diff --git "a/training.log" "b/training.log" new file mode 100644--- /dev/null +++ "b/training.log" @@ -0,0 +1,2420 @@ +2022-11-01 12:49:03,490 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,490 Model: "SequenceTagger( + (embeddings): StackedEmbeddings( + (list_embedding_0): FlairEmbeddings( + (lm): LanguageModel( + (drop): Dropout(p=0.1, inplace=False) + (encoder): Embedding(962, 100) + (rnn): LSTM(100, 1024) + (decoder): Linear(in_features=1024, out_features=962, bias=True) + ) + ) + (list_embedding_1): FlairEmbeddings( + (lm): LanguageModel( + (drop): Dropout(p=0.1, inplace=False) + (encoder): Embedding(962, 100) + (rnn): LSTM(100, 1024) + (decoder): Linear(in_features=1024, out_features=962, bias=True) + ) + ) + ) + (dropout): Dropout(p=0.3380078963015963, inplace=False) + (word_dropout): WordDropout(p=0.05) + (locked_dropout): LockedDropout(p=0.5) + (embedding2nn): Linear(in_features=2048, out_features=2048, bias=True) + (rnn): LSTM(2048, 128, num_layers=2, batch_first=True, dropout=0.5, bidirectional=True) + (linear): Linear(in_features=256, out_features=19, bias=True) + (loss_function): ViterbiLoss() + (crf): CRF() +)" +2022-11-01 12:49:03,490 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,490 Corpus: "Corpus: 7886 train + 876 dev + 4045 test sentences" +2022-11-01 12:49:03,490 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,490 Parameters: +2022-11-01 12:49:03,490 - learning_rate: "0.100000" +2022-11-01 12:49:03,490 - mini_batch_size: "32" +2022-11-01 12:49:03,490 - patience: "3" +2022-11-01 12:49:03,490 - anneal_factor: "0.5" +2022-11-01 12:49:03,490 - max_epochs: "150" +2022-11-01 12:49:03,490 - shuffle: "True" +2022-11-01 12:49:03,490 - train_with_dev: "True" +2022-11-01 12:49:03,490 - batch_growth_annealing: "False" +2022-11-01 12:49:03,490 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,490 Model training base path: "ner-tests/uk.flairembeddings.champ" +2022-11-01 12:49:03,491 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,491 Device: cpu +2022-11-01 12:49:03,491 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:49:03,491 Embeddings storage mode: gpu +2022-11-01 12:49:03,491 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:50:09,565 epoch 1 - iter 27/274 - loss 0.61951446 - samples/sec: 13.08 - lr: 0.100000 +2022-11-01 12:51:14,717 epoch 1 - iter 54/274 - loss 0.51046988 - samples/sec: 13.26 - lr: 0.100000 +2022-11-01 12:52:22,958 epoch 1 - iter 81/274 - loss 0.40838070 - samples/sec: 12.66 - lr: 0.100000 +2022-11-01 12:53:46,868 epoch 1 - iter 108/274 - loss 0.36574824 - samples/sec: 10.30 - lr: 0.100000 +2022-11-01 12:54:38,313 epoch 1 - iter 135/274 - loss 0.32373590 - samples/sec: 16.80 - lr: 0.100000 +2022-11-01 12:55:23,882 epoch 1 - iter 162/274 - loss 0.28818606 - samples/sec: 18.96 - lr: 0.100000 +2022-11-01 12:56:20,788 epoch 1 - iter 189/274 - loss 0.25828452 - samples/sec: 15.18 - lr: 0.100000 +2022-11-01 12:56:58,874 epoch 1 - iter 216/274 - loss 0.23950005 - samples/sec: 22.69 - lr: 0.100000 +2022-11-01 12:57:50,282 epoch 1 - iter 243/274 - loss 0.22160623 - samples/sec: 16.81 - lr: 0.100000 +2022-11-01 12:58:46,515 epoch 1 - iter 270/274 - loss 0.21126815 - samples/sec: 15.37 - lr: 0.100000 +2022-11-01 12:58:55,152 ---------------------------------------------------------------------------------------------------- +2022-11-01 12:58:55,153 EPOCH 1 done: loss 0.2089 - lr 0.100000 +2022-11-01 13:03:03,629 Evaluating as a multi-label problem: False +2022-11-01 13:03:03,647 TEST : loss 0.13904191553592682 - f1-score (micro avg) 0.5512 +2022-11-01 13:03:03,698 BAD EPOCHS (no improvement): 0 +2022-11-01 13:03:03,756 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:03:15,574 epoch 2 - iter 27/274 - loss 0.10819005 - samples/sec: 73.14 - lr: 0.100000 +2022-11-01 13:03:27,236 epoch 2 - iter 54/274 - loss 0.10311525 - samples/sec: 74.11 - lr: 0.100000 +2022-11-01 13:03:39,859 epoch 2 - iter 81/274 - loss 0.10132389 - samples/sec: 68.46 - lr: 0.100000 +2022-11-01 13:03:50,897 epoch 2 - iter 108/274 - loss 0.10064433 - samples/sec: 78.30 - lr: 0.100000 +2022-11-01 13:04:02,826 epoch 2 - iter 135/274 - loss 0.10064467 - samples/sec: 72.45 - lr: 0.100000 +2022-11-01 13:04:16,449 epoch 2 - iter 162/274 - loss 0.10836500 - samples/sec: 63.44 - lr: 0.100000 +2022-11-01 13:04:28,828 epoch 2 - iter 189/274 - loss 0.10522271 - samples/sec: 69.81 - lr: 0.100000 +2022-11-01 13:04:42,197 epoch 2 - iter 216/274 - loss 0.10281006 - samples/sec: 64.64 - lr: 0.100000 +2022-11-01 13:04:54,240 epoch 2 - iter 243/274 - loss 0.10025360 - samples/sec: 71.77 - lr: 0.100000 +2022-11-01 13:05:07,501 epoch 2 - iter 270/274 - loss 0.09897187 - samples/sec: 65.17 - lr: 0.100000 +2022-11-01 13:05:10,043 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:05:10,043 EPOCH 2 done: loss 0.0992 - lr 0.100000 +2022-11-01 13:05:35,346 Evaluating as a multi-label problem: False +2022-11-01 13:05:35,362 TEST : loss 0.08393135666847229 - f1-score (micro avg) 0.739 +2022-11-01 13:05:35,413 BAD EPOCHS (no improvement): 0 +2022-11-01 13:05:35,503 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:05:48,724 epoch 3 - iter 27/274 - loss 0.08097851 - samples/sec: 65.37 - lr: 0.100000 +2022-11-01 13:06:01,967 epoch 3 - iter 54/274 - loss 0.07444780 - samples/sec: 65.26 - lr: 0.100000 +2022-11-01 13:06:14,499 epoch 3 - iter 81/274 - loss 0.07164834 - samples/sec: 68.96 - lr: 0.100000 +2022-11-01 13:06:26,228 epoch 3 - iter 108/274 - loss 0.07237300 - samples/sec: 73.68 - lr: 0.100000 +2022-11-01 13:06:37,579 epoch 3 - iter 135/274 - loss 0.07152923 - samples/sec: 76.14 - lr: 0.100000 +2022-11-01 13:06:50,615 epoch 3 - iter 162/274 - loss 0.07222106 - samples/sec: 66.30 - lr: 0.100000 +2022-11-01 13:07:03,210 epoch 3 - iter 189/274 - loss 0.07203354 - samples/sec: 68.62 - lr: 0.100000 +2022-11-01 13:07:16,259 epoch 3 - iter 216/274 - loss 0.07359814 - samples/sec: 66.23 - lr: 0.100000 +2022-11-01 13:07:27,473 epoch 3 - iter 243/274 - loss 0.07244371 - samples/sec: 77.07 - lr: 0.100000 +2022-11-01 13:07:39,487 epoch 3 - iter 270/274 - loss 0.07220347 - samples/sec: 71.94 - lr: 0.100000 +2022-11-01 13:07:41,274 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:07:41,274 EPOCH 3 done: loss 0.0718 - lr 0.100000 +2022-11-01 13:08:06,634 Evaluating as a multi-label problem: False +2022-11-01 13:08:06,649 TEST : loss 0.06586140394210815 - f1-score (micro avg) 0.7879 +2022-11-01 13:08:06,702 BAD EPOCHS (no improvement): 0 +2022-11-01 13:08:06,788 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:08:17,828 epoch 4 - iter 27/274 - loss 0.06119555 - samples/sec: 78.29 - lr: 0.100000 +2022-11-01 13:08:30,426 epoch 4 - iter 54/274 - loss 0.06264965 - samples/sec: 68.60 - lr: 0.100000 +2022-11-01 13:08:42,231 epoch 4 - iter 81/274 - loss 0.06322773 - samples/sec: 73.21 - lr: 0.100000 +2022-11-01 13:08:53,700 epoch 4 - iter 108/274 - loss 0.06038977 - samples/sec: 75.35 - lr: 0.100000 +2022-11-01 13:09:06,851 epoch 4 - iter 135/274 - loss 0.06248566 - samples/sec: 65.71 - lr: 0.100000 +2022-11-01 13:09:19,477 epoch 4 - iter 162/274 - loss 0.06279878 - samples/sec: 68.45 - lr: 0.100000 +2022-11-01 13:09:33,000 epoch 4 - iter 189/274 - loss 0.06245445 - samples/sec: 63.91 - lr: 0.100000 +2022-11-01 13:09:45,946 epoch 4 - iter 216/274 - loss 0.06230904 - samples/sec: 66.76 - lr: 0.100000 +2022-11-01 13:09:59,830 epoch 4 - iter 243/274 - loss 0.06128421 - samples/sec: 62.24 - lr: 0.100000 +2022-11-01 13:10:11,584 epoch 4 - iter 270/274 - loss 0.06083109 - samples/sec: 73.53 - lr: 0.100000 +2022-11-01 13:10:13,492 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:10:13,492 EPOCH 4 done: loss 0.0608 - lr 0.100000 +2022-11-01 13:10:38,798 Evaluating as a multi-label problem: False +2022-11-01 13:10:38,813 TEST : loss 0.061087507754564285 - f1-score (micro avg) 0.7982 +2022-11-01 13:10:38,866 BAD EPOCHS (no improvement): 0 +2022-11-01 13:10:38,953 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:10:50,869 epoch 5 - iter 27/274 - loss 0.05534610 - samples/sec: 72.53 - lr: 0.100000 +2022-11-01 13:11:02,268 epoch 5 - iter 54/274 - loss 0.05243949 - samples/sec: 75.82 - lr: 0.100000 +2022-11-01 13:11:16,824 epoch 5 - iter 81/274 - loss 0.05033856 - samples/sec: 59.37 - lr: 0.100000 +2022-11-01 13:11:29,824 epoch 5 - iter 108/274 - loss 0.05199909 - samples/sec: 66.48 - lr: 0.100000 +2022-11-01 13:11:42,909 epoch 5 - iter 135/274 - loss 0.05390198 - samples/sec: 66.05 - lr: 0.100000 +2022-11-01 13:11:54,210 epoch 5 - iter 162/274 - loss 0.05559011 - samples/sec: 76.47 - lr: 0.100000 +2022-11-01 13:12:07,160 epoch 5 - iter 189/274 - loss 0.05545001 - samples/sec: 66.74 - lr: 0.100000 +2022-11-01 13:12:18,635 epoch 5 - iter 216/274 - loss 0.05452558 - samples/sec: 75.32 - lr: 0.100000 +2022-11-01 13:12:30,242 epoch 5 - iter 243/274 - loss 0.05387747 - samples/sec: 74.46 - lr: 0.100000 +2022-11-01 13:12:43,258 epoch 5 - iter 270/274 - loss 0.05358782 - samples/sec: 66.40 - lr: 0.100000 +2022-11-01 13:12:44,917 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:12:44,917 EPOCH 5 done: loss 0.0535 - lr 0.100000 +2022-11-01 13:13:10,313 Evaluating as a multi-label problem: False +2022-11-01 13:13:10,329 TEST : loss 0.045144665986299515 - f1-score (micro avg) 0.8098 +2022-11-01 13:13:10,381 BAD EPOCHS (no improvement): 0 +2022-11-01 13:13:10,468 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:13:23,647 epoch 6 - iter 27/274 - loss 0.05037224 - samples/sec: 65.57 - lr: 0.100000 +2022-11-01 13:13:36,723 epoch 6 - iter 54/274 - loss 0.04536131 - samples/sec: 66.09 - lr: 0.100000 +2022-11-01 13:13:49,037 epoch 6 - iter 81/274 - loss 0.04718256 - samples/sec: 70.18 - lr: 0.100000 +2022-11-01 13:14:01,344 epoch 6 - iter 108/274 - loss 0.04840201 - samples/sec: 70.22 - lr: 0.100000 +2022-11-01 13:14:14,416 epoch 6 - iter 135/274 - loss 0.04792430 - samples/sec: 66.11 - lr: 0.100000 +2022-11-01 13:14:26,815 epoch 6 - iter 162/274 - loss 0.04791153 - samples/sec: 69.70 - lr: 0.100000 +2022-11-01 13:14:38,924 epoch 6 - iter 189/274 - loss 0.04811161 - samples/sec: 71.37 - lr: 0.100000 +2022-11-01 13:14:50,571 epoch 6 - iter 216/274 - loss 0.04808548 - samples/sec: 74.20 - lr: 0.100000 +2022-11-01 13:15:02,316 epoch 6 - iter 243/274 - loss 0.04851904 - samples/sec: 73.59 - lr: 0.100000 +2022-11-01 13:15:15,000 epoch 6 - iter 270/274 - loss 0.04914944 - samples/sec: 68.13 - lr: 0.100000 +2022-11-01 13:15:16,810 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:15:16,811 EPOCH 6 done: loss 0.0491 - lr 0.100000 +2022-11-01 13:15:42,123 Evaluating as a multi-label problem: False +2022-11-01 13:15:42,139 TEST : loss 0.03993703052401543 - f1-score (micro avg) 0.8164 +2022-11-01 13:15:42,191 BAD EPOCHS (no improvement): 0 +2022-11-01 13:15:42,277 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:15:54,919 epoch 7 - iter 27/274 - loss 0.04702372 - samples/sec: 68.36 - lr: 0.100000 +2022-11-01 13:16:08,351 epoch 7 - iter 54/274 - loss 0.04766522 - samples/sec: 64.34 - lr: 0.100000 +2022-11-01 13:16:20,530 epoch 7 - iter 81/274 - loss 0.04786969 - samples/sec: 70.96 - lr: 0.100000 +2022-11-01 13:16:33,124 epoch 7 - iter 108/274 - loss 0.04794053 - samples/sec: 68.62 - lr: 0.100000 +2022-11-01 13:16:44,786 epoch 7 - iter 135/274 - loss 0.04732043 - samples/sec: 74.11 - lr: 0.100000 +2022-11-01 13:16:56,876 epoch 7 - iter 162/274 - loss 0.04645068 - samples/sec: 71.48 - lr: 0.100000 +2022-11-01 13:17:07,762 epoch 7 - iter 189/274 - loss 0.04566414 - samples/sec: 79.39 - lr: 0.100000 +2022-11-01 13:17:20,361 epoch 7 - iter 216/274 - loss 0.04596395 - samples/sec: 68.59 - lr: 0.100000 +2022-11-01 13:17:34,748 epoch 7 - iter 243/274 - loss 0.04585695 - samples/sec: 60.07 - lr: 0.100000 +2022-11-01 13:17:46,833 epoch 7 - iter 270/274 - loss 0.04602936 - samples/sec: 71.51 - lr: 0.100000 +2022-11-01 13:17:48,543 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:17:48,543 EPOCH 7 done: loss 0.0459 - lr 0.100000 +2022-11-01 13:18:13,817 Evaluating as a multi-label problem: False +2022-11-01 13:18:13,832 TEST : loss 0.0414385087788105 - f1-score (micro avg) 0.8123 +2022-11-01 13:18:13,885 BAD EPOCHS (no improvement): 0 +2022-11-01 13:18:13,971 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:18:27,515 epoch 8 - iter 27/274 - loss 0.03864514 - samples/sec: 63.81 - lr: 0.100000 +2022-11-01 13:18:40,798 epoch 8 - iter 54/274 - loss 0.04677644 - samples/sec: 65.07 - lr: 0.100000 +2022-11-01 13:18:52,934 epoch 8 - iter 81/274 - loss 0.04564782 - samples/sec: 71.21 - lr: 0.100000 +2022-11-01 13:19:04,156 epoch 8 - iter 108/274 - loss 0.04660204 - samples/sec: 77.01 - lr: 0.100000 +2022-11-01 13:19:16,047 epoch 8 - iter 135/274 - loss 0.04492183 - samples/sec: 72.68 - lr: 0.100000 +2022-11-01 13:19:28,142 epoch 8 - iter 162/274 - loss 0.04498433 - samples/sec: 71.45 - lr: 0.100000 +2022-11-01 13:19:39,987 epoch 8 - iter 189/274 - loss 0.04445526 - samples/sec: 72.96 - lr: 0.100000 +2022-11-01 13:19:53,894 epoch 8 - iter 216/274 - loss 0.04466556 - samples/sec: 62.14 - lr: 0.100000 +2022-11-01 13:20:06,190 epoch 8 - iter 243/274 - loss 0.04424167 - samples/sec: 70.28 - lr: 0.100000 +2022-11-01 13:20:18,046 epoch 8 - iter 270/274 - loss 0.04411825 - samples/sec: 72.90 - lr: 0.100000 +2022-11-01 13:20:19,887 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:20:19,888 EPOCH 8 done: loss 0.0442 - lr 0.100000 +2022-11-01 13:20:45,195 Evaluating as a multi-label problem: False +2022-11-01 13:20:45,210 TEST : loss 0.0352301225066185 - f1-score (micro avg) 0.8301 +2022-11-01 13:20:45,262 BAD EPOCHS (no improvement): 0 +2022-11-01 13:20:45,347 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:20:57,331 epoch 9 - iter 27/274 - loss 0.03421196 - samples/sec: 72.12 - lr: 0.100000 +2022-11-01 13:21:11,143 epoch 9 - iter 54/274 - loss 0.03958776 - samples/sec: 62.57 - lr: 0.100000 +2022-11-01 13:21:22,700 epoch 9 - iter 81/274 - loss 0.03861008 - samples/sec: 74.78 - lr: 0.100000 +2022-11-01 13:21:34,844 epoch 9 - iter 108/274 - loss 0.03858464 - samples/sec: 71.16 - lr: 0.100000 +2022-11-01 13:21:46,395 epoch 9 - iter 135/274 - loss 0.03857484 - samples/sec: 74.82 - lr: 0.100000 +2022-11-01 13:21:58,479 epoch 9 - iter 162/274 - loss 0.03923221 - samples/sec: 71.51 - lr: 0.100000 +2022-11-01 13:22:12,010 epoch 9 - iter 189/274 - loss 0.04032935 - samples/sec: 63.87 - lr: 0.100000 +2022-11-01 13:22:24,283 epoch 9 - iter 216/274 - loss 0.03989000 - samples/sec: 70.42 - lr: 0.100000 +2022-11-01 13:22:37,207 epoch 9 - iter 243/274 - loss 0.04033892 - samples/sec: 66.87 - lr: 0.100000 +2022-11-01 13:22:49,535 epoch 9 - iter 270/274 - loss 0.04091413 - samples/sec: 70.11 - lr: 0.100000 +2022-11-01 13:22:51,188 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:22:51,189 EPOCH 9 done: loss 0.0409 - lr 0.100000 +2022-11-01 13:23:16,507 Evaluating as a multi-label problem: False +2022-11-01 13:23:16,522 TEST : loss 0.035973258316516876 - f1-score (micro avg) 0.8336 +2022-11-01 13:23:16,574 BAD EPOCHS (no improvement): 0 +2022-11-01 13:23:16,659 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:23:28,888 epoch 10 - iter 27/274 - loss 0.03551569 - samples/sec: 70.67 - lr: 0.100000 +2022-11-01 13:23:40,651 epoch 10 - iter 54/274 - loss 0.03803901 - samples/sec: 73.47 - lr: 0.100000 +2022-11-01 13:23:52,937 epoch 10 - iter 81/274 - loss 0.03866324 - samples/sec: 70.34 - lr: 0.100000 +2022-11-01 13:24:04,214 epoch 10 - iter 108/274 - loss 0.03929714 - samples/sec: 76.64 - lr: 0.100000 +2022-11-01 13:24:18,658 epoch 10 - iter 135/274 - loss 0.03798954 - samples/sec: 59.83 - lr: 0.100000 +2022-11-01 13:24:31,144 epoch 10 - iter 162/274 - loss 0.03737353 - samples/sec: 69.21 - lr: 0.100000 +2022-11-01 13:24:43,524 epoch 10 - iter 189/274 - loss 0.03819265 - samples/sec: 69.81 - lr: 0.100000 +2022-11-01 13:24:55,975 epoch 10 - iter 216/274 - loss 0.03809318 - samples/sec: 69.41 - lr: 0.100000 +2022-11-01 13:25:09,174 epoch 10 - iter 243/274 - loss 0.03795923 - samples/sec: 65.48 - lr: 0.100000 +2022-11-01 13:25:21,702 epoch 10 - iter 270/274 - loss 0.03858601 - samples/sec: 68.98 - lr: 0.100000 +2022-11-01 13:25:23,304 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:25:23,304 EPOCH 10 done: loss 0.0388 - lr 0.100000 +2022-11-01 13:25:48,617 Evaluating as a multi-label problem: False +2022-11-01 13:25:48,633 TEST : loss 0.03315580636262894 - f1-score (micro avg) 0.8307 +2022-11-01 13:25:48,683 BAD EPOCHS (no improvement): 0 +2022-11-01 13:25:48,769 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:26:01,137 epoch 11 - iter 27/274 - loss 0.03336240 - samples/sec: 69.88 - lr: 0.100000 +2022-11-01 13:26:14,421 epoch 11 - iter 54/274 - loss 0.03527565 - samples/sec: 65.06 - lr: 0.100000 +2022-11-01 13:26:26,672 epoch 11 - iter 81/274 - loss 0.03575293 - samples/sec: 70.54 - lr: 0.100000 +2022-11-01 13:26:39,936 epoch 11 - iter 108/274 - loss 0.03822032 - samples/sec: 65.15 - lr: 0.100000 +2022-11-01 13:26:51,243 epoch 11 - iter 135/274 - loss 0.03800128 - samples/sec: 76.44 - lr: 0.100000 +2022-11-01 13:27:03,276 epoch 11 - iter 162/274 - loss 0.03759663 - samples/sec: 71.82 - lr: 0.100000 +2022-11-01 13:27:15,749 epoch 11 - iter 189/274 - loss 0.03792055 - samples/sec: 69.28 - lr: 0.100000 +2022-11-01 13:27:28,611 epoch 11 - iter 216/274 - loss 0.03760377 - samples/sec: 67.19 - lr: 0.100000 +2022-11-01 13:27:40,313 epoch 11 - iter 243/274 - loss 0.03749324 - samples/sec: 73.85 - lr: 0.100000 +2022-11-01 13:27:53,182 epoch 11 - iter 270/274 - loss 0.03774304 - samples/sec: 67.15 - lr: 0.100000 +2022-11-01 13:27:54,562 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:27:54,562 EPOCH 11 done: loss 0.0377 - lr 0.100000 +2022-11-01 13:28:19,892 Evaluating as a multi-label problem: False +2022-11-01 13:28:19,908 TEST : loss 0.03283185511827469 - f1-score (micro avg) 0.8212 +2022-11-01 13:28:19,960 BAD EPOCHS (no improvement): 0 +2022-11-01 13:28:20,046 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:28:32,783 epoch 12 - iter 27/274 - loss 0.03750028 - samples/sec: 67.85 - lr: 0.100000 +2022-11-01 13:28:45,843 epoch 12 - iter 54/274 - loss 0.03532475 - samples/sec: 66.17 - lr: 0.100000 +2022-11-01 13:28:57,814 epoch 12 - iter 81/274 - loss 0.03713735 - samples/sec: 72.20 - lr: 0.100000 +2022-11-01 13:29:09,768 epoch 12 - iter 108/274 - loss 0.03681510 - samples/sec: 72.30 - lr: 0.100000 +2022-11-01 13:29:24,299 epoch 12 - iter 135/274 - loss 0.03831782 - samples/sec: 59.47 - lr: 0.100000 +2022-11-01 13:29:35,963 epoch 12 - iter 162/274 - loss 0.03671352 - samples/sec: 74.10 - lr: 0.100000 +2022-11-01 13:29:47,879 epoch 12 - iter 189/274 - loss 0.03644150 - samples/sec: 72.52 - lr: 0.100000 +2022-11-01 13:30:01,084 epoch 12 - iter 216/274 - loss 0.03741624 - samples/sec: 65.45 - lr: 0.100000 +2022-11-01 13:30:12,910 epoch 12 - iter 243/274 - loss 0.03760841 - samples/sec: 73.08 - lr: 0.100000 +2022-11-01 13:30:24,282 epoch 12 - iter 270/274 - loss 0.03743746 - samples/sec: 76.00 - lr: 0.100000 +2022-11-01 13:30:26,622 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:30:26,622 EPOCH 12 done: loss 0.0372 - lr 0.100000 +2022-11-01 13:30:51,847 Evaluating as a multi-label problem: False +2022-11-01 13:30:51,862 TEST : loss 0.037361979484558105 - f1-score (micro avg) 0.8248 +2022-11-01 13:30:51,915 BAD EPOCHS (no improvement): 0 +2022-11-01 13:30:52,001 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:31:04,558 epoch 13 - iter 27/274 - loss 0.03512437 - samples/sec: 68.82 - lr: 0.100000 +2022-11-01 13:31:15,671 epoch 13 - iter 54/274 - loss 0.03410457 - samples/sec: 77.77 - lr: 0.100000 +2022-11-01 13:31:28,928 epoch 13 - iter 81/274 - loss 0.03664686 - samples/sec: 65.19 - lr: 0.100000 +2022-11-01 13:31:41,194 epoch 13 - iter 108/274 - loss 0.03708780 - samples/sec: 70.46 - lr: 0.100000 +2022-11-01 13:31:53,508 epoch 13 - iter 135/274 - loss 0.03597557 - samples/sec: 70.18 - lr: 0.100000 +2022-11-01 13:32:05,194 epoch 13 - iter 162/274 - loss 0.03576194 - samples/sec: 73.95 - lr: 0.100000 +2022-11-01 13:32:18,580 epoch 13 - iter 189/274 - loss 0.03517390 - samples/sec: 64.56 - lr: 0.100000 +2022-11-01 13:32:31,865 epoch 13 - iter 216/274 - loss 0.03618700 - samples/sec: 65.05 - lr: 0.100000 +2022-11-01 13:32:43,293 epoch 13 - iter 243/274 - loss 0.03653199 - samples/sec: 75.62 - lr: 0.100000 +2022-11-01 13:32:55,873 epoch 13 - iter 270/274 - loss 0.03649977 - samples/sec: 68.70 - lr: 0.100000 +2022-11-01 13:32:57,821 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:32:57,821 EPOCH 13 done: loss 0.0366 - lr 0.100000 +2022-11-01 13:33:23,196 Evaluating as a multi-label problem: False +2022-11-01 13:33:23,211 TEST : loss 0.03093760274350643 - f1-score (micro avg) 0.8276 +2022-11-01 13:33:23,262 BAD EPOCHS (no improvement): 0 +2022-11-01 13:33:23,348 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:33:35,596 epoch 14 - iter 27/274 - loss 0.03587195 - samples/sec: 70.57 - lr: 0.100000 +2022-11-01 13:33:47,961 epoch 14 - iter 54/274 - loss 0.03435583 - samples/sec: 69.89 - lr: 0.100000 +2022-11-01 13:33:59,808 epoch 14 - iter 81/274 - loss 0.03350450 - samples/sec: 72.95 - lr: 0.100000 +2022-11-01 13:34:11,390 epoch 14 - iter 108/274 - loss 0.03432252 - samples/sec: 74.62 - lr: 0.100000 +2022-11-01 13:34:24,737 epoch 14 - iter 135/274 - loss 0.03559134 - samples/sec: 64.75 - lr: 0.100000 +2022-11-01 13:34:37,434 epoch 14 - iter 162/274 - loss 0.03552331 - samples/sec: 68.06 - lr: 0.100000 +2022-11-01 13:34:49,584 epoch 14 - iter 189/274 - loss 0.03506626 - samples/sec: 71.13 - lr: 0.100000 +2022-11-01 13:35:03,212 epoch 14 - iter 216/274 - loss 0.03444676 - samples/sec: 63.41 - lr: 0.100000 +2022-11-01 13:35:15,032 epoch 14 - iter 243/274 - loss 0.03434282 - samples/sec: 73.12 - lr: 0.100000 +2022-11-01 13:35:27,648 epoch 14 - iter 270/274 - loss 0.03420688 - samples/sec: 68.50 - lr: 0.100000 +2022-11-01 13:35:29,536 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:35:29,536 EPOCH 14 done: loss 0.0341 - lr 0.100000 +2022-11-01 13:35:54,970 Evaluating as a multi-label problem: False +2022-11-01 13:35:54,985 TEST : loss 0.032740455120801926 - f1-score (micro avg) 0.8382 +2022-11-01 13:35:55,038 BAD EPOCHS (no improvement): 0 +2022-11-01 13:35:55,124 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:36:06,207 epoch 15 - iter 27/274 - loss 0.02621004 - samples/sec: 77.98 - lr: 0.100000 +2022-11-01 13:36:18,117 epoch 15 - iter 54/274 - loss 0.03148500 - samples/sec: 72.56 - lr: 0.100000 +2022-11-01 13:36:32,408 epoch 15 - iter 81/274 - loss 0.03283017 - samples/sec: 60.47 - lr: 0.100000 +2022-11-01 13:36:44,413 epoch 15 - iter 108/274 - loss 0.03269024 - samples/sec: 72.00 - lr: 0.100000 +2022-11-01 13:36:57,549 epoch 15 - iter 135/274 - loss 0.03234032 - samples/sec: 65.79 - lr: 0.100000 +2022-11-01 13:37:09,569 epoch 15 - iter 162/274 - loss 0.03236532 - samples/sec: 71.90 - lr: 0.100000 +2022-11-01 13:37:21,479 epoch 15 - iter 189/274 - loss 0.03211454 - samples/sec: 72.56 - lr: 0.100000 +2022-11-01 13:37:33,192 epoch 15 - iter 216/274 - loss 0.03241047 - samples/sec: 73.78 - lr: 0.100000 +2022-11-01 13:37:46,183 epoch 15 - iter 243/274 - loss 0.03314606 - samples/sec: 66.53 - lr: 0.100000 +2022-11-01 13:37:58,664 epoch 15 - iter 270/274 - loss 0.03257262 - samples/sec: 69.24 - lr: 0.100000 +2022-11-01 13:38:00,237 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:38:00,237 EPOCH 15 done: loss 0.0325 - lr 0.100000 +2022-11-01 13:38:25,551 Evaluating as a multi-label problem: False +2022-11-01 13:38:25,566 TEST : loss 0.03659946471452713 - f1-score (micro avg) 0.8396 +2022-11-01 13:38:25,619 BAD EPOCHS (no improvement): 0 +2022-11-01 13:38:25,708 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:38:38,868 epoch 16 - iter 27/274 - loss 0.04310501 - samples/sec: 65.67 - lr: 0.100000 +2022-11-01 13:38:51,141 epoch 16 - iter 54/274 - loss 0.03821968 - samples/sec: 70.42 - lr: 0.100000 +2022-11-01 13:39:03,213 epoch 16 - iter 81/274 - loss 0.03601832 - samples/sec: 71.59 - lr: 0.100000 +2022-11-01 13:39:15,515 epoch 16 - iter 108/274 - loss 0.03464665 - samples/sec: 70.25 - lr: 0.100000 +2022-11-01 13:39:28,495 epoch 16 - iter 135/274 - loss 0.03385713 - samples/sec: 66.58 - lr: 0.100000 +2022-11-01 13:39:42,428 epoch 16 - iter 162/274 - loss 0.03355248 - samples/sec: 62.02 - lr: 0.100000 +2022-11-01 13:39:55,016 epoch 16 - iter 189/274 - loss 0.03305979 - samples/sec: 68.66 - lr: 0.100000 +2022-11-01 13:40:06,660 epoch 16 - iter 216/274 - loss 0.03245928 - samples/sec: 74.22 - lr: 0.100000 +2022-11-01 13:40:18,569 epoch 16 - iter 243/274 - loss 0.03229054 - samples/sec: 72.57 - lr: 0.100000 +2022-11-01 13:40:29,519 epoch 16 - iter 270/274 - loss 0.03266463 - samples/sec: 78.93 - lr: 0.100000 +2022-11-01 13:40:31,278 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:40:31,279 EPOCH 16 done: loss 0.0324 - lr 0.100000 +2022-11-01 13:40:56,563 Evaluating as a multi-label problem: False +2022-11-01 13:40:56,579 TEST : loss 0.03419892117381096 - f1-score (micro avg) 0.8414 +2022-11-01 13:40:56,630 BAD EPOCHS (no improvement): 0 +2022-11-01 13:40:56,716 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:41:08,628 epoch 17 - iter 27/274 - loss 0.03131168 - samples/sec: 72.55 - lr: 0.100000 +2022-11-01 13:41:20,642 epoch 17 - iter 54/274 - loss 0.03329973 - samples/sec: 71.94 - lr: 0.100000 +2022-11-01 13:41:33,558 epoch 17 - iter 81/274 - loss 0.03205309 - samples/sec: 66.91 - lr: 0.100000 +2022-11-01 13:41:46,746 epoch 17 - iter 108/274 - loss 0.03106228 - samples/sec: 65.53 - lr: 0.100000 +2022-11-01 13:41:59,456 epoch 17 - iter 135/274 - loss 0.03205977 - samples/sec: 68.00 - lr: 0.100000 +2022-11-01 13:42:10,814 epoch 17 - iter 162/274 - loss 0.03230744 - samples/sec: 76.09 - lr: 0.100000 +2022-11-01 13:42:22,736 epoch 17 - iter 189/274 - loss 0.03217993 - samples/sec: 72.49 - lr: 0.100000 +2022-11-01 13:42:35,185 epoch 17 - iter 216/274 - loss 0.03154261 - samples/sec: 69.42 - lr: 0.100000 +2022-11-01 13:42:48,451 epoch 17 - iter 243/274 - loss 0.03218871 - samples/sec: 65.14 - lr: 0.100000 +2022-11-01 13:43:00,903 epoch 17 - iter 270/274 - loss 0.03216961 - samples/sec: 69.40 - lr: 0.100000 +2022-11-01 13:43:02,520 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:43:02,520 EPOCH 17 done: loss 0.0324 - lr 0.100000 +2022-11-01 13:43:27,903 Evaluating as a multi-label problem: False +2022-11-01 13:43:27,919 TEST : loss 0.032121315598487854 - f1-score (micro avg) 0.8142 +2022-11-01 13:43:27,973 BAD EPOCHS (no improvement): 0 +2022-11-01 13:43:28,061 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:43:39,245 epoch 18 - iter 27/274 - loss 0.02828295 - samples/sec: 77.28 - lr: 0.100000 +2022-11-01 13:43:51,970 epoch 18 - iter 54/274 - loss 0.02821400 - samples/sec: 67.91 - lr: 0.100000 +2022-11-01 13:44:04,671 epoch 18 - iter 81/274 - loss 0.02895659 - samples/sec: 68.04 - lr: 0.100000 +2022-11-01 13:44:17,750 epoch 18 - iter 108/274 - loss 0.02937219 - samples/sec: 66.08 - lr: 0.100000 +2022-11-01 13:44:29,293 epoch 18 - iter 135/274 - loss 0.02969136 - samples/sec: 74.87 - lr: 0.100000 +2022-11-01 13:44:41,423 epoch 18 - iter 162/274 - loss 0.03044366 - samples/sec: 71.25 - lr: 0.100000 +2022-11-01 13:44:53,180 epoch 18 - iter 189/274 - loss 0.03033224 - samples/sec: 73.51 - lr: 0.100000 +2022-11-01 13:45:05,434 epoch 18 - iter 216/274 - loss 0.03010129 - samples/sec: 70.52 - lr: 0.100000 +2022-11-01 13:45:17,103 epoch 18 - iter 243/274 - loss 0.03031468 - samples/sec: 74.07 - lr: 0.100000 +2022-11-01 13:45:31,926 epoch 18 - iter 270/274 - loss 0.03086624 - samples/sec: 58.30 - lr: 0.100000 +2022-11-01 13:45:33,720 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:45:33,720 EPOCH 18 done: loss 0.0309 - lr 0.100000 +2022-11-01 13:45:59,011 Evaluating as a multi-label problem: False +2022-11-01 13:45:59,027 TEST : loss 0.03097383677959442 - f1-score (micro avg) 0.8361 +2022-11-01 13:45:59,081 BAD EPOCHS (no improvement): 0 +2022-11-01 13:45:59,150 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:46:12,115 epoch 19 - iter 27/274 - loss 0.03291951 - samples/sec: 66.66 - lr: 0.100000 +2022-11-01 13:46:24,726 epoch 19 - iter 54/274 - loss 0.03100127 - samples/sec: 68.53 - lr: 0.100000 +2022-11-01 13:46:36,908 epoch 19 - iter 81/274 - loss 0.03008968 - samples/sec: 70.95 - lr: 0.100000 +2022-11-01 13:46:49,567 epoch 19 - iter 108/274 - loss 0.02850661 - samples/sec: 68.36 - lr: 0.100000 +2022-11-01 13:47:03,710 epoch 19 - iter 135/274 - loss 0.02973182 - samples/sec: 61.10 - lr: 0.100000 +2022-11-01 13:47:15,650 epoch 19 - iter 162/274 - loss 0.03029075 - samples/sec: 72.38 - lr: 0.100000 +2022-11-01 13:47:27,204 epoch 19 - iter 189/274 - loss 0.03061716 - samples/sec: 74.80 - lr: 0.100000 +2022-11-01 13:47:39,709 epoch 19 - iter 216/274 - loss 0.03024609 - samples/sec: 69.11 - lr: 0.100000 +2022-11-01 13:47:52,438 epoch 19 - iter 243/274 - loss 0.03075993 - samples/sec: 67.89 - lr: 0.100000 +2022-11-01 13:48:04,395 epoch 19 - iter 270/274 - loss 0.03035569 - samples/sec: 72.28 - lr: 0.100000 +2022-11-01 13:48:06,254 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:48:06,254 EPOCH 19 done: loss 0.0304 - lr 0.100000 +2022-11-01 13:48:31,545 Evaluating as a multi-label problem: False +2022-11-01 13:48:31,560 TEST : loss 0.031058575958013535 - f1-score (micro avg) 0.8361 +2022-11-01 13:48:31,612 BAD EPOCHS (no improvement): 0 +2022-11-01 13:48:31,701 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:48:43,605 epoch 20 - iter 27/274 - loss 0.03341089 - samples/sec: 72.61 - lr: 0.100000 +2022-11-01 13:48:56,331 epoch 20 - iter 54/274 - loss 0.02965002 - samples/sec: 67.91 - lr: 0.100000 +2022-11-01 13:49:08,466 epoch 20 - iter 81/274 - loss 0.02936467 - samples/sec: 71.22 - lr: 0.100000 +2022-11-01 13:49:20,359 epoch 20 - iter 108/274 - loss 0.02967577 - samples/sec: 72.67 - lr: 0.100000 +2022-11-01 13:49:31,703 epoch 20 - iter 135/274 - loss 0.02962385 - samples/sec: 76.18 - lr: 0.100000 +2022-11-01 13:49:45,689 epoch 20 - iter 162/274 - loss 0.03002445 - samples/sec: 61.79 - lr: 0.100000 +2022-11-01 13:49:59,016 epoch 20 - iter 189/274 - loss 0.02979085 - samples/sec: 64.85 - lr: 0.100000 +2022-11-01 13:50:11,482 epoch 20 - iter 216/274 - loss 0.03016882 - samples/sec: 69.33 - lr: 0.100000 +2022-11-01 13:50:23,142 epoch 20 - iter 243/274 - loss 0.03053355 - samples/sec: 74.12 - lr: 0.100000 +2022-11-01 13:50:35,085 epoch 20 - iter 270/274 - loss 0.03054658 - samples/sec: 72.37 - lr: 0.100000 +2022-11-01 13:50:36,716 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:50:36,716 EPOCH 20 done: loss 0.0304 - lr 0.100000 +2022-11-01 13:51:01,815 Evaluating as a multi-label problem: False +2022-11-01 13:51:01,830 TEST : loss 0.035328544676303864 - f1-score (micro avg) 0.8392 +2022-11-01 13:51:01,882 BAD EPOCHS (no improvement): 1 +2022-11-01 13:51:01,968 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:51:16,421 epoch 21 - iter 27/274 - loss 0.03241261 - samples/sec: 59.79 - lr: 0.100000 +2022-11-01 13:51:28,464 epoch 21 - iter 54/274 - loss 0.03286965 - samples/sec: 71.76 - lr: 0.100000 +2022-11-01 13:51:40,060 epoch 21 - iter 81/274 - loss 0.03240940 - samples/sec: 74.53 - lr: 0.100000 +2022-11-01 13:51:52,405 epoch 21 - iter 108/274 - loss 0.03079412 - samples/sec: 70.01 - lr: 0.100000 +2022-11-01 13:52:04,384 epoch 21 - iter 135/274 - loss 0.02985053 - samples/sec: 72.15 - lr: 0.100000 +2022-11-01 13:52:16,601 epoch 21 - iter 162/274 - loss 0.02987171 - samples/sec: 70.74 - lr: 0.100000 +2022-11-01 13:52:28,629 epoch 21 - iter 189/274 - loss 0.03085183 - samples/sec: 71.85 - lr: 0.100000 +2022-11-01 13:52:40,275 epoch 21 - iter 216/274 - loss 0.03117974 - samples/sec: 74.21 - lr: 0.100000 +2022-11-01 13:52:53,944 epoch 21 - iter 243/274 - loss 0.03112541 - samples/sec: 63.22 - lr: 0.100000 +2022-11-01 13:53:05,688 epoch 21 - iter 270/274 - loss 0.03062103 - samples/sec: 73.59 - lr: 0.100000 +2022-11-01 13:53:07,553 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:53:07,554 EPOCH 21 done: loss 0.0308 - lr 0.100000 +2022-11-01 13:53:32,862 Evaluating as a multi-label problem: False +2022-11-01 13:53:32,877 TEST : loss 0.029285110533237457 - f1-score (micro avg) 0.8396 +2022-11-01 13:53:32,929 BAD EPOCHS (no improvement): 2 +2022-11-01 13:53:33,017 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:53:44,810 epoch 22 - iter 27/274 - loss 0.02903520 - samples/sec: 73.29 - lr: 0.100000 +2022-11-01 13:53:57,359 epoch 22 - iter 54/274 - loss 0.02877626 - samples/sec: 68.87 - lr: 0.100000 +2022-11-01 13:54:09,305 epoch 22 - iter 81/274 - loss 0.02903053 - samples/sec: 72.34 - lr: 0.100000 +2022-11-01 13:54:22,177 epoch 22 - iter 108/274 - loss 0.02918162 - samples/sec: 67.14 - lr: 0.100000 +2022-11-01 13:54:34,724 epoch 22 - iter 135/274 - loss 0.03022362 - samples/sec: 68.88 - lr: 0.100000 +2022-11-01 13:54:47,100 epoch 22 - iter 162/274 - loss 0.02921564 - samples/sec: 69.83 - lr: 0.100000 +2022-11-01 13:54:58,855 epoch 22 - iter 189/274 - loss 0.02907579 - samples/sec: 73.52 - lr: 0.100000 +2022-11-01 13:55:11,841 epoch 22 - iter 216/274 - loss 0.02880394 - samples/sec: 66.55 - lr: 0.100000 +2022-11-01 13:55:24,785 epoch 22 - iter 243/274 - loss 0.02882432 - samples/sec: 66.76 - lr: 0.100000 +2022-11-01 13:55:35,994 epoch 22 - iter 270/274 - loss 0.02922647 - samples/sec: 77.11 - lr: 0.100000 +2022-11-01 13:55:37,631 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:55:37,631 EPOCH 22 done: loss 0.0293 - lr 0.100000 +2022-11-01 13:56:02,870 Evaluating as a multi-label problem: False +2022-11-01 13:56:02,885 TEST : loss 0.031731970608234406 - f1-score (micro avg) 0.8458 +2022-11-01 13:56:02,937 BAD EPOCHS (no improvement): 0 +2022-11-01 13:56:03,023 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:56:15,323 epoch 23 - iter 27/274 - loss 0.02954803 - samples/sec: 70.27 - lr: 0.100000 +2022-11-01 13:56:27,494 epoch 23 - iter 54/274 - loss 0.02818459 - samples/sec: 71.01 - lr: 0.100000 +2022-11-01 13:56:38,573 epoch 23 - iter 81/274 - loss 0.02966005 - samples/sec: 78.01 - lr: 0.100000 +2022-11-01 13:56:52,151 epoch 23 - iter 108/274 - loss 0.02929197 - samples/sec: 63.65 - lr: 0.100000 +2022-11-01 13:57:03,768 epoch 23 - iter 135/274 - loss 0.02938255 - samples/sec: 74.40 - lr: 0.100000 +2022-11-01 13:57:16,576 epoch 23 - iter 162/274 - loss 0.02905523 - samples/sec: 67.48 - lr: 0.100000 +2022-11-01 13:57:28,040 epoch 23 - iter 189/274 - loss 0.02845779 - samples/sec: 75.38 - lr: 0.100000 +2022-11-01 13:57:41,003 epoch 23 - iter 216/274 - loss 0.02851665 - samples/sec: 66.67 - lr: 0.100000 +2022-11-01 13:57:52,675 epoch 23 - iter 243/274 - loss 0.02836095 - samples/sec: 74.04 - lr: 0.100000 +2022-11-01 13:58:05,834 epoch 23 - iter 270/274 - loss 0.02879719 - samples/sec: 65.68 - lr: 0.100000 +2022-11-01 13:58:07,795 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:58:07,795 EPOCH 23 done: loss 0.0292 - lr 0.100000 +2022-11-01 13:58:33,309 Evaluating as a multi-label problem: False +2022-11-01 13:58:33,324 TEST : loss 0.029490221291780472 - f1-score (micro avg) 0.8464 +2022-11-01 13:58:33,376 BAD EPOCHS (no improvement): 0 +2022-11-01 13:58:33,466 ---------------------------------------------------------------------------------------------------- +2022-11-01 13:58:47,010 epoch 24 - iter 27/274 - loss 0.03114330 - samples/sec: 63.81 - lr: 0.100000 +2022-11-01 13:58:57,750 epoch 24 - iter 54/274 - loss 0.02934230 - samples/sec: 80.47 - lr: 0.100000 +2022-11-01 13:59:10,428 epoch 24 - iter 81/274 - loss 0.02821868 - samples/sec: 68.17 - lr: 0.100000 +2022-11-01 13:59:22,831 epoch 24 - iter 108/274 - loss 0.02736854 - samples/sec: 69.68 - lr: 0.100000 +2022-11-01 13:59:34,154 epoch 24 - iter 135/274 - loss 0.02744987 - samples/sec: 76.33 - lr: 0.100000 +2022-11-01 13:59:47,845 epoch 24 - iter 162/274 - loss 0.02721262 - samples/sec: 63.12 - lr: 0.100000 +2022-11-01 14:00:00,436 epoch 24 - iter 189/274 - loss 0.02819192 - samples/sec: 68.64 - lr: 0.100000 +2022-11-01 14:00:12,356 epoch 24 - iter 216/274 - loss 0.02808668 - samples/sec: 72.50 - lr: 0.100000 +2022-11-01 14:00:24,554 epoch 24 - iter 243/274 - loss 0.02787150 - samples/sec: 70.85 - lr: 0.100000 +2022-11-01 14:00:36,399 epoch 24 - iter 270/274 - loss 0.02806091 - samples/sec: 72.96 - lr: 0.100000 +2022-11-01 14:00:38,397 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:00:38,397 EPOCH 24 done: loss 0.0281 - lr 0.100000 +2022-11-01 14:01:03,905 Evaluating as a multi-label problem: False +2022-11-01 14:01:03,920 TEST : loss 0.03052011877298355 - f1-score (micro avg) 0.8427 +2022-11-01 14:01:03,971 BAD EPOCHS (no improvement): 0 +2022-11-01 14:01:04,039 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:01:15,033 epoch 25 - iter 27/274 - loss 0.02254447 - samples/sec: 78.61 - lr: 0.100000 +2022-11-01 14:01:27,113 epoch 25 - iter 54/274 - loss 0.02958591 - samples/sec: 71.54 - lr: 0.100000 +2022-11-01 14:01:39,053 epoch 25 - iter 81/274 - loss 0.02847044 - samples/sec: 72.39 - lr: 0.100000 +2022-11-01 14:01:50,919 epoch 25 - iter 108/274 - loss 0.02739965 - samples/sec: 72.83 - lr: 0.100000 +2022-11-01 14:02:02,867 epoch 25 - iter 135/274 - loss 0.02744808 - samples/sec: 72.33 - lr: 0.100000 +2022-11-01 14:02:15,744 epoch 25 - iter 162/274 - loss 0.02698485 - samples/sec: 67.12 - lr: 0.100000 +2022-11-01 14:02:27,495 epoch 25 - iter 189/274 - loss 0.02731846 - samples/sec: 73.54 - lr: 0.100000 +2022-11-01 14:02:40,427 epoch 25 - iter 216/274 - loss 0.02843243 - samples/sec: 66.83 - lr: 0.100000 +2022-11-01 14:02:54,788 epoch 25 - iter 243/274 - loss 0.02862498 - samples/sec: 60.18 - lr: 0.100000 +2022-11-01 14:03:08,086 epoch 25 - iter 270/274 - loss 0.02826127 - samples/sec: 64.99 - lr: 0.100000 +2022-11-01 14:03:09,433 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:03:09,434 EPOCH 25 done: loss 0.0284 - lr 0.100000 +2022-11-01 14:03:34,594 Evaluating as a multi-label problem: False +2022-11-01 14:03:34,610 TEST : loss 0.029107416048645973 - f1-score (micro avg) 0.8389 +2022-11-01 14:03:34,662 BAD EPOCHS (no improvement): 1 +2022-11-01 14:03:34,750 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:03:46,841 epoch 26 - iter 27/274 - loss 0.02811300 - samples/sec: 71.48 - lr: 0.100000 +2022-11-01 14:03:59,602 epoch 26 - iter 54/274 - loss 0.02743337 - samples/sec: 67.72 - lr: 0.100000 +2022-11-01 14:04:11,887 epoch 26 - iter 81/274 - loss 0.02763661 - samples/sec: 70.35 - lr: 0.100000 +2022-11-01 14:04:25,712 epoch 26 - iter 108/274 - loss 0.02912647 - samples/sec: 62.51 - lr: 0.100000 +2022-11-01 14:04:37,325 epoch 26 - iter 135/274 - loss 0.02824420 - samples/sec: 74.42 - lr: 0.100000 +2022-11-01 14:04:50,074 epoch 26 - iter 162/274 - loss 0.02814963 - samples/sec: 67.79 - lr: 0.100000 +2022-11-01 14:05:02,658 epoch 26 - iter 189/274 - loss 0.02796098 - samples/sec: 68.68 - lr: 0.100000 +2022-11-01 14:05:15,161 epoch 26 - iter 216/274 - loss 0.02806696 - samples/sec: 69.12 - lr: 0.100000 +2022-11-01 14:05:26,292 epoch 26 - iter 243/274 - loss 0.02822794 - samples/sec: 77.65 - lr: 0.100000 +2022-11-01 14:05:38,777 epoch 26 - iter 270/274 - loss 0.02796632 - samples/sec: 69.22 - lr: 0.100000 +2022-11-01 14:05:40,413 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:05:40,413 EPOCH 26 done: loss 0.0280 - lr 0.100000 +2022-11-01 14:06:05,568 Evaluating as a multi-label problem: False +2022-11-01 14:06:05,583 TEST : loss 0.028921490535140038 - f1-score (micro avg) 0.8499 +2022-11-01 14:06:05,635 BAD EPOCHS (no improvement): 0 +2022-11-01 14:06:05,720 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:06:17,118 epoch 27 - iter 27/274 - loss 0.03035630 - samples/sec: 75.83 - lr: 0.100000 +2022-11-01 14:06:28,418 epoch 27 - iter 54/274 - loss 0.02636220 - samples/sec: 76.48 - lr: 0.100000 +2022-11-01 14:06:40,920 epoch 27 - iter 81/274 - loss 0.02716773 - samples/sec: 69.13 - lr: 0.100000 +2022-11-01 14:06:53,020 epoch 27 - iter 108/274 - loss 0.02817490 - samples/sec: 71.43 - lr: 0.100000 +2022-11-01 14:07:06,130 epoch 27 - iter 135/274 - loss 0.02905628 - samples/sec: 65.92 - lr: 0.100000 +2022-11-01 14:07:19,646 epoch 27 - iter 162/274 - loss 0.02789546 - samples/sec: 63.94 - lr: 0.100000 +2022-11-01 14:07:31,413 epoch 27 - iter 189/274 - loss 0.02750674 - samples/sec: 73.44 - lr: 0.100000 +2022-11-01 14:07:43,807 epoch 27 - iter 216/274 - loss 0.02740534 - samples/sec: 69.73 - lr: 0.100000 +2022-11-01 14:07:57,071 epoch 27 - iter 243/274 - loss 0.02788272 - samples/sec: 65.15 - lr: 0.100000 +2022-11-01 14:08:09,097 epoch 27 - iter 270/274 - loss 0.02804086 - samples/sec: 71.86 - lr: 0.100000 +2022-11-01 14:08:10,721 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:08:10,721 EPOCH 27 done: loss 0.0279 - lr 0.100000 +2022-11-01 14:08:35,996 Evaluating as a multi-label problem: False +2022-11-01 14:08:36,011 TEST : loss 0.02727373316884041 - f1-score (micro avg) 0.8495 +2022-11-01 14:08:36,063 BAD EPOCHS (no improvement): 0 +2022-11-01 14:08:36,151 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:08:48,729 epoch 28 - iter 27/274 - loss 0.02792706 - samples/sec: 68.72 - lr: 0.100000 +2022-11-01 14:09:00,474 epoch 28 - iter 54/274 - loss 0.02712818 - samples/sec: 73.58 - lr: 0.100000 +2022-11-01 14:09:13,998 epoch 28 - iter 81/274 - loss 0.02881006 - samples/sec: 63.90 - lr: 0.100000 +2022-11-01 14:09:26,897 epoch 28 - iter 108/274 - loss 0.02790622 - samples/sec: 66.99 - lr: 0.100000 +2022-11-01 14:09:39,353 epoch 28 - iter 135/274 - loss 0.02765454 - samples/sec: 69.38 - lr: 0.100000 +2022-11-01 14:09:51,992 epoch 28 - iter 162/274 - loss 0.02686081 - samples/sec: 68.38 - lr: 0.100000 +2022-11-01 14:10:05,064 epoch 28 - iter 189/274 - loss 0.02634890 - samples/sec: 66.11 - lr: 0.100000 +2022-11-01 14:10:16,714 epoch 28 - iter 216/274 - loss 0.02655923 - samples/sec: 74.18 - lr: 0.100000 +2022-11-01 14:10:29,815 epoch 28 - iter 243/274 - loss 0.02663561 - samples/sec: 65.96 - lr: 0.100000 +2022-11-01 14:10:41,079 epoch 28 - iter 270/274 - loss 0.02647144 - samples/sec: 76.72 - lr: 0.100000 +2022-11-01 14:10:42,579 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:10:42,580 EPOCH 28 done: loss 0.0267 - lr 0.100000 +2022-11-01 14:11:07,885 Evaluating as a multi-label problem: False +2022-11-01 14:11:07,901 TEST : loss 0.029852760955691338 - f1-score (micro avg) 0.8372 +2022-11-01 14:11:07,953 BAD EPOCHS (no improvement): 0 +2022-11-01 14:11:08,041 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:11:20,409 epoch 29 - iter 27/274 - loss 0.02518790 - samples/sec: 69.88 - lr: 0.100000 +2022-11-01 14:11:32,626 epoch 29 - iter 54/274 - loss 0.02805683 - samples/sec: 70.74 - lr: 0.100000 +2022-11-01 14:11:45,533 epoch 29 - iter 81/274 - loss 0.02825807 - samples/sec: 66.96 - lr: 0.100000 +2022-11-01 14:11:57,137 epoch 29 - iter 108/274 - loss 0.02799206 - samples/sec: 74.48 - lr: 0.100000 +2022-11-01 14:12:08,601 epoch 29 - iter 135/274 - loss 0.02755879 - samples/sec: 75.38 - lr: 0.100000 +2022-11-01 14:12:21,338 epoch 29 - iter 162/274 - loss 0.02685576 - samples/sec: 67.85 - lr: 0.100000 +2022-11-01 14:12:33,835 epoch 29 - iter 189/274 - loss 0.02594996 - samples/sec: 69.16 - lr: 0.100000 +2022-11-01 14:12:46,797 epoch 29 - iter 216/274 - loss 0.02550550 - samples/sec: 66.67 - lr: 0.100000 +2022-11-01 14:12:59,038 epoch 29 - iter 243/274 - loss 0.02644877 - samples/sec: 70.60 - lr: 0.100000 +2022-11-01 14:13:12,139 epoch 29 - iter 270/274 - loss 0.02627661 - samples/sec: 65.96 - lr: 0.100000 +2022-11-01 14:13:13,801 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:13:13,801 EPOCH 29 done: loss 0.0265 - lr 0.100000 +2022-11-01 14:13:39,155 Evaluating as a multi-label problem: False +2022-11-01 14:13:39,171 TEST : loss 0.02927403524518013 - f1-score (micro avg) 0.8443 +2022-11-01 14:13:39,223 BAD EPOCHS (no improvement): 0 +2022-11-01 14:13:39,311 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:13:51,641 epoch 30 - iter 27/274 - loss 0.02423251 - samples/sec: 70.10 - lr: 0.100000 +2022-11-01 14:14:05,415 epoch 30 - iter 54/274 - loss 0.02348831 - samples/sec: 62.74 - lr: 0.100000 +2022-11-01 14:14:18,177 epoch 30 - iter 81/274 - loss 0.02264011 - samples/sec: 67.72 - lr: 0.100000 +2022-11-01 14:14:29,311 epoch 30 - iter 108/274 - loss 0.02290510 - samples/sec: 77.62 - lr: 0.100000 +2022-11-01 14:14:40,278 epoch 30 - iter 135/274 - loss 0.02305872 - samples/sec: 78.81 - lr: 0.100000 +2022-11-01 14:14:52,410 epoch 30 - iter 162/274 - loss 0.02371256 - samples/sec: 71.23 - lr: 0.100000 +2022-11-01 14:15:05,697 epoch 30 - iter 189/274 - loss 0.02443210 - samples/sec: 65.04 - lr: 0.100000 +2022-11-01 14:15:18,878 epoch 30 - iter 216/274 - loss 0.02487402 - samples/sec: 65.56 - lr: 0.100000 +2022-11-01 14:15:31,181 epoch 30 - iter 243/274 - loss 0.02547667 - samples/sec: 70.25 - lr: 0.100000 +2022-11-01 14:15:44,553 epoch 30 - iter 270/274 - loss 0.02573419 - samples/sec: 64.63 - lr: 0.100000 +2022-11-01 14:15:46,184 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:15:46,184 EPOCH 30 done: loss 0.0257 - lr 0.100000 +2022-11-01 14:16:11,386 Evaluating as a multi-label problem: False +2022-11-01 14:16:11,401 TEST : loss 0.030005231499671936 - f1-score (micro avg) 0.8523 +2022-11-01 14:16:11,453 BAD EPOCHS (no improvement): 0 +2022-11-01 14:16:11,541 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:16:23,665 epoch 31 - iter 27/274 - loss 0.02769051 - samples/sec: 71.29 - lr: 0.100000 +2022-11-01 14:16:35,224 epoch 31 - iter 54/274 - loss 0.02615510 - samples/sec: 74.77 - lr: 0.100000 +2022-11-01 14:16:46,401 epoch 31 - iter 81/274 - loss 0.02630420 - samples/sec: 77.32 - lr: 0.100000 +2022-11-01 14:16:59,281 epoch 31 - iter 108/274 - loss 0.02469976 - samples/sec: 67.10 - lr: 0.100000 +2022-11-01 14:17:11,971 epoch 31 - iter 135/274 - loss 0.02533977 - samples/sec: 68.10 - lr: 0.100000 +2022-11-01 14:17:25,008 epoch 31 - iter 162/274 - loss 0.02569860 - samples/sec: 66.29 - lr: 0.100000 +2022-11-01 14:17:38,425 epoch 31 - iter 189/274 - loss 0.02582364 - samples/sec: 64.41 - lr: 0.100000 +2022-11-01 14:17:50,083 epoch 31 - iter 216/274 - loss 0.02617259 - samples/sec: 74.13 - lr: 0.100000 +2022-11-01 14:18:02,399 epoch 31 - iter 243/274 - loss 0.02593181 - samples/sec: 70.17 - lr: 0.100000 +2022-11-01 14:18:14,787 epoch 31 - iter 270/274 - loss 0.02601068 - samples/sec: 69.77 - lr: 0.100000 +2022-11-01 14:18:16,416 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:18:16,416 EPOCH 31 done: loss 0.0260 - lr 0.100000 +2022-11-01 14:18:41,696 Evaluating as a multi-label problem: False +2022-11-01 14:18:41,712 TEST : loss 0.029843807220458984 - f1-score (micro avg) 0.8272 +2022-11-01 14:18:41,764 BAD EPOCHS (no improvement): 1 +2022-11-01 14:18:41,849 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:18:54,631 epoch 32 - iter 27/274 - loss 0.02580945 - samples/sec: 67.62 - lr: 0.100000 +2022-11-01 14:19:05,986 epoch 32 - iter 54/274 - loss 0.02640680 - samples/sec: 76.11 - lr: 0.100000 +2022-11-01 14:19:18,468 epoch 32 - iter 81/274 - loss 0.02720723 - samples/sec: 69.24 - lr: 0.100000 +2022-11-01 14:19:31,021 epoch 32 - iter 108/274 - loss 0.02758148 - samples/sec: 68.85 - lr: 0.100000 +2022-11-01 14:19:42,993 epoch 32 - iter 135/274 - loss 0.02673017 - samples/sec: 72.19 - lr: 0.100000 +2022-11-01 14:19:54,726 epoch 32 - iter 162/274 - loss 0.02549280 - samples/sec: 73.66 - lr: 0.100000 +2022-11-01 14:20:07,180 epoch 32 - iter 189/274 - loss 0.02547213 - samples/sec: 69.39 - lr: 0.100000 +2022-11-01 14:20:19,997 epoch 32 - iter 216/274 - loss 0.02544760 - samples/sec: 67.43 - lr: 0.100000 +2022-11-01 14:20:32,141 epoch 32 - iter 243/274 - loss 0.02578350 - samples/sec: 71.16 - lr: 0.100000 +2022-11-01 14:20:45,434 epoch 32 - iter 270/274 - loss 0.02555593 - samples/sec: 65.02 - lr: 0.100000 +2022-11-01 14:20:47,150 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:20:47,150 EPOCH 32 done: loss 0.0256 - lr 0.100000 +2022-11-01 14:21:12,438 Evaluating as a multi-label problem: False +2022-11-01 14:21:12,453 TEST : loss 0.032904475927352905 - f1-score (micro avg) 0.8416 +2022-11-01 14:21:12,505 BAD EPOCHS (no improvement): 0 +2022-11-01 14:21:12,594 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:21:24,196 epoch 33 - iter 27/274 - loss 0.02139107 - samples/sec: 74.49 - lr: 0.100000 +2022-11-01 14:21:35,808 epoch 33 - iter 54/274 - loss 0.02249589 - samples/sec: 74.43 - lr: 0.100000 +2022-11-01 14:21:48,551 epoch 33 - iter 81/274 - loss 0.02273499 - samples/sec: 67.82 - lr: 0.100000 +2022-11-01 14:22:00,045 epoch 33 - iter 108/274 - loss 0.02313428 - samples/sec: 75.19 - lr: 0.100000 +2022-11-01 14:22:12,913 epoch 33 - iter 135/274 - loss 0.02465351 - samples/sec: 67.16 - lr: 0.100000 +2022-11-01 14:22:25,998 epoch 33 - iter 162/274 - loss 0.02561604 - samples/sec: 66.04 - lr: 0.100000 +2022-11-01 14:22:39,478 epoch 33 - iter 189/274 - loss 0.02617891 - samples/sec: 64.11 - lr: 0.100000 +2022-11-01 14:22:52,040 epoch 33 - iter 216/274 - loss 0.02625557 - samples/sec: 68.80 - lr: 0.100000 +2022-11-01 14:23:05,286 epoch 33 - iter 243/274 - loss 0.02610092 - samples/sec: 65.24 - lr: 0.100000 +2022-11-01 14:23:17,260 epoch 33 - iter 270/274 - loss 0.02604854 - samples/sec: 72.18 - lr: 0.100000 +2022-11-01 14:23:18,711 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:23:18,711 EPOCH 33 done: loss 0.0261 - lr 0.100000 +2022-11-01 14:23:44,069 Evaluating as a multi-label problem: False +2022-11-01 14:23:44,084 TEST : loss 0.028233280405402184 - f1-score (micro avg) 0.8391 +2022-11-01 14:23:44,136 BAD EPOCHS (no improvement): 1 +2022-11-01 14:23:44,226 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:23:56,465 epoch 34 - iter 27/274 - loss 0.02246222 - samples/sec: 70.62 - lr: 0.100000 +2022-11-01 14:24:07,833 epoch 34 - iter 54/274 - loss 0.02635074 - samples/sec: 76.03 - lr: 0.100000 +2022-11-01 14:24:20,691 epoch 34 - iter 81/274 - loss 0.02508465 - samples/sec: 67.21 - lr: 0.100000 +2022-11-01 14:24:33,435 epoch 34 - iter 108/274 - loss 0.02542733 - samples/sec: 67.81 - lr: 0.100000 +2022-11-01 14:24:45,896 epoch 34 - iter 135/274 - loss 0.02499971 - samples/sec: 69.35 - lr: 0.100000 +2022-11-01 14:24:59,505 epoch 34 - iter 162/274 - loss 0.02484198 - samples/sec: 63.50 - lr: 0.100000 +2022-11-01 14:25:11,652 epoch 34 - iter 189/274 - loss 0.02512618 - samples/sec: 71.14 - lr: 0.100000 +2022-11-01 14:25:22,940 epoch 34 - iter 216/274 - loss 0.02466030 - samples/sec: 76.57 - lr: 0.100000 +2022-11-01 14:25:35,198 epoch 34 - iter 243/274 - loss 0.02485847 - samples/sec: 70.50 - lr: 0.100000 +2022-11-01 14:25:47,307 epoch 34 - iter 270/274 - loss 0.02483982 - samples/sec: 71.37 - lr: 0.100000 +2022-11-01 14:25:49,659 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:25:49,660 EPOCH 34 done: loss 0.0251 - lr 0.100000 +2022-11-01 14:26:14,991 Evaluating as a multi-label problem: False +2022-11-01 14:26:15,007 TEST : loss 0.03128255903720856 - f1-score (micro avg) 0.8362 +2022-11-01 14:26:15,058 BAD EPOCHS (no improvement): 0 +2022-11-01 14:26:15,146 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:26:27,562 epoch 35 - iter 27/274 - loss 0.02694894 - samples/sec: 69.61 - lr: 0.100000 +2022-11-01 14:26:40,795 epoch 35 - iter 54/274 - loss 0.02622403 - samples/sec: 65.31 - lr: 0.100000 +2022-11-01 14:26:53,932 epoch 35 - iter 81/274 - loss 0.02467823 - samples/sec: 65.78 - lr: 0.100000 +2022-11-01 14:27:08,552 epoch 35 - iter 108/274 - loss 0.02345882 - samples/sec: 59.11 - lr: 0.100000 +2022-11-01 14:27:21,143 epoch 35 - iter 135/274 - loss 0.02558701 - samples/sec: 68.63 - lr: 0.100000 +2022-11-01 14:27:33,403 epoch 35 - iter 162/274 - loss 0.02581309 - samples/sec: 70.49 - lr: 0.100000 +2022-11-01 14:27:45,796 epoch 35 - iter 189/274 - loss 0.02556739 - samples/sec: 69.73 - lr: 0.100000 +2022-11-01 14:27:57,067 epoch 35 - iter 216/274 - loss 0.02550404 - samples/sec: 76.68 - lr: 0.100000 +2022-11-01 14:28:08,594 epoch 35 - iter 243/274 - loss 0.02550350 - samples/sec: 74.98 - lr: 0.100000 +2022-11-01 14:28:20,638 epoch 35 - iter 270/274 - loss 0.02552577 - samples/sec: 71.76 - lr: 0.100000 +2022-11-01 14:28:22,286 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:28:22,286 EPOCH 35 done: loss 0.0256 - lr 0.100000 +2022-11-01 14:28:47,480 Evaluating as a multi-label problem: False +2022-11-01 14:28:47,496 TEST : loss 0.02886551432311535 - f1-score (micro avg) 0.839 +2022-11-01 14:28:47,547 BAD EPOCHS (no improvement): 1 +2022-11-01 14:28:47,616 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:28:58,605 epoch 36 - iter 27/274 - loss 0.02300676 - samples/sec: 78.66 - lr: 0.100000 +2022-11-01 14:29:11,051 epoch 36 - iter 54/274 - loss 0.02499267 - samples/sec: 69.43 - lr: 0.100000 +2022-11-01 14:29:23,960 epoch 36 - iter 81/274 - loss 0.02491617 - samples/sec: 66.95 - lr: 0.100000 +2022-11-01 14:29:35,980 epoch 36 - iter 108/274 - loss 0.02491462 - samples/sec: 71.90 - lr: 0.100000 +2022-11-01 14:29:48,361 epoch 36 - iter 135/274 - loss 0.02460620 - samples/sec: 69.80 - lr: 0.100000 +2022-11-01 14:30:00,925 epoch 36 - iter 162/274 - loss 0.02530639 - samples/sec: 68.78 - lr: 0.100000 +2022-11-01 14:30:13,191 epoch 36 - iter 189/274 - loss 0.02488329 - samples/sec: 70.46 - lr: 0.100000 +2022-11-01 14:30:26,975 epoch 36 - iter 216/274 - loss 0.02498352 - samples/sec: 62.70 - lr: 0.100000 +2022-11-01 14:30:39,154 epoch 36 - iter 243/274 - loss 0.02518749 - samples/sec: 70.96 - lr: 0.100000 +2022-11-01 14:30:51,430 epoch 36 - iter 270/274 - loss 0.02540258 - samples/sec: 70.40 - lr: 0.100000 +2022-11-01 14:30:53,449 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:30:53,449 EPOCH 36 done: loss 0.0254 - lr 0.100000 +2022-11-01 14:31:18,697 Evaluating as a multi-label problem: False +2022-11-01 14:31:18,712 TEST : loss 0.02905181795358658 - f1-score (micro avg) 0.8424 +2022-11-01 14:31:18,763 BAD EPOCHS (no improvement): 2 +2022-11-01 14:31:18,855 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:31:31,289 epoch 37 - iter 27/274 - loss 0.02678495 - samples/sec: 69.51 - lr: 0.100000 +2022-11-01 14:31:43,065 epoch 37 - iter 54/274 - loss 0.02523053 - samples/sec: 73.39 - lr: 0.100000 +2022-11-01 14:31:55,883 epoch 37 - iter 81/274 - loss 0.02558693 - samples/sec: 67.42 - lr: 0.100000 +2022-11-01 14:32:07,760 epoch 37 - iter 108/274 - loss 0.02555196 - samples/sec: 72.76 - lr: 0.100000 +2022-11-01 14:32:19,739 epoch 37 - iter 135/274 - loss 0.02508545 - samples/sec: 72.15 - lr: 0.100000 +2022-11-01 14:32:33,968 epoch 37 - iter 162/274 - loss 0.02481853 - samples/sec: 60.74 - lr: 0.100000 +2022-11-01 14:32:45,715 epoch 37 - iter 189/274 - loss 0.02523619 - samples/sec: 73.57 - lr: 0.100000 +2022-11-01 14:32:58,842 epoch 37 - iter 216/274 - loss 0.02533995 - samples/sec: 65.84 - lr: 0.100000 +2022-11-01 14:33:09,872 epoch 37 - iter 243/274 - loss 0.02496223 - samples/sec: 78.35 - lr: 0.100000 +2022-11-01 14:33:22,337 epoch 37 - iter 270/274 - loss 0.02494492 - samples/sec: 69.33 - lr: 0.100000 +2022-11-01 14:33:23,784 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:33:23,784 EPOCH 37 done: loss 0.0248 - lr 0.100000 +2022-11-01 14:33:49,123 Evaluating as a multi-label problem: False +2022-11-01 14:33:49,139 TEST : loss 0.03083939664065838 - f1-score (micro avg) 0.8404 +2022-11-01 14:33:49,191 BAD EPOCHS (no improvement): 0 +2022-11-01 14:33:49,284 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:34:01,480 epoch 38 - iter 27/274 - loss 0.02325190 - samples/sec: 70.86 - lr: 0.100000 +2022-11-01 14:34:15,709 epoch 38 - iter 54/274 - loss 0.02240111 - samples/sec: 60.73 - lr: 0.100000 +2022-11-01 14:34:28,421 epoch 38 - iter 81/274 - loss 0.02339176 - samples/sec: 67.99 - lr: 0.100000 +2022-11-01 14:34:40,651 epoch 38 - iter 108/274 - loss 0.02383358 - samples/sec: 70.66 - lr: 0.100000 +2022-11-01 14:34:52,869 epoch 38 - iter 135/274 - loss 0.02355411 - samples/sec: 70.74 - lr: 0.100000 +2022-11-01 14:35:05,634 epoch 38 - iter 162/274 - loss 0.02436854 - samples/sec: 67.70 - lr: 0.100000 +2022-11-01 14:35:18,016 epoch 38 - iter 189/274 - loss 0.02461991 - samples/sec: 69.80 - lr: 0.100000 +2022-11-01 14:35:30,070 epoch 38 - iter 216/274 - loss 0.02434924 - samples/sec: 71.70 - lr: 0.100000 +2022-11-01 14:35:40,955 epoch 38 - iter 243/274 - loss 0.02462337 - samples/sec: 79.39 - lr: 0.100000 +2022-11-01 14:35:53,586 epoch 38 - iter 270/274 - loss 0.02484028 - samples/sec: 68.42 - lr: 0.100000 +2022-11-01 14:35:55,289 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:35:55,289 EPOCH 38 done: loss 0.0247 - lr 0.100000 +2022-11-01 14:36:20,583 Evaluating as a multi-label problem: False +2022-11-01 14:36:20,598 TEST : loss 0.029346710070967674 - f1-score (micro avg) 0.8482 +2022-11-01 14:36:20,650 BAD EPOCHS (no improvement): 0 +2022-11-01 14:36:20,721 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:36:32,585 epoch 39 - iter 27/274 - loss 0.02562557 - samples/sec: 72.85 - lr: 0.100000 +2022-11-01 14:36:43,852 epoch 39 - iter 54/274 - loss 0.02372105 - samples/sec: 76.71 - lr: 0.100000 +2022-11-01 14:36:57,929 epoch 39 - iter 81/274 - loss 0.02352530 - samples/sec: 61.39 - lr: 0.100000 +2022-11-01 14:37:11,034 epoch 39 - iter 108/274 - loss 0.02507286 - samples/sec: 65.95 - lr: 0.100000 +2022-11-01 14:37:22,672 epoch 39 - iter 135/274 - loss 0.02526471 - samples/sec: 74.26 - lr: 0.100000 +2022-11-01 14:37:35,165 epoch 39 - iter 162/274 - loss 0.02549320 - samples/sec: 69.18 - lr: 0.100000 +2022-11-01 14:37:46,859 epoch 39 - iter 189/274 - loss 0.02480664 - samples/sec: 73.90 - lr: 0.100000 +2022-11-01 14:37:58,698 epoch 39 - iter 216/274 - loss 0.02442860 - samples/sec: 73.00 - lr: 0.100000 +2022-11-01 14:38:11,976 epoch 39 - iter 243/274 - loss 0.02518608 - samples/sec: 65.09 - lr: 0.100000 +2022-11-01 14:38:23,528 epoch 39 - iter 270/274 - loss 0.02512607 - samples/sec: 74.82 - lr: 0.100000 +2022-11-01 14:38:25,272 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:38:25,272 EPOCH 39 done: loss 0.0252 - lr 0.100000 +2022-11-01 14:38:50,637 Evaluating as a multi-label problem: False +2022-11-01 14:38:50,652 TEST : loss 0.030634140595793724 - f1-score (micro avg) 0.8477 +2022-11-01 14:38:50,704 BAD EPOCHS (no improvement): 1 +2022-11-01 14:38:50,781 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:39:02,083 epoch 40 - iter 27/274 - loss 0.02303791 - samples/sec: 76.47 - lr: 0.100000 +2022-11-01 14:39:15,907 epoch 40 - iter 54/274 - loss 0.02221891 - samples/sec: 62.52 - lr: 0.100000 +2022-11-01 14:39:27,953 epoch 40 - iter 81/274 - loss 0.02304378 - samples/sec: 71.74 - lr: 0.100000 +2022-11-01 14:39:40,530 epoch 40 - iter 108/274 - loss 0.02335194 - samples/sec: 68.72 - lr: 0.100000 +2022-11-01 14:39:52,052 epoch 40 - iter 135/274 - loss 0.02327292 - samples/sec: 75.01 - lr: 0.100000 +2022-11-01 14:40:04,816 epoch 40 - iter 162/274 - loss 0.02340847 - samples/sec: 67.71 - lr: 0.100000 +2022-11-01 14:40:17,337 epoch 40 - iter 189/274 - loss 0.02348761 - samples/sec: 69.02 - lr: 0.100000 +2022-11-01 14:40:30,638 epoch 40 - iter 216/274 - loss 0.02364579 - samples/sec: 64.97 - lr: 0.100000 +2022-11-01 14:40:41,862 epoch 40 - iter 243/274 - loss 0.02363918 - samples/sec: 77.00 - lr: 0.100000 +2022-11-01 14:40:54,205 epoch 40 - iter 270/274 - loss 0.02364620 - samples/sec: 70.02 - lr: 0.100000 +2022-11-01 14:40:56,428 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:40:56,428 EPOCH 40 done: loss 0.0239 - lr 0.100000 +2022-11-01 14:41:21,842 Evaluating as a multi-label problem: False +2022-11-01 14:41:21,858 TEST : loss 0.02772146463394165 - f1-score (micro avg) 0.8367 +2022-11-01 14:41:21,910 BAD EPOCHS (no improvement): 0 +2022-11-01 14:41:21,980 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:41:34,373 epoch 41 - iter 27/274 - loss 0.02218261 - samples/sec: 69.74 - lr: 0.100000 +2022-11-01 14:41:46,713 epoch 41 - iter 54/274 - loss 0.02452946 - samples/sec: 70.04 - lr: 0.100000 +2022-11-01 14:42:00,067 epoch 41 - iter 81/274 - loss 0.02464984 - samples/sec: 64.71 - lr: 0.100000 +2022-11-01 14:42:13,175 epoch 41 - iter 108/274 - loss 0.02478733 - samples/sec: 65.93 - lr: 0.100000 +2022-11-01 14:42:24,582 epoch 41 - iter 135/274 - loss 0.02416254 - samples/sec: 75.77 - lr: 0.100000 +2022-11-01 14:42:37,182 epoch 41 - iter 162/274 - loss 0.02418863 - samples/sec: 68.59 - lr: 0.100000 +2022-11-01 14:42:48,979 epoch 41 - iter 189/274 - loss 0.02391712 - samples/sec: 73.26 - lr: 0.100000 +2022-11-01 14:43:01,479 epoch 41 - iter 216/274 - loss 0.02390674 - samples/sec: 69.14 - lr: 0.100000 +2022-11-01 14:43:13,157 epoch 41 - iter 243/274 - loss 0.02392243 - samples/sec: 74.01 - lr: 0.100000 +2022-11-01 14:43:25,639 epoch 41 - iter 270/274 - loss 0.02412327 - samples/sec: 69.24 - lr: 0.100000 +2022-11-01 14:43:27,265 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:43:27,265 EPOCH 41 done: loss 0.0239 - lr 0.100000 +2022-11-01 14:43:52,553 Evaluating as a multi-label problem: False +2022-11-01 14:43:52,568 TEST : loss 0.03169442340731621 - f1-score (micro avg) 0.8514 +2022-11-01 14:43:52,619 BAD EPOCHS (no improvement): 0 +2022-11-01 14:43:52,707 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:44:04,877 epoch 42 - iter 27/274 - loss 0.02433022 - samples/sec: 71.02 - lr: 0.100000 +2022-11-01 14:44:17,429 epoch 42 - iter 54/274 - loss 0.02389634 - samples/sec: 68.85 - lr: 0.100000 +2022-11-01 14:44:29,618 epoch 42 - iter 81/274 - loss 0.02250941 - samples/sec: 70.90 - lr: 0.100000 +2022-11-01 14:44:41,866 epoch 42 - iter 108/274 - loss 0.02211868 - samples/sec: 70.56 - lr: 0.100000 +2022-11-01 14:44:55,665 epoch 42 - iter 135/274 - loss 0.02233769 - samples/sec: 62.63 - lr: 0.100000 +2022-11-01 14:45:07,849 epoch 42 - iter 162/274 - loss 0.02328487 - samples/sec: 70.93 - lr: 0.100000 +2022-11-01 14:45:18,733 epoch 42 - iter 189/274 - loss 0.02313874 - samples/sec: 79.41 - lr: 0.100000 +2022-11-01 14:45:31,192 epoch 42 - iter 216/274 - loss 0.02357150 - samples/sec: 69.37 - lr: 0.100000 +2022-11-01 14:45:44,209 epoch 42 - iter 243/274 - loss 0.02391369 - samples/sec: 66.39 - lr: 0.100000 +2022-11-01 14:45:55,304 epoch 42 - iter 270/274 - loss 0.02365274 - samples/sec: 77.90 - lr: 0.100000 +2022-11-01 14:45:57,120 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:45:57,120 EPOCH 42 done: loss 0.0235 - lr 0.100000 +2022-11-01 14:46:22,560 Evaluating as a multi-label problem: False +2022-11-01 14:46:22,576 TEST : loss 0.03278948739171028 - f1-score (micro avg) 0.8516 +2022-11-01 14:46:22,628 BAD EPOCHS (no improvement): 0 +2022-11-01 14:46:22,717 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:46:38,002 epoch 43 - iter 27/274 - loss 0.02368651 - samples/sec: 56.54 - lr: 0.100000 +2022-11-01 14:46:49,976 epoch 43 - iter 54/274 - loss 0.02517416 - samples/sec: 72.18 - lr: 0.100000 +2022-11-01 14:47:01,138 epoch 43 - iter 81/274 - loss 0.02256523 - samples/sec: 77.43 - lr: 0.100000 +2022-11-01 14:47:14,006 epoch 43 - iter 108/274 - loss 0.02355001 - samples/sec: 67.16 - lr: 0.100000 +2022-11-01 14:47:26,796 epoch 43 - iter 135/274 - loss 0.02396305 - samples/sec: 67.57 - lr: 0.100000 +2022-11-01 14:47:40,342 epoch 43 - iter 162/274 - loss 0.02362844 - samples/sec: 63.80 - lr: 0.100000 +2022-11-01 14:47:51,127 epoch 43 - iter 189/274 - loss 0.02289074 - samples/sec: 80.14 - lr: 0.100000 +2022-11-01 14:48:04,379 epoch 43 - iter 216/274 - loss 0.02336316 - samples/sec: 65.21 - lr: 0.100000 +2022-11-01 14:48:16,059 epoch 43 - iter 243/274 - loss 0.02362543 - samples/sec: 73.99 - lr: 0.100000 +2022-11-01 14:48:28,117 epoch 43 - iter 270/274 - loss 0.02350817 - samples/sec: 71.67 - lr: 0.100000 +2022-11-01 14:48:29,903 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:48:29,903 EPOCH 43 done: loss 0.0235 - lr 0.100000 +2022-11-01 14:48:55,144 Evaluating as a multi-label problem: False +2022-11-01 14:48:55,160 TEST : loss 0.032541219145059586 - f1-score (micro avg) 0.8499 +2022-11-01 14:48:55,213 BAD EPOCHS (no improvement): 0 +2022-11-01 14:48:55,302 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:49:08,036 epoch 44 - iter 27/274 - loss 0.02069038 - samples/sec: 67.87 - lr: 0.100000 +2022-11-01 14:49:20,182 epoch 44 - iter 54/274 - loss 0.02151187 - samples/sec: 71.15 - lr: 0.100000 +2022-11-01 14:49:30,865 epoch 44 - iter 81/274 - loss 0.02143477 - samples/sec: 80.90 - lr: 0.100000 +2022-11-01 14:49:42,537 epoch 44 - iter 108/274 - loss 0.02245272 - samples/sec: 74.05 - lr: 0.100000 +2022-11-01 14:49:54,536 epoch 44 - iter 135/274 - loss 0.02279972 - samples/sec: 72.02 - lr: 0.100000 +2022-11-01 14:50:05,597 epoch 44 - iter 162/274 - loss 0.02322081 - samples/sec: 78.14 - lr: 0.100000 +2022-11-01 14:50:18,330 epoch 44 - iter 189/274 - loss 0.02353130 - samples/sec: 67.87 - lr: 0.100000 +2022-11-01 14:50:32,304 epoch 44 - iter 216/274 - loss 0.02377507 - samples/sec: 61.84 - lr: 0.100000 +2022-11-01 14:50:44,805 epoch 44 - iter 243/274 - loss 0.02373147 - samples/sec: 69.13 - lr: 0.100000 +2022-11-01 14:50:57,854 epoch 44 - iter 270/274 - loss 0.02373160 - samples/sec: 66.31 - lr: 0.100000 +2022-11-01 14:50:59,998 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:50:59,998 EPOCH 44 done: loss 0.0238 - lr 0.100000 +2022-11-01 14:51:26,134 Evaluating as a multi-label problem: False +2022-11-01 14:51:26,149 TEST : loss 0.02845124527812004 - f1-score (micro avg) 0.8465 +2022-11-01 14:51:26,200 BAD EPOCHS (no improvement): 1 +2022-11-01 14:51:26,269 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:51:39,451 epoch 45 - iter 27/274 - loss 0.02757102 - samples/sec: 65.56 - lr: 0.100000 +2022-11-01 14:51:52,057 epoch 45 - iter 54/274 - loss 0.02555338 - samples/sec: 68.56 - lr: 0.100000 +2022-11-01 14:52:03,835 epoch 45 - iter 81/274 - loss 0.02440811 - samples/sec: 73.38 - lr: 0.100000 +2022-11-01 14:52:15,975 epoch 45 - iter 108/274 - loss 0.02504033 - samples/sec: 71.19 - lr: 0.100000 +2022-11-01 14:52:28,608 epoch 45 - iter 135/274 - loss 0.02481827 - samples/sec: 68.41 - lr: 0.100000 +2022-11-01 14:52:40,182 epoch 45 - iter 162/274 - loss 0.02464289 - samples/sec: 74.67 - lr: 0.100000 +2022-11-01 14:52:53,060 epoch 45 - iter 189/274 - loss 0.02493790 - samples/sec: 67.11 - lr: 0.100000 +2022-11-01 14:53:05,153 epoch 45 - iter 216/274 - loss 0.02455552 - samples/sec: 71.47 - lr: 0.100000 +2022-11-01 14:53:17,930 epoch 45 - iter 243/274 - loss 0.02398309 - samples/sec: 67.64 - lr: 0.100000 +2022-11-01 14:53:30,733 epoch 45 - iter 270/274 - loss 0.02374604 - samples/sec: 67.50 - lr: 0.100000 +2022-11-01 14:53:33,008 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:53:33,008 EPOCH 45 done: loss 0.0238 - lr 0.100000 +2022-11-01 14:53:58,283 Evaluating as a multi-label problem: False +2022-11-01 14:53:58,299 TEST : loss 0.029735716059803963 - f1-score (micro avg) 0.8508 +2022-11-01 14:53:58,351 BAD EPOCHS (no improvement): 2 +2022-11-01 14:53:58,435 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:54:09,817 epoch 46 - iter 27/274 - loss 0.02467951 - samples/sec: 75.94 - lr: 0.100000 +2022-11-01 14:54:21,873 epoch 46 - iter 54/274 - loss 0.02596354 - samples/sec: 71.69 - lr: 0.100000 +2022-11-01 14:54:34,441 epoch 46 - iter 81/274 - loss 0.02400549 - samples/sec: 68.76 - lr: 0.100000 +2022-11-01 14:54:47,134 epoch 46 - iter 108/274 - loss 0.02389095 - samples/sec: 68.09 - lr: 0.100000 +2022-11-01 14:55:01,103 epoch 46 - iter 135/274 - loss 0.02373190 - samples/sec: 61.87 - lr: 0.100000 +2022-11-01 14:55:13,471 epoch 46 - iter 162/274 - loss 0.02343819 - samples/sec: 69.88 - lr: 0.100000 +2022-11-01 14:55:25,101 epoch 46 - iter 189/274 - loss 0.02343376 - samples/sec: 74.31 - lr: 0.100000 +2022-11-01 14:55:38,007 epoch 46 - iter 216/274 - loss 0.02403790 - samples/sec: 66.96 - lr: 0.100000 +2022-11-01 14:55:50,576 epoch 46 - iter 243/274 - loss 0.02399389 - samples/sec: 68.76 - lr: 0.100000 +2022-11-01 14:56:02,258 epoch 46 - iter 270/274 - loss 0.02418122 - samples/sec: 73.98 - lr: 0.100000 +2022-11-01 14:56:04,273 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:56:04,274 EPOCH 46 done: loss 0.0243 - lr 0.100000 +2022-11-01 14:56:29,683 Evaluating as a multi-label problem: False +2022-11-01 14:56:29,698 TEST : loss 0.028860261663794518 - f1-score (micro avg) 0.8483 +2022-11-01 14:56:29,751 BAD EPOCHS (no improvement): 3 +2022-11-01 14:56:29,837 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:56:42,570 epoch 47 - iter 27/274 - loss 0.03313505 - samples/sec: 67.88 - lr: 0.100000 +2022-11-01 14:56:54,775 epoch 47 - iter 54/274 - loss 0.02904664 - samples/sec: 70.81 - lr: 0.100000 +2022-11-01 14:57:07,973 epoch 47 - iter 81/274 - loss 0.02655091 - samples/sec: 65.48 - lr: 0.100000 +2022-11-01 14:57:20,344 epoch 47 - iter 108/274 - loss 0.02502254 - samples/sec: 69.86 - lr: 0.100000 +2022-11-01 14:57:33,689 epoch 47 - iter 135/274 - loss 0.02387354 - samples/sec: 64.76 - lr: 0.100000 +2022-11-01 14:57:47,202 epoch 47 - iter 162/274 - loss 0.02337203 - samples/sec: 63.96 - lr: 0.100000 +2022-11-01 14:57:59,283 epoch 47 - iter 189/274 - loss 0.02311901 - samples/sec: 71.53 - lr: 0.100000 +2022-11-01 14:58:10,345 epoch 47 - iter 216/274 - loss 0.02312254 - samples/sec: 78.13 - lr: 0.100000 +2022-11-01 14:58:22,536 epoch 47 - iter 243/274 - loss 0.02276797 - samples/sec: 70.89 - lr: 0.100000 +2022-11-01 14:58:35,257 epoch 47 - iter 270/274 - loss 0.02288939 - samples/sec: 67.94 - lr: 0.100000 +2022-11-01 14:58:36,750 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:58:36,750 EPOCH 47 done: loss 0.0228 - lr 0.100000 +2022-11-01 14:59:01,933 Evaluating as a multi-label problem: False +2022-11-01 14:59:01,949 TEST : loss 0.02934456616640091 - f1-score (micro avg) 0.85 +2022-11-01 14:59:02,000 BAD EPOCHS (no improvement): 0 +2022-11-01 14:59:02,087 ---------------------------------------------------------------------------------------------------- +2022-11-01 14:59:14,890 epoch 48 - iter 27/274 - loss 0.02641052 - samples/sec: 67.51 - lr: 0.100000 +2022-11-01 14:59:27,300 epoch 48 - iter 54/274 - loss 0.02458621 - samples/sec: 69.64 - lr: 0.100000 +2022-11-01 14:59:41,623 epoch 48 - iter 81/274 - loss 0.02492918 - samples/sec: 60.34 - lr: 0.100000 +2022-11-01 14:59:53,214 epoch 48 - iter 108/274 - loss 0.02434256 - samples/sec: 74.56 - lr: 0.100000 +2022-11-01 15:00:05,218 epoch 48 - iter 135/274 - loss 0.02440883 - samples/sec: 72.00 - lr: 0.100000 +2022-11-01 15:00:17,655 epoch 48 - iter 162/274 - loss 0.02434351 - samples/sec: 69.49 - lr: 0.100000 +2022-11-01 15:00:29,358 epoch 48 - iter 189/274 - loss 0.02453602 - samples/sec: 73.85 - lr: 0.100000 +2022-11-01 15:00:41,290 epoch 48 - iter 216/274 - loss 0.02403384 - samples/sec: 72.43 - lr: 0.100000 +2022-11-01 15:00:52,879 epoch 48 - iter 243/274 - loss 0.02357749 - samples/sec: 74.57 - lr: 0.100000 +2022-11-01 15:01:06,810 epoch 48 - iter 270/274 - loss 0.02325659 - samples/sec: 62.04 - lr: 0.100000 +2022-11-01 15:01:08,920 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:01:08,921 EPOCH 48 done: loss 0.0233 - lr 0.100000 +2022-11-01 15:01:34,433 Evaluating as a multi-label problem: False +2022-11-01 15:01:34,449 TEST : loss 0.027938606217503548 - f1-score (micro avg) 0.8443 +2022-11-01 15:01:34,500 BAD EPOCHS (no improvement): 1 +2022-11-01 15:01:34,588 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:01:46,854 epoch 49 - iter 27/274 - loss 0.01956175 - samples/sec: 70.46 - lr: 0.100000 +2022-11-01 15:01:59,605 epoch 49 - iter 54/274 - loss 0.02219700 - samples/sec: 67.78 - lr: 0.100000 +2022-11-01 15:02:11,513 epoch 49 - iter 81/274 - loss 0.02216077 - samples/sec: 72.57 - lr: 0.100000 +2022-11-01 15:02:23,884 epoch 49 - iter 108/274 - loss 0.02166043 - samples/sec: 69.86 - lr: 0.100000 +2022-11-01 15:02:35,018 epoch 49 - iter 135/274 - loss 0.02214609 - samples/sec: 77.62 - lr: 0.100000 +2022-11-01 15:02:47,703 epoch 49 - iter 162/274 - loss 0.02230819 - samples/sec: 68.13 - lr: 0.100000 +2022-11-01 15:03:00,160 epoch 49 - iter 189/274 - loss 0.02220722 - samples/sec: 69.38 - lr: 0.100000 +2022-11-01 15:03:13,972 epoch 49 - iter 216/274 - loss 0.02222522 - samples/sec: 62.57 - lr: 0.100000 +2022-11-01 15:03:26,882 epoch 49 - iter 243/274 - loss 0.02219608 - samples/sec: 66.94 - lr: 0.100000 +2022-11-01 15:03:38,015 epoch 49 - iter 270/274 - loss 0.02232361 - samples/sec: 77.63 - lr: 0.100000 +2022-11-01 15:03:39,771 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:03:39,772 EPOCH 49 done: loss 0.0224 - lr 0.100000 +2022-11-01 15:04:05,093 Evaluating as a multi-label problem: False +2022-11-01 15:04:05,108 TEST : loss 0.02850373275578022 - f1-score (micro avg) 0.8468 +2022-11-01 15:04:05,160 BAD EPOCHS (no improvement): 0 +2022-11-01 15:04:05,249 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:04:19,274 epoch 50 - iter 27/274 - loss 0.02281989 - samples/sec: 61.62 - lr: 0.100000 +2022-11-01 15:04:32,085 epoch 50 - iter 54/274 - loss 0.02177090 - samples/sec: 67.46 - lr: 0.100000 +2022-11-01 15:04:44,255 epoch 50 - iter 81/274 - loss 0.02148794 - samples/sec: 71.01 - lr: 0.100000 +2022-11-01 15:04:55,864 epoch 50 - iter 108/274 - loss 0.02172616 - samples/sec: 74.44 - lr: 0.100000 +2022-11-01 15:05:08,711 epoch 50 - iter 135/274 - loss 0.02248392 - samples/sec: 67.27 - lr: 0.100000 +2022-11-01 15:05:19,943 epoch 50 - iter 162/274 - loss 0.02202995 - samples/sec: 76.95 - lr: 0.100000 +2022-11-01 15:05:31,349 epoch 50 - iter 189/274 - loss 0.02290603 - samples/sec: 75.77 - lr: 0.100000 +2022-11-01 15:05:43,290 epoch 50 - iter 216/274 - loss 0.02253406 - samples/sec: 72.38 - lr: 0.100000 +2022-11-01 15:05:54,958 epoch 50 - iter 243/274 - loss 0.02223297 - samples/sec: 74.07 - lr: 0.100000 +2022-11-01 15:06:08,209 epoch 50 - iter 270/274 - loss 0.02262291 - samples/sec: 65.22 - lr: 0.100000 +2022-11-01 15:06:10,014 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:06:10,015 EPOCH 50 done: loss 0.0226 - lr 0.100000 +2022-11-01 15:06:34,955 Evaluating as a multi-label problem: False +2022-11-01 15:06:34,970 TEST : loss 0.028627894818782806 - f1-score (micro avg) 0.8454 +2022-11-01 15:06:35,022 BAD EPOCHS (no improvement): 1 +2022-11-01 15:06:35,107 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:06:48,507 epoch 51 - iter 27/274 - loss 0.02238933 - samples/sec: 64.49 - lr: 0.100000 +2022-11-01 15:07:02,021 epoch 51 - iter 54/274 - loss 0.02462189 - samples/sec: 63.95 - lr: 0.100000 +2022-11-01 15:07:14,430 epoch 51 - iter 81/274 - loss 0.02400550 - samples/sec: 69.65 - lr: 0.100000 +2022-11-01 15:07:26,726 epoch 51 - iter 108/274 - loss 0.02311522 - samples/sec: 70.29 - lr: 0.100000 +2022-11-01 15:07:37,629 epoch 51 - iter 135/274 - loss 0.02300795 - samples/sec: 79.27 - lr: 0.100000 +2022-11-01 15:07:50,615 epoch 51 - iter 162/274 - loss 0.02348605 - samples/sec: 66.55 - lr: 0.100000 +2022-11-01 15:08:02,430 epoch 51 - iter 189/274 - loss 0.02283313 - samples/sec: 73.15 - lr: 0.100000 +2022-11-01 15:08:14,790 epoch 51 - iter 216/274 - loss 0.02245246 - samples/sec: 69.92 - lr: 0.100000 +2022-11-01 15:08:26,827 epoch 51 - iter 243/274 - loss 0.02276332 - samples/sec: 71.80 - lr: 0.100000 +2022-11-01 15:08:40,356 epoch 51 - iter 270/274 - loss 0.02279572 - samples/sec: 63.88 - lr: 0.100000 +2022-11-01 15:08:41,992 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:08:41,992 EPOCH 51 done: loss 0.0228 - lr 0.100000 +2022-11-01 15:09:07,240 Evaluating as a multi-label problem: False +2022-11-01 15:09:07,255 TEST : loss 0.030040256679058075 - f1-score (micro avg) 0.8562 +2022-11-01 15:09:07,307 BAD EPOCHS (no improvement): 2 +2022-11-01 15:09:07,396 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:09:19,681 epoch 52 - iter 27/274 - loss 0.02043969 - samples/sec: 70.35 - lr: 0.100000 +2022-11-01 15:09:34,320 epoch 52 - iter 54/274 - loss 0.02200447 - samples/sec: 59.03 - lr: 0.100000 +2022-11-01 15:09:47,331 epoch 52 - iter 81/274 - loss 0.02239819 - samples/sec: 66.42 - lr: 0.100000 +2022-11-01 15:10:00,542 epoch 52 - iter 108/274 - loss 0.02195955 - samples/sec: 65.41 - lr: 0.100000 +2022-11-01 15:10:12,733 epoch 52 - iter 135/274 - loss 0.02255437 - samples/sec: 70.89 - lr: 0.100000 +2022-11-01 15:10:24,202 epoch 52 - iter 162/274 - loss 0.02364029 - samples/sec: 75.36 - lr: 0.100000 +2022-11-01 15:10:35,444 epoch 52 - iter 189/274 - loss 0.02373332 - samples/sec: 76.87 - lr: 0.100000 +2022-11-01 15:10:47,265 epoch 52 - iter 216/274 - loss 0.02396143 - samples/sec: 73.11 - lr: 0.100000 +2022-11-01 15:10:59,460 epoch 52 - iter 243/274 - loss 0.02381229 - samples/sec: 70.87 - lr: 0.100000 +2022-11-01 15:11:12,304 epoch 52 - iter 270/274 - loss 0.02388624 - samples/sec: 67.28 - lr: 0.100000 +2022-11-01 15:11:13,703 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:11:13,703 EPOCH 52 done: loss 0.0240 - lr 0.100000 +2022-11-01 15:11:38,949 Evaluating as a multi-label problem: False +2022-11-01 15:11:38,965 TEST : loss 0.02899007685482502 - f1-score (micro avg) 0.8496 +2022-11-01 15:11:39,015 BAD EPOCHS (no improvement): 3 +2022-11-01 15:11:39,107 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:11:50,967 epoch 53 - iter 27/274 - loss 0.02453654 - samples/sec: 72.87 - lr: 0.100000 +2022-11-01 15:12:06,441 epoch 53 - iter 54/274 - loss 0.02250028 - samples/sec: 55.85 - lr: 0.100000 +2022-11-01 15:12:18,855 epoch 53 - iter 81/274 - loss 0.02251377 - samples/sec: 69.62 - lr: 0.100000 +2022-11-01 15:12:31,007 epoch 53 - iter 108/274 - loss 0.02219599 - samples/sec: 71.12 - lr: 0.100000 +2022-11-01 15:12:43,529 epoch 53 - iter 135/274 - loss 0.02197082 - samples/sec: 69.02 - lr: 0.100000 +2022-11-01 15:12:55,036 epoch 53 - iter 162/274 - loss 0.02234258 - samples/sec: 75.11 - lr: 0.100000 +2022-11-01 15:13:06,569 epoch 53 - iter 189/274 - loss 0.02253575 - samples/sec: 74.94 - lr: 0.100000 +2022-11-01 15:13:17,608 epoch 53 - iter 216/274 - loss 0.02244875 - samples/sec: 78.29 - lr: 0.100000 +2022-11-01 15:13:30,157 epoch 53 - iter 243/274 - loss 0.02246492 - samples/sec: 68.87 - lr: 0.100000 +2022-11-01 15:13:43,481 epoch 53 - iter 270/274 - loss 0.02199013 - samples/sec: 64.86 - lr: 0.100000 +2022-11-01 15:13:45,316 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:13:45,317 EPOCH 53 done: loss 0.0219 - lr 0.100000 +2022-11-01 15:14:10,521 Evaluating as a multi-label problem: False +2022-11-01 15:14:10,536 TEST : loss 0.031025480479002 - f1-score (micro avg) 0.8497 +2022-11-01 15:14:10,589 BAD EPOCHS (no improvement): 0 +2022-11-01 15:14:10,684 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:14:23,106 epoch 54 - iter 27/274 - loss 0.02366044 - samples/sec: 69.58 - lr: 0.100000 +2022-11-01 15:14:35,723 epoch 54 - iter 54/274 - loss 0.02131955 - samples/sec: 68.50 - lr: 0.100000 +2022-11-01 15:14:47,667 epoch 54 - iter 81/274 - loss 0.02241648 - samples/sec: 72.36 - lr: 0.100000 +2022-11-01 15:15:01,117 epoch 54 - iter 108/274 - loss 0.02264243 - samples/sec: 64.25 - lr: 0.100000 +2022-11-01 15:15:13,721 epoch 54 - iter 135/274 - loss 0.02298791 - samples/sec: 68.57 - lr: 0.100000 +2022-11-01 15:15:25,955 epoch 54 - iter 162/274 - loss 0.02242851 - samples/sec: 70.64 - lr: 0.100000 +2022-11-01 15:15:38,384 epoch 54 - iter 189/274 - loss 0.02235910 - samples/sec: 69.54 - lr: 0.100000 +2022-11-01 15:15:50,640 epoch 54 - iter 216/274 - loss 0.02201195 - samples/sec: 70.51 - lr: 0.100000 +2022-11-01 15:16:03,803 epoch 54 - iter 243/274 - loss 0.02225472 - samples/sec: 65.66 - lr: 0.100000 +2022-11-01 15:16:15,823 epoch 54 - iter 270/274 - loss 0.02218903 - samples/sec: 71.90 - lr: 0.100000 +2022-11-01 15:16:17,612 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:16:17,612 EPOCH 54 done: loss 0.0222 - lr 0.100000 +2022-11-01 15:16:42,914 Evaluating as a multi-label problem: False +2022-11-01 15:16:42,930 TEST : loss 0.030233900994062424 - f1-score (micro avg) 0.8454 +2022-11-01 15:16:42,983 BAD EPOCHS (no improvement): 1 +2022-11-01 15:16:43,079 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:16:55,349 epoch 55 - iter 27/274 - loss 0.02055602 - samples/sec: 70.44 - lr: 0.100000 +2022-11-01 15:17:08,468 epoch 55 - iter 54/274 - loss 0.01923870 - samples/sec: 65.88 - lr: 0.100000 +2022-11-01 15:17:23,027 epoch 55 - iter 81/274 - loss 0.02096547 - samples/sec: 59.36 - lr: 0.100000 +2022-11-01 15:17:34,938 epoch 55 - iter 108/274 - loss 0.02099036 - samples/sec: 72.56 - lr: 0.100000 +2022-11-01 15:17:47,602 epoch 55 - iter 135/274 - loss 0.02078503 - samples/sec: 68.24 - lr: 0.100000 +2022-11-01 15:17:59,080 epoch 55 - iter 162/274 - loss 0.02148538 - samples/sec: 75.30 - lr: 0.100000 +2022-11-01 15:18:11,657 epoch 55 - iter 189/274 - loss 0.02214461 - samples/sec: 68.71 - lr: 0.100000 +2022-11-01 15:18:23,508 epoch 55 - iter 216/274 - loss 0.02190890 - samples/sec: 72.93 - lr: 0.100000 +2022-11-01 15:18:36,762 epoch 55 - iter 243/274 - loss 0.02249219 - samples/sec: 65.20 - lr: 0.100000 +2022-11-01 15:18:48,843 epoch 55 - iter 270/274 - loss 0.02234599 - samples/sec: 71.54 - lr: 0.100000 +2022-11-01 15:18:50,379 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:18:50,379 EPOCH 55 done: loss 0.0224 - lr 0.100000 +2022-11-01 15:19:15,651 Evaluating as a multi-label problem: False +2022-11-01 15:19:15,666 TEST : loss 0.02768951654434204 - f1-score (micro avg) 0.856 +2022-11-01 15:19:15,719 BAD EPOCHS (no improvement): 2 +2022-11-01 15:19:15,811 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:19:28,337 epoch 56 - iter 27/274 - loss 0.01954876 - samples/sec: 69.00 - lr: 0.100000 +2022-11-01 15:19:40,046 epoch 56 - iter 54/274 - loss 0.02032311 - samples/sec: 73.81 - lr: 0.100000 +2022-11-01 15:19:52,765 epoch 56 - iter 81/274 - loss 0.02087417 - samples/sec: 67.95 - lr: 0.100000 +2022-11-01 15:20:04,834 epoch 56 - iter 108/274 - loss 0.02048386 - samples/sec: 71.61 - lr: 0.100000 +2022-11-01 15:20:17,273 epoch 56 - iter 135/274 - loss 0.02064770 - samples/sec: 69.47 - lr: 0.100000 +2022-11-01 15:20:28,798 epoch 56 - iter 162/274 - loss 0.02112385 - samples/sec: 74.99 - lr: 0.100000 +2022-11-01 15:20:40,648 epoch 56 - iter 189/274 - loss 0.02075702 - samples/sec: 72.93 - lr: 0.100000 +2022-11-01 15:20:53,632 epoch 56 - iter 216/274 - loss 0.02239268 - samples/sec: 66.56 - lr: 0.100000 +2022-11-01 15:21:06,045 epoch 56 - iter 243/274 - loss 0.02240334 - samples/sec: 69.62 - lr: 0.100000 +2022-11-01 15:21:18,551 epoch 56 - iter 270/274 - loss 0.02264396 - samples/sec: 69.11 - lr: 0.100000 +2022-11-01 15:21:19,946 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:21:19,946 EPOCH 56 done: loss 0.0228 - lr 0.100000 +2022-11-01 15:21:45,321 Evaluating as a multi-label problem: False +2022-11-01 15:21:45,337 TEST : loss 0.0304726455360651 - f1-score (micro avg) 0.8554 +2022-11-01 15:21:45,388 BAD EPOCHS (no improvement): 3 +2022-11-01 15:21:45,480 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:21:59,285 epoch 57 - iter 27/274 - loss 0.01858226 - samples/sec: 62.60 - lr: 0.100000 +2022-11-01 15:22:12,050 epoch 57 - iter 54/274 - loss 0.02101951 - samples/sec: 67.70 - lr: 0.100000 +2022-11-01 15:22:23,465 epoch 57 - iter 81/274 - loss 0.02165109 - samples/sec: 75.71 - lr: 0.100000 +2022-11-01 15:22:37,035 epoch 57 - iter 108/274 - loss 0.02113920 - samples/sec: 63.68 - lr: 0.100000 +2022-11-01 15:22:49,205 epoch 57 - iter 135/274 - loss 0.02123264 - samples/sec: 71.01 - lr: 0.100000 +2022-11-01 15:23:01,492 epoch 57 - iter 162/274 - loss 0.02134561 - samples/sec: 70.34 - lr: 0.100000 +2022-11-01 15:23:12,834 epoch 57 - iter 189/274 - loss 0.02164682 - samples/sec: 76.20 - lr: 0.100000 +2022-11-01 15:23:25,219 epoch 57 - iter 216/274 - loss 0.02181912 - samples/sec: 69.78 - lr: 0.100000 +2022-11-01 15:23:37,457 epoch 57 - iter 243/274 - loss 0.02190306 - samples/sec: 70.62 - lr: 0.100000 +2022-11-01 15:23:49,705 epoch 57 - iter 270/274 - loss 0.02153457 - samples/sec: 70.56 - lr: 0.100000 +2022-11-01 15:23:51,568 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:23:51,569 EPOCH 57 done: loss 0.0218 - lr 0.100000 +2022-11-01 15:24:16,774 Evaluating as a multi-label problem: False +2022-11-01 15:24:16,790 TEST : loss 0.029483051970601082 - f1-score (micro avg) 0.851 +2022-11-01 15:24:16,842 BAD EPOCHS (no improvement): 0 +2022-11-01 15:24:16,934 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:24:27,696 epoch 58 - iter 27/274 - loss 0.01840180 - samples/sec: 80.31 - lr: 0.100000 +2022-11-01 15:24:40,903 epoch 58 - iter 54/274 - loss 0.01832122 - samples/sec: 65.43 - lr: 0.100000 +2022-11-01 15:24:53,761 epoch 58 - iter 81/274 - loss 0.02185904 - samples/sec: 67.21 - lr: 0.100000 +2022-11-01 15:25:06,320 epoch 58 - iter 108/274 - loss 0.02212350 - samples/sec: 68.81 - lr: 0.100000 +2022-11-01 15:25:17,127 epoch 58 - iter 135/274 - loss 0.02206877 - samples/sec: 79.97 - lr: 0.100000 +2022-11-01 15:25:28,855 epoch 58 - iter 162/274 - loss 0.02272453 - samples/sec: 73.69 - lr: 0.100000 +2022-11-01 15:25:42,309 epoch 58 - iter 189/274 - loss 0.02193286 - samples/sec: 64.23 - lr: 0.100000 +2022-11-01 15:25:56,457 epoch 58 - iter 216/274 - loss 0.02243499 - samples/sec: 61.08 - lr: 0.100000 +2022-11-01 15:26:08,686 epoch 58 - iter 243/274 - loss 0.02276000 - samples/sec: 70.67 - lr: 0.100000 +2022-11-01 15:26:21,274 epoch 58 - iter 270/274 - loss 0.02265005 - samples/sec: 68.65 - lr: 0.100000 +2022-11-01 15:26:22,976 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:26:22,976 EPOCH 58 done: loss 0.0227 - lr 0.100000 +2022-11-01 15:26:48,369 Evaluating as a multi-label problem: False +2022-11-01 15:26:48,384 TEST : loss 0.03021113947033882 - f1-score (micro avg) 0.8549 +2022-11-01 15:26:48,438 BAD EPOCHS (no improvement): 1 +2022-11-01 15:26:48,531 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:26:59,892 epoch 59 - iter 27/274 - loss 0.02035532 - samples/sec: 76.07 - lr: 0.100000 +2022-11-01 15:27:11,943 epoch 59 - iter 54/274 - loss 0.02086338 - samples/sec: 71.71 - lr: 0.100000 +2022-11-01 15:27:25,608 epoch 59 - iter 81/274 - loss 0.02163636 - samples/sec: 63.24 - lr: 0.100000 +2022-11-01 15:27:37,361 epoch 59 - iter 108/274 - loss 0.02209525 - samples/sec: 73.53 - lr: 0.100000 +2022-11-01 15:27:50,299 epoch 59 - iter 135/274 - loss 0.02206673 - samples/sec: 66.80 - lr: 0.100000 +2022-11-01 15:28:03,802 epoch 59 - iter 162/274 - loss 0.02266218 - samples/sec: 64.00 - lr: 0.100000 +2022-11-01 15:28:17,186 epoch 59 - iter 189/274 - loss 0.02225368 - samples/sec: 64.57 - lr: 0.100000 +2022-11-01 15:28:28,801 epoch 59 - iter 216/274 - loss 0.02210266 - samples/sec: 74.40 - lr: 0.100000 +2022-11-01 15:28:41,114 epoch 59 - iter 243/274 - loss 0.02192757 - samples/sec: 70.19 - lr: 0.100000 +2022-11-01 15:28:53,424 epoch 59 - iter 270/274 - loss 0.02161121 - samples/sec: 70.20 - lr: 0.100000 +2022-11-01 15:28:54,871 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:28:54,871 EPOCH 59 done: loss 0.0217 - lr 0.100000 +2022-11-01 15:29:20,109 Evaluating as a multi-label problem: False +2022-11-01 15:29:20,124 TEST : loss 0.03019784763455391 - f1-score (micro avg) 0.8518 +2022-11-01 15:29:20,177 BAD EPOCHS (no improvement): 0 +2022-11-01 15:29:20,268 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:29:33,582 epoch 60 - iter 27/274 - loss 0.02266229 - samples/sec: 64.91 - lr: 0.100000 +2022-11-01 15:29:44,822 epoch 60 - iter 54/274 - loss 0.02097862 - samples/sec: 76.89 - lr: 0.100000 +2022-11-01 15:29:58,299 epoch 60 - iter 81/274 - loss 0.02103717 - samples/sec: 64.12 - lr: 0.100000 +2022-11-01 15:30:10,428 epoch 60 - iter 108/274 - loss 0.02157194 - samples/sec: 71.25 - lr: 0.100000 +2022-11-01 15:30:23,316 epoch 60 - iter 135/274 - loss 0.02176278 - samples/sec: 67.06 - lr: 0.100000 +2022-11-01 15:30:35,025 epoch 60 - iter 162/274 - loss 0.02124505 - samples/sec: 73.81 - lr: 0.100000 +2022-11-01 15:30:47,845 epoch 60 - iter 189/274 - loss 0.02133995 - samples/sec: 67.41 - lr: 0.100000 +2022-11-01 15:31:00,017 epoch 60 - iter 216/274 - loss 0.02152520 - samples/sec: 71.00 - lr: 0.100000 +2022-11-01 15:31:12,827 epoch 60 - iter 243/274 - loss 0.02134036 - samples/sec: 67.46 - lr: 0.100000 +2022-11-01 15:31:24,440 epoch 60 - iter 270/274 - loss 0.02164276 - samples/sec: 74.42 - lr: 0.100000 +2022-11-01 15:31:25,992 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:31:25,992 EPOCH 60 done: loss 0.0216 - lr 0.100000 +2022-11-01 15:31:51,314 Evaluating as a multi-label problem: False +2022-11-01 15:31:51,329 TEST : loss 0.030309708788990974 - f1-score (micro avg) 0.8446 +2022-11-01 15:31:51,382 BAD EPOCHS (no improvement): 0 +2022-11-01 15:31:51,474 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:32:04,475 epoch 61 - iter 27/274 - loss 0.02131620 - samples/sec: 66.48 - lr: 0.100000 +2022-11-01 15:32:16,775 epoch 61 - iter 54/274 - loss 0.01755958 - samples/sec: 70.26 - lr: 0.100000 +2022-11-01 15:32:29,944 epoch 61 - iter 81/274 - loss 0.01785219 - samples/sec: 65.63 - lr: 0.100000 +2022-11-01 15:32:42,291 epoch 61 - iter 108/274 - loss 0.01927462 - samples/sec: 69.99 - lr: 0.100000 +2022-11-01 15:32:53,782 epoch 61 - iter 135/274 - loss 0.01932511 - samples/sec: 75.21 - lr: 0.100000 +2022-11-01 15:33:05,138 epoch 61 - iter 162/274 - loss 0.02022663 - samples/sec: 76.10 - lr: 0.100000 +2022-11-01 15:33:18,348 epoch 61 - iter 189/274 - loss 0.02152986 - samples/sec: 65.42 - lr: 0.100000 +2022-11-01 15:33:30,173 epoch 61 - iter 216/274 - loss 0.02153104 - samples/sec: 73.08 - lr: 0.100000 +2022-11-01 15:33:42,662 epoch 61 - iter 243/274 - loss 0.02155148 - samples/sec: 69.20 - lr: 0.100000 +2022-11-01 15:33:54,579 epoch 61 - iter 270/274 - loss 0.02144034 - samples/sec: 72.53 - lr: 0.100000 +2022-11-01 15:33:56,381 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:33:56,381 EPOCH 61 done: loss 0.0215 - lr 0.100000 +2022-11-01 15:34:21,677 Evaluating as a multi-label problem: False +2022-11-01 15:34:21,693 TEST : loss 0.028495075181126595 - f1-score (micro avg) 0.8491 +2022-11-01 15:34:21,745 BAD EPOCHS (no improvement): 0 +2022-11-01 15:34:21,837 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:34:34,938 epoch 62 - iter 27/274 - loss 0.01744152 - samples/sec: 65.97 - lr: 0.100000 +2022-11-01 15:34:47,972 epoch 62 - iter 54/274 - loss 0.02095425 - samples/sec: 66.30 - lr: 0.100000 +2022-11-01 15:35:00,121 epoch 62 - iter 81/274 - loss 0.02182806 - samples/sec: 71.14 - lr: 0.100000 +2022-11-01 15:35:12,065 epoch 62 - iter 108/274 - loss 0.02200592 - samples/sec: 72.36 - lr: 0.100000 +2022-11-01 15:35:24,838 epoch 62 - iter 135/274 - loss 0.02188164 - samples/sec: 67.66 - lr: 0.100000 +2022-11-01 15:35:36,484 epoch 62 - iter 162/274 - loss 0.02140413 - samples/sec: 74.21 - lr: 0.100000 +2022-11-01 15:35:49,425 epoch 62 - iter 189/274 - loss 0.02147430 - samples/sec: 66.78 - lr: 0.100000 +2022-11-01 15:36:01,416 epoch 62 - iter 216/274 - loss 0.02079022 - samples/sec: 72.07 - lr: 0.100000 +2022-11-01 15:36:14,073 epoch 62 - iter 243/274 - loss 0.02100848 - samples/sec: 68.28 - lr: 0.100000 +2022-11-01 15:36:25,958 epoch 62 - iter 270/274 - loss 0.02117302 - samples/sec: 72.71 - lr: 0.100000 +2022-11-01 15:36:27,489 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:36:27,489 EPOCH 62 done: loss 0.0211 - lr 0.100000 +2022-11-01 15:36:52,787 Evaluating as a multi-label problem: False +2022-11-01 15:36:52,803 TEST : loss 0.03227972984313965 - f1-score (micro avg) 0.8455 +2022-11-01 15:36:52,856 BAD EPOCHS (no improvement): 0 +2022-11-01 15:36:52,948 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:37:04,831 epoch 63 - iter 27/274 - loss 0.02126119 - samples/sec: 72.73 - lr: 0.100000 +2022-11-01 15:37:18,535 epoch 63 - iter 54/274 - loss 0.01942961 - samples/sec: 63.06 - lr: 0.100000 +2022-11-01 15:37:31,254 epoch 63 - iter 81/274 - loss 0.02012420 - samples/sec: 67.94 - lr: 0.100000 +2022-11-01 15:37:42,705 epoch 63 - iter 108/274 - loss 0.02029080 - samples/sec: 75.48 - lr: 0.100000 +2022-11-01 15:37:55,699 epoch 63 - iter 135/274 - loss 0.02042011 - samples/sec: 66.51 - lr: 0.100000 +2022-11-01 15:38:08,123 epoch 63 - iter 162/274 - loss 0.02065848 - samples/sec: 69.56 - lr: 0.100000 +2022-11-01 15:38:19,533 epoch 63 - iter 189/274 - loss 0.02095013 - samples/sec: 75.74 - lr: 0.100000 +2022-11-01 15:38:33,075 epoch 63 - iter 216/274 - loss 0.02097885 - samples/sec: 63.82 - lr: 0.100000 +2022-11-01 15:38:45,108 epoch 63 - iter 243/274 - loss 0.02113682 - samples/sec: 71.82 - lr: 0.100000 +2022-11-01 15:38:57,147 epoch 63 - iter 270/274 - loss 0.02136165 - samples/sec: 71.79 - lr: 0.100000 +2022-11-01 15:38:58,754 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:38:58,754 EPOCH 63 done: loss 0.0214 - lr 0.100000 +2022-11-01 15:39:24,602 Evaluating as a multi-label problem: False +2022-11-01 15:39:24,617 TEST : loss 0.029485132545232773 - f1-score (micro avg) 0.8442 +2022-11-01 15:39:24,671 BAD EPOCHS (no improvement): 1 +2022-11-01 15:39:24,745 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:39:35,637 epoch 64 - iter 27/274 - loss 0.01890757 - samples/sec: 79.35 - lr: 0.100000 +2022-11-01 15:39:49,308 epoch 64 - iter 54/274 - loss 0.01938230 - samples/sec: 63.21 - lr: 0.100000 +2022-11-01 15:40:02,928 epoch 64 - iter 81/274 - loss 0.02217057 - samples/sec: 63.45 - lr: 0.100000 +2022-11-01 15:40:15,391 epoch 64 - iter 108/274 - loss 0.02165389 - samples/sec: 69.34 - lr: 0.100000 +2022-11-01 15:40:26,951 epoch 64 - iter 135/274 - loss 0.02168174 - samples/sec: 74.76 - lr: 0.100000 +2022-11-01 15:40:38,848 epoch 64 - iter 162/274 - loss 0.02134826 - samples/sec: 72.64 - lr: 0.100000 +2022-11-01 15:40:50,875 epoch 64 - iter 189/274 - loss 0.02080389 - samples/sec: 71.86 - lr: 0.100000 +2022-11-01 15:41:03,888 epoch 64 - iter 216/274 - loss 0.02074878 - samples/sec: 66.41 - lr: 0.100000 +2022-11-01 15:41:16,800 epoch 64 - iter 243/274 - loss 0.02043543 - samples/sec: 66.93 - lr: 0.100000 +2022-11-01 15:41:29,886 epoch 64 - iter 270/274 - loss 0.02087130 - samples/sec: 66.04 - lr: 0.100000 +2022-11-01 15:41:31,399 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:41:31,399 EPOCH 64 done: loss 0.0209 - lr 0.100000 +2022-11-01 15:41:56,819 Evaluating as a multi-label problem: False +2022-11-01 15:41:56,835 TEST : loss 0.030096804723143578 - f1-score (micro avg) 0.8446 +2022-11-01 15:41:56,887 BAD EPOCHS (no improvement): 0 +2022-11-01 15:41:56,980 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:42:11,007 epoch 65 - iter 27/274 - loss 0.02540958 - samples/sec: 61.61 - lr: 0.100000 +2022-11-01 15:42:23,241 epoch 65 - iter 54/274 - loss 0.02236285 - samples/sec: 70.64 - lr: 0.100000 +2022-11-01 15:42:35,599 epoch 65 - iter 81/274 - loss 0.02219879 - samples/sec: 69.93 - lr: 0.100000 +2022-11-01 15:42:47,630 epoch 65 - iter 108/274 - loss 0.02127425 - samples/sec: 71.83 - lr: 0.100000 +2022-11-01 15:43:00,252 epoch 65 - iter 135/274 - loss 0.02210803 - samples/sec: 68.47 - lr: 0.100000 +2022-11-01 15:43:12,079 epoch 65 - iter 162/274 - loss 0.02161108 - samples/sec: 73.07 - lr: 0.100000 +2022-11-01 15:43:23,801 epoch 65 - iter 189/274 - loss 0.02206507 - samples/sec: 73.73 - lr: 0.100000 +2022-11-01 15:43:34,832 epoch 65 - iter 216/274 - loss 0.02203354 - samples/sec: 78.35 - lr: 0.100000 +2022-11-01 15:43:47,550 epoch 65 - iter 243/274 - loss 0.02200313 - samples/sec: 67.95 - lr: 0.100000 +2022-11-01 15:44:00,620 epoch 65 - iter 270/274 - loss 0.02150743 - samples/sec: 66.12 - lr: 0.100000 +2022-11-01 15:44:02,372 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:44:02,372 EPOCH 65 done: loss 0.0214 - lr 0.100000 +2022-11-01 15:44:28,137 Evaluating as a multi-label problem: False +2022-11-01 15:44:28,153 TEST : loss 0.02994183637201786 - f1-score (micro avg) 0.8534 +2022-11-01 15:44:28,205 BAD EPOCHS (no improvement): 1 +2022-11-01 15:44:28,291 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:44:40,467 epoch 66 - iter 27/274 - loss 0.01805836 - samples/sec: 70.98 - lr: 0.100000 +2022-11-01 15:44:53,328 epoch 66 - iter 54/274 - loss 0.01872092 - samples/sec: 67.20 - lr: 0.100000 +2022-11-01 15:45:06,350 epoch 66 - iter 81/274 - loss 0.02087662 - samples/sec: 66.37 - lr: 0.100000 +2022-11-01 15:45:17,576 epoch 66 - iter 108/274 - loss 0.02057641 - samples/sec: 76.99 - lr: 0.100000 +2022-11-01 15:45:29,056 epoch 66 - iter 135/274 - loss 0.01985161 - samples/sec: 75.28 - lr: 0.100000 +2022-11-01 15:45:42,760 epoch 66 - iter 162/274 - loss 0.02047046 - samples/sec: 63.06 - lr: 0.100000 +2022-11-01 15:45:56,009 epoch 66 - iter 189/274 - loss 0.02016785 - samples/sec: 65.23 - lr: 0.100000 +2022-11-01 15:46:07,489 epoch 66 - iter 216/274 - loss 0.02021241 - samples/sec: 75.28 - lr: 0.100000 +2022-11-01 15:46:19,392 epoch 66 - iter 243/274 - loss 0.02018700 - samples/sec: 72.61 - lr: 0.100000 +2022-11-01 15:46:32,830 epoch 66 - iter 270/274 - loss 0.02057448 - samples/sec: 64.31 - lr: 0.100000 +2022-11-01 15:46:34,491 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:46:34,491 EPOCH 66 done: loss 0.0205 - lr 0.100000 +2022-11-01 15:46:59,926 Evaluating as a multi-label problem: False +2022-11-01 15:46:59,942 TEST : loss 0.02977355383336544 - f1-score (micro avg) 0.8492 +2022-11-01 15:46:59,994 BAD EPOCHS (no improvement): 0 +2022-11-01 15:47:00,080 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:47:12,481 epoch 67 - iter 27/274 - loss 0.02224031 - samples/sec: 69.69 - lr: 0.100000 +2022-11-01 15:47:26,274 epoch 67 - iter 54/274 - loss 0.01948851 - samples/sec: 62.66 - lr: 0.100000 +2022-11-01 15:47:37,830 epoch 67 - iter 81/274 - loss 0.02039320 - samples/sec: 74.79 - lr: 0.100000 +2022-11-01 15:47:49,569 epoch 67 - iter 108/274 - loss 0.02151655 - samples/sec: 73.62 - lr: 0.100000 +2022-11-01 15:48:01,705 epoch 67 - iter 135/274 - loss 0.02094293 - samples/sec: 71.21 - lr: 0.100000 +2022-11-01 15:48:14,965 epoch 67 - iter 162/274 - loss 0.02077230 - samples/sec: 65.18 - lr: 0.100000 +2022-11-01 15:48:27,654 epoch 67 - iter 189/274 - loss 0.02084305 - samples/sec: 68.11 - lr: 0.100000 +2022-11-01 15:48:39,855 epoch 67 - iter 216/274 - loss 0.02079591 - samples/sec: 70.83 - lr: 0.100000 +2022-11-01 15:48:51,410 epoch 67 - iter 243/274 - loss 0.02046085 - samples/sec: 74.80 - lr: 0.100000 +2022-11-01 15:49:05,305 epoch 67 - iter 270/274 - loss 0.02023832 - samples/sec: 62.19 - lr: 0.100000 +2022-11-01 15:49:07,162 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:49:07,162 EPOCH 67 done: loss 0.0203 - lr 0.100000 +2022-11-01 15:49:32,558 Evaluating as a multi-label problem: False +2022-11-01 15:49:32,574 TEST : loss 0.030972706153988838 - f1-score (micro avg) 0.8543 +2022-11-01 15:49:32,627 BAD EPOCHS (no improvement): 0 +2022-11-01 15:49:32,723 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:49:46,088 epoch 68 - iter 27/274 - loss 0.02133801 - samples/sec: 64.67 - lr: 0.100000 +2022-11-01 15:49:58,017 epoch 68 - iter 54/274 - loss 0.02034460 - samples/sec: 72.45 - lr: 0.100000 +2022-11-01 15:50:11,523 epoch 68 - iter 81/274 - loss 0.02022263 - samples/sec: 63.98 - lr: 0.100000 +2022-11-01 15:50:24,462 epoch 68 - iter 108/274 - loss 0.02108536 - samples/sec: 66.79 - lr: 0.100000 +2022-11-01 15:50:37,223 epoch 68 - iter 135/274 - loss 0.02035431 - samples/sec: 67.73 - lr: 0.100000 +2022-11-01 15:50:49,548 epoch 68 - iter 162/274 - loss 0.02128033 - samples/sec: 70.12 - lr: 0.100000 +2022-11-01 15:51:01,472 epoch 68 - iter 189/274 - loss 0.02080314 - samples/sec: 72.48 - lr: 0.100000 +2022-11-01 15:51:13,417 epoch 68 - iter 216/274 - loss 0.02127075 - samples/sec: 72.35 - lr: 0.100000 +2022-11-01 15:51:25,660 epoch 68 - iter 243/274 - loss 0.02066568 - samples/sec: 70.59 - lr: 0.100000 +2022-11-01 15:51:37,327 epoch 68 - iter 270/274 - loss 0.02080117 - samples/sec: 74.07 - lr: 0.100000 +2022-11-01 15:51:38,889 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:51:38,889 EPOCH 68 done: loss 0.0208 - lr 0.100000 +2022-11-01 15:52:04,255 Evaluating as a multi-label problem: False +2022-11-01 15:52:04,271 TEST : loss 0.030792292207479477 - f1-score (micro avg) 0.8528 +2022-11-01 15:52:04,323 BAD EPOCHS (no improvement): 1 +2022-11-01 15:52:04,414 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:52:16,801 epoch 69 - iter 27/274 - loss 0.02075958 - samples/sec: 69.77 - lr: 0.100000 +2022-11-01 15:52:28,377 epoch 69 - iter 54/274 - loss 0.02100983 - samples/sec: 74.66 - lr: 0.100000 +2022-11-01 15:52:40,744 epoch 69 - iter 81/274 - loss 0.01987977 - samples/sec: 69.88 - lr: 0.100000 +2022-11-01 15:52:52,969 epoch 69 - iter 108/274 - loss 0.01993851 - samples/sec: 70.70 - lr: 0.100000 +2022-11-01 15:53:04,669 epoch 69 - iter 135/274 - loss 0.01973035 - samples/sec: 73.87 - lr: 0.100000 +2022-11-01 15:53:16,071 epoch 69 - iter 162/274 - loss 0.01921936 - samples/sec: 75.80 - lr: 0.100000 +2022-11-01 15:53:27,126 epoch 69 - iter 189/274 - loss 0.01975087 - samples/sec: 78.17 - lr: 0.100000 +2022-11-01 15:53:39,655 epoch 69 - iter 216/274 - loss 0.02017193 - samples/sec: 68.98 - lr: 0.100000 +2022-11-01 15:53:53,330 epoch 69 - iter 243/274 - loss 0.01998366 - samples/sec: 63.19 - lr: 0.100000 +2022-11-01 15:54:06,348 epoch 69 - iter 270/274 - loss 0.01994459 - samples/sec: 66.39 - lr: 0.100000 +2022-11-01 15:54:08,088 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:54:08,088 EPOCH 69 done: loss 0.0199 - lr 0.100000 +2022-11-01 15:54:33,789 Evaluating as a multi-label problem: False +2022-11-01 15:54:33,804 TEST : loss 0.031563375145196915 - f1-score (micro avg) 0.8505 +2022-11-01 15:54:33,856 BAD EPOCHS (no improvement): 0 +2022-11-01 15:54:33,947 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:54:47,227 epoch 70 - iter 27/274 - loss 0.01858086 - samples/sec: 65.08 - lr: 0.100000 +2022-11-01 15:54:58,681 epoch 70 - iter 54/274 - loss 0.01935509 - samples/sec: 75.45 - lr: 0.100000 +2022-11-01 15:55:10,707 epoch 70 - iter 81/274 - loss 0.01941681 - samples/sec: 71.87 - lr: 0.100000 +2022-11-01 15:55:24,092 epoch 70 - iter 108/274 - loss 0.02029023 - samples/sec: 64.56 - lr: 0.100000 +2022-11-01 15:55:36,306 epoch 70 - iter 135/274 - loss 0.02080017 - samples/sec: 70.76 - lr: 0.100000 +2022-11-01 15:55:48,483 epoch 70 - iter 162/274 - loss 0.02105265 - samples/sec: 70.97 - lr: 0.100000 +2022-11-01 15:56:01,367 epoch 70 - iter 189/274 - loss 0.02042653 - samples/sec: 67.08 - lr: 0.100000 +2022-11-01 15:56:13,179 epoch 70 - iter 216/274 - loss 0.02107873 - samples/sec: 73.17 - lr: 0.100000 +2022-11-01 15:56:26,980 epoch 70 - iter 243/274 - loss 0.02108922 - samples/sec: 62.62 - lr: 0.100000 +2022-11-01 15:56:40,787 epoch 70 - iter 270/274 - loss 0.02127791 - samples/sec: 62.59 - lr: 0.100000 +2022-11-01 15:56:42,391 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:56:42,391 EPOCH 70 done: loss 0.0212 - lr 0.100000 +2022-11-01 15:57:07,366 Evaluating as a multi-label problem: False +2022-11-01 15:57:07,382 TEST : loss 0.03166978433728218 - f1-score (micro avg) 0.8539 +2022-11-01 15:57:07,435 BAD EPOCHS (no improvement): 1 +2022-11-01 15:57:07,525 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:57:18,588 epoch 71 - iter 27/274 - loss 0.02212426 - samples/sec: 78.12 - lr: 0.100000 +2022-11-01 15:57:30,305 epoch 71 - iter 54/274 - loss 0.02025799 - samples/sec: 73.76 - lr: 0.100000 +2022-11-01 15:57:42,033 epoch 71 - iter 81/274 - loss 0.02065372 - samples/sec: 73.69 - lr: 0.100000 +2022-11-01 15:57:54,142 epoch 71 - iter 108/274 - loss 0.02128302 - samples/sec: 71.37 - lr: 0.100000 +2022-11-01 15:58:07,073 epoch 71 - iter 135/274 - loss 0.02181676 - samples/sec: 66.83 - lr: 0.100000 +2022-11-01 15:58:20,111 epoch 71 - iter 162/274 - loss 0.02132020 - samples/sec: 66.28 - lr: 0.100000 +2022-11-01 15:58:32,485 epoch 71 - iter 189/274 - loss 0.02050799 - samples/sec: 69.84 - lr: 0.100000 +2022-11-01 15:58:43,824 epoch 71 - iter 216/274 - loss 0.01992917 - samples/sec: 76.22 - lr: 0.100000 +2022-11-01 15:58:56,979 epoch 71 - iter 243/274 - loss 0.02030662 - samples/sec: 65.69 - lr: 0.100000 +2022-11-01 15:59:09,144 epoch 71 - iter 270/274 - loss 0.02021591 - samples/sec: 71.04 - lr: 0.100000 +2022-11-01 15:59:11,568 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:59:11,568 EPOCH 71 done: loss 0.0204 - lr 0.100000 +2022-11-01 15:59:37,390 Evaluating as a multi-label problem: False +2022-11-01 15:59:37,406 TEST : loss 0.03054458275437355 - f1-score (micro avg) 0.854 +2022-11-01 15:59:37,458 BAD EPOCHS (no improvement): 2 +2022-11-01 15:59:37,554 ---------------------------------------------------------------------------------------------------- +2022-11-01 15:59:49,256 epoch 72 - iter 27/274 - loss 0.02002288 - samples/sec: 73.86 - lr: 0.100000 +2022-11-01 16:00:01,291 epoch 72 - iter 54/274 - loss 0.01804290 - samples/sec: 71.81 - lr: 0.100000 +2022-11-01 16:00:13,882 epoch 72 - iter 81/274 - loss 0.01876863 - samples/sec: 68.63 - lr: 0.100000 +2022-11-01 16:00:25,965 epoch 72 - iter 108/274 - loss 0.01891240 - samples/sec: 71.53 - lr: 0.100000 +2022-11-01 16:00:39,081 epoch 72 - iter 135/274 - loss 0.01882314 - samples/sec: 65.89 - lr: 0.100000 +2022-11-01 16:00:51,215 epoch 72 - iter 162/274 - loss 0.01888338 - samples/sec: 71.23 - lr: 0.100000 +2022-11-01 16:01:02,822 epoch 72 - iter 189/274 - loss 0.01859963 - samples/sec: 74.45 - lr: 0.100000 +2022-11-01 16:01:15,001 epoch 72 - iter 216/274 - loss 0.01894609 - samples/sec: 70.96 - lr: 0.100000 +2022-11-01 16:01:28,410 epoch 72 - iter 243/274 - loss 0.01937545 - samples/sec: 64.45 - lr: 0.100000 +2022-11-01 16:01:42,428 epoch 72 - iter 270/274 - loss 0.02020000 - samples/sec: 61.65 - lr: 0.100000 +2022-11-01 16:01:43,954 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:01:43,955 EPOCH 72 done: loss 0.0201 - lr 0.100000 +2022-11-01 16:02:09,347 Evaluating as a multi-label problem: False +2022-11-01 16:02:09,363 TEST : loss 0.029515517875552177 - f1-score (micro avg) 0.8582 +2022-11-01 16:02:09,415 BAD EPOCHS (no improvement): 3 +2022-11-01 16:02:09,508 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:02:23,043 epoch 73 - iter 27/274 - loss 0.02220240 - samples/sec: 63.85 - lr: 0.100000 +2022-11-01 16:02:34,503 epoch 73 - iter 54/274 - loss 0.02184526 - samples/sec: 75.42 - lr: 0.100000 +2022-11-01 16:02:47,677 epoch 73 - iter 81/274 - loss 0.02129952 - samples/sec: 65.60 - lr: 0.100000 +2022-11-01 16:03:00,508 epoch 73 - iter 108/274 - loss 0.02092159 - samples/sec: 67.35 - lr: 0.100000 +2022-11-01 16:03:11,713 epoch 73 - iter 135/274 - loss 0.02135403 - samples/sec: 77.13 - lr: 0.100000 +2022-11-01 16:03:23,418 epoch 73 - iter 162/274 - loss 0.02121899 - samples/sec: 73.84 - lr: 0.100000 +2022-11-01 16:03:35,824 epoch 73 - iter 189/274 - loss 0.02072249 - samples/sec: 69.66 - lr: 0.100000 +2022-11-01 16:03:48,819 epoch 73 - iter 216/274 - loss 0.02100808 - samples/sec: 66.50 - lr: 0.100000 +2022-11-01 16:04:01,462 epoch 73 - iter 243/274 - loss 0.02116109 - samples/sec: 68.36 - lr: 0.100000 +2022-11-01 16:04:14,781 epoch 73 - iter 270/274 - loss 0.02126688 - samples/sec: 64.88 - lr: 0.100000 +2022-11-01 16:04:16,334 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:04:16,334 EPOCH 73 done: loss 0.0212 - lr 0.100000 +2022-11-01 16:04:41,564 Evaluating as a multi-label problem: False +2022-11-01 16:04:41,579 TEST : loss 0.0294826440513134 - f1-score (micro avg) 0.8499 +2022-11-01 16:04:41,631 Epoch 73: reducing learning rate of group 0 to 5.0000e-02. +2022-11-01 16:04:41,632 BAD EPOCHS (no improvement): 4 +2022-11-01 16:04:41,723 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:04:54,382 epoch 74 - iter 27/274 - loss 0.01699297 - samples/sec: 68.27 - lr: 0.050000 +2022-11-01 16:05:07,038 epoch 74 - iter 54/274 - loss 0.01847639 - samples/sec: 68.28 - lr: 0.050000 +2022-11-01 16:05:18,943 epoch 74 - iter 81/274 - loss 0.01896710 - samples/sec: 72.59 - lr: 0.050000 +2022-11-01 16:05:30,232 epoch 74 - iter 108/274 - loss 0.01856741 - samples/sec: 76.56 - lr: 0.050000 +2022-11-01 16:05:42,326 epoch 74 - iter 135/274 - loss 0.01911050 - samples/sec: 71.46 - lr: 0.050000 +2022-11-01 16:05:53,721 epoch 74 - iter 162/274 - loss 0.01893491 - samples/sec: 75.85 - lr: 0.050000 +2022-11-01 16:06:05,986 epoch 74 - iter 189/274 - loss 0.01976027 - samples/sec: 70.47 - lr: 0.050000 +2022-11-01 16:06:18,737 epoch 74 - iter 216/274 - loss 0.01995122 - samples/sec: 67.77 - lr: 0.050000 +2022-11-01 16:06:31,727 epoch 74 - iter 243/274 - loss 0.01949284 - samples/sec: 66.53 - lr: 0.050000 +2022-11-01 16:06:44,209 epoch 74 - iter 270/274 - loss 0.01943572 - samples/sec: 69.24 - lr: 0.050000 +2022-11-01 16:06:46,178 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:06:46,179 EPOCH 74 done: loss 0.0194 - lr 0.050000 +2022-11-01 16:07:11,505 Evaluating as a multi-label problem: False +2022-11-01 16:07:11,520 TEST : loss 0.030243773013353348 - f1-score (micro avg) 0.8508 +2022-11-01 16:07:11,574 BAD EPOCHS (no improvement): 0 +2022-11-01 16:07:11,666 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:07:24,777 epoch 75 - iter 27/274 - loss 0.01546676 - samples/sec: 65.92 - lr: 0.050000 +2022-11-01 16:07:36,355 epoch 75 - iter 54/274 - loss 0.01834654 - samples/sec: 74.65 - lr: 0.050000 +2022-11-01 16:07:48,021 epoch 75 - iter 81/274 - loss 0.01790446 - samples/sec: 74.08 - lr: 0.050000 +2022-11-01 16:07:59,523 epoch 75 - iter 108/274 - loss 0.01785671 - samples/sec: 75.14 - lr: 0.050000 +2022-11-01 16:08:12,431 epoch 75 - iter 135/274 - loss 0.01831446 - samples/sec: 66.95 - lr: 0.050000 +2022-11-01 16:08:25,527 epoch 75 - iter 162/274 - loss 0.01826631 - samples/sec: 65.99 - lr: 0.050000 +2022-11-01 16:08:37,958 epoch 75 - iter 189/274 - loss 0.01816669 - samples/sec: 69.52 - lr: 0.050000 +2022-11-01 16:08:51,537 epoch 75 - iter 216/274 - loss 0.01861337 - samples/sec: 63.64 - lr: 0.050000 +2022-11-01 16:09:03,481 epoch 75 - iter 243/274 - loss 0.01881745 - samples/sec: 72.36 - lr: 0.050000 +2022-11-01 16:09:16,590 epoch 75 - iter 270/274 - loss 0.01870689 - samples/sec: 65.93 - lr: 0.050000 +2022-11-01 16:09:18,295 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:09:18,295 EPOCH 75 done: loss 0.0188 - lr 0.050000 +2022-11-01 16:09:43,737 Evaluating as a multi-label problem: False +2022-11-01 16:09:43,752 TEST : loss 0.02911132387816906 - f1-score (micro avg) 0.8527 +2022-11-01 16:09:43,804 BAD EPOCHS (no improvement): 0 +2022-11-01 16:09:43,895 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:09:56,178 epoch 76 - iter 27/274 - loss 0.01445317 - samples/sec: 70.36 - lr: 0.050000 +2022-11-01 16:10:08,517 epoch 76 - iter 54/274 - loss 0.01648596 - samples/sec: 70.04 - lr: 0.050000 +2022-11-01 16:10:20,368 epoch 76 - iter 81/274 - loss 0.01698888 - samples/sec: 72.93 - lr: 0.050000 +2022-11-01 16:10:32,873 epoch 76 - iter 108/274 - loss 0.01756096 - samples/sec: 69.11 - lr: 0.050000 +2022-11-01 16:10:46,907 epoch 76 - iter 135/274 - loss 0.01762281 - samples/sec: 61.58 - lr: 0.050000 +2022-11-01 16:10:58,979 epoch 76 - iter 162/274 - loss 0.01732201 - samples/sec: 71.60 - lr: 0.050000 +2022-11-01 16:11:11,759 epoch 76 - iter 189/274 - loss 0.01751176 - samples/sec: 67.62 - lr: 0.050000 +2022-11-01 16:11:23,975 epoch 76 - iter 216/274 - loss 0.01766946 - samples/sec: 70.74 - lr: 0.050000 +2022-11-01 16:11:35,773 epoch 76 - iter 243/274 - loss 0.01783327 - samples/sec: 73.25 - lr: 0.050000 +2022-11-01 16:11:48,911 epoch 76 - iter 270/274 - loss 0.01793928 - samples/sec: 65.78 - lr: 0.050000 +2022-11-01 16:11:50,891 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:11:50,892 EPOCH 76 done: loss 0.0180 - lr 0.050000 +2022-11-01 16:12:16,332 Evaluating as a multi-label problem: False +2022-11-01 16:12:16,347 TEST : loss 0.02934643253684044 - f1-score (micro avg) 0.857 +2022-11-01 16:12:16,399 BAD EPOCHS (no improvement): 0 +2022-11-01 16:12:16,490 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:12:28,007 epoch 77 - iter 27/274 - loss 0.01524350 - samples/sec: 75.04 - lr: 0.050000 +2022-11-01 16:12:40,880 epoch 77 - iter 54/274 - loss 0.01741012 - samples/sec: 67.14 - lr: 0.050000 +2022-11-01 16:12:53,126 epoch 77 - iter 81/274 - loss 0.01776495 - samples/sec: 70.57 - lr: 0.050000 +2022-11-01 16:13:04,214 epoch 77 - iter 108/274 - loss 0.01764313 - samples/sec: 77.95 - lr: 0.050000 +2022-11-01 16:13:18,011 epoch 77 - iter 135/274 - loss 0.01765748 - samples/sec: 62.63 - lr: 0.050000 +2022-11-01 16:13:29,621 epoch 77 - iter 162/274 - loss 0.01771770 - samples/sec: 74.44 - lr: 0.050000 +2022-11-01 16:13:43,414 epoch 77 - iter 189/274 - loss 0.01796879 - samples/sec: 62.65 - lr: 0.050000 +2022-11-01 16:13:54,588 epoch 77 - iter 216/274 - loss 0.01797517 - samples/sec: 77.35 - lr: 0.050000 +2022-11-01 16:14:07,007 epoch 77 - iter 243/274 - loss 0.01790936 - samples/sec: 69.59 - lr: 0.050000 +2022-11-01 16:14:20,191 epoch 77 - iter 270/274 - loss 0.01865935 - samples/sec: 65.55 - lr: 0.050000 +2022-11-01 16:14:22,147 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:14:22,148 EPOCH 77 done: loss 0.0186 - lr 0.050000 +2022-11-01 16:14:47,277 Evaluating as a multi-label problem: False +2022-11-01 16:14:47,293 TEST : loss 0.028807329013943672 - f1-score (micro avg) 0.8581 +2022-11-01 16:14:47,347 BAD EPOCHS (no improvement): 1 +2022-11-01 16:14:47,439 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:14:59,483 epoch 78 - iter 27/274 - loss 0.01491909 - samples/sec: 71.76 - lr: 0.050000 +2022-11-01 16:15:11,094 epoch 78 - iter 54/274 - loss 0.01479802 - samples/sec: 74.43 - lr: 0.050000 +2022-11-01 16:15:23,177 epoch 78 - iter 81/274 - loss 0.01800552 - samples/sec: 71.53 - lr: 0.050000 +2022-11-01 16:15:35,961 epoch 78 - iter 108/274 - loss 0.01651022 - samples/sec: 67.60 - lr: 0.050000 +2022-11-01 16:15:48,569 epoch 78 - iter 135/274 - loss 0.01727430 - samples/sec: 68.55 - lr: 0.050000 +2022-11-01 16:16:02,945 epoch 78 - iter 162/274 - loss 0.01702202 - samples/sec: 60.12 - lr: 0.050000 +2022-11-01 16:16:15,222 epoch 78 - iter 189/274 - loss 0.01711726 - samples/sec: 70.39 - lr: 0.050000 +2022-11-01 16:16:27,068 epoch 78 - iter 216/274 - loss 0.01707427 - samples/sec: 72.95 - lr: 0.050000 +2022-11-01 16:16:39,506 epoch 78 - iter 243/274 - loss 0.01700401 - samples/sec: 69.48 - lr: 0.050000 +2022-11-01 16:16:52,570 epoch 78 - iter 270/274 - loss 0.01712211 - samples/sec: 66.15 - lr: 0.050000 +2022-11-01 16:16:54,130 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:16:54,131 EPOCH 78 done: loss 0.0171 - lr 0.050000 +2022-11-01 16:17:19,592 Evaluating as a multi-label problem: False +2022-11-01 16:17:19,608 TEST : loss 0.03133295476436615 - f1-score (micro avg) 0.8528 +2022-11-01 16:17:19,662 BAD EPOCHS (no improvement): 0 +2022-11-01 16:17:19,735 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:17:31,215 epoch 79 - iter 27/274 - loss 0.01593943 - samples/sec: 75.29 - lr: 0.050000 +2022-11-01 16:17:43,239 epoch 79 - iter 54/274 - loss 0.01816389 - samples/sec: 71.87 - lr: 0.050000 +2022-11-01 16:17:54,562 epoch 79 - iter 81/274 - loss 0.01802346 - samples/sec: 76.33 - lr: 0.050000 +2022-11-01 16:18:07,895 epoch 79 - iter 108/274 - loss 0.01903539 - samples/sec: 64.82 - lr: 0.050000 +2022-11-01 16:18:20,020 epoch 79 - iter 135/274 - loss 0.01855551 - samples/sec: 71.28 - lr: 0.050000 +2022-11-01 16:18:33,472 epoch 79 - iter 162/274 - loss 0.01859544 - samples/sec: 64.24 - lr: 0.050000 +2022-11-01 16:18:45,736 epoch 79 - iter 189/274 - loss 0.01866095 - samples/sec: 70.47 - lr: 0.050000 +2022-11-01 16:18:58,137 epoch 79 - iter 216/274 - loss 0.01866639 - samples/sec: 69.69 - lr: 0.050000 +2022-11-01 16:19:10,045 epoch 79 - iter 243/274 - loss 0.01811509 - samples/sec: 72.57 - lr: 0.050000 +2022-11-01 16:19:23,548 epoch 79 - iter 270/274 - loss 0.01832024 - samples/sec: 64.00 - lr: 0.050000 +2022-11-01 16:19:25,173 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:19:25,174 EPOCH 79 done: loss 0.0184 - lr 0.050000 +2022-11-01 16:19:50,600 Evaluating as a multi-label problem: False +2022-11-01 16:19:50,616 TEST : loss 0.03068099543452263 - f1-score (micro avg) 0.8506 +2022-11-01 16:19:50,669 BAD EPOCHS (no improvement): 1 +2022-11-01 16:19:50,760 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:20:01,772 epoch 80 - iter 27/274 - loss 0.01991148 - samples/sec: 78.49 - lr: 0.050000 +2022-11-01 16:20:16,433 epoch 80 - iter 54/274 - loss 0.01871553 - samples/sec: 58.94 - lr: 0.050000 +2022-11-01 16:20:28,629 epoch 80 - iter 81/274 - loss 0.01907954 - samples/sec: 70.86 - lr: 0.050000 +2022-11-01 16:20:40,218 epoch 80 - iter 108/274 - loss 0.01834093 - samples/sec: 74.58 - lr: 0.050000 +2022-11-01 16:20:53,091 epoch 80 - iter 135/274 - loss 0.01859223 - samples/sec: 67.14 - lr: 0.050000 +2022-11-01 16:21:04,356 epoch 80 - iter 162/274 - loss 0.01827675 - samples/sec: 76.72 - lr: 0.050000 +2022-11-01 16:21:17,001 epoch 80 - iter 189/274 - loss 0.01822210 - samples/sec: 68.34 - lr: 0.050000 +2022-11-01 16:21:28,675 epoch 80 - iter 216/274 - loss 0.01827311 - samples/sec: 74.03 - lr: 0.050000 +2022-11-01 16:21:42,235 epoch 80 - iter 243/274 - loss 0.01796925 - samples/sec: 63.73 - lr: 0.050000 +2022-11-01 16:21:54,314 epoch 80 - iter 270/274 - loss 0.01791834 - samples/sec: 71.55 - lr: 0.050000 +2022-11-01 16:21:56,353 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:21:56,353 EPOCH 80 done: loss 0.0180 - lr 0.050000 +2022-11-01 16:22:21,823 Evaluating as a multi-label problem: False +2022-11-01 16:22:21,839 TEST : loss 0.03157917782664299 - f1-score (micro avg) 0.8551 +2022-11-01 16:22:21,892 BAD EPOCHS (no improvement): 2 +2022-11-01 16:22:21,984 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:22:34,097 epoch 81 - iter 27/274 - loss 0.01705883 - samples/sec: 71.36 - lr: 0.050000 +2022-11-01 16:22:45,629 epoch 81 - iter 54/274 - loss 0.01676405 - samples/sec: 74.94 - lr: 0.050000 +2022-11-01 16:22:57,336 epoch 81 - iter 81/274 - loss 0.01739874 - samples/sec: 73.83 - lr: 0.050000 +2022-11-01 16:23:08,562 epoch 81 - iter 108/274 - loss 0.01762212 - samples/sec: 76.98 - lr: 0.050000 +2022-11-01 16:23:21,574 epoch 81 - iter 135/274 - loss 0.01782749 - samples/sec: 66.42 - lr: 0.050000 +2022-11-01 16:23:35,270 epoch 81 - iter 162/274 - loss 0.01828249 - samples/sec: 63.10 - lr: 0.050000 +2022-11-01 16:23:48,300 epoch 81 - iter 189/274 - loss 0.01813256 - samples/sec: 66.32 - lr: 0.050000 +2022-11-01 16:24:01,404 epoch 81 - iter 216/274 - loss 0.01802512 - samples/sec: 65.95 - lr: 0.050000 +2022-11-01 16:24:12,505 epoch 81 - iter 243/274 - loss 0.01793248 - samples/sec: 77.85 - lr: 0.050000 +2022-11-01 16:24:24,473 epoch 81 - iter 270/274 - loss 0.01780714 - samples/sec: 72.21 - lr: 0.050000 +2022-11-01 16:24:26,323 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:24:26,323 EPOCH 81 done: loss 0.0179 - lr 0.050000 +2022-11-01 16:24:51,950 Evaluating as a multi-label problem: False +2022-11-01 16:24:51,966 TEST : loss 0.029629342257976532 - f1-score (micro avg) 0.8565 +2022-11-01 16:24:52,017 BAD EPOCHS (no improvement): 3 +2022-11-01 16:24:52,108 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:25:03,673 epoch 82 - iter 27/274 - loss 0.01517411 - samples/sec: 74.73 - lr: 0.050000 +2022-11-01 16:25:15,248 epoch 82 - iter 54/274 - loss 0.01566208 - samples/sec: 74.67 - lr: 0.050000 +2022-11-01 16:25:28,531 epoch 82 - iter 81/274 - loss 0.01767380 - samples/sec: 65.06 - lr: 0.050000 +2022-11-01 16:25:40,413 epoch 82 - iter 108/274 - loss 0.01710010 - samples/sec: 72.74 - lr: 0.050000 +2022-11-01 16:25:52,805 epoch 82 - iter 135/274 - loss 0.01665061 - samples/sec: 69.74 - lr: 0.050000 +2022-11-01 16:26:05,721 epoch 82 - iter 162/274 - loss 0.01717756 - samples/sec: 66.91 - lr: 0.050000 +2022-11-01 16:26:18,213 epoch 82 - iter 189/274 - loss 0.01790767 - samples/sec: 69.18 - lr: 0.050000 +2022-11-01 16:26:30,435 epoch 82 - iter 216/274 - loss 0.01790503 - samples/sec: 70.71 - lr: 0.050000 +2022-11-01 16:26:44,476 epoch 82 - iter 243/274 - loss 0.01773968 - samples/sec: 61.55 - lr: 0.050000 +2022-11-01 16:26:56,279 epoch 82 - iter 270/274 - loss 0.01752431 - samples/sec: 73.22 - lr: 0.050000 +2022-11-01 16:26:57,790 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:26:57,790 EPOCH 82 done: loss 0.0176 - lr 0.050000 +2022-11-01 16:27:23,088 Evaluating as a multi-label problem: False +2022-11-01 16:27:23,103 TEST : loss 0.02843180112540722 - f1-score (micro avg) 0.8544 +2022-11-01 16:27:23,156 Epoch 82: reducing learning rate of group 0 to 2.5000e-02. +2022-11-01 16:27:23,156 BAD EPOCHS (no improvement): 4 +2022-11-01 16:27:23,248 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:27:35,196 epoch 83 - iter 27/274 - loss 0.01636089 - samples/sec: 72.33 - lr: 0.025000 +2022-11-01 16:27:46,808 epoch 83 - iter 54/274 - loss 0.01606208 - samples/sec: 74.43 - lr: 0.025000 +2022-11-01 16:27:59,607 epoch 83 - iter 81/274 - loss 0.01687172 - samples/sec: 67.52 - lr: 0.025000 +2022-11-01 16:28:12,576 epoch 83 - iter 108/274 - loss 0.01773665 - samples/sec: 66.64 - lr: 0.025000 +2022-11-01 16:28:25,607 epoch 83 - iter 135/274 - loss 0.01707393 - samples/sec: 66.32 - lr: 0.025000 +2022-11-01 16:28:37,893 epoch 83 - iter 162/274 - loss 0.01671065 - samples/sec: 70.35 - lr: 0.025000 +2022-11-01 16:28:50,691 epoch 83 - iter 189/274 - loss 0.01697125 - samples/sec: 67.53 - lr: 0.025000 +2022-11-01 16:29:03,462 epoch 83 - iter 216/274 - loss 0.01688751 - samples/sec: 67.67 - lr: 0.025000 +2022-11-01 16:29:15,237 epoch 83 - iter 243/274 - loss 0.01724621 - samples/sec: 73.39 - lr: 0.025000 +2022-11-01 16:29:27,912 epoch 83 - iter 270/274 - loss 0.01744322 - samples/sec: 68.18 - lr: 0.025000 +2022-11-01 16:29:29,629 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:29:29,629 EPOCH 83 done: loss 0.0173 - lr 0.025000 +2022-11-01 16:29:54,787 Evaluating as a multi-label problem: False +2022-11-01 16:29:54,803 TEST : loss 0.029316166415810585 - f1-score (micro avg) 0.8533 +2022-11-01 16:29:54,856 BAD EPOCHS (no improvement): 1 +2022-11-01 16:29:54,951 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:30:06,126 epoch 84 - iter 27/274 - loss 0.01576658 - samples/sec: 77.34 - lr: 0.025000 +2022-11-01 16:30:18,356 epoch 84 - iter 54/274 - loss 0.01510948 - samples/sec: 70.67 - lr: 0.025000 +2022-11-01 16:30:30,897 epoch 84 - iter 81/274 - loss 0.01509003 - samples/sec: 68.91 - lr: 0.025000 +2022-11-01 16:30:44,239 epoch 84 - iter 108/274 - loss 0.01485943 - samples/sec: 64.77 - lr: 0.025000 +2022-11-01 16:30:57,506 epoch 84 - iter 135/274 - loss 0.01553865 - samples/sec: 65.14 - lr: 0.025000 +2022-11-01 16:31:08,699 epoch 84 - iter 162/274 - loss 0.01580709 - samples/sec: 77.21 - lr: 0.025000 +2022-11-01 16:31:21,826 epoch 84 - iter 189/274 - loss 0.01591768 - samples/sec: 65.84 - lr: 0.025000 +2022-11-01 16:31:35,047 epoch 84 - iter 216/274 - loss 0.01610133 - samples/sec: 65.36 - lr: 0.025000 +2022-11-01 16:31:47,076 epoch 84 - iter 243/274 - loss 0.01600053 - samples/sec: 71.85 - lr: 0.025000 +2022-11-01 16:31:59,719 epoch 84 - iter 270/274 - loss 0.01628348 - samples/sec: 68.36 - lr: 0.025000 +2022-11-01 16:32:01,717 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:32:01,717 EPOCH 84 done: loss 0.0164 - lr 0.025000 +2022-11-01 16:32:27,343 Evaluating as a multi-label problem: False +2022-11-01 16:32:27,359 TEST : loss 0.029401035979390144 - f1-score (micro avg) 0.8506 +2022-11-01 16:32:27,411 BAD EPOCHS (no improvement): 0 +2022-11-01 16:32:27,507 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:32:39,216 epoch 85 - iter 27/274 - loss 0.01603222 - samples/sec: 73.81 - lr: 0.025000 +2022-11-01 16:32:51,063 epoch 85 - iter 54/274 - loss 0.01741225 - samples/sec: 72.95 - lr: 0.025000 +2022-11-01 16:33:04,348 epoch 85 - iter 81/274 - loss 0.01696731 - samples/sec: 65.05 - lr: 0.025000 +2022-11-01 16:33:17,167 epoch 85 - iter 108/274 - loss 0.01676102 - samples/sec: 67.42 - lr: 0.025000 +2022-11-01 16:33:30,885 epoch 85 - iter 135/274 - loss 0.01643452 - samples/sec: 63.00 - lr: 0.025000 +2022-11-01 16:33:42,958 epoch 85 - iter 162/274 - loss 0.01683062 - samples/sec: 71.58 - lr: 0.025000 +2022-11-01 16:33:54,584 epoch 85 - iter 189/274 - loss 0.01661397 - samples/sec: 74.34 - lr: 0.025000 +2022-11-01 16:34:08,124 epoch 85 - iter 216/274 - loss 0.01674394 - samples/sec: 63.83 - lr: 0.025000 +2022-11-01 16:34:19,185 epoch 85 - iter 243/274 - loss 0.01673404 - samples/sec: 78.14 - lr: 0.025000 +2022-11-01 16:34:30,584 epoch 85 - iter 270/274 - loss 0.01678524 - samples/sec: 75.82 - lr: 0.025000 +2022-11-01 16:34:32,416 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:34:32,416 EPOCH 85 done: loss 0.0167 - lr 0.025000 +2022-11-01 16:34:57,702 Evaluating as a multi-label problem: False +2022-11-01 16:34:57,717 TEST : loss 0.030953796580433846 - f1-score (micro avg) 0.8556 +2022-11-01 16:34:57,769 BAD EPOCHS (no improvement): 1 +2022-11-01 16:34:57,860 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:35:10,313 epoch 86 - iter 27/274 - loss 0.01832310 - samples/sec: 69.40 - lr: 0.025000 +2022-11-01 16:35:24,124 epoch 86 - iter 54/274 - loss 0.01662775 - samples/sec: 62.57 - lr: 0.025000 +2022-11-01 16:35:35,622 epoch 86 - iter 81/274 - loss 0.01593853 - samples/sec: 75.17 - lr: 0.025000 +2022-11-01 16:35:48,105 epoch 86 - iter 108/274 - loss 0.01677397 - samples/sec: 69.23 - lr: 0.025000 +2022-11-01 16:35:59,618 epoch 86 - iter 135/274 - loss 0.01677152 - samples/sec: 75.07 - lr: 0.025000 +2022-11-01 16:36:11,947 epoch 86 - iter 162/274 - loss 0.01687084 - samples/sec: 70.10 - lr: 0.025000 +2022-11-01 16:36:25,305 epoch 86 - iter 189/274 - loss 0.01703050 - samples/sec: 64.70 - lr: 0.025000 +2022-11-01 16:36:37,864 epoch 86 - iter 216/274 - loss 0.01682995 - samples/sec: 68.81 - lr: 0.025000 +2022-11-01 16:36:48,783 epoch 86 - iter 243/274 - loss 0.01675319 - samples/sec: 79.15 - lr: 0.025000 +2022-11-01 16:36:59,918 epoch 86 - iter 270/274 - loss 0.01679931 - samples/sec: 77.62 - lr: 0.025000 +2022-11-01 16:37:01,938 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:37:01,938 EPOCH 86 done: loss 0.0170 - lr 0.025000 +2022-11-01 16:37:27,319 Evaluating as a multi-label problem: False +2022-11-01 16:37:27,335 TEST : loss 0.030635029077529907 - f1-score (micro avg) 0.8537 +2022-11-01 16:37:27,388 BAD EPOCHS (no improvement): 2 +2022-11-01 16:37:27,480 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:37:39,899 epoch 87 - iter 27/274 - loss 0.01457488 - samples/sec: 69.60 - lr: 0.025000 +2022-11-01 16:37:53,247 epoch 87 - iter 54/274 - loss 0.01425651 - samples/sec: 64.74 - lr: 0.025000 +2022-11-01 16:38:06,024 epoch 87 - iter 81/274 - loss 0.01547111 - samples/sec: 67.64 - lr: 0.025000 +2022-11-01 16:38:19,260 epoch 87 - iter 108/274 - loss 0.01529546 - samples/sec: 65.29 - lr: 0.025000 +2022-11-01 16:38:31,312 epoch 87 - iter 135/274 - loss 0.01584319 - samples/sec: 71.71 - lr: 0.025000 +2022-11-01 16:38:43,662 epoch 87 - iter 162/274 - loss 0.01590420 - samples/sec: 69.98 - lr: 0.025000 +2022-11-01 16:38:56,177 epoch 87 - iter 189/274 - loss 0.01631382 - samples/sec: 69.05 - lr: 0.025000 +2022-11-01 16:39:08,261 epoch 87 - iter 216/274 - loss 0.01628017 - samples/sec: 71.52 - lr: 0.025000 +2022-11-01 16:39:20,371 epoch 87 - iter 243/274 - loss 0.01615643 - samples/sec: 71.37 - lr: 0.025000 +2022-11-01 16:39:33,177 epoch 87 - iter 270/274 - loss 0.01590582 - samples/sec: 67.48 - lr: 0.025000 +2022-11-01 16:39:34,790 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:39:34,790 EPOCH 87 done: loss 0.0159 - lr 0.025000 +2022-11-01 16:40:00,078 Evaluating as a multi-label problem: False +2022-11-01 16:40:00,093 TEST : loss 0.03055056370794773 - f1-score (micro avg) 0.8535 +2022-11-01 16:40:00,146 BAD EPOCHS (no improvement): 0 +2022-11-01 16:40:00,238 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:40:11,140 epoch 88 - iter 27/274 - loss 0.01375907 - samples/sec: 79.28 - lr: 0.025000 +2022-11-01 16:40:24,674 epoch 88 - iter 54/274 - loss 0.01666760 - samples/sec: 63.86 - lr: 0.025000 +2022-11-01 16:40:36,121 epoch 88 - iter 81/274 - loss 0.01668721 - samples/sec: 75.50 - lr: 0.025000 +2022-11-01 16:40:48,625 epoch 88 - iter 108/274 - loss 0.01569771 - samples/sec: 69.12 - lr: 0.025000 +2022-11-01 16:41:02,221 epoch 88 - iter 135/274 - loss 0.01541809 - samples/sec: 63.56 - lr: 0.025000 +2022-11-01 16:41:13,833 epoch 88 - iter 162/274 - loss 0.01572390 - samples/sec: 74.43 - lr: 0.025000 +2022-11-01 16:41:26,394 epoch 88 - iter 189/274 - loss 0.01613422 - samples/sec: 68.80 - lr: 0.025000 +2022-11-01 16:41:39,138 epoch 88 - iter 216/274 - loss 0.01597918 - samples/sec: 67.81 - lr: 0.025000 +2022-11-01 16:41:50,987 epoch 88 - iter 243/274 - loss 0.01610632 - samples/sec: 72.94 - lr: 0.025000 +2022-11-01 16:42:04,017 epoch 88 - iter 270/274 - loss 0.01642128 - samples/sec: 66.33 - lr: 0.025000 +2022-11-01 16:42:05,883 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:42:05,883 EPOCH 88 done: loss 0.0166 - lr 0.025000 +2022-11-01 16:42:30,656 Evaluating as a multi-label problem: False +2022-11-01 16:42:30,672 TEST : loss 0.029628725722432137 - f1-score (micro avg) 0.8577 +2022-11-01 16:42:30,726 BAD EPOCHS (no improvement): 1 +2022-11-01 16:42:30,799 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:42:43,593 epoch 89 - iter 27/274 - loss 0.01806551 - samples/sec: 67.55 - lr: 0.025000 +2022-11-01 16:42:56,549 epoch 89 - iter 54/274 - loss 0.01773860 - samples/sec: 66.70 - lr: 0.025000 +2022-11-01 16:43:07,563 epoch 89 - iter 81/274 - loss 0.01752078 - samples/sec: 78.47 - lr: 0.025000 +2022-11-01 16:43:18,722 epoch 89 - iter 108/274 - loss 0.01689594 - samples/sec: 77.45 - lr: 0.025000 +2022-11-01 16:43:31,342 epoch 89 - iter 135/274 - loss 0.01681539 - samples/sec: 68.48 - lr: 0.025000 +2022-11-01 16:43:43,326 epoch 89 - iter 162/274 - loss 0.01672993 - samples/sec: 72.12 - lr: 0.025000 +2022-11-01 16:43:55,437 epoch 89 - iter 189/274 - loss 0.01699377 - samples/sec: 71.36 - lr: 0.025000 +2022-11-01 16:44:07,633 epoch 89 - iter 216/274 - loss 0.01664312 - samples/sec: 70.86 - lr: 0.025000 +2022-11-01 16:44:21,310 epoch 89 - iter 243/274 - loss 0.01652580 - samples/sec: 63.19 - lr: 0.025000 +2022-11-01 16:44:34,524 epoch 89 - iter 270/274 - loss 0.01646223 - samples/sec: 65.40 - lr: 0.025000 +2022-11-01 16:44:36,018 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:44:36,018 EPOCH 89 done: loss 0.0164 - lr 0.025000 +2022-11-01 16:45:01,028 Evaluating as a multi-label problem: False +2022-11-01 16:45:01,044 TEST : loss 0.030412347987294197 - f1-score (micro avg) 0.8557 +2022-11-01 16:45:01,101 BAD EPOCHS (no improvement): 2 +2022-11-01 16:45:01,197 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:45:13,274 epoch 90 - iter 27/274 - loss 0.01564131 - samples/sec: 71.56 - lr: 0.025000 +2022-11-01 16:45:25,179 epoch 90 - iter 54/274 - loss 0.01582138 - samples/sec: 72.60 - lr: 0.025000 +2022-11-01 16:45:37,427 epoch 90 - iter 81/274 - loss 0.01540488 - samples/sec: 70.56 - lr: 0.025000 +2022-11-01 16:45:48,993 epoch 90 - iter 108/274 - loss 0.01637324 - samples/sec: 74.73 - lr: 0.025000 +2022-11-01 16:46:01,317 epoch 90 - iter 135/274 - loss 0.01632562 - samples/sec: 70.13 - lr: 0.025000 +2022-11-01 16:46:13,570 epoch 90 - iter 162/274 - loss 0.01599840 - samples/sec: 70.53 - lr: 0.025000 +2022-11-01 16:46:26,019 epoch 90 - iter 189/274 - loss 0.01599910 - samples/sec: 69.43 - lr: 0.025000 +2022-11-01 16:46:38,827 epoch 90 - iter 216/274 - loss 0.01613755 - samples/sec: 67.47 - lr: 0.025000 +2022-11-01 16:46:50,421 epoch 90 - iter 243/274 - loss 0.01621818 - samples/sec: 74.55 - lr: 0.025000 +2022-11-01 16:47:03,939 epoch 90 - iter 270/274 - loss 0.01603622 - samples/sec: 63.93 - lr: 0.025000 +2022-11-01 16:47:06,316 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:47:06,316 EPOCH 90 done: loss 0.0160 - lr 0.025000 +2022-11-01 16:47:31,676 Evaluating as a multi-label problem: False +2022-11-01 16:47:31,692 TEST : loss 0.029919512569904327 - f1-score (micro avg) 0.8499 +2022-11-01 16:47:31,746 BAD EPOCHS (no improvement): 3 +2022-11-01 16:47:31,838 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:47:44,697 epoch 91 - iter 27/274 - loss 0.01229596 - samples/sec: 67.21 - lr: 0.025000 +2022-11-01 16:47:57,004 epoch 91 - iter 54/274 - loss 0.01415102 - samples/sec: 70.22 - lr: 0.025000 +2022-11-01 16:48:09,090 epoch 91 - iter 81/274 - loss 0.01421652 - samples/sec: 71.50 - lr: 0.025000 +2022-11-01 16:48:21,585 epoch 91 - iter 108/274 - loss 0.01502545 - samples/sec: 69.17 - lr: 0.025000 +2022-11-01 16:48:35,360 epoch 91 - iter 135/274 - loss 0.01534741 - samples/sec: 62.74 - lr: 0.025000 +2022-11-01 16:48:47,558 epoch 91 - iter 162/274 - loss 0.01576136 - samples/sec: 70.85 - lr: 0.025000 +2022-11-01 16:49:00,013 epoch 91 - iter 189/274 - loss 0.01573564 - samples/sec: 69.39 - lr: 0.025000 +2022-11-01 16:49:12,613 epoch 91 - iter 216/274 - loss 0.01610894 - samples/sec: 68.59 - lr: 0.025000 +2022-11-01 16:49:23,671 epoch 91 - iter 243/274 - loss 0.01583706 - samples/sec: 78.15 - lr: 0.025000 +2022-11-01 16:49:37,477 epoch 91 - iter 270/274 - loss 0.01585399 - samples/sec: 62.60 - lr: 0.025000 +2022-11-01 16:49:39,134 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:49:39,135 EPOCH 91 done: loss 0.0158 - lr 0.025000 +2022-11-01 16:50:04,527 Evaluating as a multi-label problem: False +2022-11-01 16:50:04,542 TEST : loss 0.029802754521369934 - f1-score (micro avg) 0.8562 +2022-11-01 16:50:04,594 BAD EPOCHS (no improvement): 0 +2022-11-01 16:50:04,667 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:50:17,801 epoch 92 - iter 27/274 - loss 0.01424113 - samples/sec: 65.80 - lr: 0.025000 +2022-11-01 16:50:30,363 epoch 92 - iter 54/274 - loss 0.01557183 - samples/sec: 68.80 - lr: 0.025000 +2022-11-01 16:50:43,821 epoch 92 - iter 81/274 - loss 0.01633458 - samples/sec: 64.21 - lr: 0.025000 +2022-11-01 16:50:55,674 epoch 92 - iter 108/274 - loss 0.01687727 - samples/sec: 72.92 - lr: 0.025000 +2022-11-01 16:51:08,718 epoch 92 - iter 135/274 - loss 0.01594242 - samples/sec: 66.25 - lr: 0.025000 +2022-11-01 16:51:20,596 epoch 92 - iter 162/274 - loss 0.01612769 - samples/sec: 72.76 - lr: 0.025000 +2022-11-01 16:51:32,683 epoch 92 - iter 189/274 - loss 0.01619242 - samples/sec: 71.50 - lr: 0.025000 +2022-11-01 16:51:45,275 epoch 92 - iter 216/274 - loss 0.01641394 - samples/sec: 68.63 - lr: 0.025000 +2022-11-01 16:51:57,544 epoch 92 - iter 243/274 - loss 0.01626312 - samples/sec: 70.44 - lr: 0.025000 +2022-11-01 16:52:09,360 epoch 92 - iter 270/274 - loss 0.01581703 - samples/sec: 73.14 - lr: 0.025000 +2022-11-01 16:52:11,253 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:52:11,254 EPOCH 92 done: loss 0.0158 - lr 0.025000 +2022-11-01 16:52:36,332 Evaluating as a multi-label problem: False +2022-11-01 16:52:36,347 TEST : loss 0.031193019822239876 - f1-score (micro avg) 0.852 +2022-11-01 16:52:36,399 BAD EPOCHS (no improvement): 0 +2022-11-01 16:52:36,495 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:52:47,868 epoch 93 - iter 27/274 - loss 0.01514042 - samples/sec: 75.99 - lr: 0.025000 +2022-11-01 16:52:59,621 epoch 93 - iter 54/274 - loss 0.01608344 - samples/sec: 73.54 - lr: 0.025000 +2022-11-01 16:53:12,802 epoch 93 - iter 81/274 - loss 0.01633994 - samples/sec: 65.56 - lr: 0.025000 +2022-11-01 16:53:26,430 epoch 93 - iter 108/274 - loss 0.01694982 - samples/sec: 63.41 - lr: 0.025000 +2022-11-01 16:53:39,222 epoch 93 - iter 135/274 - loss 0.01595774 - samples/sec: 67.56 - lr: 0.025000 +2022-11-01 16:53:51,426 epoch 93 - iter 162/274 - loss 0.01608164 - samples/sec: 70.81 - lr: 0.025000 +2022-11-01 16:54:03,857 epoch 93 - iter 189/274 - loss 0.01616575 - samples/sec: 69.52 - lr: 0.025000 +2022-11-01 16:54:16,142 epoch 93 - iter 216/274 - loss 0.01606524 - samples/sec: 70.35 - lr: 0.025000 +2022-11-01 16:54:28,972 epoch 93 - iter 243/274 - loss 0.01602004 - samples/sec: 67.36 - lr: 0.025000 +2022-11-01 16:54:41,141 epoch 93 - iter 270/274 - loss 0.01552356 - samples/sec: 71.02 - lr: 0.025000 +2022-11-01 16:54:42,851 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:54:42,852 EPOCH 93 done: loss 0.0155 - lr 0.025000 +2022-11-01 16:55:08,139 Evaluating as a multi-label problem: False +2022-11-01 16:55:08,154 TEST : loss 0.03080672211945057 - f1-score (micro avg) 0.8551 +2022-11-01 16:55:08,208 BAD EPOCHS (no improvement): 0 +2022-11-01 16:55:08,300 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:55:20,564 epoch 94 - iter 27/274 - loss 0.01833471 - samples/sec: 70.47 - lr: 0.025000 +2022-11-01 16:55:33,934 epoch 94 - iter 54/274 - loss 0.01785616 - samples/sec: 64.64 - lr: 0.025000 +2022-11-01 16:55:46,048 epoch 94 - iter 81/274 - loss 0.01756784 - samples/sec: 71.34 - lr: 0.025000 +2022-11-01 16:55:59,581 epoch 94 - iter 108/274 - loss 0.01710252 - samples/sec: 63.86 - lr: 0.025000 +2022-11-01 16:56:11,194 epoch 94 - iter 135/274 - loss 0.01640143 - samples/sec: 74.42 - lr: 0.025000 +2022-11-01 16:56:24,892 epoch 94 - iter 162/274 - loss 0.01595753 - samples/sec: 63.09 - lr: 0.025000 +2022-11-01 16:56:37,887 epoch 94 - iter 189/274 - loss 0.01589872 - samples/sec: 66.50 - lr: 0.025000 +2022-11-01 16:56:48,846 epoch 94 - iter 216/274 - loss 0.01636018 - samples/sec: 78.87 - lr: 0.025000 +2022-11-01 16:57:00,547 epoch 94 - iter 243/274 - loss 0.01639244 - samples/sec: 73.86 - lr: 0.025000 +2022-11-01 16:57:12,390 epoch 94 - iter 270/274 - loss 0.01644462 - samples/sec: 72.98 - lr: 0.025000 +2022-11-01 16:57:13,913 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:57:13,913 EPOCH 94 done: loss 0.0164 - lr 0.025000 +2022-11-01 16:57:39,655 Evaluating as a multi-label problem: False +2022-11-01 16:57:39,671 TEST : loss 0.030662264674901962 - f1-score (micro avg) 0.8553 +2022-11-01 16:57:39,722 BAD EPOCHS (no improvement): 1 +2022-11-01 16:57:39,814 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:57:52,162 epoch 95 - iter 27/274 - loss 0.01688978 - samples/sec: 70.00 - lr: 0.025000 +2022-11-01 16:58:05,022 epoch 95 - iter 54/274 - loss 0.01534652 - samples/sec: 67.20 - lr: 0.025000 +2022-11-01 16:58:16,780 epoch 95 - iter 81/274 - loss 0.01469917 - samples/sec: 73.50 - lr: 0.025000 +2022-11-01 16:58:28,997 epoch 95 - iter 108/274 - loss 0.01583896 - samples/sec: 70.74 - lr: 0.025000 +2022-11-01 16:58:40,603 epoch 95 - iter 135/274 - loss 0.01604019 - samples/sec: 74.46 - lr: 0.025000 +2022-11-01 16:58:52,272 epoch 95 - iter 162/274 - loss 0.01560099 - samples/sec: 74.07 - lr: 0.025000 +2022-11-01 16:59:05,106 epoch 95 - iter 189/274 - loss 0.01566128 - samples/sec: 67.33 - lr: 0.025000 +2022-11-01 16:59:16,292 epoch 95 - iter 216/274 - loss 0.01538281 - samples/sec: 77.27 - lr: 0.025000 +2022-11-01 16:59:30,105 epoch 95 - iter 243/274 - loss 0.01595071 - samples/sec: 62.56 - lr: 0.025000 +2022-11-01 16:59:42,530 epoch 95 - iter 270/274 - loss 0.01587799 - samples/sec: 69.55 - lr: 0.025000 +2022-11-01 16:59:44,417 ---------------------------------------------------------------------------------------------------- +2022-11-01 16:59:44,417 EPOCH 95 done: loss 0.0158 - lr 0.025000 +2022-11-01 17:00:09,855 Evaluating as a multi-label problem: False +2022-11-01 17:00:09,870 TEST : loss 0.030545346438884735 - f1-score (micro avg) 0.8545 +2022-11-01 17:00:09,923 BAD EPOCHS (no improvement): 2 +2022-11-01 17:00:10,015 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:00:23,419 epoch 96 - iter 27/274 - loss 0.01242489 - samples/sec: 64.48 - lr: 0.025000 +2022-11-01 17:00:35,238 epoch 96 - iter 54/274 - loss 0.01448475 - samples/sec: 73.12 - lr: 0.025000 +2022-11-01 17:00:48,022 epoch 96 - iter 81/274 - loss 0.01561201 - samples/sec: 67.60 - lr: 0.025000 +2022-11-01 17:01:00,345 epoch 96 - iter 108/274 - loss 0.01621416 - samples/sec: 70.13 - lr: 0.025000 +2022-11-01 17:01:13,192 epoch 96 - iter 135/274 - loss 0.01632154 - samples/sec: 67.27 - lr: 0.025000 +2022-11-01 17:01:24,671 epoch 96 - iter 162/274 - loss 0.01572867 - samples/sec: 75.29 - lr: 0.025000 +2022-11-01 17:01:36,808 epoch 96 - iter 189/274 - loss 0.01559104 - samples/sec: 71.21 - lr: 0.025000 +2022-11-01 17:01:50,027 epoch 96 - iter 216/274 - loss 0.01589267 - samples/sec: 65.38 - lr: 0.025000 +2022-11-01 17:02:03,405 epoch 96 - iter 243/274 - loss 0.01604069 - samples/sec: 64.60 - lr: 0.025000 +2022-11-01 17:02:14,570 epoch 96 - iter 270/274 - loss 0.01609900 - samples/sec: 77.40 - lr: 0.025000 +2022-11-01 17:02:16,458 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:02:16,458 EPOCH 96 done: loss 0.0161 - lr 0.025000 +2022-11-01 17:02:41,425 Evaluating as a multi-label problem: False +2022-11-01 17:02:41,440 TEST : loss 0.031394150108098984 - f1-score (micro avg) 0.8584 +2022-11-01 17:02:41,493 BAD EPOCHS (no improvement): 3 +2022-11-01 17:02:41,585 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:02:54,710 epoch 97 - iter 27/274 - loss 0.01492072 - samples/sec: 65.85 - lr: 0.025000 +2022-11-01 17:03:05,770 epoch 97 - iter 54/274 - loss 0.01396878 - samples/sec: 78.14 - lr: 0.025000 +2022-11-01 17:03:17,619 epoch 97 - iter 81/274 - loss 0.01413726 - samples/sec: 72.94 - lr: 0.025000 +2022-11-01 17:03:31,104 epoch 97 - iter 108/274 - loss 0.01427275 - samples/sec: 64.09 - lr: 0.025000 +2022-11-01 17:03:43,566 epoch 97 - iter 135/274 - loss 0.01438317 - samples/sec: 69.35 - lr: 0.025000 +2022-11-01 17:03:56,029 epoch 97 - iter 162/274 - loss 0.01508738 - samples/sec: 69.34 - lr: 0.025000 +2022-11-01 17:04:07,750 epoch 97 - iter 189/274 - loss 0.01543147 - samples/sec: 73.73 - lr: 0.025000 +2022-11-01 17:04:21,673 epoch 97 - iter 216/274 - loss 0.01514577 - samples/sec: 62.07 - lr: 0.025000 +2022-11-01 17:04:35,162 epoch 97 - iter 243/274 - loss 0.01554633 - samples/sec: 64.07 - lr: 0.025000 +2022-11-01 17:04:47,543 epoch 97 - iter 270/274 - loss 0.01594045 - samples/sec: 69.80 - lr: 0.025000 +2022-11-01 17:04:49,266 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:04:49,267 EPOCH 97 done: loss 0.0161 - lr 0.025000 +2022-11-01 17:05:14,559 Evaluating as a multi-label problem: False +2022-11-01 17:05:14,575 TEST : loss 0.031141091138124466 - f1-score (micro avg) 0.8548 +2022-11-01 17:05:14,626 Epoch 97: reducing learning rate of group 0 to 1.2500e-02. +2022-11-01 17:05:14,626 BAD EPOCHS (no improvement): 4 +2022-11-01 17:05:14,718 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:05:27,619 epoch 98 - iter 27/274 - loss 0.01684552 - samples/sec: 66.99 - lr: 0.012500 +2022-11-01 17:05:40,712 epoch 98 - iter 54/274 - loss 0.01617953 - samples/sec: 66.00 - lr: 0.012500 +2022-11-01 17:05:52,535 epoch 98 - iter 81/274 - loss 0.01694288 - samples/sec: 73.10 - lr: 0.012500 +2022-11-01 17:06:04,021 epoch 98 - iter 108/274 - loss 0.01581446 - samples/sec: 75.25 - lr: 0.012500 +2022-11-01 17:06:16,731 epoch 98 - iter 135/274 - loss 0.01504212 - samples/sec: 68.00 - lr: 0.012500 +2022-11-01 17:06:28,406 epoch 98 - iter 162/274 - loss 0.01514386 - samples/sec: 74.02 - lr: 0.012500 +2022-11-01 17:06:40,061 epoch 98 - iter 189/274 - loss 0.01497497 - samples/sec: 74.15 - lr: 0.012500 +2022-11-01 17:06:51,963 epoch 98 - iter 216/274 - loss 0.01510213 - samples/sec: 72.61 - lr: 0.012500 +2022-11-01 17:07:04,163 epoch 98 - iter 243/274 - loss 0.01520530 - samples/sec: 70.84 - lr: 0.012500 +2022-11-01 17:07:18,137 epoch 98 - iter 270/274 - loss 0.01495979 - samples/sec: 61.84 - lr: 0.012500 +2022-11-01 17:07:19,938 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:07:19,938 EPOCH 98 done: loss 0.0150 - lr 0.012500 +2022-11-01 17:07:45,296 Evaluating as a multi-label problem: False +2022-11-01 17:07:45,312 TEST : loss 0.0315224826335907 - f1-score (micro avg) 0.8517 +2022-11-01 17:07:45,364 BAD EPOCHS (no improvement): 0 +2022-11-01 17:07:45,457 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:07:59,107 epoch 99 - iter 27/274 - loss 0.01568841 - samples/sec: 63.31 - lr: 0.012500 +2022-11-01 17:08:11,036 epoch 99 - iter 54/274 - loss 0.01701872 - samples/sec: 72.45 - lr: 0.012500 +2022-11-01 17:08:22,893 epoch 99 - iter 81/274 - loss 0.01531658 - samples/sec: 72.89 - lr: 0.012500 +2022-11-01 17:08:34,443 epoch 99 - iter 108/274 - loss 0.01571024 - samples/sec: 74.83 - lr: 0.012500 +2022-11-01 17:08:45,990 epoch 99 - iter 135/274 - loss 0.01567341 - samples/sec: 74.85 - lr: 0.012500 +2022-11-01 17:08:58,358 epoch 99 - iter 162/274 - loss 0.01522725 - samples/sec: 69.88 - lr: 0.012500 +2022-11-01 17:09:10,655 epoch 99 - iter 189/274 - loss 0.01517455 - samples/sec: 70.28 - lr: 0.012500 +2022-11-01 17:09:24,581 epoch 99 - iter 216/274 - loss 0.01501352 - samples/sec: 62.06 - lr: 0.012500 +2022-11-01 17:09:36,581 epoch 99 - iter 243/274 - loss 0.01514386 - samples/sec: 72.02 - lr: 0.012500 +2022-11-01 17:09:48,961 epoch 99 - iter 270/274 - loss 0.01501936 - samples/sec: 69.81 - lr: 0.012500 +2022-11-01 17:09:50,696 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:09:50,696 EPOCH 99 done: loss 0.0149 - lr 0.012500 +2022-11-01 17:10:16,131 Evaluating as a multi-label problem: False +2022-11-01 17:10:16,146 TEST : loss 0.032214682549238205 - f1-score (micro avg) 0.8528 +2022-11-01 17:10:16,198 BAD EPOCHS (no improvement): 0 +2022-11-01 17:10:16,290 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:10:28,380 epoch 100 - iter 27/274 - loss 0.01049140 - samples/sec: 71.49 - lr: 0.012500 +2022-11-01 17:10:41,052 epoch 100 - iter 54/274 - loss 0.01500905 - samples/sec: 68.20 - lr: 0.012500 +2022-11-01 17:10:53,501 epoch 100 - iter 81/274 - loss 0.01512699 - samples/sec: 69.42 - lr: 0.012500 +2022-11-01 17:11:05,018 epoch 100 - iter 108/274 - loss 0.01472317 - samples/sec: 75.04 - lr: 0.012500 +2022-11-01 17:11:16,311 epoch 100 - iter 135/274 - loss 0.01471632 - samples/sec: 76.53 - lr: 0.012500 +2022-11-01 17:11:28,068 epoch 100 - iter 162/274 - loss 0.01508426 - samples/sec: 73.51 - lr: 0.012500 +2022-11-01 17:11:42,352 epoch 100 - iter 189/274 - loss 0.01528565 - samples/sec: 60.50 - lr: 0.012500 +2022-11-01 17:11:54,868 epoch 100 - iter 216/274 - loss 0.01551813 - samples/sec: 69.05 - lr: 0.012500 +2022-11-01 17:12:09,315 epoch 100 - iter 243/274 - loss 0.01560369 - samples/sec: 59.82 - lr: 0.012500 +2022-11-01 17:12:20,899 epoch 100 - iter 270/274 - loss 0.01542870 - samples/sec: 74.61 - lr: 0.012500 +2022-11-01 17:12:22,620 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:12:22,620 EPOCH 100 done: loss 0.0153 - lr 0.012500 +2022-11-01 17:12:47,951 Evaluating as a multi-label problem: False +2022-11-01 17:12:47,966 TEST : loss 0.03205437958240509 - f1-score (micro avg) 0.8544 +2022-11-01 17:12:48,018 BAD EPOCHS (no improvement): 1 +2022-11-01 17:12:48,109 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:13:00,180 epoch 101 - iter 27/274 - loss 0.01378529 - samples/sec: 71.60 - lr: 0.012500 +2022-11-01 17:13:12,215 epoch 101 - iter 54/274 - loss 0.01337199 - samples/sec: 71.81 - lr: 0.012500 +2022-11-01 17:13:25,504 epoch 101 - iter 81/274 - loss 0.01404534 - samples/sec: 65.03 - lr: 0.012500 +2022-11-01 17:13:36,981 epoch 101 - iter 108/274 - loss 0.01373175 - samples/sec: 75.30 - lr: 0.012500 +2022-11-01 17:13:48,891 epoch 101 - iter 135/274 - loss 0.01451741 - samples/sec: 72.56 - lr: 0.012500 +2022-11-01 17:14:01,244 epoch 101 - iter 162/274 - loss 0.01501925 - samples/sec: 69.96 - lr: 0.012500 +2022-11-01 17:14:14,210 epoch 101 - iter 189/274 - loss 0.01503842 - samples/sec: 66.65 - lr: 0.012500 +2022-11-01 17:14:26,461 epoch 101 - iter 216/274 - loss 0.01533271 - samples/sec: 70.55 - lr: 0.012500 +2022-11-01 17:14:38,050 epoch 101 - iter 243/274 - loss 0.01542822 - samples/sec: 74.57 - lr: 0.012500 +2022-11-01 17:14:52,728 epoch 101 - iter 270/274 - loss 0.01542944 - samples/sec: 58.88 - lr: 0.012500 +2022-11-01 17:14:54,387 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:14:54,387 EPOCH 101 done: loss 0.0153 - lr 0.012500 +2022-11-01 17:15:19,832 Evaluating as a multi-label problem: False +2022-11-01 17:15:19,847 TEST : loss 0.03180859610438347 - f1-score (micro avg) 0.8518 +2022-11-01 17:15:19,900 BAD EPOCHS (no improvement): 2 +2022-11-01 17:15:19,996 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:15:30,919 epoch 102 - iter 27/274 - loss 0.01367323 - samples/sec: 79.13 - lr: 0.012500 +2022-11-01 17:15:42,942 epoch 102 - iter 54/274 - loss 0.01496790 - samples/sec: 71.88 - lr: 0.012500 +2022-11-01 17:15:54,982 epoch 102 - iter 81/274 - loss 0.01427020 - samples/sec: 71.78 - lr: 0.012500 +2022-11-01 17:16:07,360 epoch 102 - iter 108/274 - loss 0.01451117 - samples/sec: 69.82 - lr: 0.012500 +2022-11-01 17:16:19,150 epoch 102 - iter 135/274 - loss 0.01477473 - samples/sec: 73.31 - lr: 0.012500 +2022-11-01 17:16:32,137 epoch 102 - iter 162/274 - loss 0.01509181 - samples/sec: 66.54 - lr: 0.012500 +2022-11-01 17:16:44,150 epoch 102 - iter 189/274 - loss 0.01558677 - samples/sec: 71.94 - lr: 0.012500 +2022-11-01 17:16:55,429 epoch 102 - iter 216/274 - loss 0.01557646 - samples/sec: 76.63 - lr: 0.012500 +2022-11-01 17:17:08,071 epoch 102 - iter 243/274 - loss 0.01558887 - samples/sec: 68.36 - lr: 0.012500 +2022-11-01 17:17:21,624 epoch 102 - iter 270/274 - loss 0.01573576 - samples/sec: 63.77 - lr: 0.012500 +2022-11-01 17:17:24,639 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:17:24,640 EPOCH 102 done: loss 0.0157 - lr 0.012500 +2022-11-01 17:17:49,335 Evaluating as a multi-label problem: False +2022-11-01 17:17:49,351 TEST : loss 0.03114163875579834 - f1-score (micro avg) 0.8522 +2022-11-01 17:17:49,402 BAD EPOCHS (no improvement): 3 +2022-11-01 17:17:49,497 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:18:01,427 epoch 103 - iter 27/274 - loss 0.01511439 - samples/sec: 72.45 - lr: 0.012500 +2022-11-01 17:18:13,288 epoch 103 - iter 54/274 - loss 0.01521225 - samples/sec: 72.87 - lr: 0.012500 +2022-11-01 17:18:27,608 epoch 103 - iter 81/274 - loss 0.01588243 - samples/sec: 60.35 - lr: 0.012500 +2022-11-01 17:18:40,062 epoch 103 - iter 108/274 - loss 0.01620946 - samples/sec: 69.39 - lr: 0.012500 +2022-11-01 17:18:53,137 epoch 103 - iter 135/274 - loss 0.01627265 - samples/sec: 66.10 - lr: 0.012500 +2022-11-01 17:19:05,918 epoch 103 - iter 162/274 - loss 0.01616743 - samples/sec: 67.62 - lr: 0.012500 +2022-11-01 17:19:18,579 epoch 103 - iter 189/274 - loss 0.01595910 - samples/sec: 68.26 - lr: 0.012500 +2022-11-01 17:19:30,844 epoch 103 - iter 216/274 - loss 0.01601796 - samples/sec: 70.46 - lr: 0.012500 +2022-11-01 17:19:42,438 epoch 103 - iter 243/274 - loss 0.01586805 - samples/sec: 74.54 - lr: 0.012500 +2022-11-01 17:19:54,280 epoch 103 - iter 270/274 - loss 0.01587716 - samples/sec: 72.98 - lr: 0.012500 +2022-11-01 17:19:55,910 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:19:55,910 EPOCH 103 done: loss 0.0159 - lr 0.012500 +2022-11-01 17:20:21,470 Evaluating as a multi-label problem: False +2022-11-01 17:20:21,486 TEST : loss 0.03149925917387009 - f1-score (micro avg) 0.8538 +2022-11-01 17:20:21,538 Epoch 103: reducing learning rate of group 0 to 6.2500e-03. +2022-11-01 17:20:21,539 BAD EPOCHS (no improvement): 4 +2022-11-01 17:20:21,631 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:20:34,090 epoch 104 - iter 27/274 - loss 0.01498141 - samples/sec: 69.37 - lr: 0.006250 +2022-11-01 17:20:46,629 epoch 104 - iter 54/274 - loss 0.01501934 - samples/sec: 68.92 - lr: 0.006250 +2022-11-01 17:20:57,980 epoch 104 - iter 81/274 - loss 0.01434988 - samples/sec: 76.14 - lr: 0.006250 +2022-11-01 17:21:09,792 epoch 104 - iter 108/274 - loss 0.01473952 - samples/sec: 73.17 - lr: 0.006250 +2022-11-01 17:21:23,026 epoch 104 - iter 135/274 - loss 0.01529435 - samples/sec: 65.30 - lr: 0.006250 +2022-11-01 17:21:36,383 epoch 104 - iter 162/274 - loss 0.01527378 - samples/sec: 64.70 - lr: 0.006250 +2022-11-01 17:21:50,064 epoch 104 - iter 189/274 - loss 0.01508563 - samples/sec: 63.17 - lr: 0.006250 +2022-11-01 17:22:02,774 epoch 104 - iter 216/274 - loss 0.01520574 - samples/sec: 68.00 - lr: 0.006250 +2022-11-01 17:22:14,747 epoch 104 - iter 243/274 - loss 0.01531841 - samples/sec: 72.18 - lr: 0.006250 +2022-11-01 17:22:25,810 epoch 104 - iter 270/274 - loss 0.01495468 - samples/sec: 78.12 - lr: 0.006250 +2022-11-01 17:22:27,314 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:22:27,314 EPOCH 104 done: loss 0.0150 - lr 0.006250 +2022-11-01 17:22:52,615 Evaluating as a multi-label problem: False +2022-11-01 17:22:52,631 TEST : loss 0.03160782903432846 - f1-score (micro avg) 0.8545 +2022-11-01 17:22:52,682 BAD EPOCHS (no improvement): 1 +2022-11-01 17:22:52,774 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:23:04,512 epoch 105 - iter 27/274 - loss 0.01478439 - samples/sec: 73.63 - lr: 0.006250 +2022-11-01 17:23:17,554 epoch 105 - iter 54/274 - loss 0.01580731 - samples/sec: 66.26 - lr: 0.006250 +2022-11-01 17:23:29,786 epoch 105 - iter 81/274 - loss 0.01527523 - samples/sec: 70.66 - lr: 0.006250 +2022-11-01 17:23:42,262 epoch 105 - iter 108/274 - loss 0.01556524 - samples/sec: 69.27 - lr: 0.006250 +2022-11-01 17:23:53,798 epoch 105 - iter 135/274 - loss 0.01510414 - samples/sec: 74.92 - lr: 0.006250 +2022-11-01 17:24:05,883 epoch 105 - iter 162/274 - loss 0.01499963 - samples/sec: 71.52 - lr: 0.006250 +2022-11-01 17:24:18,145 epoch 105 - iter 189/274 - loss 0.01459439 - samples/sec: 70.48 - lr: 0.006250 +2022-11-01 17:24:31,529 epoch 105 - iter 216/274 - loss 0.01450208 - samples/sec: 64.57 - lr: 0.006250 +2022-11-01 17:24:44,094 epoch 105 - iter 243/274 - loss 0.01431071 - samples/sec: 68.78 - lr: 0.006250 +2022-11-01 17:24:56,610 epoch 105 - iter 270/274 - loss 0.01451876 - samples/sec: 69.05 - lr: 0.006250 +2022-11-01 17:24:58,538 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:24:58,539 EPOCH 105 done: loss 0.0145 - lr 0.006250 +2022-11-01 17:25:24,716 Evaluating as a multi-label problem: False +2022-11-01 17:25:24,732 TEST : loss 0.031382638961076736 - f1-score (micro avg) 0.8549 +2022-11-01 17:25:24,783 BAD EPOCHS (no improvement): 0 +2022-11-01 17:25:24,878 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:25:37,729 epoch 106 - iter 27/274 - loss 0.01310063 - samples/sec: 67.26 - lr: 0.006250 +2022-11-01 17:25:49,473 epoch 106 - iter 54/274 - loss 0.01383816 - samples/sec: 73.59 - lr: 0.006250 +2022-11-01 17:26:02,132 epoch 106 - iter 81/274 - loss 0.01373350 - samples/sec: 68.27 - lr: 0.006250 +2022-11-01 17:26:14,016 epoch 106 - iter 108/274 - loss 0.01442718 - samples/sec: 72.72 - lr: 0.006250 +2022-11-01 17:26:26,053 epoch 106 - iter 135/274 - loss 0.01401087 - samples/sec: 71.80 - lr: 0.006250 +2022-11-01 17:26:38,918 epoch 106 - iter 162/274 - loss 0.01399659 - samples/sec: 67.18 - lr: 0.006250 +2022-11-01 17:26:51,716 epoch 106 - iter 189/274 - loss 0.01399994 - samples/sec: 67.53 - lr: 0.006250 +2022-11-01 17:27:04,149 epoch 106 - iter 216/274 - loss 0.01436065 - samples/sec: 69.51 - lr: 0.006250 +2022-11-01 17:27:16,644 epoch 106 - iter 243/274 - loss 0.01474534 - samples/sec: 69.17 - lr: 0.006250 +2022-11-01 17:27:28,686 epoch 106 - iter 270/274 - loss 0.01480237 - samples/sec: 71.77 - lr: 0.006250 +2022-11-01 17:27:30,054 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:27:30,054 EPOCH 106 done: loss 0.0147 - lr 0.006250 +2022-11-01 17:27:55,476 Evaluating as a multi-label problem: False +2022-11-01 17:27:55,492 TEST : loss 0.03141792118549347 - f1-score (micro avg) 0.8558 +2022-11-01 17:27:55,546 BAD EPOCHS (no improvement): 1 +2022-11-01 17:27:55,639 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:28:08,177 epoch 107 - iter 27/274 - loss 0.01872842 - samples/sec: 68.93 - lr: 0.006250 +2022-11-01 17:28:19,630 epoch 107 - iter 54/274 - loss 0.01616813 - samples/sec: 75.46 - lr: 0.006250 +2022-11-01 17:28:32,113 epoch 107 - iter 81/274 - loss 0.01536312 - samples/sec: 69.23 - lr: 0.006250 +2022-11-01 17:28:44,519 epoch 107 - iter 108/274 - loss 0.01581316 - samples/sec: 69.67 - lr: 0.006250 +2022-11-01 17:28:57,543 epoch 107 - iter 135/274 - loss 0.01573153 - samples/sec: 66.35 - lr: 0.006250 +2022-11-01 17:29:09,596 epoch 107 - iter 162/274 - loss 0.01590482 - samples/sec: 71.71 - lr: 0.006250 +2022-11-01 17:29:21,223 epoch 107 - iter 189/274 - loss 0.01568356 - samples/sec: 74.32 - lr: 0.006250 +2022-11-01 17:29:35,337 epoch 107 - iter 216/274 - loss 0.01557378 - samples/sec: 61.23 - lr: 0.006250 +2022-11-01 17:29:47,568 epoch 107 - iter 243/274 - loss 0.01547147 - samples/sec: 70.66 - lr: 0.006250 +2022-11-01 17:30:00,199 epoch 107 - iter 270/274 - loss 0.01556995 - samples/sec: 68.42 - lr: 0.006250 +2022-11-01 17:30:02,023 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:30:02,024 EPOCH 107 done: loss 0.0156 - lr 0.006250 +2022-11-01 17:30:26,714 Evaluating as a multi-label problem: False +2022-11-01 17:30:26,729 TEST : loss 0.031312357634305954 - f1-score (micro avg) 0.8558 +2022-11-01 17:30:26,780 BAD EPOCHS (no improvement): 2 +2022-11-01 17:30:26,872 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:30:39,718 epoch 108 - iter 27/274 - loss 0.01390738 - samples/sec: 67.28 - lr: 0.006250 +2022-11-01 17:30:52,052 epoch 108 - iter 54/274 - loss 0.01439151 - samples/sec: 70.07 - lr: 0.006250 +2022-11-01 17:31:05,111 epoch 108 - iter 81/274 - loss 0.01442134 - samples/sec: 66.17 - lr: 0.006250 +2022-11-01 17:31:16,827 epoch 108 - iter 108/274 - loss 0.01435974 - samples/sec: 73.77 - lr: 0.006250 +2022-11-01 17:31:29,153 epoch 108 - iter 135/274 - loss 0.01387339 - samples/sec: 70.11 - lr: 0.006250 +2022-11-01 17:31:43,801 epoch 108 - iter 162/274 - loss 0.01425564 - samples/sec: 59.00 - lr: 0.006250 +2022-11-01 17:31:55,727 epoch 108 - iter 189/274 - loss 0.01421163 - samples/sec: 72.46 - lr: 0.006250 +2022-11-01 17:32:07,607 epoch 108 - iter 216/274 - loss 0.01410484 - samples/sec: 72.75 - lr: 0.006250 +2022-11-01 17:32:20,751 epoch 108 - iter 243/274 - loss 0.01457425 - samples/sec: 65.75 - lr: 0.006250 +2022-11-01 17:32:32,581 epoch 108 - iter 270/274 - loss 0.01465172 - samples/sec: 73.05 - lr: 0.006250 +2022-11-01 17:32:34,099 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:32:34,100 EPOCH 108 done: loss 0.0148 - lr 0.006250 +2022-11-01 17:32:58,961 Evaluating as a multi-label problem: False +2022-11-01 17:32:58,977 TEST : loss 0.031135080382227898 - f1-score (micro avg) 0.8554 +2022-11-01 17:32:59,030 BAD EPOCHS (no improvement): 3 +2022-11-01 17:32:59,122 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:33:12,240 epoch 109 - iter 27/274 - loss 0.01912379 - samples/sec: 65.88 - lr: 0.006250 +2022-11-01 17:33:24,444 epoch 109 - iter 54/274 - loss 0.01804758 - samples/sec: 70.82 - lr: 0.006250 +2022-11-01 17:33:37,289 epoch 109 - iter 81/274 - loss 0.01646409 - samples/sec: 67.28 - lr: 0.006250 +2022-11-01 17:33:49,388 epoch 109 - iter 108/274 - loss 0.01560171 - samples/sec: 71.43 - lr: 0.006250 +2022-11-01 17:34:01,172 epoch 109 - iter 135/274 - loss 0.01511687 - samples/sec: 73.34 - lr: 0.006250 +2022-11-01 17:34:12,746 epoch 109 - iter 162/274 - loss 0.01504958 - samples/sec: 74.68 - lr: 0.006250 +2022-11-01 17:34:25,860 epoch 109 - iter 189/274 - loss 0.01522205 - samples/sec: 65.90 - lr: 0.006250 +2022-11-01 17:34:38,292 epoch 109 - iter 216/274 - loss 0.01524269 - samples/sec: 69.52 - lr: 0.006250 +2022-11-01 17:34:51,412 epoch 109 - iter 243/274 - loss 0.01492633 - samples/sec: 65.87 - lr: 0.006250 +2022-11-01 17:35:04,115 epoch 109 - iter 270/274 - loss 0.01465676 - samples/sec: 68.04 - lr: 0.006250 +2022-11-01 17:35:05,583 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:35:05,583 EPOCH 109 done: loss 0.0147 - lr 0.006250 +2022-11-01 17:35:30,502 Evaluating as a multi-label problem: False +2022-11-01 17:35:30,517 TEST : loss 0.031781088560819626 - f1-score (micro avg) 0.8552 +2022-11-01 17:35:30,570 Epoch 109: reducing learning rate of group 0 to 3.1250e-03. +2022-11-01 17:35:30,571 BAD EPOCHS (no improvement): 4 +2022-11-01 17:35:30,662 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:35:43,277 epoch 110 - iter 27/274 - loss 0.01618152 - samples/sec: 68.51 - lr: 0.003125 +2022-11-01 17:35:57,703 epoch 110 - iter 54/274 - loss 0.01398249 - samples/sec: 59.91 - lr: 0.003125 +2022-11-01 17:36:11,539 epoch 110 - iter 81/274 - loss 0.01436806 - samples/sec: 62.46 - lr: 0.003125 +2022-11-01 17:36:23,687 epoch 110 - iter 108/274 - loss 0.01402755 - samples/sec: 71.14 - lr: 0.003125 +2022-11-01 17:36:35,831 epoch 110 - iter 135/274 - loss 0.01429670 - samples/sec: 71.17 - lr: 0.003125 +2022-11-01 17:36:47,885 epoch 110 - iter 162/274 - loss 0.01429064 - samples/sec: 71.69 - lr: 0.003125 +2022-11-01 17:36:59,675 epoch 110 - iter 189/274 - loss 0.01471822 - samples/sec: 73.30 - lr: 0.003125 +2022-11-01 17:37:12,360 epoch 110 - iter 216/274 - loss 0.01430368 - samples/sec: 68.13 - lr: 0.003125 +2022-11-01 17:37:23,509 epoch 110 - iter 243/274 - loss 0.01448710 - samples/sec: 77.52 - lr: 0.003125 +2022-11-01 17:37:35,507 epoch 110 - iter 270/274 - loss 0.01446019 - samples/sec: 72.03 - lr: 0.003125 +2022-11-01 17:37:37,495 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:37:37,495 EPOCH 110 done: loss 0.0144 - lr 0.003125 +2022-11-01 17:38:02,941 Evaluating as a multi-label problem: False +2022-11-01 17:38:02,956 TEST : loss 0.031605690717697144 - f1-score (micro avg) 0.8551 +2022-11-01 17:38:03,011 BAD EPOCHS (no improvement): 0 +2022-11-01 17:38:03,085 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:38:15,036 epoch 111 - iter 27/274 - loss 0.01596760 - samples/sec: 72.32 - lr: 0.003125 +2022-11-01 17:38:28,050 epoch 111 - iter 54/274 - loss 0.01611072 - samples/sec: 66.40 - lr: 0.003125 +2022-11-01 17:38:41,281 epoch 111 - iter 81/274 - loss 0.01586174 - samples/sec: 65.32 - lr: 0.003125 +2022-11-01 17:38:54,263 epoch 111 - iter 108/274 - loss 0.01557685 - samples/sec: 66.57 - lr: 0.003125 +2022-11-01 17:39:08,244 epoch 111 - iter 135/274 - loss 0.01580835 - samples/sec: 61.81 - lr: 0.003125 +2022-11-01 17:39:19,514 epoch 111 - iter 162/274 - loss 0.01606974 - samples/sec: 76.68 - lr: 0.003125 +2022-11-01 17:39:31,520 epoch 111 - iter 189/274 - loss 0.01547722 - samples/sec: 71.98 - lr: 0.003125 +2022-11-01 17:39:42,815 epoch 111 - iter 216/274 - loss 0.01515104 - samples/sec: 76.52 - lr: 0.003125 +2022-11-01 17:39:54,557 epoch 111 - iter 243/274 - loss 0.01496053 - samples/sec: 73.60 - lr: 0.003125 +2022-11-01 17:40:07,087 epoch 111 - iter 270/274 - loss 0.01483213 - samples/sec: 68.97 - lr: 0.003125 +2022-11-01 17:40:08,469 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:40:08,469 EPOCH 111 done: loss 0.0149 - lr 0.003125 +2022-11-01 17:40:33,329 Evaluating as a multi-label problem: False +2022-11-01 17:40:33,344 TEST : loss 0.031536173075437546 - f1-score (micro avg) 0.8541 +2022-11-01 17:40:33,396 BAD EPOCHS (no improvement): 1 +2022-11-01 17:40:33,470 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:40:46,575 epoch 112 - iter 27/274 - loss 0.01439567 - samples/sec: 65.95 - lr: 0.003125 +2022-11-01 17:40:58,836 epoch 112 - iter 54/274 - loss 0.01354366 - samples/sec: 70.48 - lr: 0.003125 +2022-11-01 17:41:10,562 epoch 112 - iter 81/274 - loss 0.01444438 - samples/sec: 73.70 - lr: 0.003125 +2022-11-01 17:41:24,112 epoch 112 - iter 108/274 - loss 0.01493261 - samples/sec: 63.78 - lr: 0.003125 +2022-11-01 17:41:35,909 epoch 112 - iter 135/274 - loss 0.01562564 - samples/sec: 73.26 - lr: 0.003125 +2022-11-01 17:41:48,092 epoch 112 - iter 162/274 - loss 0.01544606 - samples/sec: 70.94 - lr: 0.003125 +2022-11-01 17:42:00,153 epoch 112 - iter 189/274 - loss 0.01543938 - samples/sec: 71.65 - lr: 0.003125 +2022-11-01 17:42:12,466 epoch 112 - iter 216/274 - loss 0.01503371 - samples/sec: 70.19 - lr: 0.003125 +2022-11-01 17:42:24,873 epoch 112 - iter 243/274 - loss 0.01527409 - samples/sec: 69.66 - lr: 0.003125 +2022-11-01 17:42:37,180 epoch 112 - iter 270/274 - loss 0.01508578 - samples/sec: 70.22 - lr: 0.003125 +2022-11-01 17:42:38,763 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:42:38,763 EPOCH 112 done: loss 0.0151 - lr 0.003125 +2022-11-01 17:43:04,124 Evaluating as a multi-label problem: False +2022-11-01 17:43:04,139 TEST : loss 0.031474340707063675 - f1-score (micro avg) 0.855 +2022-11-01 17:43:04,191 BAD EPOCHS (no improvement): 2 +2022-11-01 17:43:04,280 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:43:16,911 epoch 113 - iter 27/274 - loss 0.01609706 - samples/sec: 68.43 - lr: 0.003125 +2022-11-01 17:43:29,310 epoch 113 - iter 54/274 - loss 0.01433556 - samples/sec: 69.70 - lr: 0.003125 +2022-11-01 17:43:42,128 epoch 113 - iter 81/274 - loss 0.01434582 - samples/sec: 67.42 - lr: 0.003125 +2022-11-01 17:43:55,192 epoch 113 - iter 108/274 - loss 0.01474083 - samples/sec: 66.16 - lr: 0.003125 +2022-11-01 17:44:07,374 epoch 113 - iter 135/274 - loss 0.01445667 - samples/sec: 70.94 - lr: 0.003125 +2022-11-01 17:44:19,671 epoch 113 - iter 162/274 - loss 0.01481096 - samples/sec: 70.28 - lr: 0.003125 +2022-11-01 17:44:31,736 epoch 113 - iter 189/274 - loss 0.01481574 - samples/sec: 71.64 - lr: 0.003125 +2022-11-01 17:44:45,034 epoch 113 - iter 216/274 - loss 0.01524675 - samples/sec: 64.99 - lr: 0.003125 +2022-11-01 17:44:58,586 epoch 113 - iter 243/274 - loss 0.01492049 - samples/sec: 63.77 - lr: 0.003125 +2022-11-01 17:45:09,603 epoch 113 - iter 270/274 - loss 0.01468932 - samples/sec: 78.45 - lr: 0.003125 +2022-11-01 17:45:11,032 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:45:11,032 EPOCH 113 done: loss 0.0147 - lr 0.003125 +2022-11-01 17:45:36,455 Evaluating as a multi-label problem: False +2022-11-01 17:45:36,471 TEST : loss 0.031519342213869095 - f1-score (micro avg) 0.8545 +2022-11-01 17:45:36,523 BAD EPOCHS (no improvement): 3 +2022-11-01 17:45:36,616 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:45:49,215 epoch 114 - iter 27/274 - loss 0.01487123 - samples/sec: 68.60 - lr: 0.003125 +2022-11-01 17:46:00,350 epoch 114 - iter 54/274 - loss 0.01485395 - samples/sec: 77.61 - lr: 0.003125 +2022-11-01 17:46:13,743 epoch 114 - iter 81/274 - loss 0.01571063 - samples/sec: 64.53 - lr: 0.003125 +2022-11-01 17:46:25,662 epoch 114 - iter 108/274 - loss 0.01471453 - samples/sec: 72.51 - lr: 0.003125 +2022-11-01 17:46:38,373 epoch 114 - iter 135/274 - loss 0.01512168 - samples/sec: 67.99 - lr: 0.003125 +2022-11-01 17:46:50,844 epoch 114 - iter 162/274 - loss 0.01516243 - samples/sec: 69.30 - lr: 0.003125 +2022-11-01 17:47:04,008 epoch 114 - iter 189/274 - loss 0.01502249 - samples/sec: 65.65 - lr: 0.003125 +2022-11-01 17:47:15,595 epoch 114 - iter 216/274 - loss 0.01471831 - samples/sec: 74.58 - lr: 0.003125 +2022-11-01 17:47:29,477 epoch 114 - iter 243/274 - loss 0.01445627 - samples/sec: 62.25 - lr: 0.003125 +2022-11-01 17:47:40,993 epoch 114 - iter 270/274 - loss 0.01491303 - samples/sec: 75.05 - lr: 0.003125 +2022-11-01 17:47:43,070 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:47:43,070 EPOCH 114 done: loss 0.0150 - lr 0.003125 +2022-11-01 17:48:08,286 Evaluating as a multi-label problem: False +2022-11-01 17:48:08,302 TEST : loss 0.031727951020002365 - f1-score (micro avg) 0.8533 +2022-11-01 17:48:08,354 Epoch 114: reducing learning rate of group 0 to 1.5625e-03. +2022-11-01 17:48:08,354 BAD EPOCHS (no improvement): 4 +2022-11-01 17:48:08,429 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:48:21,757 epoch 115 - iter 27/274 - loss 0.01438955 - samples/sec: 64.85 - lr: 0.001563 +2022-11-01 17:48:35,019 epoch 115 - iter 54/274 - loss 0.01465102 - samples/sec: 65.16 - lr: 0.001563 +2022-11-01 17:48:48,715 epoch 115 - iter 81/274 - loss 0.01452675 - samples/sec: 63.10 - lr: 0.001563 +2022-11-01 17:49:00,439 epoch 115 - iter 108/274 - loss 0.01446702 - samples/sec: 73.71 - lr: 0.001563 +2022-11-01 17:49:13,470 epoch 115 - iter 135/274 - loss 0.01355820 - samples/sec: 66.32 - lr: 0.001563 +2022-11-01 17:49:26,293 epoch 115 - iter 162/274 - loss 0.01370481 - samples/sec: 67.40 - lr: 0.001563 +2022-11-01 17:49:38,891 epoch 115 - iter 189/274 - loss 0.01345347 - samples/sec: 68.60 - lr: 0.001563 +2022-11-01 17:49:50,147 epoch 115 - iter 216/274 - loss 0.01344039 - samples/sec: 76.78 - lr: 0.001563 +2022-11-01 17:50:01,283 epoch 115 - iter 243/274 - loss 0.01399875 - samples/sec: 77.61 - lr: 0.001563 +2022-11-01 17:50:14,106 epoch 115 - iter 270/274 - loss 0.01443076 - samples/sec: 67.40 - lr: 0.001563 +2022-11-01 17:50:15,622 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:50:15,622 EPOCH 115 done: loss 0.0146 - lr 0.001563 +2022-11-01 17:50:40,571 Evaluating as a multi-label problem: False +2022-11-01 17:50:40,587 TEST : loss 0.03165162727236748 - f1-score (micro avg) 0.8539 +2022-11-01 17:50:40,639 BAD EPOCHS (no improvement): 1 +2022-11-01 17:50:40,731 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:50:54,027 epoch 116 - iter 27/274 - loss 0.01425236 - samples/sec: 65.00 - lr: 0.001563 +2022-11-01 17:51:06,232 epoch 116 - iter 54/274 - loss 0.01383829 - samples/sec: 70.81 - lr: 0.001563 +2022-11-01 17:51:18,685 epoch 116 - iter 81/274 - loss 0.01359765 - samples/sec: 69.40 - lr: 0.001563 +2022-11-01 17:51:29,472 epoch 116 - iter 108/274 - loss 0.01347194 - samples/sec: 80.12 - lr: 0.001563 +2022-11-01 17:51:42,835 epoch 116 - iter 135/274 - loss 0.01379473 - samples/sec: 64.67 - lr: 0.001563 +2022-11-01 17:51:55,231 epoch 116 - iter 162/274 - loss 0.01379061 - samples/sec: 69.72 - lr: 0.001563 +2022-11-01 17:52:08,602 epoch 116 - iter 189/274 - loss 0.01405799 - samples/sec: 64.63 - lr: 0.001563 +2022-11-01 17:52:19,838 epoch 116 - iter 216/274 - loss 0.01425247 - samples/sec: 76.92 - lr: 0.001563 +2022-11-01 17:52:33,205 epoch 116 - iter 243/274 - loss 0.01416433 - samples/sec: 64.65 - lr: 0.001563 +2022-11-01 17:52:45,518 epoch 116 - iter 270/274 - loss 0.01401386 - samples/sec: 70.19 - lr: 0.001563 +2022-11-01 17:52:46,821 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:52:46,821 EPOCH 116 done: loss 0.0141 - lr 0.001563 +2022-11-01 17:53:11,731 Evaluating as a multi-label problem: False +2022-11-01 17:53:11,746 TEST : loss 0.03173290938138962 - f1-score (micro avg) 0.8549 +2022-11-01 17:53:11,799 BAD EPOCHS (no improvement): 0 +2022-11-01 17:53:11,891 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:53:24,606 epoch 117 - iter 27/274 - loss 0.01300331 - samples/sec: 67.97 - lr: 0.001563 +2022-11-01 17:53:36,989 epoch 117 - iter 54/274 - loss 0.01595312 - samples/sec: 69.79 - lr: 0.001563 +2022-11-01 17:53:48,545 epoch 117 - iter 81/274 - loss 0.01527940 - samples/sec: 74.79 - lr: 0.001563 +2022-11-01 17:54:00,263 epoch 117 - iter 108/274 - loss 0.01460286 - samples/sec: 73.76 - lr: 0.001563 +2022-11-01 17:54:12,584 epoch 117 - iter 135/274 - loss 0.01422859 - samples/sec: 70.14 - lr: 0.001563 +2022-11-01 17:54:25,742 epoch 117 - iter 162/274 - loss 0.01434427 - samples/sec: 65.68 - lr: 0.001563 +2022-11-01 17:54:38,379 epoch 117 - iter 189/274 - loss 0.01401961 - samples/sec: 68.39 - lr: 0.001563 +2022-11-01 17:54:51,636 epoch 117 - iter 216/274 - loss 0.01447595 - samples/sec: 65.19 - lr: 0.001563 +2022-11-01 17:55:04,763 epoch 117 - iter 243/274 - loss 0.01405447 - samples/sec: 65.84 - lr: 0.001563 +2022-11-01 17:55:17,004 epoch 117 - iter 270/274 - loss 0.01409952 - samples/sec: 70.60 - lr: 0.001563 +2022-11-01 17:55:18,621 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:55:18,621 EPOCH 117 done: loss 0.0141 - lr 0.001563 +2022-11-01 17:55:43,762 Evaluating as a multi-label problem: False +2022-11-01 17:55:43,777 TEST : loss 0.03180387616157532 - f1-score (micro avg) 0.8554 +2022-11-01 17:55:43,830 BAD EPOCHS (no improvement): 0 +2022-11-01 17:55:43,922 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:55:55,269 epoch 118 - iter 27/274 - loss 0.01405596 - samples/sec: 76.17 - lr: 0.001563 +2022-11-01 17:56:06,720 epoch 118 - iter 54/274 - loss 0.01339267 - samples/sec: 75.48 - lr: 0.001563 +2022-11-01 17:56:20,308 epoch 118 - iter 81/274 - loss 0.01339778 - samples/sec: 63.60 - lr: 0.001563 +2022-11-01 17:56:32,577 epoch 118 - iter 108/274 - loss 0.01319099 - samples/sec: 70.44 - lr: 0.001563 +2022-11-01 17:56:44,998 epoch 118 - iter 135/274 - loss 0.01301660 - samples/sec: 69.58 - lr: 0.001563 +2022-11-01 17:56:56,910 epoch 118 - iter 162/274 - loss 0.01359261 - samples/sec: 72.55 - lr: 0.001563 +2022-11-01 17:57:08,695 epoch 118 - iter 189/274 - loss 0.01402305 - samples/sec: 73.33 - lr: 0.001563 +2022-11-01 17:57:20,558 epoch 118 - iter 216/274 - loss 0.01374466 - samples/sec: 72.85 - lr: 0.001563 +2022-11-01 17:57:33,907 epoch 118 - iter 243/274 - loss 0.01374517 - samples/sec: 64.74 - lr: 0.001563 +2022-11-01 17:57:46,542 epoch 118 - iter 270/274 - loss 0.01403553 - samples/sec: 68.40 - lr: 0.001563 +2022-11-01 17:57:47,973 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:57:47,973 EPOCH 118 done: loss 0.0140 - lr 0.001563 +2022-11-01 17:58:13,100 Evaluating as a multi-label problem: False +2022-11-01 17:58:13,116 TEST : loss 0.03177444264292717 - f1-score (micro avg) 0.8549 +2022-11-01 17:58:13,167 BAD EPOCHS (no improvement): 0 +2022-11-01 17:58:13,258 ---------------------------------------------------------------------------------------------------- +2022-11-01 17:58:25,375 epoch 119 - iter 27/274 - loss 0.01538861 - samples/sec: 71.33 - lr: 0.001563 +2022-11-01 17:58:38,665 epoch 119 - iter 54/274 - loss 0.01428429 - samples/sec: 65.03 - lr: 0.001563 +2022-11-01 17:58:50,968 epoch 119 - iter 81/274 - loss 0.01545027 - samples/sec: 70.24 - lr: 0.001563 +2022-11-01 17:59:03,236 epoch 119 - iter 108/274 - loss 0.01576570 - samples/sec: 70.45 - lr: 0.001563 +2022-11-01 17:59:15,846 epoch 119 - iter 135/274 - loss 0.01500808 - samples/sec: 68.53 - lr: 0.001563 +2022-11-01 17:59:28,587 epoch 119 - iter 162/274 - loss 0.01529803 - samples/sec: 67.83 - lr: 0.001563 +2022-11-01 17:59:40,199 epoch 119 - iter 189/274 - loss 0.01492457 - samples/sec: 74.43 - lr: 0.001563 +2022-11-01 17:59:53,221 epoch 119 - iter 216/274 - loss 0.01480307 - samples/sec: 66.37 - lr: 0.001563 +2022-11-01 18:00:05,989 epoch 119 - iter 243/274 - loss 0.01461764 - samples/sec: 67.69 - lr: 0.001563 +2022-11-01 18:00:18,288 epoch 119 - iter 270/274 - loss 0.01486278 - samples/sec: 70.27 - lr: 0.001563 +2022-11-01 18:00:19,889 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:00:19,889 EPOCH 119 done: loss 0.0150 - lr 0.001563 +2022-11-01 18:00:45,262 Evaluating as a multi-label problem: False +2022-11-01 18:00:45,278 TEST : loss 0.03172260522842407 - f1-score (micro avg) 0.8543 +2022-11-01 18:00:45,330 BAD EPOCHS (no improvement): 1 +2022-11-01 18:00:45,422 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:00:57,044 epoch 120 - iter 27/274 - loss 0.00899055 - samples/sec: 74.37 - lr: 0.001563 +2022-11-01 18:01:09,522 epoch 120 - iter 54/274 - loss 0.01259727 - samples/sec: 69.26 - lr: 0.001563 +2022-11-01 18:01:22,694 epoch 120 - iter 81/274 - loss 0.01366828 - samples/sec: 65.61 - lr: 0.001563 +2022-11-01 18:01:34,264 epoch 120 - iter 108/274 - loss 0.01391092 - samples/sec: 74.69 - lr: 0.001563 +2022-11-01 18:01:45,942 epoch 120 - iter 135/274 - loss 0.01388514 - samples/sec: 74.00 - lr: 0.001563 +2022-11-01 18:01:58,326 epoch 120 - iter 162/274 - loss 0.01440931 - samples/sec: 69.79 - lr: 0.001563 +2022-11-01 18:02:11,386 epoch 120 - iter 189/274 - loss 0.01447825 - samples/sec: 66.17 - lr: 0.001563 +2022-11-01 18:02:24,050 epoch 120 - iter 216/274 - loss 0.01423748 - samples/sec: 68.24 - lr: 0.001563 +2022-11-01 18:02:35,638 epoch 120 - iter 243/274 - loss 0.01403297 - samples/sec: 74.58 - lr: 0.001563 +2022-11-01 18:02:49,124 epoch 120 - iter 270/274 - loss 0.01421427 - samples/sec: 64.08 - lr: 0.001563 +2022-11-01 18:02:51,039 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:02:51,039 EPOCH 120 done: loss 0.0142 - lr 0.001563 +2022-11-01 18:03:16,381 Evaluating as a multi-label problem: False +2022-11-01 18:03:16,397 TEST : loss 0.031805865466594696 - f1-score (micro avg) 0.8541 +2022-11-01 18:03:16,449 BAD EPOCHS (no improvement): 2 +2022-11-01 18:03:16,534 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:03:28,361 epoch 121 - iter 27/274 - loss 0.01605437 - samples/sec: 73.07 - lr: 0.001563 +2022-11-01 18:03:40,389 epoch 121 - iter 54/274 - loss 0.01495214 - samples/sec: 71.86 - lr: 0.001563 +2022-11-01 18:03:52,570 epoch 121 - iter 81/274 - loss 0.01478860 - samples/sec: 70.95 - lr: 0.001563 +2022-11-01 18:04:05,835 epoch 121 - iter 108/274 - loss 0.01482221 - samples/sec: 65.15 - lr: 0.001563 +2022-11-01 18:04:19,311 epoch 121 - iter 135/274 - loss 0.01481010 - samples/sec: 64.13 - lr: 0.001563 +2022-11-01 18:04:31,812 epoch 121 - iter 162/274 - loss 0.01420799 - samples/sec: 69.13 - lr: 0.001563 +2022-11-01 18:04:45,297 epoch 121 - iter 189/274 - loss 0.01428585 - samples/sec: 64.09 - lr: 0.001563 +2022-11-01 18:04:56,845 epoch 121 - iter 216/274 - loss 0.01414983 - samples/sec: 74.84 - lr: 0.001563 +2022-11-01 18:05:10,343 epoch 121 - iter 243/274 - loss 0.01463416 - samples/sec: 64.02 - lr: 0.001563 +2022-11-01 18:05:22,196 epoch 121 - iter 270/274 - loss 0.01435355 - samples/sec: 72.92 - lr: 0.001563 +2022-11-01 18:05:23,959 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:05:23,959 EPOCH 121 done: loss 0.0143 - lr 0.001563 +2022-11-01 18:05:49,338 Evaluating as a multi-label problem: False +2022-11-01 18:05:49,354 TEST : loss 0.03179682791233063 - f1-score (micro avg) 0.8553 +2022-11-01 18:05:49,405 BAD EPOCHS (no improvement): 3 +2022-11-01 18:05:49,496 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:06:02,504 epoch 122 - iter 27/274 - loss 0.01348554 - samples/sec: 66.44 - lr: 0.001563 +2022-11-01 18:06:15,580 epoch 122 - iter 54/274 - loss 0.01432921 - samples/sec: 66.10 - lr: 0.001563 +2022-11-01 18:06:28,964 epoch 122 - iter 81/274 - loss 0.01316887 - samples/sec: 64.57 - lr: 0.001563 +2022-11-01 18:06:40,994 epoch 122 - iter 108/274 - loss 0.01422191 - samples/sec: 71.84 - lr: 0.001563 +2022-11-01 18:06:52,690 epoch 122 - iter 135/274 - loss 0.01408750 - samples/sec: 73.89 - lr: 0.001563 +2022-11-01 18:07:04,944 epoch 122 - iter 162/274 - loss 0.01386067 - samples/sec: 70.53 - lr: 0.001563 +2022-11-01 18:07:17,208 epoch 122 - iter 189/274 - loss 0.01357114 - samples/sec: 70.47 - lr: 0.001563 +2022-11-01 18:07:29,672 epoch 122 - iter 216/274 - loss 0.01412466 - samples/sec: 69.33 - lr: 0.001563 +2022-11-01 18:07:42,807 epoch 122 - iter 243/274 - loss 0.01395056 - samples/sec: 65.79 - lr: 0.001563 +2022-11-01 18:07:55,077 epoch 122 - iter 270/274 - loss 0.01399248 - samples/sec: 70.44 - lr: 0.001563 +2022-11-01 18:07:57,015 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:07:57,015 EPOCH 122 done: loss 0.0140 - lr 0.001563 +2022-11-01 18:08:22,422 Evaluating as a multi-label problem: False +2022-11-01 18:08:22,438 TEST : loss 0.03200670704245567 - f1-score (micro avg) 0.8546 +2022-11-01 18:08:22,489 BAD EPOCHS (no improvement): 0 +2022-11-01 18:08:22,581 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:08:35,223 epoch 123 - iter 27/274 - loss 0.01535170 - samples/sec: 68.37 - lr: 0.001563 +2022-11-01 18:08:46,897 epoch 123 - iter 54/274 - loss 0.01369532 - samples/sec: 74.03 - lr: 0.001563 +2022-11-01 18:08:59,453 epoch 123 - iter 81/274 - loss 0.01398782 - samples/sec: 68.83 - lr: 0.001563 +2022-11-01 18:09:11,954 epoch 123 - iter 108/274 - loss 0.01383519 - samples/sec: 69.13 - lr: 0.001563 +2022-11-01 18:09:26,337 epoch 123 - iter 135/274 - loss 0.01394853 - samples/sec: 60.08 - lr: 0.001563 +2022-11-01 18:09:37,371 epoch 123 - iter 162/274 - loss 0.01390282 - samples/sec: 78.33 - lr: 0.001563 +2022-11-01 18:09:49,682 epoch 123 - iter 189/274 - loss 0.01422790 - samples/sec: 70.20 - lr: 0.001563 +2022-11-01 18:10:02,333 epoch 123 - iter 216/274 - loss 0.01462927 - samples/sec: 68.31 - lr: 0.001563 +2022-11-01 18:10:13,694 epoch 123 - iter 243/274 - loss 0.01470027 - samples/sec: 76.07 - lr: 0.001563 +2022-11-01 18:10:26,453 epoch 123 - iter 270/274 - loss 0.01468566 - samples/sec: 67.73 - lr: 0.001563 +2022-11-01 18:10:28,284 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:10:28,284 EPOCH 123 done: loss 0.0147 - lr 0.001563 +2022-11-01 18:10:53,622 Evaluating as a multi-label problem: False +2022-11-01 18:10:53,638 TEST : loss 0.03187215328216553 - f1-score (micro avg) 0.8541 +2022-11-01 18:10:53,691 BAD EPOCHS (no improvement): 1 +2022-11-01 18:10:53,786 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:11:07,362 epoch 124 - iter 27/274 - loss 0.01179336 - samples/sec: 63.66 - lr: 0.001563 +2022-11-01 18:11:19,048 epoch 124 - iter 54/274 - loss 0.01307793 - samples/sec: 73.95 - lr: 0.001563 +2022-11-01 18:11:31,062 epoch 124 - iter 81/274 - loss 0.01339808 - samples/sec: 71.94 - lr: 0.001563 +2022-11-01 18:11:42,429 epoch 124 - iter 108/274 - loss 0.01306621 - samples/sec: 76.03 - lr: 0.001563 +2022-11-01 18:11:54,785 epoch 124 - iter 135/274 - loss 0.01296568 - samples/sec: 69.94 - lr: 0.001563 +2022-11-01 18:12:06,411 epoch 124 - iter 162/274 - loss 0.01327152 - samples/sec: 74.34 - lr: 0.001563 +2022-11-01 18:12:18,715 epoch 124 - iter 189/274 - loss 0.01373990 - samples/sec: 70.24 - lr: 0.001563 +2022-11-01 18:12:31,980 epoch 124 - iter 216/274 - loss 0.01394854 - samples/sec: 65.15 - lr: 0.001563 +2022-11-01 18:12:44,200 epoch 124 - iter 243/274 - loss 0.01405277 - samples/sec: 70.73 - lr: 0.001563 +2022-11-01 18:12:57,416 epoch 124 - iter 270/274 - loss 0.01405971 - samples/sec: 65.39 - lr: 0.001563 +2022-11-01 18:12:59,384 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:12:59,384 EPOCH 124 done: loss 0.0141 - lr 0.001563 +2022-11-01 18:13:24,782 Evaluating as a multi-label problem: False +2022-11-01 18:13:24,798 TEST : loss 0.03188449889421463 - f1-score (micro avg) 0.8543 +2022-11-01 18:13:24,850 BAD EPOCHS (no improvement): 2 +2022-11-01 18:13:24,945 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:13:37,316 epoch 125 - iter 27/274 - loss 0.01168586 - samples/sec: 69.86 - lr: 0.001563 +2022-11-01 18:13:51,327 epoch 125 - iter 54/274 - loss 0.01431803 - samples/sec: 61.68 - lr: 0.001563 +2022-11-01 18:14:03,919 epoch 125 - iter 81/274 - loss 0.01415967 - samples/sec: 68.63 - lr: 0.001563 +2022-11-01 18:14:16,961 epoch 125 - iter 108/274 - loss 0.01380225 - samples/sec: 66.26 - lr: 0.001563 +2022-11-01 18:14:28,811 epoch 125 - iter 135/274 - loss 0.01381803 - samples/sec: 72.93 - lr: 0.001563 +2022-11-01 18:14:41,675 epoch 125 - iter 162/274 - loss 0.01389812 - samples/sec: 67.18 - lr: 0.001563 +2022-11-01 18:14:53,191 epoch 125 - iter 189/274 - loss 0.01408517 - samples/sec: 75.05 - lr: 0.001563 +2022-11-01 18:15:05,054 epoch 125 - iter 216/274 - loss 0.01435856 - samples/sec: 72.85 - lr: 0.001563 +2022-11-01 18:15:17,052 epoch 125 - iter 243/274 - loss 0.01424790 - samples/sec: 72.04 - lr: 0.001563 +2022-11-01 18:15:29,655 epoch 125 - iter 270/274 - loss 0.01424784 - samples/sec: 68.57 - lr: 0.001563 +2022-11-01 18:15:31,485 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:15:31,485 EPOCH 125 done: loss 0.0142 - lr 0.001563 +2022-11-01 18:15:56,846 Evaluating as a multi-label problem: False +2022-11-01 18:15:56,861 TEST : loss 0.03190324455499649 - f1-score (micro avg) 0.8544 +2022-11-01 18:15:56,915 BAD EPOCHS (no improvement): 3 +2022-11-01 18:15:57,007 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:16:10,448 epoch 126 - iter 27/274 - loss 0.01233038 - samples/sec: 64.30 - lr: 0.001563 +2022-11-01 18:16:22,275 epoch 126 - iter 54/274 - loss 0.01381905 - samples/sec: 73.07 - lr: 0.001563 +2022-11-01 18:16:34,930 epoch 126 - iter 81/274 - loss 0.01419482 - samples/sec: 68.30 - lr: 0.001563 +2022-11-01 18:16:46,563 epoch 126 - iter 108/274 - loss 0.01483839 - samples/sec: 74.29 - lr: 0.001563 +2022-11-01 18:16:58,287 epoch 126 - iter 135/274 - loss 0.01521833 - samples/sec: 73.72 - lr: 0.001563 +2022-11-01 18:17:09,874 epoch 126 - iter 162/274 - loss 0.01466584 - samples/sec: 74.59 - lr: 0.001563 +2022-11-01 18:17:24,081 epoch 126 - iter 189/274 - loss 0.01470213 - samples/sec: 60.83 - lr: 0.001563 +2022-11-01 18:17:36,797 epoch 126 - iter 216/274 - loss 0.01444898 - samples/sec: 67.96 - lr: 0.001563 +2022-11-01 18:17:48,690 epoch 126 - iter 243/274 - loss 0.01437726 - samples/sec: 72.67 - lr: 0.001563 +2022-11-01 18:18:00,074 epoch 126 - iter 270/274 - loss 0.01456913 - samples/sec: 75.92 - lr: 0.001563 +2022-11-01 18:18:01,780 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:18:01,780 EPOCH 126 done: loss 0.0145 - lr 0.001563 +2022-11-01 18:18:27,195 Evaluating as a multi-label problem: False +2022-11-01 18:18:27,211 TEST : loss 0.031878840178251266 - f1-score (micro avg) 0.8544 +2022-11-01 18:18:27,263 Epoch 126: reducing learning rate of group 0 to 7.8125e-04. +2022-11-01 18:18:27,263 BAD EPOCHS (no improvement): 4 +2022-11-01 18:18:27,356 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:18:38,405 epoch 127 - iter 27/274 - loss 0.01214851 - samples/sec: 78.22 - lr: 0.000781 +2022-11-01 18:18:51,529 epoch 127 - iter 54/274 - loss 0.01322803 - samples/sec: 65.85 - lr: 0.000781 +2022-11-01 18:19:03,957 epoch 127 - iter 81/274 - loss 0.01371365 - samples/sec: 69.54 - lr: 0.000781 +2022-11-01 18:19:17,792 epoch 127 - iter 108/274 - loss 0.01357113 - samples/sec: 62.46 - lr: 0.000781 +2022-11-01 18:19:30,305 epoch 127 - iter 135/274 - loss 0.01397682 - samples/sec: 69.07 - lr: 0.000781 +2022-11-01 18:19:44,368 epoch 127 - iter 162/274 - loss 0.01396536 - samples/sec: 61.45 - lr: 0.000781 +2022-11-01 18:19:55,789 epoch 127 - iter 189/274 - loss 0.01376907 - samples/sec: 75.68 - lr: 0.000781 +2022-11-01 18:20:09,810 epoch 127 - iter 216/274 - loss 0.01406742 - samples/sec: 61.64 - lr: 0.000781 +2022-11-01 18:20:20,817 epoch 127 - iter 243/274 - loss 0.01420367 - samples/sec: 78.52 - lr: 0.000781 +2022-11-01 18:20:32,276 epoch 127 - iter 270/274 - loss 0.01427245 - samples/sec: 75.42 - lr: 0.000781 +2022-11-01 18:20:33,974 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:20:33,975 EPOCH 127 done: loss 0.0141 - lr 0.000781 +2022-11-01 18:20:59,316 Evaluating as a multi-label problem: False +2022-11-01 18:20:59,332 TEST : loss 0.031853314489126205 - f1-score (micro avg) 0.8541 +2022-11-01 18:20:59,384 BAD EPOCHS (no improvement): 1 +2022-11-01 18:20:59,476 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:21:12,554 epoch 128 - iter 27/274 - loss 0.01442018 - samples/sec: 66.08 - lr: 0.000781 +2022-11-01 18:21:25,402 epoch 128 - iter 54/274 - loss 0.01455128 - samples/sec: 67.26 - lr: 0.000781 +2022-11-01 18:21:37,344 epoch 128 - iter 81/274 - loss 0.01443058 - samples/sec: 72.37 - lr: 0.000781 +2022-11-01 18:21:49,031 epoch 128 - iter 108/274 - loss 0.01426873 - samples/sec: 73.95 - lr: 0.000781 +2022-11-01 18:22:01,548 epoch 128 - iter 135/274 - loss 0.01495891 - samples/sec: 69.04 - lr: 0.000781 +2022-11-01 18:22:13,136 epoch 128 - iter 162/274 - loss 0.01507623 - samples/sec: 74.58 - lr: 0.000781 +2022-11-01 18:22:25,508 epoch 128 - iter 189/274 - loss 0.01498890 - samples/sec: 69.85 - lr: 0.000781 +2022-11-01 18:22:38,731 epoch 128 - iter 216/274 - loss 0.01477757 - samples/sec: 65.36 - lr: 0.000781 +2022-11-01 18:22:52,156 epoch 128 - iter 243/274 - loss 0.01465474 - samples/sec: 64.37 - lr: 0.000781 +2022-11-01 18:23:04,893 epoch 128 - iter 270/274 - loss 0.01489369 - samples/sec: 67.85 - lr: 0.000781 +2022-11-01 18:23:06,594 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:23:06,594 EPOCH 128 done: loss 0.0149 - lr 0.000781 +2022-11-01 18:23:31,895 Evaluating as a multi-label problem: False +2022-11-01 18:23:31,911 TEST : loss 0.0317995622754097 - f1-score (micro avg) 0.8545 +2022-11-01 18:23:31,962 BAD EPOCHS (no improvement): 2 +2022-11-01 18:23:32,056 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:23:44,890 epoch 129 - iter 27/274 - loss 0.01701574 - samples/sec: 67.34 - lr: 0.000781 +2022-11-01 18:23:56,118 epoch 129 - iter 54/274 - loss 0.01559604 - samples/sec: 76.98 - lr: 0.000781 +2022-11-01 18:24:08,335 epoch 129 - iter 81/274 - loss 0.01464102 - samples/sec: 70.74 - lr: 0.000781 +2022-11-01 18:24:21,755 epoch 129 - iter 108/274 - loss 0.01516544 - samples/sec: 64.39 - lr: 0.000781 +2022-11-01 18:24:34,920 epoch 129 - iter 135/274 - loss 0.01553544 - samples/sec: 65.65 - lr: 0.000781 +2022-11-01 18:24:46,816 epoch 129 - iter 162/274 - loss 0.01577649 - samples/sec: 72.65 - lr: 0.000781 +2022-11-01 18:24:59,344 epoch 129 - iter 189/274 - loss 0.01573528 - samples/sec: 68.98 - lr: 0.000781 +2022-11-01 18:25:12,318 epoch 129 - iter 216/274 - loss 0.01545947 - samples/sec: 66.61 - lr: 0.000781 +2022-11-01 18:25:23,959 epoch 129 - iter 243/274 - loss 0.01549187 - samples/sec: 74.24 - lr: 0.000781 +2022-11-01 18:25:36,740 epoch 129 - iter 270/274 - loss 0.01594032 - samples/sec: 67.62 - lr: 0.000781 +2022-11-01 18:25:38,294 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:25:38,295 EPOCH 129 done: loss 0.0159 - lr 0.000781 +2022-11-01 18:26:03,654 Evaluating as a multi-label problem: False +2022-11-01 18:26:03,669 TEST : loss 0.031778719276189804 - f1-score (micro avg) 0.8547 +2022-11-01 18:26:03,722 BAD EPOCHS (no improvement): 3 +2022-11-01 18:26:03,813 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:26:15,664 epoch 130 - iter 27/274 - loss 0.01545049 - samples/sec: 72.93 - lr: 0.000781 +2022-11-01 18:26:28,299 epoch 130 - iter 54/274 - loss 0.01380701 - samples/sec: 68.40 - lr: 0.000781 +2022-11-01 18:26:41,697 epoch 130 - iter 81/274 - loss 0.01339731 - samples/sec: 64.50 - lr: 0.000781 +2022-11-01 18:26:54,110 epoch 130 - iter 108/274 - loss 0.01311691 - samples/sec: 69.62 - lr: 0.000781 +2022-11-01 18:27:06,825 epoch 130 - iter 135/274 - loss 0.01372726 - samples/sec: 67.97 - lr: 0.000781 +2022-11-01 18:27:18,546 epoch 130 - iter 162/274 - loss 0.01377890 - samples/sec: 73.74 - lr: 0.000781 +2022-11-01 18:27:29,845 epoch 130 - iter 189/274 - loss 0.01383286 - samples/sec: 76.49 - lr: 0.000781 +2022-11-01 18:27:43,698 epoch 130 - iter 216/274 - loss 0.01401131 - samples/sec: 62.39 - lr: 0.000781 +2022-11-01 18:27:55,900 epoch 130 - iter 243/274 - loss 0.01402296 - samples/sec: 70.83 - lr: 0.000781 +2022-11-01 18:28:07,241 epoch 130 - iter 270/274 - loss 0.01396332 - samples/sec: 76.21 - lr: 0.000781 +2022-11-01 18:28:08,598 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:28:08,598 EPOCH 130 done: loss 0.0140 - lr 0.000781 +2022-11-01 18:28:33,883 Evaluating as a multi-label problem: False +2022-11-01 18:28:33,898 TEST : loss 0.031718671321868896 - f1-score (micro avg) 0.8547 +2022-11-01 18:28:33,952 BAD EPOCHS (no improvement): 0 +2022-11-01 18:28:34,043 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:28:45,979 epoch 131 - iter 27/274 - loss 0.01307243 - samples/sec: 72.41 - lr: 0.000781 +2022-11-01 18:28:58,110 epoch 131 - iter 54/274 - loss 0.01315823 - samples/sec: 71.24 - lr: 0.000781 +2022-11-01 18:29:11,717 epoch 131 - iter 81/274 - loss 0.01382737 - samples/sec: 63.51 - lr: 0.000781 +2022-11-01 18:29:24,334 epoch 131 - iter 108/274 - loss 0.01367923 - samples/sec: 68.50 - lr: 0.000781 +2022-11-01 18:29:36,846 epoch 131 - iter 135/274 - loss 0.01293479 - samples/sec: 69.07 - lr: 0.000781 +2022-11-01 18:29:49,418 epoch 131 - iter 162/274 - loss 0.01360035 - samples/sec: 68.74 - lr: 0.000781 +2022-11-01 18:30:00,934 epoch 131 - iter 189/274 - loss 0.01349732 - samples/sec: 75.05 - lr: 0.000781 +2022-11-01 18:30:13,375 epoch 131 - iter 216/274 - loss 0.01383598 - samples/sec: 69.47 - lr: 0.000781 +2022-11-01 18:30:25,302 epoch 131 - iter 243/274 - loss 0.01377255 - samples/sec: 72.46 - lr: 0.000781 +2022-11-01 18:30:37,001 epoch 131 - iter 270/274 - loss 0.01388772 - samples/sec: 73.88 - lr: 0.000781 +2022-11-01 18:30:38,646 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:30:38,646 EPOCH 131 done: loss 0.0138 - lr 0.000781 +2022-11-01 18:31:04,103 Evaluating as a multi-label problem: False +2022-11-01 18:31:04,119 TEST : loss 0.03182306885719299 - f1-score (micro avg) 0.8546 +2022-11-01 18:31:04,173 BAD EPOCHS (no improvement): 0 +2022-11-01 18:31:04,247 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:31:16,478 epoch 132 - iter 27/274 - loss 0.01766349 - samples/sec: 70.66 - lr: 0.000781 +2022-11-01 18:31:28,684 epoch 132 - iter 54/274 - loss 0.01453588 - samples/sec: 70.80 - lr: 0.000781 +2022-11-01 18:31:40,661 epoch 132 - iter 81/274 - loss 0.01396542 - samples/sec: 72.16 - lr: 0.000781 +2022-11-01 18:31:53,393 epoch 132 - iter 108/274 - loss 0.01430618 - samples/sec: 67.88 - lr: 0.000781 +2022-11-01 18:32:06,520 epoch 132 - iter 135/274 - loss 0.01439286 - samples/sec: 65.83 - lr: 0.000781 +2022-11-01 18:32:19,528 epoch 132 - iter 162/274 - loss 0.01473819 - samples/sec: 66.43 - lr: 0.000781 +2022-11-01 18:32:31,572 epoch 132 - iter 189/274 - loss 0.01429222 - samples/sec: 71.76 - lr: 0.000781 +2022-11-01 18:32:43,127 epoch 132 - iter 216/274 - loss 0.01431037 - samples/sec: 74.79 - lr: 0.000781 +2022-11-01 18:32:57,838 epoch 132 - iter 243/274 - loss 0.01464379 - samples/sec: 58.75 - lr: 0.000781 +2022-11-01 18:33:10,135 epoch 132 - iter 270/274 - loss 0.01477125 - samples/sec: 70.28 - lr: 0.000781 +2022-11-01 18:33:12,056 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:33:12,056 EPOCH 132 done: loss 0.0148 - lr 0.000781 +2022-11-01 18:33:37,535 Evaluating as a multi-label problem: False +2022-11-01 18:33:37,551 TEST : loss 0.03184701129794121 - f1-score (micro avg) 0.8546 +2022-11-01 18:33:37,601 BAD EPOCHS (no improvement): 1 +2022-11-01 18:33:37,697 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:33:50,117 epoch 133 - iter 27/274 - loss 0.01314103 - samples/sec: 69.59 - lr: 0.000781 +2022-11-01 18:34:02,137 epoch 133 - iter 54/274 - loss 0.01319767 - samples/sec: 71.90 - lr: 0.000781 +2022-11-01 18:34:15,737 epoch 133 - iter 81/274 - loss 0.01357056 - samples/sec: 63.55 - lr: 0.000781 +2022-11-01 18:34:27,341 epoch 133 - iter 108/274 - loss 0.01377149 - samples/sec: 74.48 - lr: 0.000781 +2022-11-01 18:34:39,606 epoch 133 - iter 135/274 - loss 0.01401248 - samples/sec: 70.46 - lr: 0.000781 +2022-11-01 18:34:53,225 epoch 133 - iter 162/274 - loss 0.01435865 - samples/sec: 63.46 - lr: 0.000781 +2022-11-01 18:35:05,127 epoch 133 - iter 189/274 - loss 0.01460999 - samples/sec: 72.61 - lr: 0.000781 +2022-11-01 18:35:17,438 epoch 133 - iter 216/274 - loss 0.01523430 - samples/sec: 70.20 - lr: 0.000781 +2022-11-01 18:35:30,196 epoch 133 - iter 243/274 - loss 0.01523406 - samples/sec: 67.74 - lr: 0.000781 +2022-11-01 18:35:42,029 epoch 133 - iter 270/274 - loss 0.01521377 - samples/sec: 73.03 - lr: 0.000781 +2022-11-01 18:35:43,607 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:35:43,607 EPOCH 133 done: loss 0.0151 - lr 0.000781 +2022-11-01 18:36:09,113 Evaluating as a multi-label problem: False +2022-11-01 18:36:09,129 TEST : loss 0.03188365697860718 - f1-score (micro avg) 0.8546 +2022-11-01 18:36:09,182 BAD EPOCHS (no improvement): 2 +2022-11-01 18:36:09,268 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:36:21,391 epoch 134 - iter 27/274 - loss 0.01570005 - samples/sec: 71.29 - lr: 0.000781 +2022-11-01 18:36:34,709 epoch 134 - iter 54/274 - loss 0.01353171 - samples/sec: 64.89 - lr: 0.000781 +2022-11-01 18:36:47,667 epoch 134 - iter 81/274 - loss 0.01290484 - samples/sec: 66.70 - lr: 0.000781 +2022-11-01 18:36:59,759 epoch 134 - iter 108/274 - loss 0.01333661 - samples/sec: 71.47 - lr: 0.000781 +2022-11-01 18:37:12,839 epoch 134 - iter 135/274 - loss 0.01340435 - samples/sec: 66.07 - lr: 0.000781 +2022-11-01 18:37:25,282 epoch 134 - iter 162/274 - loss 0.01310120 - samples/sec: 69.45 - lr: 0.000781 +2022-11-01 18:37:37,095 epoch 134 - iter 189/274 - loss 0.01362252 - samples/sec: 73.16 - lr: 0.000781 +2022-11-01 18:37:49,281 epoch 134 - iter 216/274 - loss 0.01378086 - samples/sec: 70.92 - lr: 0.000781 +2022-11-01 18:38:01,142 epoch 134 - iter 243/274 - loss 0.01385806 - samples/sec: 72.87 - lr: 0.000781 +2022-11-01 18:38:14,124 epoch 134 - iter 270/274 - loss 0.01414799 - samples/sec: 66.57 - lr: 0.000781 +2022-11-01 18:38:15,844 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:38:15,844 EPOCH 134 done: loss 0.0142 - lr 0.000781 +2022-11-01 18:38:41,212 Evaluating as a multi-label problem: False +2022-11-01 18:38:41,227 TEST : loss 0.03192955255508423 - f1-score (micro avg) 0.8538 +2022-11-01 18:38:41,279 BAD EPOCHS (no improvement): 3 +2022-11-01 18:38:41,364 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:38:54,723 epoch 135 - iter 27/274 - loss 0.01327526 - samples/sec: 64.69 - lr: 0.000781 +2022-11-01 18:39:07,129 epoch 135 - iter 54/274 - loss 0.01409919 - samples/sec: 69.67 - lr: 0.000781 +2022-11-01 18:39:19,915 epoch 135 - iter 81/274 - loss 0.01531283 - samples/sec: 67.59 - lr: 0.000781 +2022-11-01 18:39:32,995 epoch 135 - iter 108/274 - loss 0.01543934 - samples/sec: 66.07 - lr: 0.000781 +2022-11-01 18:39:45,099 epoch 135 - iter 135/274 - loss 0.01553804 - samples/sec: 71.41 - lr: 0.000781 +2022-11-01 18:39:58,722 epoch 135 - iter 162/274 - loss 0.01537747 - samples/sec: 63.44 - lr: 0.000781 +2022-11-01 18:40:10,924 epoch 135 - iter 189/274 - loss 0.01505536 - samples/sec: 70.82 - lr: 0.000781 +2022-11-01 18:40:22,920 epoch 135 - iter 216/274 - loss 0.01518738 - samples/sec: 72.05 - lr: 0.000781 +2022-11-01 18:40:34,740 epoch 135 - iter 243/274 - loss 0.01497708 - samples/sec: 73.12 - lr: 0.000781 +2022-11-01 18:40:47,071 epoch 135 - iter 270/274 - loss 0.01503585 - samples/sec: 70.08 - lr: 0.000781 +2022-11-01 18:40:48,750 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:40:48,750 EPOCH 135 done: loss 0.0152 - lr 0.000781 +2022-11-01 18:41:13,738 Evaluating as a multi-label problem: False +2022-11-01 18:41:13,753 TEST : loss 0.031969308853149414 - f1-score (micro avg) 0.8544 +2022-11-01 18:41:13,805 Epoch 135: reducing learning rate of group 0 to 3.9063e-04. +2022-11-01 18:41:13,805 BAD EPOCHS (no improvement): 4 +2022-11-01 18:41:13,900 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:41:26,650 epoch 136 - iter 27/274 - loss 0.01290276 - samples/sec: 67.79 - lr: 0.000391 +2022-11-01 18:41:39,459 epoch 136 - iter 54/274 - loss 0.01299663 - samples/sec: 67.47 - lr: 0.000391 +2022-11-01 18:41:51,985 epoch 136 - iter 81/274 - loss 0.01282157 - samples/sec: 68.99 - lr: 0.000391 +2022-11-01 18:42:06,560 epoch 136 - iter 108/274 - loss 0.01339859 - samples/sec: 59.30 - lr: 0.000391 +2022-11-01 18:42:18,770 epoch 136 - iter 135/274 - loss 0.01366404 - samples/sec: 70.78 - lr: 0.000391 +2022-11-01 18:42:32,008 epoch 136 - iter 162/274 - loss 0.01492463 - samples/sec: 65.28 - lr: 0.000391 +2022-11-01 18:42:42,929 epoch 136 - iter 189/274 - loss 0.01462456 - samples/sec: 79.14 - lr: 0.000391 +2022-11-01 18:42:55,591 epoch 136 - iter 216/274 - loss 0.01414258 - samples/sec: 68.26 - lr: 0.000391 +2022-11-01 18:43:07,774 epoch 136 - iter 243/274 - loss 0.01382027 - samples/sec: 70.93 - lr: 0.000391 +2022-11-01 18:43:19,311 epoch 136 - iter 270/274 - loss 0.01399665 - samples/sec: 74.91 - lr: 0.000391 +2022-11-01 18:43:20,917 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:43:20,917 EPOCH 136 done: loss 0.0140 - lr 0.000391 +2022-11-01 18:43:46,411 Evaluating as a multi-label problem: False +2022-11-01 18:43:46,426 TEST : loss 0.0319695845246315 - f1-score (micro avg) 0.855 +2022-11-01 18:43:46,478 BAD EPOCHS (no improvement): 1 +2022-11-01 18:43:46,571 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:43:59,477 epoch 137 - iter 27/274 - loss 0.01202838 - samples/sec: 66.96 - lr: 0.000391 +2022-11-01 18:44:12,382 epoch 137 - iter 54/274 - loss 0.01280634 - samples/sec: 66.97 - lr: 0.000391 +2022-11-01 18:44:23,487 epoch 137 - iter 81/274 - loss 0.01300539 - samples/sec: 77.82 - lr: 0.000391 +2022-11-01 18:44:35,621 epoch 137 - iter 108/274 - loss 0.01354442 - samples/sec: 71.22 - lr: 0.000391 +2022-11-01 18:44:47,256 epoch 137 - iter 135/274 - loss 0.01373392 - samples/sec: 74.28 - lr: 0.000391 +2022-11-01 18:44:59,898 epoch 137 - iter 162/274 - loss 0.01416349 - samples/sec: 68.36 - lr: 0.000391 +2022-11-01 18:45:13,470 epoch 137 - iter 189/274 - loss 0.01416036 - samples/sec: 63.67 - lr: 0.000391 +2022-11-01 18:45:27,207 epoch 137 - iter 216/274 - loss 0.01452940 - samples/sec: 62.91 - lr: 0.000391 +2022-11-01 18:45:39,752 epoch 137 - iter 243/274 - loss 0.01448564 - samples/sec: 68.89 - lr: 0.000391 +2022-11-01 18:45:51,493 epoch 137 - iter 270/274 - loss 0.01453954 - samples/sec: 73.61 - lr: 0.000391 +2022-11-01 18:45:53,154 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:45:53,154 EPOCH 137 done: loss 0.0145 - lr 0.000391 +2022-11-01 18:46:18,540 Evaluating as a multi-label problem: False +2022-11-01 18:46:18,556 TEST : loss 0.03197849541902542 - f1-score (micro avg) 0.8548 +2022-11-01 18:46:18,609 BAD EPOCHS (no improvement): 2 +2022-11-01 18:46:18,701 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:46:32,629 epoch 138 - iter 27/274 - loss 0.01287313 - samples/sec: 62.05 - lr: 0.000391 +2022-11-01 18:46:44,889 epoch 138 - iter 54/274 - loss 0.01411019 - samples/sec: 70.49 - lr: 0.000391 +2022-11-01 18:46:57,085 epoch 138 - iter 81/274 - loss 0.01373632 - samples/sec: 70.86 - lr: 0.000391 +2022-11-01 18:47:10,008 epoch 138 - iter 108/274 - loss 0.01368310 - samples/sec: 66.88 - lr: 0.000391 +2022-11-01 18:47:22,002 epoch 138 - iter 135/274 - loss 0.01385494 - samples/sec: 72.05 - lr: 0.000391 +2022-11-01 18:47:34,426 epoch 138 - iter 162/274 - loss 0.01378742 - samples/sec: 69.56 - lr: 0.000391 +2022-11-01 18:47:46,756 epoch 138 - iter 189/274 - loss 0.01386216 - samples/sec: 70.09 - lr: 0.000391 +2022-11-01 18:47:58,425 epoch 138 - iter 216/274 - loss 0.01407536 - samples/sec: 74.06 - lr: 0.000391 +2022-11-01 18:48:10,418 epoch 138 - iter 243/274 - loss 0.01377845 - samples/sec: 72.06 - lr: 0.000391 +2022-11-01 18:48:22,138 epoch 138 - iter 270/274 - loss 0.01386241 - samples/sec: 73.74 - lr: 0.000391 +2022-11-01 18:48:24,823 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:48:24,823 EPOCH 138 done: loss 0.0137 - lr 0.000391 +2022-11-01 18:48:50,296 Evaluating as a multi-label problem: False +2022-11-01 18:48:50,312 TEST : loss 0.03200221434235573 - f1-score (micro avg) 0.8548 +2022-11-01 18:48:50,364 BAD EPOCHS (no improvement): 0 +2022-11-01 18:48:50,457 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:49:02,999 epoch 139 - iter 27/274 - loss 0.01582375 - samples/sec: 68.91 - lr: 0.000391 +2022-11-01 18:49:15,457 epoch 139 - iter 54/274 - loss 0.01495674 - samples/sec: 69.37 - lr: 0.000391 +2022-11-01 18:49:28,117 epoch 139 - iter 81/274 - loss 0.01450503 - samples/sec: 68.26 - lr: 0.000391 +2022-11-01 18:49:40,212 epoch 139 - iter 108/274 - loss 0.01445288 - samples/sec: 71.45 - lr: 0.000391 +2022-11-01 18:49:53,995 epoch 139 - iter 135/274 - loss 0.01467858 - samples/sec: 62.70 - lr: 0.000391 +2022-11-01 18:50:06,504 epoch 139 - iter 162/274 - loss 0.01471299 - samples/sec: 69.08 - lr: 0.000391 +2022-11-01 18:50:19,341 epoch 139 - iter 189/274 - loss 0.01431085 - samples/sec: 67.32 - lr: 0.000391 +2022-11-01 18:50:30,753 epoch 139 - iter 216/274 - loss 0.01414775 - samples/sec: 75.73 - lr: 0.000391 +2022-11-01 18:50:43,649 epoch 139 - iter 243/274 - loss 0.01416123 - samples/sec: 67.01 - lr: 0.000391 +2022-11-01 18:50:56,349 epoch 139 - iter 270/274 - loss 0.01429129 - samples/sec: 68.05 - lr: 0.000391 +2022-11-01 18:50:57,846 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:50:57,846 EPOCH 139 done: loss 0.0142 - lr 0.000391 +2022-11-01 18:51:23,229 Evaluating as a multi-label problem: False +2022-11-01 18:51:23,244 TEST : loss 0.03198350593447685 - f1-score (micro avg) 0.8544 +2022-11-01 18:51:23,296 BAD EPOCHS (no improvement): 1 +2022-11-01 18:51:23,387 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:51:36,170 epoch 140 - iter 27/274 - loss 0.01491385 - samples/sec: 67.61 - lr: 0.000391 +2022-11-01 18:51:48,603 epoch 140 - iter 54/274 - loss 0.01542907 - samples/sec: 69.51 - lr: 0.000391 +2022-11-01 18:52:02,681 epoch 140 - iter 81/274 - loss 0.01483332 - samples/sec: 61.39 - lr: 0.000391 +2022-11-01 18:52:14,616 epoch 140 - iter 108/274 - loss 0.01461136 - samples/sec: 72.41 - lr: 0.000391 +2022-11-01 18:52:26,886 epoch 140 - iter 135/274 - loss 0.01441321 - samples/sec: 70.44 - lr: 0.000391 +2022-11-01 18:52:38,892 epoch 140 - iter 162/274 - loss 0.01482984 - samples/sec: 71.98 - lr: 0.000391 +2022-11-01 18:52:51,513 epoch 140 - iter 189/274 - loss 0.01465169 - samples/sec: 68.48 - lr: 0.000391 +2022-11-01 18:53:03,540 epoch 140 - iter 216/274 - loss 0.01454677 - samples/sec: 71.86 - lr: 0.000391 +2022-11-01 18:53:17,309 epoch 140 - iter 243/274 - loss 0.01465699 - samples/sec: 62.77 - lr: 0.000391 +2022-11-01 18:53:29,003 epoch 140 - iter 270/274 - loss 0.01447624 - samples/sec: 73.91 - lr: 0.000391 +2022-11-01 18:53:30,881 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:53:30,881 EPOCH 140 done: loss 0.0146 - lr 0.000391 +2022-11-01 18:53:56,246 Evaluating as a multi-label problem: False +2022-11-01 18:53:56,262 TEST : loss 0.03198152035474777 - f1-score (micro avg) 0.8548 +2022-11-01 18:53:56,314 BAD EPOCHS (no improvement): 2 +2022-11-01 18:53:56,401 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:54:07,635 epoch 141 - iter 27/274 - loss 0.01380211 - samples/sec: 76.94 - lr: 0.000391 +2022-11-01 18:54:20,777 epoch 141 - iter 54/274 - loss 0.01299416 - samples/sec: 65.76 - lr: 0.000391 +2022-11-01 18:54:32,989 epoch 141 - iter 81/274 - loss 0.01288500 - samples/sec: 70.77 - lr: 0.000391 +2022-11-01 18:54:44,408 epoch 141 - iter 108/274 - loss 0.01280394 - samples/sec: 75.69 - lr: 0.000391 +2022-11-01 18:54:56,270 epoch 141 - iter 135/274 - loss 0.01294786 - samples/sec: 72.86 - lr: 0.000391 +2022-11-01 18:55:09,407 epoch 141 - iter 162/274 - loss 0.01290578 - samples/sec: 65.78 - lr: 0.000391 +2022-11-01 18:55:21,882 epoch 141 - iter 189/274 - loss 0.01312051 - samples/sec: 69.28 - lr: 0.000391 +2022-11-01 18:55:33,330 epoch 141 - iter 216/274 - loss 0.01338580 - samples/sec: 75.50 - lr: 0.000391 +2022-11-01 18:55:47,281 epoch 141 - iter 243/274 - loss 0.01371702 - samples/sec: 61.94 - lr: 0.000391 +2022-11-01 18:55:59,370 epoch 141 - iter 270/274 - loss 0.01411856 - samples/sec: 71.49 - lr: 0.000391 +2022-11-01 18:56:01,282 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:56:01,282 EPOCH 141 done: loss 0.0141 - lr 0.000391 +2022-11-01 18:56:26,636 Evaluating as a multi-label problem: False +2022-11-01 18:56:26,651 TEST : loss 0.032018985599279404 - f1-score (micro avg) 0.8544 +2022-11-01 18:56:26,705 BAD EPOCHS (no improvement): 3 +2022-11-01 18:56:26,796 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:56:38,798 epoch 142 - iter 27/274 - loss 0.01461087 - samples/sec: 72.01 - lr: 0.000391 +2022-11-01 18:56:50,263 epoch 142 - iter 54/274 - loss 0.01406950 - samples/sec: 75.38 - lr: 0.000391 +2022-11-01 18:57:01,513 epoch 142 - iter 81/274 - loss 0.01326957 - samples/sec: 76.82 - lr: 0.000391 +2022-11-01 18:57:13,833 epoch 142 - iter 108/274 - loss 0.01459213 - samples/sec: 70.15 - lr: 0.000391 +2022-11-01 18:57:25,595 epoch 142 - iter 135/274 - loss 0.01422328 - samples/sec: 73.48 - lr: 0.000391 +2022-11-01 18:57:39,117 epoch 142 - iter 162/274 - loss 0.01387491 - samples/sec: 63.91 - lr: 0.000391 +2022-11-01 18:57:53,314 epoch 142 - iter 189/274 - loss 0.01399542 - samples/sec: 60.87 - lr: 0.000391 +2022-11-01 18:58:06,060 epoch 142 - iter 216/274 - loss 0.01406924 - samples/sec: 67.80 - lr: 0.000391 +2022-11-01 18:58:18,871 epoch 142 - iter 243/274 - loss 0.01429993 - samples/sec: 67.46 - lr: 0.000391 +2022-11-01 18:58:32,342 epoch 142 - iter 270/274 - loss 0.01424921 - samples/sec: 64.15 - lr: 0.000391 +2022-11-01 18:58:34,122 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:58:34,122 EPOCH 142 done: loss 0.0142 - lr 0.000391 +2022-11-01 18:58:59,595 Evaluating as a multi-label problem: False +2022-11-01 18:58:59,611 TEST : loss 0.03204723075032234 - f1-score (micro avg) 0.8541 +2022-11-01 18:58:59,664 Epoch 142: reducing learning rate of group 0 to 1.9531e-04. +2022-11-01 18:58:59,664 BAD EPOCHS (no improvement): 4 +2022-11-01 18:58:59,757 ---------------------------------------------------------------------------------------------------- +2022-11-01 18:59:12,947 epoch 143 - iter 27/274 - loss 0.01607101 - samples/sec: 65.52 - lr: 0.000195 +2022-11-01 18:59:25,410 epoch 143 - iter 54/274 - loss 0.01551964 - samples/sec: 69.34 - lr: 0.000195 +2022-11-01 18:59:37,705 epoch 143 - iter 81/274 - loss 0.01508179 - samples/sec: 70.29 - lr: 0.000195 +2022-11-01 18:59:50,633 epoch 143 - iter 108/274 - loss 0.01503203 - samples/sec: 66.85 - lr: 0.000195 +2022-11-01 19:00:02,333 epoch 143 - iter 135/274 - loss 0.01500703 - samples/sec: 73.87 - lr: 0.000195 +2022-11-01 19:00:15,575 epoch 143 - iter 162/274 - loss 0.01451339 - samples/sec: 65.26 - lr: 0.000195 +2022-11-01 19:00:29,024 epoch 143 - iter 189/274 - loss 0.01453377 - samples/sec: 64.26 - lr: 0.000195 +2022-11-01 19:00:40,418 epoch 143 - iter 216/274 - loss 0.01460606 - samples/sec: 75.85 - lr: 0.000195 +2022-11-01 19:00:53,208 epoch 143 - iter 243/274 - loss 0.01465891 - samples/sec: 67.57 - lr: 0.000195 +2022-11-01 19:01:05,277 epoch 143 - iter 270/274 - loss 0.01452026 - samples/sec: 71.61 - lr: 0.000195 +2022-11-01 19:01:06,801 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:01:06,801 EPOCH 143 done: loss 0.0145 - lr 0.000195 +2022-11-01 19:01:32,286 Evaluating as a multi-label problem: False +2022-11-01 19:01:32,301 TEST : loss 0.03204527124762535 - f1-score (micro avg) 0.8544 +2022-11-01 19:01:32,353 BAD EPOCHS (no improvement): 1 +2022-11-01 19:01:32,446 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:01:43,483 epoch 144 - iter 27/274 - loss 0.01275661 - samples/sec: 78.31 - lr: 0.000195 +2022-11-01 19:01:55,891 epoch 144 - iter 54/274 - loss 0.01255751 - samples/sec: 69.65 - lr: 0.000195 +2022-11-01 19:02:08,138 epoch 144 - iter 81/274 - loss 0.01352715 - samples/sec: 70.57 - lr: 0.000195 +2022-11-01 19:02:20,657 epoch 144 - iter 108/274 - loss 0.01424597 - samples/sec: 69.03 - lr: 0.000195 +2022-11-01 19:02:32,689 epoch 144 - iter 135/274 - loss 0.01388532 - samples/sec: 71.83 - lr: 0.000195 +2022-11-01 19:02:46,254 epoch 144 - iter 162/274 - loss 0.01418345 - samples/sec: 63.71 - lr: 0.000195 +2022-11-01 19:02:58,873 epoch 144 - iter 189/274 - loss 0.01401984 - samples/sec: 68.49 - lr: 0.000195 +2022-11-01 19:03:10,582 epoch 144 - iter 216/274 - loss 0.01378628 - samples/sec: 73.81 - lr: 0.000195 +2022-11-01 19:03:23,555 epoch 144 - iter 243/274 - loss 0.01386198 - samples/sec: 66.62 - lr: 0.000195 +2022-11-01 19:03:37,102 epoch 144 - iter 270/274 - loss 0.01403064 - samples/sec: 63.79 - lr: 0.000195 +2022-11-01 19:03:38,807 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:03:38,807 EPOCH 144 done: loss 0.0141 - lr 0.000195 +2022-11-01 19:04:04,183 Evaluating as a multi-label problem: False +2022-11-01 19:04:04,199 TEST : loss 0.03205322101712227 - f1-score (micro avg) 0.8544 +2022-11-01 19:04:04,251 BAD EPOCHS (no improvement): 2 +2022-11-01 19:04:04,337 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:04:15,584 epoch 145 - iter 27/274 - loss 0.01196807 - samples/sec: 76.84 - lr: 0.000195 +2022-11-01 19:04:27,733 epoch 145 - iter 54/274 - loss 0.01428555 - samples/sec: 71.14 - lr: 0.000195 +2022-11-01 19:04:39,618 epoch 145 - iter 81/274 - loss 0.01458192 - samples/sec: 72.72 - lr: 0.000195 +2022-11-01 19:04:52,925 epoch 145 - iter 108/274 - loss 0.01460566 - samples/sec: 64.95 - lr: 0.000195 +2022-11-01 19:05:04,454 epoch 145 - iter 135/274 - loss 0.01511987 - samples/sec: 74.96 - lr: 0.000195 +2022-11-01 19:05:16,725 epoch 145 - iter 162/274 - loss 0.01514862 - samples/sec: 70.43 - lr: 0.000195 +2022-11-01 19:05:29,601 epoch 145 - iter 189/274 - loss 0.01476270 - samples/sec: 67.12 - lr: 0.000195 +2022-11-01 19:05:42,378 epoch 145 - iter 216/274 - loss 0.01491464 - samples/sec: 67.64 - lr: 0.000195 +2022-11-01 19:05:54,791 epoch 145 - iter 243/274 - loss 0.01472325 - samples/sec: 69.62 - lr: 0.000195 +2022-11-01 19:06:08,380 epoch 145 - iter 270/274 - loss 0.01450260 - samples/sec: 63.59 - lr: 0.000195 +2022-11-01 19:06:10,102 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:06:10,103 EPOCH 145 done: loss 0.0145 - lr 0.000195 +2022-11-01 19:06:35,540 Evaluating as a multi-label problem: False +2022-11-01 19:06:35,556 TEST : loss 0.03206166997551918 - f1-score (micro avg) 0.8544 +2022-11-01 19:06:35,609 BAD EPOCHS (no improvement): 3 +2022-11-01 19:06:35,703 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:06:48,592 epoch 146 - iter 27/274 - loss 0.01138730 - samples/sec: 67.06 - lr: 0.000195 +2022-11-01 19:07:00,468 epoch 146 - iter 54/274 - loss 0.01167755 - samples/sec: 72.77 - lr: 0.000195 +2022-11-01 19:07:12,555 epoch 146 - iter 81/274 - loss 0.01291096 - samples/sec: 71.50 - lr: 0.000195 +2022-11-01 19:07:25,188 epoch 146 - iter 108/274 - loss 0.01365870 - samples/sec: 68.41 - lr: 0.000195 +2022-11-01 19:07:39,012 epoch 146 - iter 135/274 - loss 0.01360006 - samples/sec: 62.51 - lr: 0.000195 +2022-11-01 19:07:50,620 epoch 146 - iter 162/274 - loss 0.01400603 - samples/sec: 74.45 - lr: 0.000195 +2022-11-01 19:08:02,972 epoch 146 - iter 189/274 - loss 0.01390354 - samples/sec: 69.97 - lr: 0.000195 +2022-11-01 19:08:15,150 epoch 146 - iter 216/274 - loss 0.01413519 - samples/sec: 70.96 - lr: 0.000195 +2022-11-01 19:08:27,039 epoch 146 - iter 243/274 - loss 0.01425737 - samples/sec: 72.69 - lr: 0.000195 +2022-11-01 19:08:38,896 epoch 146 - iter 270/274 - loss 0.01407049 - samples/sec: 72.89 - lr: 0.000195 +2022-11-01 19:08:41,119 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:08:41,119 EPOCH 146 done: loss 0.0140 - lr 0.000195 +2022-11-01 19:09:06,382 Evaluating as a multi-label problem: False +2022-11-01 19:09:06,397 TEST : loss 0.032056890428066254 - f1-score (micro avg) 0.8544 +2022-11-01 19:09:06,450 Epoch 146: reducing learning rate of group 0 to 9.7656e-05. +2022-11-01 19:09:06,451 BAD EPOCHS (no improvement): 4 +2022-11-01 19:09:06,524 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:09:06,524 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:09:06,524 learning rate too small - quitting training! +2022-11-01 19:09:06,524 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:09:06,599 ---------------------------------------------------------------------------------------------------- +2022-11-01 19:09:06,599 Testing using last state of model ... +2022-11-01 19:09:31,767 Evaluating as a multi-label problem: False +2022-11-01 19:09:31,783 0.8572 0.8516 0.8544 0.798 +2022-11-01 19:09:31,783 +Results: +- F-score (micro) 0.8544 +- F-score (macro) 0.7406 +- Accuracy 0.798 + +By class: + precision recall f1-score support + + PERS 0.9231 0.9374 0.9302 1678 + LOC 0.8204 0.8429 0.8315 401 + ORG 0.6708 0.6245 0.6468 261 + MISC 0.6029 0.5125 0.5541 240 + + micro avg 0.8572 0.8516 0.8544 2580 + macro avg 0.7543 0.7293 0.7406 2580 +weighted avg 0.8518 0.8516 0.8512 2580 + +2022-11-01 19:09:31,783 ----------------------------------------------------------------------------------------------------