2023-10-25 02:46:56,140 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(64001, 768)
        (position_embeddings): Embedding(512, 768)
        (token_type_embeddings): Embedding(2, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): BertEncoder(
        (layer): ModuleList(
          (0): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (1): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (2): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (3): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (4): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (5): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (6): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (7): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (8): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (9): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (10): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (11): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
  )
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=768, out_features=13, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 MultiCorpus: 5777 train + 722 dev + 723 test sentences
 - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/nl
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Train:  5777 sentences
2023-10-25 02:46:56,141         (train_with_dev=False, train_with_test=False)
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Training Params:
2023-10-25 02:46:56,141  - learning_rate: "5e-05" 
2023-10-25 02:46:56,141  - mini_batch_size: "4"
2023-10-25 02:46:56,141  - max_epochs: "10"
2023-10-25 02:46:56,141  - shuffle: "True"
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Plugins:
2023-10-25 02:46:56,141  - TensorboardLogger
2023-10-25 02:46:56,141  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 02:46:56,141  - metric: "('micro avg', 'f1-score')"
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,141 Computation:
2023-10-25 02:46:56,141  - compute on device: cuda:0
2023-10-25 02:46:56,141  - embedding storage: none
2023-10-25 02:46:56,141 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,142 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-25 02:46:56,142 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,142 ----------------------------------------------------------------------------------------------------
2023-10-25 02:46:56,142 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 02:47:06,559 epoch 1 - iter 144/1445 - loss 1.41992500 - time (sec): 10.42 - samples/sec: 1608.70 - lr: 0.000005 - momentum: 0.000000
2023-10-25 02:47:16,662 epoch 1 - iter 288/1445 - loss 0.83750215 - time (sec): 20.52 - samples/sec: 1606.10 - lr: 0.000010 - momentum: 0.000000
2023-10-25 02:47:26,992 epoch 1 - iter 432/1445 - loss 0.61481097 - time (sec): 30.85 - samples/sec: 1627.37 - lr: 0.000015 - momentum: 0.000000
2023-10-25 02:47:37,751 epoch 1 - iter 576/1445 - loss 0.49739072 - time (sec): 41.61 - samples/sec: 1645.66 - lr: 0.000020 - momentum: 0.000000
2023-10-25 02:47:47,972 epoch 1 - iter 720/1445 - loss 0.43005049 - time (sec): 51.83 - samples/sec: 1642.73 - lr: 0.000025 - momentum: 0.000000
2023-10-25 02:47:58,593 epoch 1 - iter 864/1445 - loss 0.37973109 - time (sec): 62.45 - samples/sec: 1661.45 - lr: 0.000030 - momentum: 0.000000
2023-10-25 02:48:09,290 epoch 1 - iter 1008/1445 - loss 0.34700059 - time (sec): 73.15 - samples/sec: 1663.30 - lr: 0.000035 - momentum: 0.000000
2023-10-25 02:48:19,641 epoch 1 - iter 1152/1445 - loss 0.32342178 - time (sec): 83.50 - samples/sec: 1663.16 - lr: 0.000040 - momentum: 0.000000
2023-10-25 02:48:30,241 epoch 1 - iter 1296/1445 - loss 0.30192614 - time (sec): 94.10 - samples/sec: 1673.20 - lr: 0.000045 - momentum: 0.000000
2023-10-25 02:48:41,018 epoch 1 - iter 1440/1445 - loss 0.28526748 - time (sec): 104.88 - samples/sec: 1674.11 - lr: 0.000050 - momentum: 0.000000
2023-10-25 02:48:41,391 ----------------------------------------------------------------------------------------------------
2023-10-25 02:48:41,391 EPOCH 1 done: loss 0.2846 - lr: 0.000050
2023-10-25 02:48:44,710 DEV : loss 0.1542755663394928 - f1-score (micro avg)  0.6051
2023-10-25 02:48:44,722 saving best model
2023-10-25 02:48:45,190 ----------------------------------------------------------------------------------------------------
2023-10-25 02:48:55,635 epoch 2 - iter 144/1445 - loss 0.13673856 - time (sec): 10.44 - samples/sec: 1638.04 - lr: 0.000049 - momentum: 0.000000
2023-10-25 02:49:05,928 epoch 2 - iter 288/1445 - loss 0.12547644 - time (sec): 20.74 - samples/sec: 1655.38 - lr: 0.000049 - momentum: 0.000000
2023-10-25 02:49:16,263 epoch 2 - iter 432/1445 - loss 0.12065053 - time (sec): 31.07 - samples/sec: 1663.96 - lr: 0.000048 - momentum: 0.000000
2023-10-25 02:49:26,771 epoch 2 - iter 576/1445 - loss 0.11765343 - time (sec): 41.58 - samples/sec: 1664.67 - lr: 0.000048 - momentum: 0.000000
2023-10-25 02:49:37,344 epoch 2 - iter 720/1445 - loss 0.11380688 - time (sec): 52.15 - samples/sec: 1658.88 - lr: 0.000047 - momentum: 0.000000
2023-10-25 02:49:47,754 epoch 2 - iter 864/1445 - loss 0.10924427 - time (sec): 62.56 - samples/sec: 1659.33 - lr: 0.000047 - momentum: 0.000000
2023-10-25 02:49:58,240 epoch 2 - iter 1008/1445 - loss 0.10937149 - time (sec): 73.05 - samples/sec: 1657.31 - lr: 0.000046 - momentum: 0.000000
2023-10-25 02:50:08,713 epoch 2 - iter 1152/1445 - loss 0.10758530 - time (sec): 83.52 - samples/sec: 1657.90 - lr: 0.000046 - momentum: 0.000000
2023-10-25 02:50:19,491 epoch 2 - iter 1296/1445 - loss 0.10797866 - time (sec): 94.30 - samples/sec: 1664.21 - lr: 0.000045 - momentum: 0.000000
2023-10-25 02:50:30,412 epoch 2 - iter 1440/1445 - loss 0.10647364 - time (sec): 105.22 - samples/sec: 1669.24 - lr: 0.000044 - momentum: 0.000000
2023-10-25 02:50:30,787 ----------------------------------------------------------------------------------------------------
2023-10-25 02:50:30,787 EPOCH 2 done: loss 0.1066 - lr: 0.000044
2023-10-25 02:50:34,509 DEV : loss 0.11031629890203476 - f1-score (micro avg)  0.7728
2023-10-25 02:50:34,521 saving best model
2023-10-25 02:50:35,113 ----------------------------------------------------------------------------------------------------
2023-10-25 02:50:45,558 epoch 3 - iter 144/1445 - loss 0.07409640 - time (sec): 10.44 - samples/sec: 1639.70 - lr: 0.000044 - momentum: 0.000000
2023-10-25 02:50:56,017 epoch 3 - iter 288/1445 - loss 0.07630135 - time (sec): 20.90 - samples/sec: 1654.39 - lr: 0.000043 - momentum: 0.000000
2023-10-25 02:51:07,031 epoch 3 - iter 432/1445 - loss 0.08021788 - time (sec): 31.92 - samples/sec: 1679.11 - lr: 0.000043 - momentum: 0.000000
2023-10-25 02:51:17,656 epoch 3 - iter 576/1445 - loss 0.07837193 - time (sec): 42.54 - samples/sec: 1682.70 - lr: 0.000042 - momentum: 0.000000
2023-10-25 02:51:28,235 epoch 3 - iter 720/1445 - loss 0.07656273 - time (sec): 53.12 - samples/sec: 1688.18 - lr: 0.000042 - momentum: 0.000000
2023-10-25 02:51:38,586 epoch 3 - iter 864/1445 - loss 0.07895927 - time (sec): 63.47 - samples/sec: 1678.32 - lr: 0.000041 - momentum: 0.000000
2023-10-25 02:51:48,847 epoch 3 - iter 1008/1445 - loss 0.08436579 - time (sec): 73.73 - samples/sec: 1672.24 - lr: 0.000041 - momentum: 0.000000
2023-10-25 02:51:59,241 epoch 3 - iter 1152/1445 - loss 0.09116929 - time (sec): 84.13 - samples/sec: 1671.53 - lr: 0.000040 - momentum: 0.000000
2023-10-25 02:52:09,636 epoch 3 - iter 1296/1445 - loss 0.09128422 - time (sec): 94.52 - samples/sec: 1669.67 - lr: 0.000039 - momentum: 0.000000
2023-10-25 02:52:20,362 epoch 3 - iter 1440/1445 - loss 0.08962111 - time (sec): 105.25 - samples/sec: 1667.25 - lr: 0.000039 - momentum: 0.000000
2023-10-25 02:52:20,775 ----------------------------------------------------------------------------------------------------
2023-10-25 02:52:20,775 EPOCH 3 done: loss 0.0894 - lr: 0.000039
2023-10-25 02:52:24,214 DEV : loss 0.11695380508899689 - f1-score (micro avg)  0.8041
2023-10-25 02:52:24,226 saving best model
2023-10-25 02:52:24,813 ----------------------------------------------------------------------------------------------------
2023-10-25 02:52:35,169 epoch 4 - iter 144/1445 - loss 0.03918180 - time (sec): 10.36 - samples/sec: 1624.10 - lr: 0.000038 - momentum: 0.000000
2023-10-25 02:52:45,714 epoch 4 - iter 288/1445 - loss 0.04881504 - time (sec): 20.90 - samples/sec: 1665.17 - lr: 0.000038 - momentum: 0.000000
2023-10-25 02:52:56,634 epoch 4 - iter 432/1445 - loss 0.05723016 - time (sec): 31.82 - samples/sec: 1675.80 - lr: 0.000037 - momentum: 0.000000
2023-10-25 02:53:07,551 epoch 4 - iter 576/1445 - loss 0.05964875 - time (sec): 42.74 - samples/sec: 1662.42 - lr: 0.000037 - momentum: 0.000000
2023-10-25 02:53:18,165 epoch 4 - iter 720/1445 - loss 0.06496166 - time (sec): 53.35 - samples/sec: 1663.62 - lr: 0.000036 - momentum: 0.000000
2023-10-25 02:53:28,417 epoch 4 - iter 864/1445 - loss 0.06350446 - time (sec): 63.60 - samples/sec: 1657.23 - lr: 0.000036 - momentum: 0.000000
2023-10-25 02:53:39,264 epoch 4 - iter 1008/1445 - loss 0.06051938 - time (sec): 74.45 - samples/sec: 1668.13 - lr: 0.000035 - momentum: 0.000000
2023-10-25 02:53:49,798 epoch 4 - iter 1152/1445 - loss 0.05887437 - time (sec): 84.98 - samples/sec: 1664.26 - lr: 0.000034 - momentum: 0.000000
2023-10-25 02:53:59,973 epoch 4 - iter 1296/1445 - loss 0.05970754 - time (sec): 95.16 - samples/sec: 1658.41 - lr: 0.000034 - momentum: 0.000000
2023-10-25 02:54:10,424 epoch 4 - iter 1440/1445 - loss 0.06161537 - time (sec): 105.61 - samples/sec: 1665.35 - lr: 0.000033 - momentum: 0.000000
2023-10-25 02:54:10,740 ----------------------------------------------------------------------------------------------------
2023-10-25 02:54:10,741 EPOCH 4 done: loss 0.0615 - lr: 0.000033
2023-10-25 02:54:14,480 DEV : loss 0.13216571509838104 - f1-score (micro avg)  0.8015
2023-10-25 02:54:14,492 ----------------------------------------------------------------------------------------------------
2023-10-25 02:54:24,879 epoch 5 - iter 144/1445 - loss 0.06199165 - time (sec): 10.39 - samples/sec: 1705.07 - lr: 0.000033 - momentum: 0.000000
2023-10-25 02:54:35,549 epoch 5 - iter 288/1445 - loss 0.05502521 - time (sec): 21.06 - samples/sec: 1682.58 - lr: 0.000032 - momentum: 0.000000
2023-10-25 02:54:45,983 epoch 5 - iter 432/1445 - loss 0.04870086 - time (sec): 31.49 - samples/sec: 1677.67 - lr: 0.000032 - momentum: 0.000000
2023-10-25 02:54:56,195 epoch 5 - iter 576/1445 - loss 0.04642585 - time (sec): 41.70 - samples/sec: 1658.92 - lr: 0.000031 - momentum: 0.000000
2023-10-25 02:55:06,571 epoch 5 - iter 720/1445 - loss 0.04392696 - time (sec): 52.08 - samples/sec: 1655.67 - lr: 0.000031 - momentum: 0.000000
2023-10-25 02:55:17,601 epoch 5 - iter 864/1445 - loss 0.04447623 - time (sec): 63.11 - samples/sec: 1657.97 - lr: 0.000030 - momentum: 0.000000
2023-10-25 02:55:27,945 epoch 5 - iter 1008/1445 - loss 0.04459240 - time (sec): 73.45 - samples/sec: 1653.81 - lr: 0.000029 - momentum: 0.000000
2023-10-25 02:55:38,678 epoch 5 - iter 1152/1445 - loss 0.04961076 - time (sec): 84.18 - samples/sec: 1658.29 - lr: 0.000029 - momentum: 0.000000
2023-10-25 02:55:49,606 epoch 5 - iter 1296/1445 - loss 0.04875402 - time (sec): 95.11 - samples/sec: 1664.22 - lr: 0.000028 - momentum: 0.000000
2023-10-25 02:56:00,149 epoch 5 - iter 1440/1445 - loss 0.04823764 - time (sec): 105.66 - samples/sec: 1663.89 - lr: 0.000028 - momentum: 0.000000
2023-10-25 02:56:00,456 ----------------------------------------------------------------------------------------------------
2023-10-25 02:56:00,456 EPOCH 5 done: loss 0.0481 - lr: 0.000028
2023-10-25 02:56:03,895 DEV : loss 0.17967477440834045 - f1-score (micro avg)  0.7802
2023-10-25 02:56:03,907 ----------------------------------------------------------------------------------------------------
2023-10-25 02:56:14,551 epoch 6 - iter 144/1445 - loss 0.03163337 - time (sec): 10.64 - samples/sec: 1693.03 - lr: 0.000027 - momentum: 0.000000
2023-10-25 02:56:24,608 epoch 6 - iter 288/1445 - loss 0.03147930 - time (sec): 20.70 - samples/sec: 1646.79 - lr: 0.000027 - momentum: 0.000000
2023-10-25 02:56:35,463 epoch 6 - iter 432/1445 - loss 0.03580689 - time (sec): 31.56 - samples/sec: 1649.58 - lr: 0.000026 - momentum: 0.000000
2023-10-25 02:56:46,549 epoch 6 - iter 576/1445 - loss 0.03627773 - time (sec): 42.64 - samples/sec: 1670.01 - lr: 0.000026 - momentum: 0.000000
2023-10-25 02:56:57,225 epoch 6 - iter 720/1445 - loss 0.03566348 - time (sec): 53.32 - samples/sec: 1669.72 - lr: 0.000025 - momentum: 0.000000
2023-10-25 02:57:07,988 epoch 6 - iter 864/1445 - loss 0.03475012 - time (sec): 64.08 - samples/sec: 1668.18 - lr: 0.000024 - momentum: 0.000000
2023-10-25 02:57:18,683 epoch 6 - iter 1008/1445 - loss 0.03482640 - time (sec): 74.78 - samples/sec: 1666.19 - lr: 0.000024 - momentum: 0.000000
2023-10-25 02:57:29,048 epoch 6 - iter 1152/1445 - loss 0.03505707 - time (sec): 85.14 - samples/sec: 1665.92 - lr: 0.000023 - momentum: 0.000000
2023-10-25 02:57:39,148 epoch 6 - iter 1296/1445 - loss 0.03463365 - time (sec): 95.24 - samples/sec: 1662.76 - lr: 0.000023 - momentum: 0.000000
2023-10-25 02:57:49,762 epoch 6 - iter 1440/1445 - loss 0.03384896 - time (sec): 105.85 - samples/sec: 1660.33 - lr: 0.000022 - momentum: 0.000000
2023-10-25 02:57:50,108 ----------------------------------------------------------------------------------------------------
2023-10-25 02:57:50,109 EPOCH 6 done: loss 0.0340 - lr: 0.000022
2023-10-25 02:57:53,734 DEV : loss 0.19392693042755127 - f1-score (micro avg)  0.7865
2023-10-25 02:57:53,746 ----------------------------------------------------------------------------------------------------
2023-10-25 02:58:04,444 epoch 7 - iter 144/1445 - loss 0.02104653 - time (sec): 10.70 - samples/sec: 1703.89 - lr: 0.000022 - momentum: 0.000000
2023-10-25 02:58:15,335 epoch 7 - iter 288/1445 - loss 0.02262133 - time (sec): 21.59 - samples/sec: 1693.04 - lr: 0.000021 - momentum: 0.000000
2023-10-25 02:58:25,695 epoch 7 - iter 432/1445 - loss 0.02260463 - time (sec): 31.95 - samples/sec: 1671.25 - lr: 0.000021 - momentum: 0.000000
2023-10-25 02:58:36,269 epoch 7 - iter 576/1445 - loss 0.02285538 - time (sec): 42.52 - samples/sec: 1671.62 - lr: 0.000020 - momentum: 0.000000
2023-10-25 02:58:46,882 epoch 7 - iter 720/1445 - loss 0.02395447 - time (sec): 53.14 - samples/sec: 1666.26 - lr: 0.000019 - momentum: 0.000000
2023-10-25 02:58:57,348 epoch 7 - iter 864/1445 - loss 0.02356108 - time (sec): 63.60 - samples/sec: 1666.38 - lr: 0.000019 - momentum: 0.000000
2023-10-25 02:59:08,001 epoch 7 - iter 1008/1445 - loss 0.02380507 - time (sec): 74.25 - samples/sec: 1657.93 - lr: 0.000018 - momentum: 0.000000
2023-10-25 02:59:18,803 epoch 7 - iter 1152/1445 - loss 0.02353631 - time (sec): 85.06 - samples/sec: 1664.56 - lr: 0.000018 - momentum: 0.000000
2023-10-25 02:59:29,267 epoch 7 - iter 1296/1445 - loss 0.02194398 - time (sec): 95.52 - samples/sec: 1663.25 - lr: 0.000017 - momentum: 0.000000
2023-10-25 02:59:39,492 epoch 7 - iter 1440/1445 - loss 0.02210131 - time (sec): 105.75 - samples/sec: 1659.64 - lr: 0.000017 - momentum: 0.000000
2023-10-25 02:59:39,930 ----------------------------------------------------------------------------------------------------
2023-10-25 02:59:39,931 EPOCH 7 done: loss 0.0220 - lr: 0.000017
2023-10-25 02:59:43,674 DEV : loss 0.23535600304603577 - f1-score (micro avg)  0.7756
2023-10-25 02:59:43,687 ----------------------------------------------------------------------------------------------------
2023-10-25 02:59:53,987 epoch 8 - iter 144/1445 - loss 0.03149949 - time (sec): 10.30 - samples/sec: 1642.87 - lr: 0.000016 - momentum: 0.000000
2023-10-25 03:00:04,253 epoch 8 - iter 288/1445 - loss 0.02071536 - time (sec): 20.57 - samples/sec: 1650.08 - lr: 0.000016 - momentum: 0.000000
2023-10-25 03:00:14,564 epoch 8 - iter 432/1445 - loss 0.01773973 - time (sec): 30.88 - samples/sec: 1634.62 - lr: 0.000015 - momentum: 0.000000
2023-10-25 03:00:25,173 epoch 8 - iter 576/1445 - loss 0.01610270 - time (sec): 41.49 - samples/sec: 1626.91 - lr: 0.000014 - momentum: 0.000000
2023-10-25 03:00:35,755 epoch 8 - iter 720/1445 - loss 0.01622486 - time (sec): 52.07 - samples/sec: 1630.60 - lr: 0.000014 - momentum: 0.000000
2023-10-25 03:00:46,361 epoch 8 - iter 864/1445 - loss 0.01676869 - time (sec): 62.67 - samples/sec: 1637.19 - lr: 0.000013 - momentum: 0.000000
2023-10-25 03:00:57,090 epoch 8 - iter 1008/1445 - loss 0.01710768 - time (sec): 73.40 - samples/sec: 1634.69 - lr: 0.000013 - momentum: 0.000000
2023-10-25 03:01:07,556 epoch 8 - iter 1152/1445 - loss 0.01752298 - time (sec): 83.87 - samples/sec: 1640.12 - lr: 0.000012 - momentum: 0.000000
2023-10-25 03:01:18,207 epoch 8 - iter 1296/1445 - loss 0.01776129 - time (sec): 94.52 - samples/sec: 1653.16 - lr: 0.000012 - momentum: 0.000000
2023-10-25 03:01:29,416 epoch 8 - iter 1440/1445 - loss 0.01686894 - time (sec): 105.73 - samples/sec: 1661.17 - lr: 0.000011 - momentum: 0.000000
2023-10-25 03:01:29,739 ----------------------------------------------------------------------------------------------------
2023-10-25 03:01:29,739 EPOCH 8 done: loss 0.0169 - lr: 0.000011
2023-10-25 03:01:33,176 DEV : loss 0.18213523924350739 - f1-score (micro avg)  0.8075
2023-10-25 03:01:33,188 saving best model
2023-10-25 03:01:33,784 ----------------------------------------------------------------------------------------------------
2023-10-25 03:01:44,818 epoch 9 - iter 144/1445 - loss 0.00928022 - time (sec): 11.03 - samples/sec: 1645.09 - lr: 0.000011 - momentum: 0.000000
2023-10-25 03:01:55,751 epoch 9 - iter 288/1445 - loss 0.00982455 - time (sec): 21.97 - samples/sec: 1642.30 - lr: 0.000010 - momentum: 0.000000
2023-10-25 03:02:06,431 epoch 9 - iter 432/1445 - loss 0.00960726 - time (sec): 32.65 - samples/sec: 1673.59 - lr: 0.000009 - momentum: 0.000000
2023-10-25 03:02:16,942 epoch 9 - iter 576/1445 - loss 0.01120061 - time (sec): 43.16 - samples/sec: 1678.01 - lr: 0.000009 - momentum: 0.000000
2023-10-25 03:02:27,098 epoch 9 - iter 720/1445 - loss 0.01132071 - time (sec): 53.31 - samples/sec: 1666.57 - lr: 0.000008 - momentum: 0.000000
2023-10-25 03:02:37,414 epoch 9 - iter 864/1445 - loss 0.01068480 - time (sec): 63.63 - samples/sec: 1655.90 - lr: 0.000008 - momentum: 0.000000
2023-10-25 03:02:48,001 epoch 9 - iter 1008/1445 - loss 0.01040525 - time (sec): 74.22 - samples/sec: 1664.80 - lr: 0.000007 - momentum: 0.000000
2023-10-25 03:02:58,532 epoch 9 - iter 1152/1445 - loss 0.01019932 - time (sec): 84.75 - samples/sec: 1665.27 - lr: 0.000007 - momentum: 0.000000
2023-10-25 03:03:09,258 epoch 9 - iter 1296/1445 - loss 0.01091489 - time (sec): 95.47 - samples/sec: 1663.60 - lr: 0.000006 - momentum: 0.000000
2023-10-25 03:03:19,627 epoch 9 - iter 1440/1445 - loss 0.01075625 - time (sec): 105.84 - samples/sec: 1660.69 - lr: 0.000006 - momentum: 0.000000
2023-10-25 03:03:19,963 ----------------------------------------------------------------------------------------------------
2023-10-25 03:03:19,963 EPOCH 9 done: loss 0.0107 - lr: 0.000006
2023-10-25 03:03:23,388 DEV : loss 0.170689657330513 - f1-score (micro avg)  0.8228
2023-10-25 03:03:23,400 saving best model
2023-10-25 03:03:23,962 ----------------------------------------------------------------------------------------------------
2023-10-25 03:03:34,646 epoch 10 - iter 144/1445 - loss 0.00334886 - time (sec): 10.68 - samples/sec: 1665.67 - lr: 0.000005 - momentum: 0.000000
2023-10-25 03:03:45,380 epoch 10 - iter 288/1445 - loss 0.00315989 - time (sec): 21.42 - samples/sec: 1672.04 - lr: 0.000004 - momentum: 0.000000
2023-10-25 03:03:55,756 epoch 10 - iter 432/1445 - loss 0.00562550 - time (sec): 31.79 - samples/sec: 1651.83 - lr: 0.000004 - momentum: 0.000000
2023-10-25 03:04:06,159 epoch 10 - iter 576/1445 - loss 0.00612415 - time (sec): 42.20 - samples/sec: 1646.36 - lr: 0.000003 - momentum: 0.000000
2023-10-25 03:04:16,580 epoch 10 - iter 720/1445 - loss 0.00595122 - time (sec): 52.62 - samples/sec: 1645.55 - lr: 0.000003 - momentum: 0.000000
2023-10-25 03:04:26,978 epoch 10 - iter 864/1445 - loss 0.00564152 - time (sec): 63.02 - samples/sec: 1654.45 - lr: 0.000002 - momentum: 0.000000
2023-10-25 03:04:37,572 epoch 10 - iter 1008/1445 - loss 0.00580851 - time (sec): 73.61 - samples/sec: 1649.51 - lr: 0.000002 - momentum: 0.000000
2023-10-25 03:04:48,061 epoch 10 - iter 1152/1445 - loss 0.00639612 - time (sec): 84.10 - samples/sec: 1643.68 - lr: 0.000001 - momentum: 0.000000
2023-10-25 03:04:58,876 epoch 10 - iter 1296/1445 - loss 0.00636865 - time (sec): 94.91 - samples/sec: 1649.65 - lr: 0.000001 - momentum: 0.000000
2023-10-25 03:05:09,697 epoch 10 - iter 1440/1445 - loss 0.00635474 - time (sec): 105.73 - samples/sec: 1660.15 - lr: 0.000000 - momentum: 0.000000
2023-10-25 03:05:10,044 ----------------------------------------------------------------------------------------------------
2023-10-25 03:05:10,044 EPOCH 10 done: loss 0.0065 - lr: 0.000000
2023-10-25 03:05:13,783 DEV : loss 0.2022934854030609 - f1-score (micro avg)  0.8098
2023-10-25 03:05:14,262 ----------------------------------------------------------------------------------------------------
2023-10-25 03:05:14,263 Loading model from best epoch ...
2023-10-25 03:05:15,995 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-25 03:05:19,560 
Results:
- F-score (micro) 0.8085
- F-score (macro) 0.7092
- Accuracy 0.6905

By class:
              precision    recall  f1-score   support

         PER     0.8294    0.7967    0.8127       482
         LOC     0.8900    0.8122    0.8493       458
         ORG     0.5745    0.3913    0.4655        69

   micro avg     0.8438    0.7760    0.8085      1009
   macro avg     0.7646    0.6667    0.7092      1009
weighted avg     0.8394    0.7760    0.8056      1009

2023-10-25 03:05:19,560 ----------------------------------------------------------------------------------------------------