2023-10-20 10:18:41,990 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,990 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(32001, 128)
        (position_embeddings): Embedding(512, 128)
        (token_type_embeddings): Embedding(2, 128)
        (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): BertEncoder(
        (layer): ModuleList(
          (0-1): 2 x BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=128, out_features=128, bias=True)
                (key): Linear(in_features=128, out_features=128, bias=True)
                (value): Linear(in_features=128, out_features=128, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=128, out_features=128, bias=True)
                (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=128, out_features=512, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=512, out_features=128, bias=True)
              (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=128, out_features=128, bias=True)
        (activation): Tanh()
      )
    )
  )
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=128, out_features=13, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-20 10:18:41,990 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
 - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Train:  6183 sentences
2023-10-20 10:18:41,991         (train_with_dev=False, train_with_test=False)
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Training Params:
2023-10-20 10:18:41,991  - learning_rate: "5e-05" 
2023-10-20 10:18:41,991  - mini_batch_size: "8"
2023-10-20 10:18:41,991  - max_epochs: "10"
2023-10-20 10:18:41,991  - shuffle: "True"
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Plugins:
2023-10-20 10:18:41,991  - TensorboardLogger
2023-10-20 10:18:41,991  - LinearScheduler | warmup_fraction: '0.1'
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Final evaluation on model from best epoch (best-model.pt)
2023-10-20 10:18:41,991  - metric: "('micro avg', 'f1-score')"
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Computation:
2023-10-20 10:18:41,991  - compute on device: cuda:0
2023-10-20 10:18:41,991  - embedding storage: none
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:41,991 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-20 10:18:43,737 epoch 1 - iter 77/773 - loss 2.76081357 - time (sec): 1.75 - samples/sec: 6847.88 - lr: 0.000005 - momentum: 0.000000
2023-10-20 10:18:45,553 epoch 1 - iter 154/773 - loss 2.49025256 - time (sec): 3.56 - samples/sec: 6893.04 - lr: 0.000010 - momentum: 0.000000
2023-10-20 10:18:47,348 epoch 1 - iter 231/773 - loss 2.06885508 - time (sec): 5.36 - samples/sec: 6935.37 - lr: 0.000015 - momentum: 0.000000
2023-10-20 10:18:49,131 epoch 1 - iter 308/773 - loss 1.68478080 - time (sec): 7.14 - samples/sec: 6911.07 - lr: 0.000020 - momentum: 0.000000
2023-10-20 10:18:50,956 epoch 1 - iter 385/773 - loss 1.40792105 - time (sec): 8.96 - samples/sec: 6895.16 - lr: 0.000025 - momentum: 0.000000
2023-10-20 10:18:52,667 epoch 1 - iter 462/773 - loss 1.21130332 - time (sec): 10.67 - samples/sec: 6976.42 - lr: 0.000030 - momentum: 0.000000
2023-10-20 10:18:54,479 epoch 1 - iter 539/773 - loss 1.07143392 - time (sec): 12.49 - samples/sec: 6984.16 - lr: 0.000035 - momentum: 0.000000
2023-10-20 10:18:56,262 epoch 1 - iter 616/773 - loss 0.96856792 - time (sec): 14.27 - samples/sec: 6956.59 - lr: 0.000040 - momentum: 0.000000
2023-10-20 10:18:58,015 epoch 1 - iter 693/773 - loss 0.88498916 - time (sec): 16.02 - samples/sec: 7008.21 - lr: 0.000045 - momentum: 0.000000
2023-10-20 10:18:59,721 epoch 1 - iter 770/773 - loss 0.82734217 - time (sec): 17.73 - samples/sec: 6979.35 - lr: 0.000050 - momentum: 0.000000
2023-10-20 10:18:59,793 ----------------------------------------------------------------------------------------------------
2023-10-20 10:18:59,793 EPOCH 1 done: loss 0.8246 - lr: 0.000050
2023-10-20 10:19:00,757 DEV : loss 0.13438178598880768 - f1-score (micro avg)  0.0
2023-10-20 10:19:00,769 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:02,611 epoch 2 - iter 77/773 - loss 0.21322552 - time (sec): 1.84 - samples/sec: 7093.97 - lr: 0.000049 - momentum: 0.000000
2023-10-20 10:19:04,402 epoch 2 - iter 154/773 - loss 0.21500217 - time (sec): 3.63 - samples/sec: 7159.82 - lr: 0.000049 - momentum: 0.000000
2023-10-20 10:19:06,169 epoch 2 - iter 231/773 - loss 0.20279902 - time (sec): 5.40 - samples/sec: 7164.36 - lr: 0.000048 - momentum: 0.000000
2023-10-20 10:19:07,981 epoch 2 - iter 308/773 - loss 0.19576272 - time (sec): 7.21 - samples/sec: 7091.38 - lr: 0.000048 - momentum: 0.000000
2023-10-20 10:19:09,778 epoch 2 - iter 385/773 - loss 0.19373068 - time (sec): 9.01 - samples/sec: 7031.61 - lr: 0.000047 - momentum: 0.000000
2023-10-20 10:19:11,544 epoch 2 - iter 462/773 - loss 0.19162637 - time (sec): 10.77 - samples/sec: 6997.23 - lr: 0.000047 - momentum: 0.000000
2023-10-20 10:19:13,330 epoch 2 - iter 539/773 - loss 0.18956385 - time (sec): 12.56 - samples/sec: 6995.11 - lr: 0.000046 - momentum: 0.000000
2023-10-20 10:19:15,046 epoch 2 - iter 616/773 - loss 0.18775229 - time (sec): 14.28 - samples/sec: 7033.48 - lr: 0.000046 - momentum: 0.000000
2023-10-20 10:19:16,741 epoch 2 - iter 693/773 - loss 0.18551744 - time (sec): 15.97 - samples/sec: 7026.58 - lr: 0.000045 - momentum: 0.000000
2023-10-20 10:19:18,462 epoch 2 - iter 770/773 - loss 0.18371429 - time (sec): 17.69 - samples/sec: 7002.49 - lr: 0.000044 - momentum: 0.000000
2023-10-20 10:19:18,526 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:18,526 EPOCH 2 done: loss 0.1838 - lr: 0.000044
2023-10-20 10:19:19,602 DEV : loss 0.0927828922867775 - f1-score (micro avg)  0.3561
2023-10-20 10:19:19,613 saving best model
2023-10-20 10:19:19,641 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:21,317 epoch 3 - iter 77/773 - loss 0.12862111 - time (sec): 1.68 - samples/sec: 7202.29 - lr: 0.000044 - momentum: 0.000000
2023-10-20 10:19:23,022 epoch 3 - iter 154/773 - loss 0.13829102 - time (sec): 3.38 - samples/sec: 7209.97 - lr: 0.000043 - momentum: 0.000000
2023-10-20 10:19:24,819 epoch 3 - iter 231/773 - loss 0.14396600 - time (sec): 5.18 - samples/sec: 7263.82 - lr: 0.000043 - momentum: 0.000000
2023-10-20 10:19:26,633 epoch 3 - iter 308/773 - loss 0.14985513 - time (sec): 6.99 - samples/sec: 7206.66 - lr: 0.000042 - momentum: 0.000000
2023-10-20 10:19:28,366 epoch 3 - iter 385/773 - loss 0.14727970 - time (sec): 8.72 - samples/sec: 7228.75 - lr: 0.000042 - momentum: 0.000000
2023-10-20 10:19:30,085 epoch 3 - iter 462/773 - loss 0.15254413 - time (sec): 10.44 - samples/sec: 7150.46 - lr: 0.000041 - momentum: 0.000000
2023-10-20 10:19:31,810 epoch 3 - iter 539/773 - loss 0.15014457 - time (sec): 12.17 - samples/sec: 7151.46 - lr: 0.000041 - momentum: 0.000000
2023-10-20 10:19:33,550 epoch 3 - iter 616/773 - loss 0.15014077 - time (sec): 13.91 - samples/sec: 7122.98 - lr: 0.000040 - momentum: 0.000000
2023-10-20 10:19:35,289 epoch 3 - iter 693/773 - loss 0.15350555 - time (sec): 15.65 - samples/sec: 7130.39 - lr: 0.000039 - momentum: 0.000000
2023-10-20 10:19:37,008 epoch 3 - iter 770/773 - loss 0.15441552 - time (sec): 17.37 - samples/sec: 7124.27 - lr: 0.000039 - momentum: 0.000000
2023-10-20 10:19:37,075 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:37,075 EPOCH 3 done: loss 0.1541 - lr: 0.000039
2023-10-20 10:19:38,138 DEV : loss 0.084617480635643 - f1-score (micro avg)  0.4567
2023-10-20 10:19:38,150 saving best model
2023-10-20 10:19:38,185 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:39,874 epoch 4 - iter 77/773 - loss 0.12106919 - time (sec): 1.69 - samples/sec: 7626.66 - lr: 0.000038 - momentum: 0.000000
2023-10-20 10:19:41,612 epoch 4 - iter 154/773 - loss 0.11504532 - time (sec): 3.43 - samples/sec: 7345.90 - lr: 0.000038 - momentum: 0.000000
2023-10-20 10:19:43,406 epoch 4 - iter 231/773 - loss 0.11895267 - time (sec): 5.22 - samples/sec: 7123.90 - lr: 0.000037 - momentum: 0.000000
2023-10-20 10:19:45,175 epoch 4 - iter 308/773 - loss 0.12487455 - time (sec): 6.99 - samples/sec: 7164.55 - lr: 0.000037 - momentum: 0.000000
2023-10-20 10:19:46,889 epoch 4 - iter 385/773 - loss 0.12594846 - time (sec): 8.70 - samples/sec: 7202.58 - lr: 0.000036 - momentum: 0.000000
2023-10-20 10:19:48,672 epoch 4 - iter 462/773 - loss 0.12764145 - time (sec): 10.49 - samples/sec: 7134.85 - lr: 0.000036 - momentum: 0.000000
2023-10-20 10:19:50,495 epoch 4 - iter 539/773 - loss 0.13107008 - time (sec): 12.31 - samples/sec: 7013.80 - lr: 0.000035 - momentum: 0.000000
2023-10-20 10:19:52,305 epoch 4 - iter 616/773 - loss 0.13554526 - time (sec): 14.12 - samples/sec: 6990.45 - lr: 0.000034 - momentum: 0.000000
2023-10-20 10:19:54,018 epoch 4 - iter 693/773 - loss 0.13496751 - time (sec): 15.83 - samples/sec: 6990.21 - lr: 0.000034 - momentum: 0.000000
2023-10-20 10:19:55,817 epoch 4 - iter 770/773 - loss 0.13519161 - time (sec): 17.63 - samples/sec: 7021.09 - lr: 0.000033 - momentum: 0.000000
2023-10-20 10:19:55,893 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:55,893 EPOCH 4 done: loss 0.1351 - lr: 0.000033
2023-10-20 10:19:57,288 DEV : loss 0.0839473307132721 - f1-score (micro avg)  0.5499
2023-10-20 10:19:57,300 saving best model
2023-10-20 10:19:57,331 ----------------------------------------------------------------------------------------------------
2023-10-20 10:19:59,013 epoch 5 - iter 77/773 - loss 0.12213229 - time (sec): 1.68 - samples/sec: 7265.57 - lr: 0.000033 - momentum: 0.000000
2023-10-20 10:20:00,701 epoch 5 - iter 154/773 - loss 0.12055572 - time (sec): 3.37 - samples/sec: 7464.07 - lr: 0.000032 - momentum: 0.000000
2023-10-20 10:20:02,455 epoch 5 - iter 231/773 - loss 0.12157099 - time (sec): 5.12 - samples/sec: 7243.51 - lr: 0.000032 - momentum: 0.000000
2023-10-20 10:20:04,200 epoch 5 - iter 308/773 - loss 0.11807165 - time (sec): 6.87 - samples/sec: 7190.00 - lr: 0.000031 - momentum: 0.000000
2023-10-20 10:20:05,954 epoch 5 - iter 385/773 - loss 0.12115097 - time (sec): 8.62 - samples/sec: 7241.57 - lr: 0.000031 - momentum: 0.000000
2023-10-20 10:20:07,703 epoch 5 - iter 462/773 - loss 0.12082630 - time (sec): 10.37 - samples/sec: 7199.19 - lr: 0.000030 - momentum: 0.000000
2023-10-20 10:20:09,452 epoch 5 - iter 539/773 - loss 0.12301358 - time (sec): 12.12 - samples/sec: 7200.49 - lr: 0.000029 - momentum: 0.000000
2023-10-20 10:20:11,161 epoch 5 - iter 616/773 - loss 0.12323717 - time (sec): 13.83 - samples/sec: 7218.90 - lr: 0.000029 - momentum: 0.000000
2023-10-20 10:20:12,848 epoch 5 - iter 693/773 - loss 0.12371624 - time (sec): 15.52 - samples/sec: 7218.93 - lr: 0.000028 - momentum: 0.000000
2023-10-20 10:20:14,577 epoch 5 - iter 770/773 - loss 0.12519008 - time (sec): 17.25 - samples/sec: 7183.33 - lr: 0.000028 - momentum: 0.000000
2023-10-20 10:20:14,644 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:14,644 EPOCH 5 done: loss 0.1255 - lr: 0.000028
2023-10-20 10:20:15,740 DEV : loss 0.08093783259391785 - f1-score (micro avg)  0.5624
2023-10-20 10:20:15,752 saving best model
2023-10-20 10:20:15,787 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:17,528 epoch 6 - iter 77/773 - loss 0.11746877 - time (sec): 1.74 - samples/sec: 7216.53 - lr: 0.000027 - momentum: 0.000000
2023-10-20 10:20:19,261 epoch 6 - iter 154/773 - loss 0.10613002 - time (sec): 3.47 - samples/sec: 7147.55 - lr: 0.000027 - momentum: 0.000000
2023-10-20 10:20:21,050 epoch 6 - iter 231/773 - loss 0.10693685 - time (sec): 5.26 - samples/sec: 7117.39 - lr: 0.000026 - momentum: 0.000000
2023-10-20 10:20:22,761 epoch 6 - iter 308/773 - loss 0.10922407 - time (sec): 6.97 - samples/sec: 7043.40 - lr: 0.000026 - momentum: 0.000000
2023-10-20 10:20:24,521 epoch 6 - iter 385/773 - loss 0.11360514 - time (sec): 8.73 - samples/sec: 7057.18 - lr: 0.000025 - momentum: 0.000000
2023-10-20 10:20:26,292 epoch 6 - iter 462/773 - loss 0.11438363 - time (sec): 10.50 - samples/sec: 7089.40 - lr: 0.000024 - momentum: 0.000000
2023-10-20 10:20:28,060 epoch 6 - iter 539/773 - loss 0.11502393 - time (sec): 12.27 - samples/sec: 7121.44 - lr: 0.000024 - momentum: 0.000000
2023-10-20 10:20:29,797 epoch 6 - iter 616/773 - loss 0.11536019 - time (sec): 14.01 - samples/sec: 7118.05 - lr: 0.000023 - momentum: 0.000000
2023-10-20 10:20:31,497 epoch 6 - iter 693/773 - loss 0.11465378 - time (sec): 15.71 - samples/sec: 7130.83 - lr: 0.000023 - momentum: 0.000000
2023-10-20 10:20:33,255 epoch 6 - iter 770/773 - loss 0.11661110 - time (sec): 17.47 - samples/sec: 7085.16 - lr: 0.000022 - momentum: 0.000000
2023-10-20 10:20:33,324 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:33,325 EPOCH 6 done: loss 0.1163 - lr: 0.000022
2023-10-20 10:20:34,423 DEV : loss 0.07920077443122864 - f1-score (micro avg)  0.5938
2023-10-20 10:20:34,434 saving best model
2023-10-20 10:20:34,470 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:36,168 epoch 7 - iter 77/773 - loss 0.09474261 - time (sec): 1.70 - samples/sec: 7339.27 - lr: 0.000022 - momentum: 0.000000
2023-10-20 10:20:37,847 epoch 7 - iter 154/773 - loss 0.11040553 - time (sec): 3.38 - samples/sec: 7152.24 - lr: 0.000021 - momentum: 0.000000
2023-10-20 10:20:39,639 epoch 7 - iter 231/773 - loss 0.10910553 - time (sec): 5.17 - samples/sec: 7035.86 - lr: 0.000021 - momentum: 0.000000
2023-10-20 10:20:41,210 epoch 7 - iter 308/773 - loss 0.10937316 - time (sec): 6.74 - samples/sec: 7219.39 - lr: 0.000020 - momentum: 0.000000
2023-10-20 10:20:43,003 epoch 7 - iter 385/773 - loss 0.11012476 - time (sec): 8.53 - samples/sec: 7185.89 - lr: 0.000019 - momentum: 0.000000
2023-10-20 10:20:44,892 epoch 7 - iter 462/773 - loss 0.10863752 - time (sec): 10.42 - samples/sec: 7076.21 - lr: 0.000019 - momentum: 0.000000
2023-10-20 10:20:46,629 epoch 7 - iter 539/773 - loss 0.11063320 - time (sec): 12.16 - samples/sec: 7116.68 - lr: 0.000018 - momentum: 0.000000
2023-10-20 10:20:48,375 epoch 7 - iter 616/773 - loss 0.11080838 - time (sec): 13.90 - samples/sec: 7158.60 - lr: 0.000018 - momentum: 0.000000
2023-10-20 10:20:50,075 epoch 7 - iter 693/773 - loss 0.10962384 - time (sec): 15.60 - samples/sec: 7182.38 - lr: 0.000017 - momentum: 0.000000
2023-10-20 10:20:51,796 epoch 7 - iter 770/773 - loss 0.11036441 - time (sec): 17.33 - samples/sec: 7152.72 - lr: 0.000017 - momentum: 0.000000
2023-10-20 10:20:51,856 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:51,856 EPOCH 7 done: loss 0.1102 - lr: 0.000017
2023-10-20 10:20:52,939 DEV : loss 0.08024124056100845 - f1-score (micro avg)  0.5759
2023-10-20 10:20:52,951 ----------------------------------------------------------------------------------------------------
2023-10-20 10:20:54,677 epoch 8 - iter 77/773 - loss 0.09697879 - time (sec): 1.73 - samples/sec: 7324.84 - lr: 0.000016 - momentum: 0.000000
2023-10-20 10:20:56,401 epoch 8 - iter 154/773 - loss 0.10163992 - time (sec): 3.45 - samples/sec: 6933.69 - lr: 0.000016 - momentum: 0.000000
2023-10-20 10:20:58,130 epoch 8 - iter 231/773 - loss 0.10296558 - time (sec): 5.18 - samples/sec: 6998.96 - lr: 0.000015 - momentum: 0.000000
2023-10-20 10:20:59,877 epoch 8 - iter 308/773 - loss 0.10472086 - time (sec): 6.93 - samples/sec: 7099.31 - lr: 0.000014 - momentum: 0.000000
2023-10-20 10:21:01,656 epoch 8 - iter 385/773 - loss 0.10171931 - time (sec): 8.70 - samples/sec: 7078.82 - lr: 0.000014 - momentum: 0.000000
2023-10-20 10:21:03,414 epoch 8 - iter 462/773 - loss 0.10123830 - time (sec): 10.46 - samples/sec: 7071.45 - lr: 0.000013 - momentum: 0.000000
2023-10-20 10:21:05,121 epoch 8 - iter 539/773 - loss 0.10188542 - time (sec): 12.17 - samples/sec: 7010.05 - lr: 0.000013 - momentum: 0.000000
2023-10-20 10:21:06,893 epoch 8 - iter 616/773 - loss 0.10110334 - time (sec): 13.94 - samples/sec: 7076.37 - lr: 0.000012 - momentum: 0.000000
2023-10-20 10:21:08,793 epoch 8 - iter 693/773 - loss 0.10353577 - time (sec): 15.84 - samples/sec: 7019.44 - lr: 0.000012 - momentum: 0.000000
2023-10-20 10:21:10,571 epoch 8 - iter 770/773 - loss 0.10656965 - time (sec): 17.62 - samples/sec: 7032.87 - lr: 0.000011 - momentum: 0.000000
2023-10-20 10:21:10,637 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:10,637 EPOCH 8 done: loss 0.1065 - lr: 0.000011
2023-10-20 10:21:11,725 DEV : loss 0.08284606039524078 - f1-score (micro avg)  0.5864
2023-10-20 10:21:11,737 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:13,496 epoch 9 - iter 77/773 - loss 0.10668199 - time (sec): 1.76 - samples/sec: 7717.89 - lr: 0.000011 - momentum: 0.000000
2023-10-20 10:21:15,237 epoch 9 - iter 154/773 - loss 0.10089596 - time (sec): 3.50 - samples/sec: 7436.55 - lr: 0.000010 - momentum: 0.000000
2023-10-20 10:21:17,044 epoch 9 - iter 231/773 - loss 0.10023690 - time (sec): 5.31 - samples/sec: 7290.69 - lr: 0.000009 - momentum: 0.000000
2023-10-20 10:21:18,782 epoch 9 - iter 308/773 - loss 0.10112886 - time (sec): 7.04 - samples/sec: 7224.41 - lr: 0.000009 - momentum: 0.000000
2023-10-20 10:21:20,480 epoch 9 - iter 385/773 - loss 0.09928799 - time (sec): 8.74 - samples/sec: 7262.97 - lr: 0.000008 - momentum: 0.000000
2023-10-20 10:21:22,194 epoch 9 - iter 462/773 - loss 0.10228269 - time (sec): 10.46 - samples/sec: 7222.17 - lr: 0.000008 - momentum: 0.000000
2023-10-20 10:21:23,955 epoch 9 - iter 539/773 - loss 0.09979659 - time (sec): 12.22 - samples/sec: 7174.05 - lr: 0.000007 - momentum: 0.000000
2023-10-20 10:21:25,713 epoch 9 - iter 616/773 - loss 0.09923517 - time (sec): 13.98 - samples/sec: 7078.44 - lr: 0.000007 - momentum: 0.000000
2023-10-20 10:21:27,481 epoch 9 - iter 693/773 - loss 0.10044792 - time (sec): 15.74 - samples/sec: 7108.21 - lr: 0.000006 - momentum: 0.000000
2023-10-20 10:21:29,198 epoch 9 - iter 770/773 - loss 0.10167632 - time (sec): 17.46 - samples/sec: 7088.31 - lr: 0.000006 - momentum: 0.000000
2023-10-20 10:21:29,267 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:29,267 EPOCH 9 done: loss 0.1015 - lr: 0.000006
2023-10-20 10:21:30,360 DEV : loss 0.08339545875787735 - f1-score (micro avg)  0.5895
2023-10-20 10:21:30,372 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:32,116 epoch 10 - iter 77/773 - loss 0.10844329 - time (sec): 1.74 - samples/sec: 7021.81 - lr: 0.000005 - momentum: 0.000000
2023-10-20 10:21:33,887 epoch 10 - iter 154/773 - loss 0.10838063 - time (sec): 3.52 - samples/sec: 7150.42 - lr: 0.000005 - momentum: 0.000000
2023-10-20 10:21:35,563 epoch 10 - iter 231/773 - loss 0.09648269 - time (sec): 5.19 - samples/sec: 7088.88 - lr: 0.000004 - momentum: 0.000000
2023-10-20 10:21:37,267 epoch 10 - iter 308/773 - loss 0.09663622 - time (sec): 6.90 - samples/sec: 7001.59 - lr: 0.000003 - momentum: 0.000000
2023-10-20 10:21:38,966 epoch 10 - iter 385/773 - loss 0.09900535 - time (sec): 8.59 - samples/sec: 7102.73 - lr: 0.000003 - momentum: 0.000000
2023-10-20 10:21:40,567 epoch 10 - iter 462/773 - loss 0.09936474 - time (sec): 10.19 - samples/sec: 7201.67 - lr: 0.000002 - momentum: 0.000000
2023-10-20 10:21:42,271 epoch 10 - iter 539/773 - loss 0.09809994 - time (sec): 11.90 - samples/sec: 7266.80 - lr: 0.000002 - momentum: 0.000000
2023-10-20 10:21:44,006 epoch 10 - iter 616/773 - loss 0.09826543 - time (sec): 13.63 - samples/sec: 7217.04 - lr: 0.000001 - momentum: 0.000000
2023-10-20 10:21:45,897 epoch 10 - iter 693/773 - loss 0.09749620 - time (sec): 15.52 - samples/sec: 7190.67 - lr: 0.000001 - momentum: 0.000000
2023-10-20 10:21:47,593 epoch 10 - iter 770/773 - loss 0.10058972 - time (sec): 17.22 - samples/sec: 7193.03 - lr: 0.000000 - momentum: 0.000000
2023-10-20 10:21:47,655 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:47,656 EPOCH 10 done: loss 0.1007 - lr: 0.000000
2023-10-20 10:21:48,756 DEV : loss 0.08416001498699188 - f1-score (micro avg)  0.5843
2023-10-20 10:21:48,800 ----------------------------------------------------------------------------------------------------
2023-10-20 10:21:48,800 Loading model from best epoch ...
2023-10-20 10:21:48,876 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
2023-10-20 10:21:51,832 
Results:
- F-score (micro) 0.5388
- F-score (macro) 0.2565
- Accuracy 0.381

By class:
              precision    recall  f1-score   support

         LOC     0.5544    0.6628    0.6038       946
    BUILDING     0.2267    0.0919    0.1308       185
      STREET     1.0000    0.0179    0.0351        56

   micro avg     0.5344    0.5434    0.5388      1187
   macro avg     0.5937    0.2575    0.2565      1187
weighted avg     0.5243    0.5434    0.5032      1187

2023-10-20 10:21:51,832 ----------------------------------------------------------------------------------------------------