 - loss 0.00582178 - time (sec): 3.47 - samples/sec: 7446.87 - lr: 0.001563
2023-03-29 17:49:18,605 epoch 114 - iter 98/493 - loss 0.00568014 - time (sec): 6.94 - samples/sec: 7419.33 - lr: 0.001563
2023-03-29 17:49:22,077 epoch 114 - iter 147/493 - loss 0.00645996 - time (sec): 10.41 - samples/sec: 7433.19 - lr: 0.001563
2023-03-29 17:49:25,684 epoch 114 - iter 196/493 - loss 0.00657209 - time (sec): 14.01 - samples/sec: 7330.94 - lr: 0.001563
2023-03-29 17:49:29,159 epoch 114 - iter 245/493 - loss 0.00649124 - time (sec): 17.49 - samples/sec: 7354.09 - lr: 0.001563
2023-03-29 17:49:32,724 epoch 114 - iter 294/493 - loss 0.00619404 - time (sec): 21.05 - samples/sec: 7348.35 - lr: 0.001563
2023-03-29 17:49:36,268 epoch 114 - iter 343/493 - loss 0.00629866 - time (sec): 24.60 - samples/sec: 7323.60 - lr: 0.001563
2023-03-29 17:49:39,668 epoch 114 - iter 392/493 - loss 0.00642217 - time (sec): 28.00 - samples/sec: 7353.46 - lr: 0.001563
2023-03-29 17:49:43,217 epoch 114 - iter 441/493 - loss 0.00643458 - time (sec): 31.55 - samples/sec: 7354.00 - lr: 0.001563
2023-03-29 17:49:46,671 epoch 114 - iter 490/493 - loss 0.00646185 - time (sec): 35.00 - samples/sec: 7360.80 - lr: 0.001563
2023-03-29 17:49:46,871 ----------------------------------------------------------------------------------------------------
2023-03-29 17:49:46,872 EPOCH 114 done: loss 0.0064 - lr 0.001563
2023-03-29 17:49:46,872 BAD EPOCHS (no improvement): 1
2023-03-29 17:49:46,874 ----------------------------------------------------------------------------------------------------
2023-03-29 17:49:50,486 epoch 115 - iter 49/493 - loss 0.00507041 - time (sec): 3.61 - samples/sec: 7260.80 - lr: 0.001563
2023-03-29 17:49:53,929 epoch 115 - iter 98/493 - loss 0.00574398 - time (sec): 7.05 - samples/sec: 7327.51 - lr: 0.001563
2023-03-29 17:49:57,433 epoch 115 - iter 147/493 - loss 0.00604956 - time (sec): 10.56 - samples/sec: 7371.63 - lr: 0.001563
2023-03-29 17:50:01,133 epoch 115 - iter 196/493 - loss 0.00613802 - time (sec): 14.26 - samples/sec: 7294.70 - lr: 0.001563
2023-03-29 17:50:04,578 epoch 115 - iter 245/493 - loss 0.00621049 - time (sec): 17.70 - samples/sec: 7318.98 - lr: 0.001563
2023-03-29 17:50:08,025 epoch 115 - iter 294/493 - loss 0.00645544 - time (sec): 21.15 - samples/sec: 7347.54 - lr: 0.001563
2023-03-29 17:50:11,550 epoch 115 - iter 343/493 - loss 0.00667081 - time (sec): 24.68 - samples/sec: 7346.36 - lr: 0.001563
2023-03-29 17:50:14,993 epoch 115 - iter 392/493 - loss 0.00666151 - time (sec): 28.12 - samples/sec: 7356.19 - lr: 0.001563
2023-03-29 17:50:18,534 epoch 115 - iter 441/493 - loss 0.00665130 - time (sec): 31.66 - samples/sec: 7358.85 - lr: 0.001563
2023-03-29 17:50:21,883 epoch 115 - iter 490/493 - loss 0.00649272 - time (sec): 35.01 - samples/sec: 7359.94 - lr: 0.001563
2023-03-29 17:50:22,081 ----------------------------------------------------------------------------------------------------
2023-03-29 17:50:22,081 EPOCH 115 done: loss 0.0065 - lr 0.001563
2023-03-29 17:50:22,081 BAD EPOCHS (no improvement): 2
2023-03-29 17:50:22,084 ----------------------------------------------------------------------------------------------------
2023-03-29 17:50:25,578 epoch 116 - iter 49/493 - loss 0.00628401 - time (sec): 3.49 - samples/sec: 7506.81 - lr: 0.001563
2023-03-29 17:50:29,035 epoch 116 - iter 98/493 - loss 0.00559306 - time (sec): 6.95 - samples/sec: 7504.01 - lr: 0.001563
2023-03-29 17:50:32,553 epoch 116 - iter 147/493 - loss 0.00625377 - time (sec): 10.47 - samples/sec: 7452.97 - lr: 0.001563
2023-03-29 17:50:35,882 epoch 116 - iter 196/493 - loss 0.00592304 - time (sec): 13.80 - samples/sec: 7517.16 - lr: 0.001563
2023-03-29 17:50:39,297 epoch 116 - iter 245/493 - loss 0.00590425 - time (sec): 17.21 - samples/sec: 7523.15 - lr: 0.001563
2023-03-29 17:50:42,685 epoch 116 - iter 294/493 - loss 0.00576106 - time (sec): 20.60 - samples/sec: 7535.89 - lr: 0.001563
2023-03-29 17:50:46,147 epoch 116 - iter 343/493 - loss 0.00582314 - time (sec): 24.06 - samples/sec: 7493.23 - lr: 0.001563
2023-03-29 17:50:49,452 epoch 116 - iter 392/493 - loss 0.00596749 - time (sec): 27.37 - samples/sec: 7518.31 - lr: 0.001563
2023-03-29 17:50:52,898 epoch 116 - iter 441/493 - loss 0.00600771 - time (sec): 30.81 - samples/sec: 7511.51 - lr: 0.001563
2023-03-29 17:50:56,294 epoch 116 - iter 490/493 - loss 0.00596664 - time (sec): 34.21 - samples/sec: 7525.35 - lr: 0.001563
2023-03-29 17:50:56,507 ----------------------------------------------------------------------------------------------------
2023-03-29 17:50:56,507 EPOCH 116 done: loss 0.0060 - lr 0.001563
2023-03-29 17:50:56,507 BAD EPOCHS (no improvement): 3
2023-03-29 17:50:56,510 ----------------------------------------------------------------------------------------------------
2023-03-29 17:50:59,914 epoch 117 - iter 49/493 - loss 0.00556065 - time (sec): 3.40 - samples/sec: 7544.28 - lr: 0.001563
2023-03-29 17:51:03,329 epoch 117 - iter 98/493 - loss 0.00649514 - time (sec): 6.82 - samples/sec: 7579.51 - lr: 0.001563
2023-03-29 17:51:06,676 epoch 117 - iter 147/493 - loss 0.00642426 - time (sec): 10.17 - samples/sec: 7553.38 - lr: 0.001563
2023-03-29 17:51:10,071 epoch 117 - iter 196/493 - loss 0.00675116 - time (sec): 13.56 - samples/sec: 7585.11 - lr: 0.001563
2023-03-29 17:51:13,545 epoch 117 - iter 245/493 - loss 0.00669259 - time (sec): 17.04 - samples/sec: 7596.62 - lr: 0.001563
2023-03-29 17:51:16,865 epoch 117 - iter 294/493 - loss 0.00665603 - time (sec): 20.36 - samples/sec: 7585.05 - lr: 0.001563
2023-03-29 17:51:20,395 epoch 117 - iter 343/493 - loss 0.00675382 - time (sec): 23.89 - samples/sec: 7553.47 - lr: 0.001563
2023-03-29 17:51:23,823 epoch 117 - iter 392/493 - loss 0.00670269 - time (sec): 27.31 - samples/sec: 7534.44 - lr: 0.001563
2023-03-29 17:51:27,112 epoch 117 - iter 441/493 - loss 0.00659943 - time (sec): 30.60 - samples/sec: 7560.58 - lr: 0.001563
2023-03-29 17:51:33,536 epoch 117 - iter 490/493 - loss 0.00678322 - time (sec): 37.03 - samples/sec: 6956.63 - lr: 0.001563
2023-03-29 17:51:33,731 ----------------------------------------------------------------------------------------------------
2023-03-29 17:51:33,732 EPOCH 117 done: loss 0.0068 - lr 0.001563
2023-03-29 17:51:33,732 Epoch 117: reducing learning rate of group 0 to 7.8125e-04.
2023-03-29 17:51:33,732 BAD EPOCHS (no improvement): 4
2023-03-29 17:51:33,734 ----------------------------------------------------------------------------------------------------
2023-03-29 17:51:37,327 epoch 118 - iter 49/493 - loss 0.00658638 - time (sec): 3.59 - samples/sec: 7364.27 - lr: 0.000781
2023-03-29 17:51:40,893 epoch 118 - iter 98/493 - loss 0.00652703 - time (sec): 7.16 - samples/sec: 7281.79 - lr: 0.000781
2023-03-29 17:51:44,404 epoch 118 - iter 147/493 - loss 0.00668505 - time (sec): 10.67 - samples/sec: 7256.93 - lr: 0.000781
2023-03-29 17:51:47,830 epoch 118 - iter 196/493 - loss 0.00658835 - time (sec): 14.10 - samples/sec: 7319.76 - lr: 0.000781
2023-03-29 17:51:51,383 epoch 118 - iter 245/493 - loss 0.00644215 - time (sec): 17.65 - samples/sec: 7301.99 - lr: 0.000781
2023-03-29 17:51:54,956 epoch 118 - iter 294/493 - loss 0.00652385 - time (sec): 21.22 - samples/sec: 7321.91 - lr: 0.000781
2023-03-29 17:51:58,365 epoch 118 - iter 343/493 - loss 0.00654024 - time (sec): 24.63 - samples/sec: 7341.06 - lr: 0.000781
2023-03-29 17:52:01,784 epoch 118 - iter 392/493 - loss 0.00647899 - time (sec): 28.05 - samples/sec: 7356.38 - lr: 0.000781
2023-03-29 17:52:05,158 epoch 118 - iter 441/493 - loss 0.00650460 - time (sec): 31.42 - samples/sec: 7376.41 - lr: 0.000781
2023-03-29 17:52:08,687 epoch 118 - iter 490/493 - loss 0.00667973 - time (sec): 34.95 - samples/sec: 7369.45 - lr: 0.000781
2023-03-29 17:52:08,887 ----------------------------------------------------------------------------------------------------
2023-03-29 17:52:08,887 EPOCH 118 done: loss 0.0067 - lr 0.000781
2023-03-29 17:52:08,888 BAD EPOCHS (no improvement): 1
2023-03-29 17:52:08,890 ----------------------------------------------------------------------------------------------------
2023-03-29 17:52:12,419 epoch 119 - iter 49/493 - loss 0.00608181 - time (sec): 3.53 - samples/sec: 7257.05 - lr: 0.000781
2023-03-29 17:52:16,256 epoch 119 - iter 98/493 - loss 0.00601208 - time (sec): 7.37 - samples/sec: 7146.06 - lr: 0.000781
2023-03-29 17:52:19,748 epoch 119 - iter 147/493 - loss 0.00548327 - time (sec): 10.86 - samples/sec: 7198.80 - lr: 0.000781
2023-03-29 17:52:23,111 epoch 119 - iter 196/493 - loss 0.00564948 - time (sec): 14.22 - samples/sec: 7294.38 - lr: 0.000781
2023-03-29 17:52:26,511 epoch 119 - iter 245/493 - loss 0.00584250 - time (sec): 17.62 - samples/sec: 7330.89 - lr: 0.000781
2023-03-29 17:52:29,881 epoch 119 - iter 294/493 - loss 0.00591830 - time (sec): 20.99 - samples/sec: 7366.79 - lr: 0.000781
2023-03-29 17:52:33,421 epoch 119 - iter 343/493 - loss 0.00591154 - time (sec): 24.53 - samples/sec: 7364.12 - lr: 0.000781
2023-03-29 17:52:36,821 epoch 119 - iter 392/493 - loss 0.00590758 - time (sec): 27.93 - samples/sec: 7383.71 - lr: 0.000781
2023-03-29 17:52:40,260 epoch 119 - iter 441/493 - loss 0.00592919 - time (sec): 31.37 - samples/sec: 7396.53 - lr: 0.000781
2023-03-29 17:52:43,596 epoch 119 - iter 490/493 - loss 0.00607027 - time (sec): 34.71 - samples/sec: 7421.29 - lr: 0.000781
2023-03-29 17:52:43,796 ----------------------------------------------------------------------------------------------------
2023-03-29 17:52:43,796 EPOCH 119 done: loss 0.0061 - lr 0.000781
2023-03-29 17:52:43,796 BAD EPOCHS (no improvement): 2
2023-03-29 17:52:43,799 ----------------------------------------------------------------------------------------------------
2023-03-29 17:52:47,054 epoch 120 - iter 49/493 - loss 0.00638801 - time (sec): 3.26 - samples/sec: 7779.34 - lr: 0.000781
2023-03-29 17:52:50,431 epoch 120 - iter 98/493 - loss 0.00652179 - time (sec): 6.63 - samples/sec: 7675.93 - lr: 0.000781
2023-03-29 17:52:53,913 epoch 120 - iter 147/493 - loss 0.00667454 - time (sec): 10.11 - samples/sec: 7604.93 - lr: 0.000781
2023-03-29 17:52:57,357 epoch 120 - iter 196/493 - loss 0.00686319 - time (sec): 13.56 - samples/sec: 7552.15 - lr: 0.000781
2023-03-29 17:53:00,807 epoch 120 - iter 245/493 - loss 0.00669489 - time (sec): 17.01 - samples/sec: 7573.54 - lr: 0.000781
2023-03-29 17:53:04,276 epoch 120 - iter 294/493 - loss 0.00652595 - time (sec): 20.48 - samples/sec: 7595.73 - lr: 0.000781
2023-03-29 17:53:07,618 epoch 120 - iter 343/493 - loss 0.00638514 - time (sec): 23.82 - samples/sec: 7570.84 - lr: 0.000781
2023-03-29 17:53:10,932 epoch 120 - iter 392/493 - loss 0.00630731 - time (sec): 27.13 - samples/sec: 7610.17 - lr: 0.000781
2023-03-29 17:53:14,360 epoch 120 - iter 441/493 - loss 0.00614567 - time (sec): 30.56 - samples/sec: 7602.69 - lr: 0.000781
2023-03-29 17:53:17,709 epoch 120 - iter 490/493 - loss 0.00608156 - time (sec): 33.91 - samples/sec: 7596.26 - lr: 0.000781
2023-03-29 17:53:17,913 ----------------------------------------------------------------------------------------------------
2023-03-29 17:53:17,913 EPOCH 120 done: loss 0.0061 - lr 0.000781
2023-03-29 17:53:17,913 BAD EPOCHS (no improvement): 3
2023-03-29 17:53:17,916 ----------------------------------------------------------------------------------------------------
2023-03-29 17:53:21,507 epoch 121 - iter 49/493 - loss 0.00710549 - time (sec): 3.59 - samples/sec: 7375.04 - lr: 0.000781
2023-03-29 17:53:24,793 epoch 121 - iter 98/493 - loss 0.00692539 - time (sec): 6.88 - samples/sec: 7482.88 - lr: 0.000781
2023-03-29 17:53:28,111 epoch 121 - iter 147/493 - loss 0.00682256 - time (sec): 10.19 - samples/sec: 7556.39 - lr: 0.000781
2023-03-29 17:53:31,517 epoch 121 - iter 196/493 - loss 0.00661373 - time (sec): 13.60 - samples/sec: 7543.69 - lr: 0.000781
2023-03-29 17:53:34,915 epoch 121 - iter 245/493 - loss 0.00632979 - time (sec): 17.00 - samples/sec: 7559.63 - lr: 0.000781
2023-03-29 17:53:38,474 epoch 121 - iter 294/493 - loss 0.00626038 - time (sec): 20.56 - samples/sec: 7544.41 - lr: 0.000781
2023-03-29 17:53:41,893 epoch 121 - iter 343/493 - loss 0.00611005 - time (sec): 23.98 - samples/sec: 7534.68 - lr: 0.000781
2023-03-29 17:53:45,366 epoch 121 - iter 392/493 - loss 0.00608508 - time (sec): 27.45 - samples/sec: 7537.61 - lr: 0.000781
2023-03-29 17:53:48,668 epoch 121 - iter 441/493 - loss 0.00613797 - time (sec): 30.75 - samples/sec: 7558.66 - lr: 0.000781
2023-03-29 17:53:52,012 epoch 121 - iter 490/493 - loss 0.00612733 - time (sec): 34.10 - samples/sec: 7555.54 - lr: 0.000781
2023-03-29 17:53:52,223 ----------------------------------------------------------------------------------------------------
2023-03-29 17:53:52,223 EPOCH 121 done: loss 0.0061 - lr 0.000781
2023-03-29 17:53:52,223 Epoch 121: reducing learning rate of group 0 to 3.9063e-04.
2023-03-29 17:53:52,223 BAD EPOCHS (no improvement): 4
2023-03-29 17:53:52,226 ----------------------------------------------------------------------------------------------------
2023-03-29 17:53:55,489 epoch 122 - iter 49/493 - loss 0.00684342 - time (sec): 3.26 - samples/sec: 7798.87 - lr: 0.000391
2023-03-29 17:53:58,851 epoch 122 - iter 98/493 - loss 0.00644594 - time (sec): 6.62 - samples/sec: 7630.21 - lr: 0.000391
2023-03-29 17:54:02,201 epoch 122 - iter 147/493 - loss 0.00663640 - time (sec): 9.97 - samples/sec: 7642.93 - lr: 0.000391
2023-03-29 17:54:05,502 epoch 122 - iter 196/493 - loss 0.00632482 - time (sec): 13.28 - samples/sec: 7670.34 - lr: 0.000391
2023-03-29 17:54:08,944 epoch 122 - iter 245/493 - loss 0.00611891 - time (sec): 16.72 - samples/sec: 7655.80 - lr: 0.000391
2023-03-29 17:54:12,525 epoch 122 - iter 294/493 - loss 0.00601900 - time (sec): 20.30 - samples/sec: 7561.93 - lr: 0.000391
2023-03-29 17:54:15,910 epoch 122 - iter 343/493 - loss 0.00610750 - time (sec): 23.68 - samples/sec: 7581.99 - lr: 0.000391
2023-03-29 17:54:19,343 epoch 122 - iter 392/493 - loss 0.00604042 - time (sec): 27.12 - samples/sec: 7580.58 - lr: 0.000391
2023-03-29 17:54:22,802 epoch 122 - iter 441/493 - loss 0.00615812 - time (sec): 30.58 - samples/sec: 7596.56 - lr: 0.000391
2023-03-29 17:54:26,211 epoch 122 - iter 490/493 - loss 0.00622035 - time (sec): 33.99 - samples/sec: 7580.78 - lr: 0.000391
2023-03-29 17:54:26,412 ----------------------------------------------------------------------------------------------------
2023-03-29 17:54:26,412 EPOCH 122 done: loss 0.0062 - lr 0.000391
2023-03-29 17:54:26,413 BAD EPOCHS (no improvement): 1
2023-03-29 17:54:26,415 ----------------------------------------------------------------------------------------------------
2023-03-29 17:54:29,660 epoch 123 - iter 49/493 - loss 0.00617172 - time (sec): 3.25 - samples/sec: 7676.88 - lr: 0.000391
2023-03-29 17:54:33,060 epoch 123 - iter 98/493 - loss 0.00567255 - time (sec): 6.65 - samples/sec: 7670.11 - lr: 0.000391
2023-03-29 17:54:36,441 epoch 123 - iter 147/493 - loss 0.00669341 - time (sec): 10.03 - samples/sec: 7639.61 - lr: 0.000391
2023-03-29 17:54:39,889 epoch 123 - iter 196/493 - loss 0.00641510 - time (sec): 13.47 - samples/sec: 7646.20 - lr: 0.000391
2023-03-29 17:54:43,354 epoch 123 - iter 245/493 - loss 0.00608828 - time (sec): 16.94 - samples/sec: 7597.34 - lr: 0.000391
2023-03-29 17:54:46,604 epoch 123 - iter 294/493 - loss 0.00589168 - time (sec): 20.19 - samples/sec: 7612.71 - lr: 0.000391
2023-03-29 17:54:50,123 epoch 123 - iter 343/493 - loss 0.00597445 - time (sec): 23.71 - samples/sec: 7592.08 - lr: 0.000391
2023-03-29 17:54:53,561 epoch 123 - iter 392/493 - loss 0.00588624 - time (sec): 27.15 - samples/sec: 7588.63 - lr: 0.000391
2023-03-29 17:54:56,930 epoch 123 - iter 441/493 - loss 0.00583986 - time (sec): 30.52 - samples/sec: 7589.08 - lr: 0.000391
2023-03-29 17:55:00,352 epoch 123 - iter 490/493 - loss 0.00599199 - time (sec): 33.94 - samples/sec: 7589.98 - lr: 0.000391
2023-03-29 17:55:00,547 ----------------------------------------------------------------------------------------------------
2023-03-29 17:55:00,547 EPOCH 123 done: loss 0.0060 - lr 0.000391
2023-03-29 17:55:00,547 BAD EPOCHS (no improvement): 2
2023-03-29 17:55:00,553 ----------------------------------------------------------------------------------------------------
2023-03-29 17:55:04,116 epoch 124 - iter 49/493 - loss 0.00551931 - time (sec): 3.56 - samples/sec: 7324.41 - lr: 0.000391
2023-03-29 17:55:07,617 epoch 124 - iter 98/493 - loss 0.00591350 - time (sec): 7.06 - samples/sec: 7347.75 - lr: 0.000391
2023-03-29 17:55:10,979 epoch 124 - iter 147/493 - loss 0.00640294 - time (sec): 10.43 - samples/sec: 7441.71 - lr: 0.000391
2023-03-29 17:55:14,538 epoch 124 - iter 196/493 - loss 0.00633526 - time (sec): 13.98 - samples/sec: 7363.55 - lr: 0.000391
2023-03-29 17:55:17,923 epoch 124 - iter 245/493 - loss 0.00638028 - time (sec): 17.37 - samples/sec: 7414.25 - lr: 0.000391
2023-03-29 17:55:21,355 epoch 124 - iter 294/493 - loss 0.00638010 - time (sec): 20.80 - samples/sec: 7423.24 - lr: 0.000391
2023-03-29 17:55:24,843 epoch 124 - iter 343/493 - loss 0.00640306 - time (sec): 24.29 - samples/sec: 7398.28 - lr: 0.000391
2023-03-29 17:55:28,432 epoch 124 - iter 392/493 - loss 0.00635066 - time (sec): 27.88 - samples/sec: 7370.61 - lr: 0.000391
2023-03-29 17:55:31,896 epoch 124 - iter 441/493 - loss 0.00645959 - time (sec): 31.34 - samples/sec: 7379.77 - lr: 0.000391
2023-03-29 17:55:35,330 epoch 124 - iter 490/493 - loss 0.00650392 - time (sec): 34.78 - samples/sec: 7405.20 - lr: 0.000391
2023-03-29 17:55:35,527 ----------------------------------------------------------------------------------------------------
2023-03-29 17:55:35,528 EPOCH 124 done: loss 0.0065 - lr 0.000391
2023-03-29 17:55:35,528 BAD EPOCHS (no improvement): 3
2023-03-29 17:55:35,530 ----------------------------------------------------------------------------------------------------
2023-03-29 17:55:38,957 epoch 125 - iter 49/493 - loss 0.00658978 - time (sec): 3.43 - samples/sec: 7302.63 - lr: 0.000391
2023-03-29 17:55:42,569 epoch 125 - iter 98/493 - loss 0.00604369 - time (sec): 7.04 - samples/sec: 7352.72 - lr: 0.000391
2023-03-29 17:55:45,996 epoch 125 - iter 147/493 - loss 0.00564770 - time (sec): 10.47 - samples/sec: 7436.05 - lr: 0.000391
2023-03-29 17:55:49,590 epoch 125 - iter 196/493 - loss 0.00609854 - time (sec): 14.06 - samples/sec: 7366.06 - lr: 0.000391
2023-03-29 17:55:52,947 epoch 125 - iter 245/493 - loss 0.00647855 - time (sec): 17.42 - samples/sec: 7402.15 - lr: 0.000391
2023-03-29 17:55:56,587 epoch 125 - iter 294/493 - loss 0.00668196 - time (sec): 21.06 - samples/sec: 7371.10 - lr: 0.000391
2023-03-29 17:56:00,011 epoch 125 - iter 343/493 - loss 0.00675026 - time (sec): 24.48 - samples/sec: 7370.68 - lr: 0.000391
2023-03-29 17:56:03,432 epoch 125 - iter 392/493 - loss 0.00679369 - time (sec): 27.90 - samples/sec: 7386.65 - lr: 0.000391
2023-03-29 17:56:06,883 epoch 125 - iter 441/493 - loss 0.00666613 - time (sec): 31.35 - samples/sec: 7401.87 - lr: 0.000391
2023-03-29 17:56:10,189 epoch 125 - iter 490/493 - loss 0.00672782 - time (sec): 34.66 - samples/sec: 7433.46 - lr: 0.000391
2023-03-29 17:56:10,386 ----------------------------------------------------------------------------------------------------
2023-03-29 17:56:10,386 EPOCH 125 done: loss 0.0067 - lr 0.000391
2023-03-29 17:56:10,386 Epoch 125: reducing learning rate of group 0 to 1.9531e-04.
2023-03-29 17:56:10,386 BAD EPOCHS (no improvement): 4
2023-03-29 17:56:10,389 ----------------------------------------------------------------------------------------------------
2023-03-29 17:56:13,825 epoch 126 - iter 49/493 - loss 0.00677817 - time (sec): 3.44 - samples/sec: 7556.68 - lr: 0.000195
2023-03-29 17:56:17,210 epoch 126 - iter 98/493 - loss 0.00613157 - time (sec): 6.82 - samples/sec: 7564.58 - lr: 0.000195
2023-03-29 17:56:20,576 epoch 126 - iter 147/493 - loss 0.00616837 - time (sec): 10.19 - samples/sec: 7638.47 - lr: 0.000195
2023-03-29 17:56:23,824 epoch 126 - iter 196/493 - loss 0.00596208 - time (sec): 13.43 - samples/sec: 7676.03 - lr: 0.000195
2023-03-29 17:56:27,454 epoch 126 - iter 245/493 - loss 0.00597387 - time (sec): 17.06 - samples/sec: 7579.73 - lr: 0.000195
2023-03-29 17:56:30,986 epoch 126 - iter 294/493 - loss 0.00612076 - time (sec): 20.60 - samples/sec: 7529.77 - lr: 0.000195
2023-03-29 17:56:34,370 epoch 126 - iter 343/493 - loss 0.00623216 - time (sec): 23.98 - samples/sec: 7545.42 - lr: 0.000195
2023-03-29 17:56:37,690 epoch 126 - iter 392/493 - loss 0.00608157 - time (sec): 27.30 - samples/sec: 7558.87 - lr: 0.000195
2023-03-29 17:56:41,217 epoch 126 - iter 441/493 - loss 0.00609667 - time (sec): 30.83 - samples/sec: 7526.10 - lr: 0.000195
2023-03-29 17:56:44,820 epoch 126 - iter 490/493 - loss 0.00597955 - time (sec): 34.43 - samples/sec: 7480.24 - lr: 0.000195
2023-03-29 17:56:45,039 ----------------------------------------------------------------------------------------------------
2023-03-29 17:56:45,039 EPOCH 126 done: loss 0.0060 - lr 0.000195
2023-03-29 17:56:45,040 BAD EPOCHS (no improvement): 1
2023-03-29 17:56:45,042 ----------------------------------------------------------------------------------------------------
2023-03-29 17:56:48,635 epoch 127 - iter 49/493 - loss 0.00792995 - time (sec): 3.59 - samples/sec: 7159.51 - lr: 0.000195
2023-03-29 17:56:52,093 epoch 127 - iter 98/493 - loss 0.00637629 - time (sec): 7.05 - samples/sec: 7253.13 - lr: 0.000195
2023-03-29 17:56:55,589 epoch 127 - iter 147/493 - loss 0.00617894 - time (sec): 10.55 - samples/sec: 7273.58 - lr: 0.000195
2023-03-29 17:56:59,189 epoch 127 - iter 196/493 - loss 0.00608748 - time (sec): 14.15 - samples/sec: 7268.28 - lr: 0.000195
2023-03-29 17:57:02,785 epoch 127 - iter 245/493 - loss 0.00603498 - time (sec): 17.74 - samples/sec: 7266.59 - lr: 0.000195
2023-03-29 17:57:06,220 epoch 127 - iter 294/493 - loss 0.00615045 - time (sec): 21.18 - samples/sec: 7316.83 - lr: 0.000195
2023-03-29 17:57:09,644 epoch 127 - iter 343/493 - loss 0.00612571 - time (sec): 24.60 - samples/sec: 7342.44 - lr: 0.000195
2023-03-29 17:57:12,918 epoch 127 - iter 392/493 - loss 0.00613199 - time (sec): 27.88 - samples/sec: 7384.95 - lr: 0.000195
2023-03-29 17:57:16,356 epoch 127 - iter 441/493 - loss 0.00614883 - time (sec): 31.31 - samples/sec: 7396.48 - lr: 0.000195
2023-03-29 17:57:19,891 epoch 127 - iter 490/493 - loss 0.00591375 - time (sec): 34.85 - samples/sec: 7392.05 - lr: 0.000195
2023-03-29 17:57:20,083 ----------------------------------------------------------------------------------------------------
2023-03-29 17:57:20,083 EPOCH 127 done: loss 0.0059 - lr 0.000195
2023-03-29 17:57:20,083 BAD EPOCHS (no improvement): 2
2023-03-29 17:57:20,086 ----------------------------------------------------------------------------------------------------
2023-03-29 17:57:23,457 epoch 128 - iter 49/493 - loss 0.00656639 - time (sec): 3.37 - samples/sec: 7663.82 - lr: 0.000195
2023-03-29 17:57:26,901 epoch 128 - iter 98/493 - loss 0.00669642 - time (sec): 6.81 - samples/sec: 7573.89 - lr: 0.000195
2023-03-29 17:57:30,313 epoch 128 - iter 147/493 - loss 0.00723402 - time (sec): 10.23 - samples/sec: 7616.30 - lr: 0.000195
2023-03-29 17:57:33,609 epoch 128 - iter 196/493 - loss 0.00689746 - time (sec): 13.52 - samples/sec: 7581.50 - lr: 0.000195
2023-03-29 17:57:37,084 epoch 128 - iter 245/493 - loss 0.00678309 - time (sec): 17.00 - samples/sec: 7558.15 - lr: 0.000195
2023-03-29 17:57:40,479 epoch 128 - iter 294/493 - loss 0.00675309 - time (sec): 20.39 - samples/sec: 7566.31 - lr: 0.000195
2023-03-29 17:57:43,787 epoch 128 - iter 343/493 - loss 0.00681580 - time (sec): 23.70 - samples/sec: 7600.83 - lr: 0.000195
2023-03-29 17:57:47,283 epoch 128 - iter 392/493 - loss 0.00674115 - time (sec): 27.20 - samples/sec: 7580.60 - lr: 0.000195
2023-03-29 17:57:50,613 epoch 128 - iter 441/493 - loss 0.00665183 - time (sec): 30.53 - samples/sec: 7593.71 - lr: 0.000195
2023-03-29 17:57:54,084 epoch 128 - iter 490/493 - loss 0.00671389 - time (sec): 34.00 - samples/sec: 7577.51 - lr: 0.000195
2023-03-29 17:57:54,282 ----------------------------------------------------------------------------------------------------
2023-03-29 17:57:54,282 EPOCH 128 done: loss 0.0067 - lr 0.000195
2023-03-29 17:57:54,282 BAD EPOCHS (no improvement): 3
2023-03-29 17:57:54,285 ----------------------------------------------------------------------------------------------------
2023-03-29 17:57:57,711 epoch 129 - iter 49/493 - loss 0.00723180 - time (sec): 3.43 - samples/sec: 7595.09 - lr: 0.000195
2023-03-29 17:58:01,130 epoch 129 - iter 98/493 - loss 0.00660335 - time (sec): 6.84 - samples/sec: 7512.29 - lr: 0.000195
2023-03-29 17:58:04,637 epoch 129 - iter 147/493 - loss 0.00653070 - time (sec): 10.35 - samples/sec: 7491.41 - lr: 0.000195
2023-03-29 17:58:08,032 epoch 129 - iter 196/493 - loss 0.00667291 - time (sec): 13.75 - samples/sec: 7523.23 - lr: 0.000195
2023-03-29 17:58:11,433 epoch 129 - iter 245/493 - loss 0.00661422 - time (sec): 17.15 - samples/sec: 7523.71 - lr: 0.000195
2023-03-29 17:58:14,804 epoch 129 - iter 294/493 - loss 0.00623407 - time (sec): 20.52 - samples/sec: 7539.20 - lr: 0.000195
2023-03-29 17:58:18,120 epoch 129 - iter 343/493 - loss 0.00659638 - time (sec): 23.83 - samples/sec: 7559.03 - lr: 0.000195
2023-03-29 17:58:21,529 epoch 129 - iter 392/493 - loss 0.00666303 - time (sec): 27.24 - samples/sec: 7579.16 - lr: 0.000195
2023-03-29 17:58:25,095 epoch 129 - iter 441/493 - loss 0.00657534 - time (sec): 30.81 - samples/sec: 7542.97 - lr: 0.000195
2023-03-29 17:58:28,374 epoch 129 - iter 490/493 - loss 0.00663830 - time (sec): 34.09 - samples/sec: 7559.31 - lr: 0.000195
2023-03-29 17:58:28,582 ----------------------------------------------------------------------------------------------------
2023-03-29 17:58:28,582 EPOCH 129 done: loss 0.0066 - lr 0.000195
2023-03-29 17:58:28,582 Epoch 129: reducing learning rate of group 0 to 9.7656e-05.
2023-03-29 17:58:28,582 BAD EPOCHS (no improvement): 4
2023-03-29 17:58:28,585 ----------------------------------------------------------------------------------------------------
2023-03-29 17:58:28,585 ----------------------------------------------------------------------------------------------------
2023-03-29 17:58:28,585 learning rate too small - quitting training!
2023-03-29 17:58:28,585 ----------------------------------------------------------------------------------------------------
2023-03-29 17:58:35,394 ----------------------------------------------------------------------------------------------------
2023-03-29 17:58:35,394 Testing using last state of model ...
2023-03-29 17:58:49,720 Evaluating as a multi-label problem: False
2023-03-29 17:58:49,743 0.8966 0.8584 0.8771 0.8024
2023-03-29 17:58:49,743
Results:
- F-score (micro) 0.8771
- F-score (macro) 0.8091
- Accuracy 0.8024
By class:
precision recall f1-score support
PER 0.9367 0.9413 0.9390 1210
LOC 0.8997 0.8877 0.8937 1051
ORG 0.8226 0.7620 0.7911 584
MISC 0.8031 0.4951 0.6126 206
micro avg 0.8966 0.8584 0.8771 3051
macro avg 0.8655 0.7715 0.8091 3051
weighted avg 0.8931 0.8584 0.8730 3051
2023-03-29 17:58:49,743 ----------------------------------------------------------------------------------------------------