2023-10-25 01:57:10,020 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 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 01:57:10,021 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 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 01:57:10,021 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 Train:  5777 sentences
2023-10-25 01:57:10,021         (train_with_dev=False, train_with_test=False)
2023-10-25 01:57:10,021 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 Training Params:
2023-10-25 01:57:10,021  - learning_rate: "3e-05" 
2023-10-25 01:57:10,021  - mini_batch_size: "8"
2023-10-25 01:57:10,021  - max_epochs: "10"
2023-10-25 01:57:10,021  - shuffle: "True"
2023-10-25 01:57:10,021 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 Plugins:
2023-10-25 01:57:10,021  - TensorboardLogger
2023-10-25 01:57:10,021  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 01:57:10,021 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,021 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 01:57:10,021  - metric: "('micro avg', 'f1-score')"
2023-10-25 01:57:10,022 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,022 Computation:
2023-10-25 01:57:10,022  - compute on device: cuda:0
2023-10-25 01:57:10,022  - embedding storage: none
2023-10-25 01:57:10,022 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,022 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-25 01:57:10,022 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,022 ----------------------------------------------------------------------------------------------------
2023-10-25 01:57:10,022 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 01:57:18,564 epoch 1 - iter 72/723 - loss 1.76923904 - time (sec): 8.54 - samples/sec: 2081.38 - lr: 0.000003 - momentum: 0.000000
2023-10-25 01:57:27,609 epoch 1 - iter 144/723 - loss 1.02194984 - time (sec): 17.59 - samples/sec: 2076.99 - lr: 0.000006 - momentum: 0.000000
2023-10-25 01:57:36,349 epoch 1 - iter 216/723 - loss 0.76572650 - time (sec): 26.33 - samples/sec: 2059.56 - lr: 0.000009 - momentum: 0.000000
2023-10-25 01:57:44,054 epoch 1 - iter 288/723 - loss 0.63100097 - time (sec): 34.03 - samples/sec: 2065.69 - lr: 0.000012 - momentum: 0.000000
2023-10-25 01:57:52,520 epoch 1 - iter 360/723 - loss 0.53899991 - time (sec): 42.50 - samples/sec: 2046.32 - lr: 0.000015 - momentum: 0.000000
2023-10-25 01:58:00,735 epoch 1 - iter 432/723 - loss 0.47542277 - time (sec): 50.71 - samples/sec: 2052.53 - lr: 0.000018 - momentum: 0.000000
2023-10-25 01:58:09,949 epoch 1 - iter 504/723 - loss 0.42433087 - time (sec): 59.93 - samples/sec: 2063.60 - lr: 0.000021 - momentum: 0.000000
2023-10-25 01:58:17,923 epoch 1 - iter 576/723 - loss 0.39260870 - time (sec): 67.90 - samples/sec: 2064.22 - lr: 0.000024 - momentum: 0.000000
2023-10-25 01:58:26,808 epoch 1 - iter 648/723 - loss 0.36287974 - time (sec): 76.79 - samples/sec: 2059.99 - lr: 0.000027 - momentum: 0.000000
2023-10-25 01:58:35,478 epoch 1 - iter 720/723 - loss 0.33846946 - time (sec): 85.46 - samples/sec: 2055.41 - lr: 0.000030 - momentum: 0.000000
2023-10-25 01:58:35,775 ----------------------------------------------------------------------------------------------------
2023-10-25 01:58:35,775 EPOCH 1 done: loss 0.3379 - lr: 0.000030
2023-10-25 01:58:39,066 DEV : loss 0.11231282353401184 - f1-score (micro avg)  0.674
2023-10-25 01:58:39,078 saving best model
2023-10-25 01:58:39,545 ----------------------------------------------------------------------------------------------------
2023-10-25 01:58:48,181 epoch 2 - iter 72/723 - loss 0.09877093 - time (sec): 8.64 - samples/sec: 2036.26 - lr: 0.000030 - momentum: 0.000000
2023-10-25 01:58:56,556 epoch 2 - iter 144/723 - loss 0.10109280 - time (sec): 17.01 - samples/sec: 2056.82 - lr: 0.000029 - momentum: 0.000000
2023-10-25 01:59:05,625 epoch 2 - iter 216/723 - loss 0.09847841 - time (sec): 26.08 - samples/sec: 2047.40 - lr: 0.000029 - momentum: 0.000000
2023-10-25 01:59:14,560 epoch 2 - iter 288/723 - loss 0.09458357 - time (sec): 35.01 - samples/sec: 2059.57 - lr: 0.000029 - momentum: 0.000000
2023-10-25 01:59:23,407 epoch 2 - iter 360/723 - loss 0.09619714 - time (sec): 43.86 - samples/sec: 2056.17 - lr: 0.000028 - momentum: 0.000000
2023-10-25 01:59:32,184 epoch 2 - iter 432/723 - loss 0.09830646 - time (sec): 52.64 - samples/sec: 2040.11 - lr: 0.000028 - momentum: 0.000000
2023-10-25 01:59:40,263 epoch 2 - iter 504/723 - loss 0.09849915 - time (sec): 60.72 - samples/sec: 2044.13 - lr: 0.000028 - momentum: 0.000000
2023-10-25 01:59:48,249 epoch 2 - iter 576/723 - loss 0.09981080 - time (sec): 68.70 - samples/sec: 2042.04 - lr: 0.000027 - momentum: 0.000000
2023-10-25 01:59:56,577 epoch 2 - iter 648/723 - loss 0.09929029 - time (sec): 77.03 - samples/sec: 2042.02 - lr: 0.000027 - momentum: 0.000000
2023-10-25 02:00:05,960 epoch 2 - iter 720/723 - loss 0.09794570 - time (sec): 86.41 - samples/sec: 2033.04 - lr: 0.000027 - momentum: 0.000000
2023-10-25 02:00:06,223 ----------------------------------------------------------------------------------------------------
2023-10-25 02:00:06,223 EPOCH 2 done: loss 0.0980 - lr: 0.000027
2023-10-25 02:00:09,924 DEV : loss 0.07828789204359055 - f1-score (micro avg)  0.806
2023-10-25 02:00:09,935 saving best model
2023-10-25 02:00:10,523 ----------------------------------------------------------------------------------------------------
2023-10-25 02:00:18,673 epoch 3 - iter 72/723 - loss 0.06198109 - time (sec): 8.15 - samples/sec: 2012.08 - lr: 0.000026 - momentum: 0.000000
2023-10-25 02:00:27,884 epoch 3 - iter 144/723 - loss 0.06527874 - time (sec): 17.36 - samples/sec: 2022.88 - lr: 0.000026 - momentum: 0.000000
2023-10-25 02:00:37,322 epoch 3 - iter 216/723 - loss 0.06427805 - time (sec): 26.80 - samples/sec: 2020.15 - lr: 0.000026 - momentum: 0.000000
2023-10-25 02:00:45,394 epoch 3 - iter 288/723 - loss 0.06175598 - time (sec): 34.87 - samples/sec: 2037.50 - lr: 0.000025 - momentum: 0.000000
2023-10-25 02:00:54,010 epoch 3 - iter 360/723 - loss 0.06098889 - time (sec): 43.49 - samples/sec: 2039.72 - lr: 0.000025 - momentum: 0.000000
2023-10-25 02:01:02,672 epoch 3 - iter 432/723 - loss 0.06065212 - time (sec): 52.15 - samples/sec: 2028.25 - lr: 0.000025 - momentum: 0.000000
2023-10-25 02:01:11,492 epoch 3 - iter 504/723 - loss 0.06224962 - time (sec): 60.97 - samples/sec: 2025.42 - lr: 0.000024 - momentum: 0.000000
2023-10-25 02:01:19,924 epoch 3 - iter 576/723 - loss 0.06131250 - time (sec): 69.40 - samples/sec: 2032.42 - lr: 0.000024 - momentum: 0.000000
2023-10-25 02:01:28,012 epoch 3 - iter 648/723 - loss 0.06236989 - time (sec): 77.49 - samples/sec: 2030.94 - lr: 0.000024 - momentum: 0.000000
2023-10-25 02:01:36,993 epoch 3 - iter 720/723 - loss 0.06197838 - time (sec): 86.47 - samples/sec: 2030.66 - lr: 0.000023 - momentum: 0.000000
2023-10-25 02:01:37,283 ----------------------------------------------------------------------------------------------------
2023-10-25 02:01:37,283 EPOCH 3 done: loss 0.0619 - lr: 0.000023
2023-10-25 02:01:40,715 DEV : loss 0.07889249920845032 - f1-score (micro avg)  0.8187
2023-10-25 02:01:40,727 saving best model
2023-10-25 02:01:41,604 ----------------------------------------------------------------------------------------------------
2023-10-25 02:01:49,477 epoch 4 - iter 72/723 - loss 0.03547065 - time (sec): 7.87 - samples/sec: 2115.66 - lr: 0.000023 - momentum: 0.000000
2023-10-25 02:01:57,245 epoch 4 - iter 144/723 - loss 0.03615245 - time (sec): 15.64 - samples/sec: 2088.46 - lr: 0.000023 - momentum: 0.000000
2023-10-25 02:02:06,293 epoch 4 - iter 216/723 - loss 0.03524641 - time (sec): 24.69 - samples/sec: 2067.24 - lr: 0.000022 - momentum: 0.000000
2023-10-25 02:02:15,868 epoch 4 - iter 288/723 - loss 0.03601960 - time (sec): 34.26 - samples/sec: 2036.14 - lr: 0.000022 - momentum: 0.000000
2023-10-25 02:02:24,460 epoch 4 - iter 360/723 - loss 0.03839060 - time (sec): 42.86 - samples/sec: 2035.86 - lr: 0.000022 - momentum: 0.000000
2023-10-25 02:02:32,074 epoch 4 - iter 432/723 - loss 0.03960256 - time (sec): 50.47 - samples/sec: 2039.66 - lr: 0.000021 - momentum: 0.000000
2023-10-25 02:02:41,518 epoch 4 - iter 504/723 - loss 0.03882792 - time (sec): 59.91 - samples/sec: 2043.37 - lr: 0.000021 - momentum: 0.000000
2023-10-25 02:02:50,069 epoch 4 - iter 576/723 - loss 0.04084126 - time (sec): 68.46 - samples/sec: 2051.86 - lr: 0.000021 - momentum: 0.000000
2023-10-25 02:02:59,175 epoch 4 - iter 648/723 - loss 0.04148523 - time (sec): 77.57 - samples/sec: 2039.34 - lr: 0.000020 - momentum: 0.000000
2023-10-25 02:03:07,642 epoch 4 - iter 720/723 - loss 0.04215552 - time (sec): 86.04 - samples/sec: 2040.91 - lr: 0.000020 - momentum: 0.000000
2023-10-25 02:03:08,002 ----------------------------------------------------------------------------------------------------
2023-10-25 02:03:08,002 EPOCH 4 done: loss 0.0422 - lr: 0.000020
2023-10-25 02:03:11,428 DEV : loss 0.08857569843530655 - f1-score (micro avg)  0.8152
2023-10-25 02:03:11,440 ----------------------------------------------------------------------------------------------------
2023-10-25 02:03:20,580 epoch 5 - iter 72/723 - loss 0.03032337 - time (sec): 9.14 - samples/sec: 2016.26 - lr: 0.000020 - momentum: 0.000000
2023-10-25 02:03:28,862 epoch 5 - iter 144/723 - loss 0.03022295 - time (sec): 17.42 - samples/sec: 2045.28 - lr: 0.000019 - momentum: 0.000000
2023-10-25 02:03:37,784 epoch 5 - iter 216/723 - loss 0.03156000 - time (sec): 26.34 - samples/sec: 2026.79 - lr: 0.000019 - momentum: 0.000000
2023-10-25 02:03:46,416 epoch 5 - iter 288/723 - loss 0.03054376 - time (sec): 34.98 - samples/sec: 2024.47 - lr: 0.000019 - momentum: 0.000000
2023-10-25 02:03:55,592 epoch 5 - iter 360/723 - loss 0.03181466 - time (sec): 44.15 - samples/sec: 2018.45 - lr: 0.000018 - momentum: 0.000000
2023-10-25 02:04:04,054 epoch 5 - iter 432/723 - loss 0.03195174 - time (sec): 52.61 - samples/sec: 2031.68 - lr: 0.000018 - momentum: 0.000000
2023-10-25 02:04:13,084 epoch 5 - iter 504/723 - loss 0.03082310 - time (sec): 61.64 - samples/sec: 2019.75 - lr: 0.000018 - momentum: 0.000000
2023-10-25 02:04:21,429 epoch 5 - iter 576/723 - loss 0.03053546 - time (sec): 69.99 - samples/sec: 2021.67 - lr: 0.000017 - momentum: 0.000000
2023-10-25 02:04:29,957 epoch 5 - iter 648/723 - loss 0.03077615 - time (sec): 78.52 - samples/sec: 2018.21 - lr: 0.000017 - momentum: 0.000000
2023-10-25 02:04:38,508 epoch 5 - iter 720/723 - loss 0.03132395 - time (sec): 87.07 - samples/sec: 2017.06 - lr: 0.000017 - momentum: 0.000000
2023-10-25 02:04:38,820 ----------------------------------------------------------------------------------------------------
2023-10-25 02:04:38,820 EPOCH 5 done: loss 0.0313 - lr: 0.000017
2023-10-25 02:04:42,571 DEV : loss 0.13429175317287445 - f1-score (micro avg)  0.8056
2023-10-25 02:04:42,583 ----------------------------------------------------------------------------------------------------
2023-10-25 02:04:51,054 epoch 6 - iter 72/723 - loss 0.01367169 - time (sec): 8.47 - samples/sec: 2080.33 - lr: 0.000016 - momentum: 0.000000
2023-10-25 02:04:59,541 epoch 6 - iter 144/723 - loss 0.01585753 - time (sec): 16.96 - samples/sec: 2057.02 - lr: 0.000016 - momentum: 0.000000
2023-10-25 02:05:08,192 epoch 6 - iter 216/723 - loss 0.02218546 - time (sec): 25.61 - samples/sec: 2067.32 - lr: 0.000016 - momentum: 0.000000
2023-10-25 02:05:16,920 epoch 6 - iter 288/723 - loss 0.02190850 - time (sec): 34.34 - samples/sec: 2058.93 - lr: 0.000015 - momentum: 0.000000
2023-10-25 02:05:26,395 epoch 6 - iter 360/723 - loss 0.02267499 - time (sec): 43.81 - samples/sec: 2046.85 - lr: 0.000015 - momentum: 0.000000
2023-10-25 02:05:35,128 epoch 6 - iter 432/723 - loss 0.02297097 - time (sec): 52.54 - samples/sec: 2041.22 - lr: 0.000015 - momentum: 0.000000
2023-10-25 02:05:43,638 epoch 6 - iter 504/723 - loss 0.02330794 - time (sec): 61.05 - samples/sec: 2029.07 - lr: 0.000014 - momentum: 0.000000
2023-10-25 02:05:52,188 epoch 6 - iter 576/723 - loss 0.02379736 - time (sec): 69.60 - samples/sec: 2023.47 - lr: 0.000014 - momentum: 0.000000
2023-10-25 02:06:01,280 epoch 6 - iter 648/723 - loss 0.02466991 - time (sec): 78.70 - samples/sec: 2020.22 - lr: 0.000014 - momentum: 0.000000
2023-10-25 02:06:09,367 epoch 6 - iter 720/723 - loss 0.02437194 - time (sec): 86.78 - samples/sec: 2024.28 - lr: 0.000013 - momentum: 0.000000
2023-10-25 02:06:09,695 ----------------------------------------------------------------------------------------------------
2023-10-25 02:06:09,695 EPOCH 6 done: loss 0.0245 - lr: 0.000013
2023-10-25 02:06:13,131 DEV : loss 0.14080575108528137 - f1-score (micro avg)  0.8217
2023-10-25 02:06:13,143 saving best model
2023-10-25 02:06:13,735 ----------------------------------------------------------------------------------------------------
2023-10-25 02:06:23,735 epoch 7 - iter 72/723 - loss 0.01098581 - time (sec): 10.00 - samples/sec: 1887.19 - lr: 0.000013 - momentum: 0.000000
2023-10-25 02:06:33,054 epoch 7 - iter 144/723 - loss 0.01537901 - time (sec): 19.32 - samples/sec: 1911.08 - lr: 0.000013 - momentum: 0.000000
2023-10-25 02:06:41,678 epoch 7 - iter 216/723 - loss 0.01497113 - time (sec): 27.94 - samples/sec: 1932.38 - lr: 0.000012 - momentum: 0.000000
2023-10-25 02:06:50,197 epoch 7 - iter 288/723 - loss 0.01604563 - time (sec): 36.46 - samples/sec: 1964.82 - lr: 0.000012 - momentum: 0.000000
2023-10-25 02:06:58,743 epoch 7 - iter 360/723 - loss 0.01505398 - time (sec): 45.01 - samples/sec: 1993.38 - lr: 0.000012 - momentum: 0.000000
2023-10-25 02:07:06,856 epoch 7 - iter 432/723 - loss 0.01538597 - time (sec): 53.12 - samples/sec: 2011.13 - lr: 0.000011 - momentum: 0.000000
2023-10-25 02:07:15,150 epoch 7 - iter 504/723 - loss 0.01617676 - time (sec): 61.41 - samples/sec: 2008.32 - lr: 0.000011 - momentum: 0.000000
2023-10-25 02:07:23,595 epoch 7 - iter 576/723 - loss 0.01694236 - time (sec): 69.86 - samples/sec: 2013.89 - lr: 0.000011 - momentum: 0.000000
2023-10-25 02:07:32,512 epoch 7 - iter 648/723 - loss 0.01645753 - time (sec): 78.78 - samples/sec: 2023.17 - lr: 0.000010 - momentum: 0.000000
2023-10-25 02:07:40,519 epoch 7 - iter 720/723 - loss 0.01637803 - time (sec): 86.78 - samples/sec: 2025.51 - lr: 0.000010 - momentum: 0.000000
2023-10-25 02:07:40,756 ----------------------------------------------------------------------------------------------------
2023-10-25 02:07:40,757 EPOCH 7 done: loss 0.0164 - lr: 0.000010
2023-10-25 02:07:44,192 DEV : loss 0.15570510923862457 - f1-score (micro avg)  0.8346
2023-10-25 02:07:44,204 saving best model
2023-10-25 02:07:44,786 ----------------------------------------------------------------------------------------------------
2023-10-25 02:07:53,036 epoch 8 - iter 72/723 - loss 0.01309712 - time (sec): 8.25 - samples/sec: 2153.09 - lr: 0.000010 - momentum: 0.000000
2023-10-25 02:08:01,661 epoch 8 - iter 144/723 - loss 0.01223716 - time (sec): 16.87 - samples/sec: 2119.06 - lr: 0.000009 - momentum: 0.000000
2023-10-25 02:08:10,351 epoch 8 - iter 216/723 - loss 0.01227785 - time (sec): 25.56 - samples/sec: 2072.17 - lr: 0.000009 - momentum: 0.000000
2023-10-25 02:08:19,092 epoch 8 - iter 288/723 - loss 0.01256366 - time (sec): 34.31 - samples/sec: 2062.39 - lr: 0.000009 - momentum: 0.000000
2023-10-25 02:08:27,865 epoch 8 - iter 360/723 - loss 0.01225996 - time (sec): 43.08 - samples/sec: 2059.21 - lr: 0.000008 - momentum: 0.000000
2023-10-25 02:08:36,583 epoch 8 - iter 432/723 - loss 0.01189296 - time (sec): 51.80 - samples/sec: 2067.58 - lr: 0.000008 - momentum: 0.000000
2023-10-25 02:08:44,833 epoch 8 - iter 504/723 - loss 0.01204948 - time (sec): 60.05 - samples/sec: 2071.09 - lr: 0.000008 - momentum: 0.000000
2023-10-25 02:08:52,800 epoch 8 - iter 576/723 - loss 0.01168071 - time (sec): 68.01 - samples/sec: 2062.87 - lr: 0.000007 - momentum: 0.000000
2023-10-25 02:09:01,566 epoch 8 - iter 648/723 - loss 0.01278714 - time (sec): 76.78 - samples/sec: 2056.45 - lr: 0.000007 - momentum: 0.000000
2023-10-25 02:09:10,329 epoch 8 - iter 720/723 - loss 0.01274436 - time (sec): 85.54 - samples/sec: 2052.17 - lr: 0.000007 - momentum: 0.000000
2023-10-25 02:09:10,650 ----------------------------------------------------------------------------------------------------
2023-10-25 02:09:10,650 EPOCH 8 done: loss 0.0127 - lr: 0.000007
2023-10-25 02:09:14,365 DEV : loss 0.1717204749584198 - f1-score (micro avg)  0.8326
2023-10-25 02:09:14,377 ----------------------------------------------------------------------------------------------------
2023-10-25 02:09:23,098 epoch 9 - iter 72/723 - loss 0.00789912 - time (sec): 8.72 - samples/sec: 2081.85 - lr: 0.000006 - momentum: 0.000000
2023-10-25 02:09:30,935 epoch 9 - iter 144/723 - loss 0.00864702 - time (sec): 16.56 - samples/sec: 2058.46 - lr: 0.000006 - momentum: 0.000000
2023-10-25 02:09:39,734 epoch 9 - iter 216/723 - loss 0.00868959 - time (sec): 25.36 - samples/sec: 2036.57 - lr: 0.000006 - momentum: 0.000000
2023-10-25 02:09:48,226 epoch 9 - iter 288/723 - loss 0.00778029 - time (sec): 33.85 - samples/sec: 2043.96 - lr: 0.000005 - momentum: 0.000000
2023-10-25 02:09:56,296 epoch 9 - iter 360/723 - loss 0.00691008 - time (sec): 41.92 - samples/sec: 2048.82 - lr: 0.000005 - momentum: 0.000000
2023-10-25 02:10:05,211 epoch 9 - iter 432/723 - loss 0.00740542 - time (sec): 50.83 - samples/sec: 2058.24 - lr: 0.000005 - momentum: 0.000000
2023-10-25 02:10:13,970 epoch 9 - iter 504/723 - loss 0.00767085 - time (sec): 59.59 - samples/sec: 2060.52 - lr: 0.000004 - momentum: 0.000000
2023-10-25 02:10:22,837 epoch 9 - iter 576/723 - loss 0.00813665 - time (sec): 68.46 - samples/sec: 2047.75 - lr: 0.000004 - momentum: 0.000000
2023-10-25 02:10:31,665 epoch 9 - iter 648/723 - loss 0.00835648 - time (sec): 77.29 - samples/sec: 2046.98 - lr: 0.000004 - momentum: 0.000000
2023-10-25 02:10:40,427 epoch 9 - iter 720/723 - loss 0.00850227 - time (sec): 86.05 - samples/sec: 2042.09 - lr: 0.000003 - momentum: 0.000000
2023-10-25 02:10:40,686 ----------------------------------------------------------------------------------------------------
2023-10-25 02:10:40,687 EPOCH 9 done: loss 0.0085 - lr: 0.000003
2023-10-25 02:10:44,419 DEV : loss 0.1841525286436081 - f1-score (micro avg)  0.825
2023-10-25 02:10:44,431 ----------------------------------------------------------------------------------------------------
2023-10-25 02:10:52,780 epoch 10 - iter 72/723 - loss 0.00481871 - time (sec): 8.35 - samples/sec: 2007.01 - lr: 0.000003 - momentum: 0.000000
2023-10-25 02:11:01,397 epoch 10 - iter 144/723 - loss 0.00626100 - time (sec): 16.97 - samples/sec: 2046.98 - lr: 0.000003 - momentum: 0.000000
2023-10-25 02:11:09,955 epoch 10 - iter 216/723 - loss 0.00618329 - time (sec): 25.52 - samples/sec: 2053.89 - lr: 0.000002 - momentum: 0.000000
2023-10-25 02:11:19,139 epoch 10 - iter 288/723 - loss 0.00580240 - time (sec): 34.71 - samples/sec: 2024.11 - lr: 0.000002 - momentum: 0.000000
2023-10-25 02:11:27,711 epoch 10 - iter 360/723 - loss 0.00586626 - time (sec): 43.28 - samples/sec: 2019.33 - lr: 0.000002 - momentum: 0.000000
2023-10-25 02:11:36,279 epoch 10 - iter 432/723 - loss 0.00601919 - time (sec): 51.85 - samples/sec: 2027.37 - lr: 0.000001 - momentum: 0.000000
2023-10-25 02:11:44,889 epoch 10 - iter 504/723 - loss 0.00603383 - time (sec): 60.46 - samples/sec: 2033.59 - lr: 0.000001 - momentum: 0.000000
2023-10-25 02:11:53,227 epoch 10 - iter 576/723 - loss 0.00737357 - time (sec): 68.80 - samples/sec: 2028.89 - lr: 0.000001 - momentum: 0.000000
2023-10-25 02:12:01,809 epoch 10 - iter 648/723 - loss 0.00682436 - time (sec): 77.38 - samples/sec: 2028.68 - lr: 0.000000 - momentum: 0.000000
2023-10-25 02:12:10,623 epoch 10 - iter 720/723 - loss 0.00665171 - time (sec): 86.19 - samples/sec: 2035.60 - lr: 0.000000 - momentum: 0.000000
2023-10-25 02:12:10,917 ----------------------------------------------------------------------------------------------------
2023-10-25 02:12:10,918 EPOCH 10 done: loss 0.0066 - lr: 0.000000
2023-10-25 02:12:14,347 DEV : loss 0.19385258853435516 - f1-score (micro avg)  0.833
2023-10-25 02:12:14,823 ----------------------------------------------------------------------------------------------------
2023-10-25 02:12:14,823 Loading model from best epoch ...
2023-10-25 02:12:16,332 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 02:12:19,857 
Results:
- F-score (micro) 0.8133
- F-score (macro) 0.7041
- Accuracy 0.6967

By class:
              precision    recall  f1-score   support

         PER     0.8452    0.8154    0.8300       482
         LOC     0.8847    0.8210    0.8516       458
         ORG     0.4590    0.4058    0.4308        69

   micro avg     0.8381    0.7899    0.8133      1009
   macro avg     0.7296    0.6807    0.7041      1009
weighted avg     0.8367    0.7899    0.8125      1009

2023-10-25 02:12:19,857 ----------------------------------------------------------------------------------------------------