2023-10-24 19:20:16,509 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,510 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 19:20:16,511 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,511 MultiCorpus: 7936 train + 992 dev + 992 test sentences
 - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/fr
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Train:  7936 sentences
2023-10-24 19:20:16,512         (train_with_dev=False, train_with_test=False)
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Training Params:
2023-10-24 19:20:16,512  - learning_rate: "3e-05" 
2023-10-24 19:20:16,512  - mini_batch_size: "4"
2023-10-24 19:20:16,512  - max_epochs: "10"
2023-10-24 19:20:16,512  - shuffle: "True"
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Plugins:
2023-10-24 19:20:16,512  - TensorboardLogger
2023-10-24 19:20:16,512  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 19:20:16,512  - metric: "('micro avg', 'f1-score')"
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Computation:
2023-10-24 19:20:16,512  - compute on device: cuda:0
2023-10-24 19:20:16,512  - embedding storage: none
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,512 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-24 19:20:16,512 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,513 ----------------------------------------------------------------------------------------------------
2023-10-24 19:20:16,513 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 19:20:28,549 epoch 1 - iter 198/1984 - loss 1.32014092 - time (sec): 12.04 - samples/sec: 1372.54 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:20:40,509 epoch 1 - iter 396/1984 - loss 0.82590169 - time (sec): 24.00 - samples/sec: 1347.40 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:20:52,633 epoch 1 - iter 594/1984 - loss 0.62234473 - time (sec): 36.12 - samples/sec: 1359.25 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:21:04,703 epoch 1 - iter 792/1984 - loss 0.51779669 - time (sec): 48.19 - samples/sec: 1349.30 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:21:16,796 epoch 1 - iter 990/1984 - loss 0.44752052 - time (sec): 60.28 - samples/sec: 1352.27 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:21:28,869 epoch 1 - iter 1188/1984 - loss 0.39941383 - time (sec): 72.36 - samples/sec: 1352.98 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:21:40,973 epoch 1 - iter 1386/1984 - loss 0.36252978 - time (sec): 84.46 - samples/sec: 1355.89 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:21:53,022 epoch 1 - iter 1584/1984 - loss 0.33296148 - time (sec): 96.51 - samples/sec: 1351.32 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:22:05,124 epoch 1 - iter 1782/1984 - loss 0.31002868 - time (sec): 108.61 - samples/sec: 1353.86 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:22:17,309 epoch 1 - iter 1980/1984 - loss 0.29254745 - time (sec): 120.80 - samples/sec: 1355.42 - lr: 0.000030 - momentum: 0.000000
2023-10-24 19:22:17,540 ----------------------------------------------------------------------------------------------------
2023-10-24 19:22:17,540 EPOCH 1 done: loss 0.2922 - lr: 0.000030
2023-10-24 19:22:20,599 DEV : loss 0.11393631994724274 - f1-score (micro avg)  0.7142
2023-10-24 19:22:20,614 saving best model
2023-10-24 19:22:21,081 ----------------------------------------------------------------------------------------------------
2023-10-24 19:22:33,239 epoch 2 - iter 198/1984 - loss 0.11109567 - time (sec): 12.16 - samples/sec: 1354.61 - lr: 0.000030 - momentum: 0.000000
2023-10-24 19:22:45,371 epoch 2 - iter 396/1984 - loss 0.11188014 - time (sec): 24.29 - samples/sec: 1357.95 - lr: 0.000029 - momentum: 0.000000
2023-10-24 19:22:57,459 epoch 2 - iter 594/1984 - loss 0.12088148 - time (sec): 36.38 - samples/sec: 1369.44 - lr: 0.000029 - momentum: 0.000000
2023-10-24 19:23:09,475 epoch 2 - iter 792/1984 - loss 0.12005888 - time (sec): 48.39 - samples/sec: 1355.48 - lr: 0.000029 - momentum: 0.000000
2023-10-24 19:23:21,419 epoch 2 - iter 990/1984 - loss 0.11907747 - time (sec): 60.34 - samples/sec: 1344.35 - lr: 0.000028 - momentum: 0.000000
2023-10-24 19:23:33,494 epoch 2 - iter 1188/1984 - loss 0.11881279 - time (sec): 72.41 - samples/sec: 1342.66 - lr: 0.000028 - momentum: 0.000000
2023-10-24 19:23:45,448 epoch 2 - iter 1386/1984 - loss 0.11809499 - time (sec): 84.37 - samples/sec: 1344.77 - lr: 0.000028 - momentum: 0.000000
2023-10-24 19:23:57,836 epoch 2 - iter 1584/1984 - loss 0.11496911 - time (sec): 96.75 - samples/sec: 1350.51 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:24:10,044 epoch 2 - iter 1782/1984 - loss 0.11353484 - time (sec): 108.96 - samples/sec: 1347.87 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:24:22,155 epoch 2 - iter 1980/1984 - loss 0.11233027 - time (sec): 121.07 - samples/sec: 1353.14 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:24:22,383 ----------------------------------------------------------------------------------------------------
2023-10-24 19:24:22,383 EPOCH 2 done: loss 0.1126 - lr: 0.000027
2023-10-24 19:24:25,798 DEV : loss 0.11593124270439148 - f1-score (micro avg)  0.7271
2023-10-24 19:24:25,813 saving best model
2023-10-24 19:24:26,407 ----------------------------------------------------------------------------------------------------
2023-10-24 19:24:38,620 epoch 3 - iter 198/1984 - loss 0.08265116 - time (sec): 12.21 - samples/sec: 1416.54 - lr: 0.000026 - momentum: 0.000000
2023-10-24 19:24:50,809 epoch 3 - iter 396/1984 - loss 0.07804517 - time (sec): 24.40 - samples/sec: 1401.12 - lr: 0.000026 - momentum: 0.000000
2023-10-24 19:25:03,281 epoch 3 - iter 594/1984 - loss 0.08404645 - time (sec): 36.87 - samples/sec: 1385.28 - lr: 0.000026 - momentum: 0.000000
2023-10-24 19:25:15,312 epoch 3 - iter 792/1984 - loss 0.08231776 - time (sec): 48.90 - samples/sec: 1359.00 - lr: 0.000025 - momentum: 0.000000
2023-10-24 19:25:27,283 epoch 3 - iter 990/1984 - loss 0.08429583 - time (sec): 60.87 - samples/sec: 1354.01 - lr: 0.000025 - momentum: 0.000000
2023-10-24 19:25:39,410 epoch 3 - iter 1188/1984 - loss 0.08375321 - time (sec): 73.00 - samples/sec: 1341.90 - lr: 0.000025 - momentum: 0.000000
2023-10-24 19:25:51,397 epoch 3 - iter 1386/1984 - loss 0.08571122 - time (sec): 84.99 - samples/sec: 1343.09 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:26:03,534 epoch 3 - iter 1584/1984 - loss 0.08551290 - time (sec): 97.13 - samples/sec: 1344.76 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:26:15,614 epoch 3 - iter 1782/1984 - loss 0.08579605 - time (sec): 109.21 - samples/sec: 1348.07 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:26:27,719 epoch 3 - iter 1980/1984 - loss 0.08549504 - time (sec): 121.31 - samples/sec: 1349.14 - lr: 0.000023 - momentum: 0.000000
2023-10-24 19:26:27,962 ----------------------------------------------------------------------------------------------------
2023-10-24 19:26:27,962 EPOCH 3 done: loss 0.0857 - lr: 0.000023
2023-10-24 19:26:31,075 DEV : loss 0.12287832796573639 - f1-score (micro avg)  0.756
2023-10-24 19:26:31,090 saving best model
2023-10-24 19:26:31,684 ----------------------------------------------------------------------------------------------------
2023-10-24 19:26:43,776 epoch 4 - iter 198/1984 - loss 0.05492174 - time (sec): 12.09 - samples/sec: 1306.03 - lr: 0.000023 - momentum: 0.000000
2023-10-24 19:26:55,794 epoch 4 - iter 396/1984 - loss 0.06173660 - time (sec): 24.11 - samples/sec: 1325.23 - lr: 0.000023 - momentum: 0.000000
2023-10-24 19:27:07,916 epoch 4 - iter 594/1984 - loss 0.06108648 - time (sec): 36.23 - samples/sec: 1329.97 - lr: 0.000022 - momentum: 0.000000
2023-10-24 19:27:19,998 epoch 4 - iter 792/1984 - loss 0.06054768 - time (sec): 48.31 - samples/sec: 1333.58 - lr: 0.000022 - momentum: 0.000000
2023-10-24 19:27:32,167 epoch 4 - iter 990/1984 - loss 0.06244785 - time (sec): 60.48 - samples/sec: 1341.29 - lr: 0.000022 - momentum: 0.000000
2023-10-24 19:27:44,204 epoch 4 - iter 1188/1984 - loss 0.06144580 - time (sec): 72.52 - samples/sec: 1342.52 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:27:56,373 epoch 4 - iter 1386/1984 - loss 0.06113227 - time (sec): 84.69 - samples/sec: 1348.41 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:28:09,135 epoch 4 - iter 1584/1984 - loss 0.06036745 - time (sec): 97.45 - samples/sec: 1352.40 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:28:21,273 epoch 4 - iter 1782/1984 - loss 0.06099629 - time (sec): 109.59 - samples/sec: 1351.83 - lr: 0.000020 - momentum: 0.000000
2023-10-24 19:28:33,327 epoch 4 - iter 1980/1984 - loss 0.06067905 - time (sec): 121.64 - samples/sec: 1346.46 - lr: 0.000020 - momentum: 0.000000
2023-10-24 19:28:33,553 ----------------------------------------------------------------------------------------------------
2023-10-24 19:28:33,553 EPOCH 4 done: loss 0.0607 - lr: 0.000020
2023-10-24 19:28:36,684 DEV : loss 0.1927175521850586 - f1-score (micro avg)  0.7183
2023-10-24 19:28:36,699 ----------------------------------------------------------------------------------------------------
2023-10-24 19:28:48,910 epoch 5 - iter 198/1984 - loss 0.04671831 - time (sec): 12.21 - samples/sec: 1361.09 - lr: 0.000020 - momentum: 0.000000
2023-10-24 19:29:01,027 epoch 5 - iter 396/1984 - loss 0.04574779 - time (sec): 24.33 - samples/sec: 1356.48 - lr: 0.000019 - momentum: 0.000000
2023-10-24 19:29:13,073 epoch 5 - iter 594/1984 - loss 0.04539830 - time (sec): 36.37 - samples/sec: 1356.89 - lr: 0.000019 - momentum: 0.000000
2023-10-24 19:29:25,286 epoch 5 - iter 792/1984 - loss 0.04680807 - time (sec): 48.59 - samples/sec: 1358.20 - lr: 0.000019 - momentum: 0.000000
2023-10-24 19:29:37,625 epoch 5 - iter 990/1984 - loss 0.04441270 - time (sec): 60.93 - samples/sec: 1373.34 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:29:49,703 epoch 5 - iter 1188/1984 - loss 0.04380522 - time (sec): 73.00 - samples/sec: 1369.44 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:30:02,105 epoch 5 - iter 1386/1984 - loss 0.04443524 - time (sec): 85.41 - samples/sec: 1371.38 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:30:14,134 epoch 5 - iter 1584/1984 - loss 0.04578146 - time (sec): 97.43 - samples/sec: 1363.32 - lr: 0.000017 - momentum: 0.000000
2023-10-24 19:30:26,194 epoch 5 - iter 1782/1984 - loss 0.04603563 - time (sec): 109.49 - samples/sec: 1350.91 - lr: 0.000017 - momentum: 0.000000
2023-10-24 19:30:38,245 epoch 5 - iter 1980/1984 - loss 0.04522297 - time (sec): 121.55 - samples/sec: 1347.11 - lr: 0.000017 - momentum: 0.000000
2023-10-24 19:30:38,479 ----------------------------------------------------------------------------------------------------
2023-10-24 19:30:38,479 EPOCH 5 done: loss 0.0455 - lr: 0.000017
2023-10-24 19:30:41,600 DEV : loss 0.1995469629764557 - f1-score (micro avg)  0.7543
2023-10-24 19:30:41,615 ----------------------------------------------------------------------------------------------------
2023-10-24 19:30:53,777 epoch 6 - iter 198/1984 - loss 0.03231291 - time (sec): 12.16 - samples/sec: 1357.15 - lr: 0.000016 - momentum: 0.000000
2023-10-24 19:31:05,778 epoch 6 - iter 396/1984 - loss 0.03397784 - time (sec): 24.16 - samples/sec: 1328.30 - lr: 0.000016 - momentum: 0.000000
2023-10-24 19:31:17,884 epoch 6 - iter 594/1984 - loss 0.03041311 - time (sec): 36.27 - samples/sec: 1346.65 - lr: 0.000016 - momentum: 0.000000
2023-10-24 19:31:30,370 epoch 6 - iter 792/1984 - loss 0.03190695 - time (sec): 48.75 - samples/sec: 1370.84 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:31:42,871 epoch 6 - iter 990/1984 - loss 0.03341697 - time (sec): 61.25 - samples/sec: 1348.17 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:31:54,884 epoch 6 - iter 1188/1984 - loss 0.03375744 - time (sec): 73.27 - samples/sec: 1340.20 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:32:06,956 epoch 6 - iter 1386/1984 - loss 0.03312953 - time (sec): 85.34 - samples/sec: 1337.39 - lr: 0.000014 - momentum: 0.000000
2023-10-24 19:32:19,204 epoch 6 - iter 1584/1984 - loss 0.03383901 - time (sec): 97.59 - samples/sec: 1339.64 - lr: 0.000014 - momentum: 0.000000
2023-10-24 19:32:31,450 epoch 6 - iter 1782/1984 - loss 0.03389974 - time (sec): 109.83 - samples/sec: 1343.73 - lr: 0.000014 - momentum: 0.000000
2023-10-24 19:32:43,633 epoch 6 - iter 1980/1984 - loss 0.03407852 - time (sec): 122.02 - samples/sec: 1341.61 - lr: 0.000013 - momentum: 0.000000
2023-10-24 19:32:43,869 ----------------------------------------------------------------------------------------------------
2023-10-24 19:32:43,870 EPOCH 6 done: loss 0.0340 - lr: 0.000013
2023-10-24 19:32:46,992 DEV : loss 0.20763596892356873 - f1-score (micro avg)  0.774
2023-10-24 19:32:47,007 saving best model
2023-10-24 19:32:47,627 ----------------------------------------------------------------------------------------------------
2023-10-24 19:32:59,661 epoch 7 - iter 198/1984 - loss 0.02133725 - time (sec): 12.03 - samples/sec: 1354.69 - lr: 0.000013 - momentum: 0.000000
2023-10-24 19:33:11,642 epoch 7 - iter 396/1984 - loss 0.02091982 - time (sec): 24.01 - samples/sec: 1330.34 - lr: 0.000013 - momentum: 0.000000
2023-10-24 19:33:23,661 epoch 7 - iter 594/1984 - loss 0.02302967 - time (sec): 36.03 - samples/sec: 1331.94 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:33:36,085 epoch 7 - iter 792/1984 - loss 0.02423421 - time (sec): 48.46 - samples/sec: 1350.67 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:33:48,050 epoch 7 - iter 990/1984 - loss 0.02379088 - time (sec): 60.42 - samples/sec: 1344.83 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:34:00,094 epoch 7 - iter 1188/1984 - loss 0.02343269 - time (sec): 72.47 - samples/sec: 1345.70 - lr: 0.000011 - momentum: 0.000000
2023-10-24 19:34:12,236 epoch 7 - iter 1386/1984 - loss 0.02524471 - time (sec): 84.61 - samples/sec: 1347.56 - lr: 0.000011 - momentum: 0.000000
2023-10-24 19:34:24,424 epoch 7 - iter 1584/1984 - loss 0.02464132 - time (sec): 96.80 - samples/sec: 1347.23 - lr: 0.000011 - momentum: 0.000000
2023-10-24 19:34:36,539 epoch 7 - iter 1782/1984 - loss 0.02431973 - time (sec): 108.91 - samples/sec: 1347.67 - lr: 0.000010 - momentum: 0.000000
2023-10-24 19:34:48,863 epoch 7 - iter 1980/1984 - loss 0.02469436 - time (sec): 121.23 - samples/sec: 1350.73 - lr: 0.000010 - momentum: 0.000000
2023-10-24 19:34:49,087 ----------------------------------------------------------------------------------------------------
2023-10-24 19:34:49,087 EPOCH 7 done: loss 0.0247 - lr: 0.000010
2023-10-24 19:34:52,192 DEV : loss 0.22793228924274445 - f1-score (micro avg)  0.7628
2023-10-24 19:34:52,207 ----------------------------------------------------------------------------------------------------
2023-10-24 19:35:04,591 epoch 8 - iter 198/1984 - loss 0.01770350 - time (sec): 12.38 - samples/sec: 1317.10 - lr: 0.000010 - momentum: 0.000000
2023-10-24 19:35:16,521 epoch 8 - iter 396/1984 - loss 0.01496629 - time (sec): 24.31 - samples/sec: 1309.49 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:35:28,965 epoch 8 - iter 594/1984 - loss 0.01607839 - time (sec): 36.76 - samples/sec: 1345.79 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:35:40,927 epoch 8 - iter 792/1984 - loss 0.01770098 - time (sec): 48.72 - samples/sec: 1335.77 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:35:53,081 epoch 8 - iter 990/1984 - loss 0.01788262 - time (sec): 60.87 - samples/sec: 1342.78 - lr: 0.000008 - momentum: 0.000000
2023-10-24 19:36:05,273 epoch 8 - iter 1188/1984 - loss 0.01779408 - time (sec): 73.06 - samples/sec: 1342.96 - lr: 0.000008 - momentum: 0.000000
2023-10-24 19:36:17,387 epoch 8 - iter 1386/1984 - loss 0.01703299 - time (sec): 85.18 - samples/sec: 1345.43 - lr: 0.000008 - momentum: 0.000000
2023-10-24 19:36:29,612 epoch 8 - iter 1584/1984 - loss 0.01716121 - time (sec): 97.40 - samples/sec: 1341.02 - lr: 0.000007 - momentum: 0.000000
2023-10-24 19:36:41,523 epoch 8 - iter 1782/1984 - loss 0.01672368 - time (sec): 109.31 - samples/sec: 1345.12 - lr: 0.000007 - momentum: 0.000000
2023-10-24 19:36:53,631 epoch 8 - iter 1980/1984 - loss 0.01650254 - time (sec): 121.42 - samples/sec: 1347.56 - lr: 0.000007 - momentum: 0.000000
2023-10-24 19:36:53,873 ----------------------------------------------------------------------------------------------------
2023-10-24 19:36:53,873 EPOCH 8 done: loss 0.0165 - lr: 0.000007
2023-10-24 19:36:56,983 DEV : loss 0.23265020549297333 - f1-score (micro avg)  0.765
2023-10-24 19:36:56,998 ----------------------------------------------------------------------------------------------------
2023-10-24 19:37:08,934 epoch 9 - iter 198/1984 - loss 0.01460665 - time (sec): 11.94 - samples/sec: 1310.79 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:37:20,956 epoch 9 - iter 396/1984 - loss 0.01489846 - time (sec): 23.96 - samples/sec: 1330.22 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:37:32,982 epoch 9 - iter 594/1984 - loss 0.01459467 - time (sec): 35.98 - samples/sec: 1306.08 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:37:45,075 epoch 9 - iter 792/1984 - loss 0.01270058 - time (sec): 48.08 - samples/sec: 1327.28 - lr: 0.000005 - momentum: 0.000000
2023-10-24 19:37:57,137 epoch 9 - iter 990/1984 - loss 0.01265837 - time (sec): 60.14 - samples/sec: 1334.58 - lr: 0.000005 - momentum: 0.000000
2023-10-24 19:38:09,538 epoch 9 - iter 1188/1984 - loss 0.01297891 - time (sec): 72.54 - samples/sec: 1344.49 - lr: 0.000005 - momentum: 0.000000
2023-10-24 19:38:21,385 epoch 9 - iter 1386/1984 - loss 0.01248831 - time (sec): 84.39 - samples/sec: 1340.15 - lr: 0.000004 - momentum: 0.000000
2023-10-24 19:38:33,965 epoch 9 - iter 1584/1984 - loss 0.01258510 - time (sec): 96.97 - samples/sec: 1356.27 - lr: 0.000004 - momentum: 0.000000
2023-10-24 19:38:46,104 epoch 9 - iter 1782/1984 - loss 0.01225636 - time (sec): 109.11 - samples/sec: 1353.36 - lr: 0.000004 - momentum: 0.000000
2023-10-24 19:38:58,070 epoch 9 - iter 1980/1984 - loss 0.01210063 - time (sec): 121.07 - samples/sec: 1351.07 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:38:58,346 ----------------------------------------------------------------------------------------------------
2023-10-24 19:38:58,346 EPOCH 9 done: loss 0.0121 - lr: 0.000003
2023-10-24 19:39:01,778 DEV : loss 0.244042307138443 - f1-score (micro avg)  0.7587
2023-10-24 19:39:01,793 ----------------------------------------------------------------------------------------------------
2023-10-24 19:39:14,043 epoch 10 - iter 198/1984 - loss 0.01126873 - time (sec): 12.25 - samples/sec: 1403.09 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:39:26,290 epoch 10 - iter 396/1984 - loss 0.01079960 - time (sec): 24.50 - samples/sec: 1376.43 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:39:38,492 epoch 10 - iter 594/1984 - loss 0.00920357 - time (sec): 36.70 - samples/sec: 1391.31 - lr: 0.000002 - momentum: 0.000000
2023-10-24 19:39:50,933 epoch 10 - iter 792/1984 - loss 0.00891660 - time (sec): 49.14 - samples/sec: 1389.24 - lr: 0.000002 - momentum: 0.000000
2023-10-24 19:40:02,800 epoch 10 - iter 990/1984 - loss 0.00864161 - time (sec): 61.01 - samples/sec: 1368.26 - lr: 0.000002 - momentum: 0.000000
2023-10-24 19:40:14,924 epoch 10 - iter 1188/1984 - loss 0.00926189 - time (sec): 73.13 - samples/sec: 1364.12 - lr: 0.000001 - momentum: 0.000000
2023-10-24 19:40:26,822 epoch 10 - iter 1386/1984 - loss 0.00915410 - time (sec): 85.03 - samples/sec: 1349.75 - lr: 0.000001 - momentum: 0.000000
2023-10-24 19:40:38,890 epoch 10 - iter 1584/1984 - loss 0.00899681 - time (sec): 97.10 - samples/sec: 1349.54 - lr: 0.000001 - momentum: 0.000000
2023-10-24 19:40:51,050 epoch 10 - iter 1782/1984 - loss 0.00863704 - time (sec): 109.26 - samples/sec: 1350.21 - lr: 0.000000 - momentum: 0.000000
2023-10-24 19:41:03,100 epoch 10 - iter 1980/1984 - loss 0.00877194 - time (sec): 121.31 - samples/sec: 1348.60 - lr: 0.000000 - momentum: 0.000000
2023-10-24 19:41:03,350 ----------------------------------------------------------------------------------------------------
2023-10-24 19:41:03,350 EPOCH 10 done: loss 0.0088 - lr: 0.000000
2023-10-24 19:41:06,471 DEV : loss 0.25166356563568115 - f1-score (micro avg)  0.7624
2023-10-24 19:41:06,956 ----------------------------------------------------------------------------------------------------
2023-10-24 19:41:06,956 Loading model from best epoch ...
2023-10-24 19:41:08,420 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-24 19:41:11,490 
Results:
- F-score (micro) 0.7761
- F-score (macro) 0.6778
- Accuracy 0.6586

By class:
              precision    recall  f1-score   support

         LOC     0.8447    0.8305    0.8376       655
         PER     0.6996    0.7937    0.7437       223
         ORG     0.6250    0.3543    0.4523       127

   micro avg     0.7905    0.7622    0.7761      1005
   macro avg     0.7231    0.6595    0.6778      1005
weighted avg     0.7848    0.7622    0.7680      1005

2023-10-24 19:41:11,490 ----------------------------------------------------------------------------------------------------