2023-10-24 22:31:59,069 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,070 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()
)"
2023-10-24 22:31:59,071 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,071 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
2023-10-24 22:31:59,071 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,071 Train:  5777 sentences
2023-10-24 22:31:59,071         (train_with_dev=False, train_with_test=False)
2023-10-24 22:31:59,071 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,071 Training Params:
2023-10-24 22:31:59,071  - learning_rate: "3e-05" 
2023-10-24 22:31:59,071  - mini_batch_size: "8"
2023-10-24 22:31:59,071  - max_epochs: "10"
2023-10-24 22:31:59,071  - shuffle: "True"
2023-10-24 22:31:59,071 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,071 Plugins:
2023-10-24 22:31:59,071  - TensorboardLogger
2023-10-24 22:31:59,072  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 22:31:59,072 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,072 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 22:31:59,072  - metric: "('micro avg', 'f1-score')"
2023-10-24 22:31:59,072 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,072 Computation:
2023-10-24 22:31:59,072  - compute on device: cuda:0
2023-10-24 22:31:59,072  - embedding storage: none
2023-10-24 22:31:59,072 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,072 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-24 22:31:59,072 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,072 ----------------------------------------------------------------------------------------------------
2023-10-24 22:31:59,072 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 22:32:07,563 epoch 1 - iter 72/723 - loss 2.31947311 - time (sec): 8.49 - samples/sec: 2083.66 - lr: 0.000003 - momentum: 0.000000
2023-10-24 22:32:16,346 epoch 1 - iter 144/723 - loss 1.32909159 - time (sec): 17.27 - samples/sec: 2038.93 - lr: 0.000006 - momentum: 0.000000
2023-10-24 22:32:25,292 epoch 1 - iter 216/723 - loss 0.94456255 - time (sec): 26.22 - samples/sec: 2064.96 - lr: 0.000009 - momentum: 0.000000
2023-10-24 22:32:33,521 epoch 1 - iter 288/723 - loss 0.76663770 - time (sec): 34.45 - samples/sec: 2047.33 - lr: 0.000012 - momentum: 0.000000
2023-10-24 22:32:41,645 epoch 1 - iter 360/723 - loss 0.64951811 - time (sec): 42.57 - samples/sec: 2047.01 - lr: 0.000015 - momentum: 0.000000
2023-10-24 22:32:49,977 epoch 1 - iter 432/723 - loss 0.57340174 - time (sec): 50.90 - samples/sec: 2047.02 - lr: 0.000018 - momentum: 0.000000
2023-10-24 22:32:58,323 epoch 1 - iter 504/723 - loss 0.51388230 - time (sec): 59.25 - samples/sec: 2039.16 - lr: 0.000021 - momentum: 0.000000
2023-10-24 22:33:07,442 epoch 1 - iter 576/723 - loss 0.46626848 - time (sec): 68.37 - samples/sec: 2030.93 - lr: 0.000024 - momentum: 0.000000
2023-10-24 22:33:16,119 epoch 1 - iter 648/723 - loss 0.42649097 - time (sec): 77.05 - samples/sec: 2038.95 - lr: 0.000027 - momentum: 0.000000
2023-10-24 22:33:25,266 epoch 1 - iter 720/723 - loss 0.39365540 - time (sec): 86.19 - samples/sec: 2039.10 - lr: 0.000030 - momentum: 0.000000
2023-10-24 22:33:25,516 ----------------------------------------------------------------------------------------------------
2023-10-24 22:33:25,516 EPOCH 1 done: loss 0.3931 - lr: 0.000030
2023-10-24 22:33:28,789 DEV : loss 0.13080401718616486 - f1-score (micro avg)  0.5705
2023-10-24 22:33:28,801 saving best model
2023-10-24 22:33:29,271 ----------------------------------------------------------------------------------------------------
2023-10-24 22:33:37,630 epoch 2 - iter 72/723 - loss 0.11662981 - time (sec): 8.36 - samples/sec: 2039.80 - lr: 0.000030 - momentum: 0.000000
2023-10-24 22:33:45,571 epoch 2 - iter 144/723 - loss 0.11114776 - time (sec): 16.30 - samples/sec: 2050.45 - lr: 0.000029 - momentum: 0.000000
2023-10-24 22:33:53,911 epoch 2 - iter 216/723 - loss 0.10664717 - time (sec): 24.64 - samples/sec: 2054.36 - lr: 0.000029 - momentum: 0.000000
2023-10-24 22:34:03,044 epoch 2 - iter 288/723 - loss 0.10255450 - time (sec): 33.77 - samples/sec: 2051.08 - lr: 0.000029 - momentum: 0.000000
2023-10-24 22:34:12,351 epoch 2 - iter 360/723 - loss 0.09854358 - time (sec): 43.08 - samples/sec: 2054.75 - lr: 0.000028 - momentum: 0.000000
2023-10-24 22:34:21,686 epoch 2 - iter 432/723 - loss 0.09691315 - time (sec): 52.41 - samples/sec: 2047.19 - lr: 0.000028 - momentum: 0.000000
2023-10-24 22:34:30,078 epoch 2 - iter 504/723 - loss 0.09403782 - time (sec): 60.81 - samples/sec: 2046.78 - lr: 0.000028 - momentum: 0.000000
2023-10-24 22:34:37,733 epoch 2 - iter 576/723 - loss 0.09689121 - time (sec): 68.46 - samples/sec: 2048.84 - lr: 0.000027 - momentum: 0.000000
2023-10-24 22:34:46,175 epoch 2 - iter 648/723 - loss 0.09667821 - time (sec): 76.90 - samples/sec: 2048.92 - lr: 0.000027 - momentum: 0.000000
2023-10-24 22:34:54,725 epoch 2 - iter 720/723 - loss 0.09635443 - time (sec): 85.45 - samples/sec: 2054.74 - lr: 0.000027 - momentum: 0.000000
2023-10-24 22:34:54,971 ----------------------------------------------------------------------------------------------------
2023-10-24 22:34:54,971 EPOCH 2 done: loss 0.0964 - lr: 0.000027
2023-10-24 22:34:58,678 DEV : loss 0.07759504020214081 - f1-score (micro avg)  0.8195
2023-10-24 22:34:58,690 saving best model
2023-10-24 22:34:59,285 ----------------------------------------------------------------------------------------------------
2023-10-24 22:35:07,943 epoch 3 - iter 72/723 - loss 0.06713425 - time (sec): 8.66 - samples/sec: 2019.48 - lr: 0.000026 - momentum: 0.000000
2023-10-24 22:35:16,408 epoch 3 - iter 144/723 - loss 0.05848043 - time (sec): 17.12 - samples/sec: 2041.94 - lr: 0.000026 - momentum: 0.000000
2023-10-24 22:35:24,682 epoch 3 - iter 216/723 - loss 0.06611272 - time (sec): 25.40 - samples/sec: 2057.98 - lr: 0.000026 - momentum: 0.000000
2023-10-24 22:35:33,448 epoch 3 - iter 288/723 - loss 0.06373711 - time (sec): 34.16 - samples/sec: 2062.71 - lr: 0.000025 - momentum: 0.000000
2023-10-24 22:35:42,258 epoch 3 - iter 360/723 - loss 0.06368511 - time (sec): 42.97 - samples/sec: 2052.83 - lr: 0.000025 - momentum: 0.000000
2023-10-24 22:35:51,380 epoch 3 - iter 432/723 - loss 0.06405055 - time (sec): 52.09 - samples/sec: 2054.55 - lr: 0.000025 - momentum: 0.000000
2023-10-24 22:35:59,698 epoch 3 - iter 504/723 - loss 0.06454130 - time (sec): 60.41 - samples/sec: 2043.44 - lr: 0.000024 - momentum: 0.000000
2023-10-24 22:36:08,056 epoch 3 - iter 576/723 - loss 0.06344541 - time (sec): 68.77 - samples/sec: 2037.40 - lr: 0.000024 - momentum: 0.000000
2023-10-24 22:36:16,742 epoch 3 - iter 648/723 - loss 0.06359618 - time (sec): 77.46 - samples/sec: 2037.63 - lr: 0.000024 - momentum: 0.000000
2023-10-24 22:36:25,498 epoch 3 - iter 720/723 - loss 0.06294517 - time (sec): 86.21 - samples/sec: 2040.20 - lr: 0.000023 - momentum: 0.000000
2023-10-24 22:36:25,702 ----------------------------------------------------------------------------------------------------
2023-10-24 22:36:25,702 EPOCH 3 done: loss 0.0631 - lr: 0.000023
2023-10-24 22:36:29,121 DEV : loss 0.06691966950893402 - f1-score (micro avg)  0.8335
2023-10-24 22:36:29,133 saving best model
2023-10-24 22:36:29,728 ----------------------------------------------------------------------------------------------------
2023-10-24 22:36:38,347 epoch 4 - iter 72/723 - loss 0.04289293 - time (sec): 8.62 - samples/sec: 2030.37 - lr: 0.000023 - momentum: 0.000000
2023-10-24 22:36:46,920 epoch 4 - iter 144/723 - loss 0.04393330 - time (sec): 17.19 - samples/sec: 2020.50 - lr: 0.000023 - momentum: 0.000000
2023-10-24 22:36:54,721 epoch 4 - iter 216/723 - loss 0.04626933 - time (sec): 24.99 - samples/sec: 2029.60 - lr: 0.000022 - momentum: 0.000000
2023-10-24 22:37:03,203 epoch 4 - iter 288/723 - loss 0.04679271 - time (sec): 33.47 - samples/sec: 2008.90 - lr: 0.000022 - momentum: 0.000000
2023-10-24 22:37:12,171 epoch 4 - iter 360/723 - loss 0.04474950 - time (sec): 42.44 - samples/sec: 2022.65 - lr: 0.000022 - momentum: 0.000000
2023-10-24 22:37:21,110 epoch 4 - iter 432/723 - loss 0.04661379 - time (sec): 51.38 - samples/sec: 2025.29 - lr: 0.000021 - momentum: 0.000000
2023-10-24 22:37:30,179 epoch 4 - iter 504/723 - loss 0.04617695 - time (sec): 60.45 - samples/sec: 2026.61 - lr: 0.000021 - momentum: 0.000000
2023-10-24 22:37:38,883 epoch 4 - iter 576/723 - loss 0.04515587 - time (sec): 69.15 - samples/sec: 2031.07 - lr: 0.000021 - momentum: 0.000000
2023-10-24 22:37:47,642 epoch 4 - iter 648/723 - loss 0.04439814 - time (sec): 77.91 - samples/sec: 2028.48 - lr: 0.000020 - momentum: 0.000000
2023-10-24 22:37:56,158 epoch 4 - iter 720/723 - loss 0.04362410 - time (sec): 86.43 - samples/sec: 2033.94 - lr: 0.000020 - momentum: 0.000000
2023-10-24 22:37:56,386 ----------------------------------------------------------------------------------------------------
2023-10-24 22:37:56,387 EPOCH 4 done: loss 0.0437 - lr: 0.000020
2023-10-24 22:37:59,816 DEV : loss 0.09226194024085999 - f1-score (micro avg)  0.8141
2023-10-24 22:37:59,828 ----------------------------------------------------------------------------------------------------
2023-10-24 22:38:08,904 epoch 5 - iter 72/723 - loss 0.03491869 - time (sec): 9.08 - samples/sec: 2016.25 - lr: 0.000020 - momentum: 0.000000
2023-10-24 22:38:18,027 epoch 5 - iter 144/723 - loss 0.03697398 - time (sec): 18.20 - samples/sec: 1966.32 - lr: 0.000019 - momentum: 0.000000
2023-10-24 22:38:26,766 epoch 5 - iter 216/723 - loss 0.03299498 - time (sec): 26.94 - samples/sec: 1980.81 - lr: 0.000019 - momentum: 0.000000
2023-10-24 22:38:36,258 epoch 5 - iter 288/723 - loss 0.03395920 - time (sec): 36.43 - samples/sec: 1983.77 - lr: 0.000019 - momentum: 0.000000
2023-10-24 22:38:44,704 epoch 5 - iter 360/723 - loss 0.03351756 - time (sec): 44.88 - samples/sec: 1993.52 - lr: 0.000018 - momentum: 0.000000
2023-10-24 22:38:53,420 epoch 5 - iter 432/723 - loss 0.03259007 - time (sec): 53.59 - samples/sec: 2008.90 - lr: 0.000018 - momentum: 0.000000
2023-10-24 22:39:01,181 epoch 5 - iter 504/723 - loss 0.03251132 - time (sec): 61.35 - samples/sec: 2013.69 - lr: 0.000018 - momentum: 0.000000
2023-10-24 22:39:09,786 epoch 5 - iter 576/723 - loss 0.03147036 - time (sec): 69.96 - samples/sec: 2022.20 - lr: 0.000017 - momentum: 0.000000
2023-10-24 22:39:18,155 epoch 5 - iter 648/723 - loss 0.03152705 - time (sec): 78.33 - samples/sec: 2016.73 - lr: 0.000017 - momentum: 0.000000
2023-10-24 22:39:26,576 epoch 5 - iter 720/723 - loss 0.03165355 - time (sec): 86.75 - samples/sec: 2022.49 - lr: 0.000017 - momentum: 0.000000
2023-10-24 22:39:26,978 ----------------------------------------------------------------------------------------------------
2023-10-24 22:39:26,979 EPOCH 5 done: loss 0.0317 - lr: 0.000017
2023-10-24 22:39:30,691 DEV : loss 0.1143888533115387 - f1-score (micro avg)  0.8319
2023-10-24 22:39:30,703 ----------------------------------------------------------------------------------------------------
2023-10-24 22:39:39,467 epoch 6 - iter 72/723 - loss 0.01995720 - time (sec): 8.76 - samples/sec: 1955.67 - lr: 0.000016 - momentum: 0.000000
2023-10-24 22:39:47,873 epoch 6 - iter 144/723 - loss 0.02213871 - time (sec): 17.17 - samples/sec: 2001.18 - lr: 0.000016 - momentum: 0.000000
2023-10-24 22:39:57,180 epoch 6 - iter 216/723 - loss 0.02122386 - time (sec): 26.48 - samples/sec: 2013.81 - lr: 0.000016 - momentum: 0.000000
2023-10-24 22:40:05,862 epoch 6 - iter 288/723 - loss 0.02103884 - time (sec): 35.16 - samples/sec: 1996.29 - lr: 0.000015 - momentum: 0.000000
2023-10-24 22:40:14,288 epoch 6 - iter 360/723 - loss 0.02213591 - time (sec): 43.58 - samples/sec: 2004.08 - lr: 0.000015 - momentum: 0.000000
2023-10-24 22:40:22,944 epoch 6 - iter 432/723 - loss 0.02306774 - time (sec): 52.24 - samples/sec: 2015.55 - lr: 0.000015 - momentum: 0.000000
2023-10-24 22:40:31,393 epoch 6 - iter 504/723 - loss 0.02312191 - time (sec): 60.69 - samples/sec: 2032.38 - lr: 0.000014 - momentum: 0.000000
2023-10-24 22:40:40,001 epoch 6 - iter 576/723 - loss 0.02377623 - time (sec): 69.30 - samples/sec: 2032.40 - lr: 0.000014 - momentum: 0.000000
2023-10-24 22:40:48,317 epoch 6 - iter 648/723 - loss 0.02402287 - time (sec): 77.61 - samples/sec: 2042.80 - lr: 0.000014 - momentum: 0.000000
2023-10-24 22:40:56,641 epoch 6 - iter 720/723 - loss 0.02443272 - time (sec): 85.94 - samples/sec: 2044.18 - lr: 0.000013 - momentum: 0.000000
2023-10-24 22:40:56,909 ----------------------------------------------------------------------------------------------------
2023-10-24 22:40:56,910 EPOCH 6 done: loss 0.0244 - lr: 0.000013
2023-10-24 22:41:00,364 DEV : loss 0.12616097927093506 - f1-score (micro avg)  0.8405
2023-10-24 22:41:00,376 saving best model
2023-10-24 22:41:01,246 ----------------------------------------------------------------------------------------------------
2023-10-24 22:41:09,652 epoch 7 - iter 72/723 - loss 0.01313625 - time (sec): 8.40 - samples/sec: 2128.95 - lr: 0.000013 - momentum: 0.000000
2023-10-24 22:41:18,753 epoch 7 - iter 144/723 - loss 0.01797221 - time (sec): 17.51 - samples/sec: 2020.29 - lr: 0.000013 - momentum: 0.000000
2023-10-24 22:41:27,131 epoch 7 - iter 216/723 - loss 0.01779934 - time (sec): 25.88 - samples/sec: 2033.59 - lr: 0.000012 - momentum: 0.000000
2023-10-24 22:41:35,855 epoch 7 - iter 288/723 - loss 0.01742948 - time (sec): 34.61 - samples/sec: 2048.28 - lr: 0.000012 - momentum: 0.000000
2023-10-24 22:41:44,958 epoch 7 - iter 360/723 - loss 0.01829595 - time (sec): 43.71 - samples/sec: 2038.76 - lr: 0.000012 - momentum: 0.000000
2023-10-24 22:41:53,223 epoch 7 - iter 432/723 - loss 0.01860388 - time (sec): 51.98 - samples/sec: 2027.05 - lr: 0.000011 - momentum: 0.000000
2023-10-24 22:42:01,586 epoch 7 - iter 504/723 - loss 0.01859120 - time (sec): 60.34 - samples/sec: 2027.45 - lr: 0.000011 - momentum: 0.000000
2023-10-24 22:42:10,140 epoch 7 - iter 576/723 - loss 0.01846148 - time (sec): 68.89 - samples/sec: 2029.92 - lr: 0.000011 - momentum: 0.000000
2023-10-24 22:42:18,997 epoch 7 - iter 648/723 - loss 0.01760306 - time (sec): 77.75 - samples/sec: 2032.59 - lr: 0.000010 - momentum: 0.000000
2023-10-24 22:42:27,610 epoch 7 - iter 720/723 - loss 0.01743141 - time (sec): 86.36 - samples/sec: 2032.66 - lr: 0.000010 - momentum: 0.000000
2023-10-24 22:42:27,974 ----------------------------------------------------------------------------------------------------
2023-10-24 22:42:27,975 EPOCH 7 done: loss 0.0174 - lr: 0.000010
2023-10-24 22:42:31,416 DEV : loss 0.1625511348247528 - f1-score (micro avg)  0.8273
2023-10-24 22:42:31,428 ----------------------------------------------------------------------------------------------------
2023-10-24 22:42:40,071 epoch 8 - iter 72/723 - loss 0.01217969 - time (sec): 8.64 - samples/sec: 2041.96 - lr: 0.000010 - momentum: 0.000000
2023-10-24 22:42:49,190 epoch 8 - iter 144/723 - loss 0.01421228 - time (sec): 17.76 - samples/sec: 1996.70 - lr: 0.000009 - momentum: 0.000000
2023-10-24 22:42:57,430 epoch 8 - iter 216/723 - loss 0.01295467 - time (sec): 26.00 - samples/sec: 2040.84 - lr: 0.000009 - momentum: 0.000000
2023-10-24 22:43:06,802 epoch 8 - iter 288/723 - loss 0.01304675 - time (sec): 35.37 - samples/sec: 2069.04 - lr: 0.000009 - momentum: 0.000000
2023-10-24 22:43:15,158 epoch 8 - iter 360/723 - loss 0.01147798 - time (sec): 43.73 - samples/sec: 2062.23 - lr: 0.000008 - momentum: 0.000000
2023-10-24 22:43:23,633 epoch 8 - iter 432/723 - loss 0.01210736 - time (sec): 52.20 - samples/sec: 2063.22 - lr: 0.000008 - momentum: 0.000000
2023-10-24 22:43:32,367 epoch 8 - iter 504/723 - loss 0.01300207 - time (sec): 60.94 - samples/sec: 2051.84 - lr: 0.000008 - momentum: 0.000000
2023-10-24 22:43:40,103 epoch 8 - iter 576/723 - loss 0.01331943 - time (sec): 68.67 - samples/sec: 2042.03 - lr: 0.000007 - momentum: 0.000000
2023-10-24 22:43:48,376 epoch 8 - iter 648/723 - loss 0.01306185 - time (sec): 76.95 - samples/sec: 2042.52 - lr: 0.000007 - momentum: 0.000000
2023-10-24 22:43:57,171 epoch 8 - iter 720/723 - loss 0.01323653 - time (sec): 85.74 - samples/sec: 2046.87 - lr: 0.000007 - momentum: 0.000000
2023-10-24 22:43:57,642 ----------------------------------------------------------------------------------------------------
2023-10-24 22:43:57,642 EPOCH 8 done: loss 0.0132 - lr: 0.000007
2023-10-24 22:44:01,377 DEV : loss 0.14701317250728607 - f1-score (micro avg)  0.8396
2023-10-24 22:44:01,389 ----------------------------------------------------------------------------------------------------
2023-10-24 22:44:10,338 epoch 9 - iter 72/723 - loss 0.00421793 - time (sec): 8.95 - samples/sec: 2094.09 - lr: 0.000006 - momentum: 0.000000
2023-10-24 22:44:18,282 epoch 9 - iter 144/723 - loss 0.00746426 - time (sec): 16.89 - samples/sec: 2075.48 - lr: 0.000006 - momentum: 0.000000
2023-10-24 22:44:27,384 epoch 9 - iter 216/723 - loss 0.00859736 - time (sec): 25.99 - samples/sec: 2060.21 - lr: 0.000006 - momentum: 0.000000
2023-10-24 22:44:36,026 epoch 9 - iter 288/723 - loss 0.00966802 - time (sec): 34.64 - samples/sec: 2050.75 - lr: 0.000005 - momentum: 0.000000
2023-10-24 22:44:44,734 epoch 9 - iter 360/723 - loss 0.00936446 - time (sec): 43.34 - samples/sec: 2037.71 - lr: 0.000005 - momentum: 0.000000
2023-10-24 22:44:53,267 epoch 9 - iter 432/723 - loss 0.00876449 - time (sec): 51.88 - samples/sec: 2046.44 - lr: 0.000005 - momentum: 0.000000
2023-10-24 22:45:01,957 epoch 9 - iter 504/723 - loss 0.00947271 - time (sec): 60.57 - samples/sec: 2046.52 - lr: 0.000004 - momentum: 0.000000
2023-10-24 22:45:10,195 epoch 9 - iter 576/723 - loss 0.00911775 - time (sec): 68.81 - samples/sec: 2050.71 - lr: 0.000004 - momentum: 0.000000
2023-10-24 22:45:18,773 epoch 9 - iter 648/723 - loss 0.00878954 - time (sec): 77.38 - samples/sec: 2047.93 - lr: 0.000004 - momentum: 0.000000
2023-10-24 22:45:27,488 epoch 9 - iter 720/723 - loss 0.00902168 - time (sec): 86.10 - samples/sec: 2042.23 - lr: 0.000003 - momentum: 0.000000
2023-10-24 22:45:27,703 ----------------------------------------------------------------------------------------------------
2023-10-24 22:45:27,703 EPOCH 9 done: loss 0.0090 - lr: 0.000003
2023-10-24 22:45:31,141 DEV : loss 0.16477558016777039 - f1-score (micro avg)  0.8348
2023-10-24 22:45:31,153 ----------------------------------------------------------------------------------------------------
2023-10-24 22:45:39,876 epoch 10 - iter 72/723 - loss 0.00532785 - time (sec): 8.72 - samples/sec: 2001.01 - lr: 0.000003 - momentum: 0.000000
2023-10-24 22:45:48,365 epoch 10 - iter 144/723 - loss 0.00549018 - time (sec): 17.21 - samples/sec: 2063.17 - lr: 0.000003 - momentum: 0.000000
2023-10-24 22:45:57,326 epoch 10 - iter 216/723 - loss 0.00530542 - time (sec): 26.17 - samples/sec: 2080.27 - lr: 0.000002 - momentum: 0.000000
2023-10-24 22:46:06,688 epoch 10 - iter 288/723 - loss 0.00594591 - time (sec): 35.53 - samples/sec: 2048.79 - lr: 0.000002 - momentum: 0.000000
2023-10-24 22:46:15,127 epoch 10 - iter 360/723 - loss 0.00637310 - time (sec): 43.97 - samples/sec: 2036.30 - lr: 0.000002 - momentum: 0.000000
2023-10-24 22:46:24,052 epoch 10 - iter 432/723 - loss 0.00626112 - time (sec): 52.90 - samples/sec: 2018.61 - lr: 0.000001 - momentum: 0.000000
2023-10-24 22:46:32,684 epoch 10 - iter 504/723 - loss 0.00700602 - time (sec): 61.53 - samples/sec: 2017.36 - lr: 0.000001 - momentum: 0.000000
2023-10-24 22:46:41,008 epoch 10 - iter 576/723 - loss 0.00726040 - time (sec): 69.85 - samples/sec: 2026.17 - lr: 0.000001 - momentum: 0.000000
2023-10-24 22:46:49,862 epoch 10 - iter 648/723 - loss 0.00745651 - time (sec): 78.71 - samples/sec: 2015.95 - lr: 0.000000 - momentum: 0.000000
2023-10-24 22:46:58,135 epoch 10 - iter 720/723 - loss 0.00724114 - time (sec): 86.98 - samples/sec: 2021.35 - lr: 0.000000 - momentum: 0.000000
2023-10-24 22:46:58,346 ----------------------------------------------------------------------------------------------------
2023-10-24 22:46:58,347 EPOCH 10 done: loss 0.0072 - lr: 0.000000
2023-10-24 22:47:01,783 DEV : loss 0.16929292678833008 - f1-score (micro avg)  0.8392
2023-10-24 22:47:02,271 ----------------------------------------------------------------------------------------------------
2023-10-24 22:47:02,272 Loading model from best epoch ...
2023-10-24 22:47:04,037 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
2023-10-24 22:47:07,593 
Results:
- F-score (micro) 0.8156
- F-score (macro) 0.6995
- Accuracy 0.6985

By class:
              precision    recall  f1-score   support

         PER     0.8537    0.8112    0.8319       482
         LOC     0.8956    0.8057    0.8483       458
         ORG     0.5610    0.3333    0.4182        69

   micro avg     0.8595    0.7760    0.8156      1009
   macro avg     0.7701    0.6501    0.6995      1009
weighted avg     0.8527    0.7760    0.8110      1009

2023-10-24 22:47:07,593 ----------------------------------------------------------------------------------------------------