2023-10-24 19:05:23,213 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,214 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 19:05:23,214 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,214 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 19:05:23,214 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,214 Train:  7936 sentences
2023-10-24 19:05:23,214         (train_with_dev=False, train_with_test=False)
2023-10-24 19:05:23,214 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,214 Training Params:
2023-10-24 19:05:23,214  - learning_rate: "5e-05" 
2023-10-24 19:05:23,214  - mini_batch_size: "8"
2023-10-24 19:05:23,215  - max_epochs: "10"
2023-10-24 19:05:23,215  - shuffle: "True"
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 Plugins:
2023-10-24 19:05:23,215  - TensorboardLogger
2023-10-24 19:05:23,215  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 19:05:23,215  - metric: "('micro avg', 'f1-score')"
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 Computation:
2023-10-24 19:05:23,215  - compute on device: cuda:0
2023-10-24 19:05:23,215  - embedding storage: none
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 ----------------------------------------------------------------------------------------------------
2023-10-24 19:05:23,215 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 19:05:31,175 epoch 1 - iter 99/992 - loss 1.70950296 - time (sec): 7.96 - samples/sec: 2082.83 - lr: 0.000005 - momentum: 0.000000
2023-10-24 19:05:39,330 epoch 1 - iter 198/992 - loss 1.01384479 - time (sec): 16.11 - samples/sec: 2064.96 - lr: 0.000010 - momentum: 0.000000
2023-10-24 19:05:47,790 epoch 1 - iter 297/992 - loss 0.75778922 - time (sec): 24.57 - samples/sec: 1996.91 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:05:55,836 epoch 1 - iter 396/992 - loss 0.61189230 - time (sec): 32.62 - samples/sec: 1991.62 - lr: 0.000020 - momentum: 0.000000
2023-10-24 19:06:04,134 epoch 1 - iter 495/992 - loss 0.51884386 - time (sec): 40.92 - samples/sec: 1990.45 - lr: 0.000025 - momentum: 0.000000
2023-10-24 19:06:12,350 epoch 1 - iter 594/992 - loss 0.45856004 - time (sec): 49.13 - samples/sec: 1977.54 - lr: 0.000030 - momentum: 0.000000
2023-10-24 19:06:21,080 epoch 1 - iter 693/992 - loss 0.41271354 - time (sec): 57.86 - samples/sec: 1966.53 - lr: 0.000035 - momentum: 0.000000
2023-10-24 19:06:29,237 epoch 1 - iter 792/992 - loss 0.37655176 - time (sec): 66.02 - samples/sec: 1973.90 - lr: 0.000040 - momentum: 0.000000
2023-10-24 19:06:37,225 epoch 1 - iter 891/992 - loss 0.34959778 - time (sec): 74.01 - samples/sec: 1978.32 - lr: 0.000045 - momentum: 0.000000
2023-10-24 19:06:46,108 epoch 1 - iter 990/992 - loss 0.32534380 - time (sec): 82.89 - samples/sec: 1975.55 - lr: 0.000050 - momentum: 0.000000
2023-10-24 19:06:46,247 ----------------------------------------------------------------------------------------------------
2023-10-24 19:06:46,248 EPOCH 1 done: loss 0.3253 - lr: 0.000050
2023-10-24 19:06:49,320 DEV : loss 0.10130015760660172 - f1-score (micro avg)  0.6799
2023-10-24 19:06:49,335 saving best model
2023-10-24 19:06:49,808 ----------------------------------------------------------------------------------------------------
2023-10-24 19:06:58,310 epoch 2 - iter 99/992 - loss 0.10678352 - time (sec): 8.50 - samples/sec: 2028.19 - lr: 0.000049 - momentum: 0.000000
2023-10-24 19:07:06,731 epoch 2 - iter 198/992 - loss 0.10123782 - time (sec): 16.92 - samples/sec: 1993.53 - lr: 0.000049 - momentum: 0.000000
2023-10-24 19:07:14,788 epoch 2 - iter 297/992 - loss 0.09886519 - time (sec): 24.98 - samples/sec: 1996.00 - lr: 0.000048 - momentum: 0.000000
2023-10-24 19:07:23,057 epoch 2 - iter 396/992 - loss 0.10164530 - time (sec): 33.25 - samples/sec: 1994.28 - lr: 0.000048 - momentum: 0.000000
2023-10-24 19:07:31,670 epoch 2 - iter 495/992 - loss 0.10087299 - time (sec): 41.86 - samples/sec: 1992.96 - lr: 0.000047 - momentum: 0.000000
2023-10-24 19:07:40,135 epoch 2 - iter 594/992 - loss 0.10136669 - time (sec): 50.33 - samples/sec: 1981.49 - lr: 0.000047 - momentum: 0.000000
2023-10-24 19:07:48,052 epoch 2 - iter 693/992 - loss 0.10102277 - time (sec): 58.24 - samples/sec: 1974.27 - lr: 0.000046 - momentum: 0.000000
2023-10-24 19:07:56,239 epoch 2 - iter 792/992 - loss 0.10046863 - time (sec): 66.43 - samples/sec: 1969.35 - lr: 0.000046 - momentum: 0.000000
2023-10-24 19:08:04,561 epoch 2 - iter 891/992 - loss 0.09965890 - time (sec): 74.75 - samples/sec: 1974.95 - lr: 0.000045 - momentum: 0.000000
2023-10-24 19:08:12,651 epoch 2 - iter 990/992 - loss 0.09937356 - time (sec): 82.84 - samples/sec: 1969.96 - lr: 0.000044 - momentum: 0.000000
2023-10-24 19:08:13,107 ----------------------------------------------------------------------------------------------------
2023-10-24 19:08:13,107 EPOCH 2 done: loss 0.0995 - lr: 0.000044
2023-10-24 19:08:16,521 DEV : loss 0.0830492153763771 - f1-score (micro avg)  0.7227
2023-10-24 19:08:16,537 saving best model
2023-10-24 19:08:17,173 ----------------------------------------------------------------------------------------------------
2023-10-24 19:08:25,132 epoch 3 - iter 99/992 - loss 0.06256824 - time (sec): 7.96 - samples/sec: 2024.19 - lr: 0.000044 - momentum: 0.000000
2023-10-24 19:08:33,694 epoch 3 - iter 198/992 - loss 0.06110784 - time (sec): 16.52 - samples/sec: 2002.92 - lr: 0.000043 - momentum: 0.000000
2023-10-24 19:08:42,023 epoch 3 - iter 297/992 - loss 0.06752868 - time (sec): 24.85 - samples/sec: 1959.14 - lr: 0.000043 - momentum: 0.000000
2023-10-24 19:08:50,107 epoch 3 - iter 396/992 - loss 0.06822405 - time (sec): 32.93 - samples/sec: 1940.81 - lr: 0.000042 - momentum: 0.000000
2023-10-24 19:08:58,559 epoch 3 - iter 495/992 - loss 0.06716269 - time (sec): 41.39 - samples/sec: 1946.31 - lr: 0.000042 - momentum: 0.000000
2023-10-24 19:09:06,889 epoch 3 - iter 594/992 - loss 0.06703667 - time (sec): 49.72 - samples/sec: 1956.04 - lr: 0.000041 - momentum: 0.000000
2023-10-24 19:09:15,261 epoch 3 - iter 693/992 - loss 0.06724873 - time (sec): 58.09 - samples/sec: 1972.02 - lr: 0.000041 - momentum: 0.000000
2023-10-24 19:09:23,760 epoch 3 - iter 792/992 - loss 0.06798579 - time (sec): 66.59 - samples/sec: 1967.26 - lr: 0.000040 - momentum: 0.000000
2023-10-24 19:09:32,288 epoch 3 - iter 891/992 - loss 0.06874500 - time (sec): 75.11 - samples/sec: 1967.00 - lr: 0.000039 - momentum: 0.000000
2023-10-24 19:09:40,478 epoch 3 - iter 990/992 - loss 0.06831140 - time (sec): 83.30 - samples/sec: 1963.52 - lr: 0.000039 - momentum: 0.000000
2023-10-24 19:09:40,679 ----------------------------------------------------------------------------------------------------
2023-10-24 19:09:40,679 EPOCH 3 done: loss 0.0682 - lr: 0.000039
2023-10-24 19:09:43,796 DEV : loss 0.11285286396741867 - f1-score (micro avg)  0.7414
2023-10-24 19:09:43,812 saving best model
2023-10-24 19:09:44,464 ----------------------------------------------------------------------------------------------------
2023-10-24 19:09:52,525 epoch 4 - iter 99/992 - loss 0.03625260 - time (sec): 8.06 - samples/sec: 1924.31 - lr: 0.000038 - momentum: 0.000000
2023-10-24 19:10:01,030 epoch 4 - iter 198/992 - loss 0.04677937 - time (sec): 16.57 - samples/sec: 1953.03 - lr: 0.000038 - momentum: 0.000000
2023-10-24 19:10:09,422 epoch 4 - iter 297/992 - loss 0.04578826 - time (sec): 24.96 - samples/sec: 1983.09 - lr: 0.000037 - momentum: 0.000000
2023-10-24 19:10:17,505 epoch 4 - iter 396/992 - loss 0.04479099 - time (sec): 33.04 - samples/sec: 1961.58 - lr: 0.000037 - momentum: 0.000000
2023-10-24 19:10:25,630 epoch 4 - iter 495/992 - loss 0.04686146 - time (sec): 41.17 - samples/sec: 1954.14 - lr: 0.000036 - momentum: 0.000000
2023-10-24 19:10:34,259 epoch 4 - iter 594/992 - loss 0.04762399 - time (sec): 49.79 - samples/sec: 1960.97 - lr: 0.000036 - momentum: 0.000000
2023-10-24 19:10:42,614 epoch 4 - iter 693/992 - loss 0.04722873 - time (sec): 58.15 - samples/sec: 1957.15 - lr: 0.000035 - momentum: 0.000000
2023-10-24 19:10:51,075 epoch 4 - iter 792/992 - loss 0.04821478 - time (sec): 66.61 - samples/sec: 1951.82 - lr: 0.000034 - momentum: 0.000000
2023-10-24 19:10:59,484 epoch 4 - iter 891/992 - loss 0.04777276 - time (sec): 75.02 - samples/sec: 1963.79 - lr: 0.000034 - momentum: 0.000000
2023-10-24 19:11:08,254 epoch 4 - iter 990/992 - loss 0.04940618 - time (sec): 83.79 - samples/sec: 1952.77 - lr: 0.000033 - momentum: 0.000000
2023-10-24 19:11:08,452 ----------------------------------------------------------------------------------------------------
2023-10-24 19:11:08,452 EPOCH 4 done: loss 0.0493 - lr: 0.000033
2023-10-24 19:11:11,571 DEV : loss 0.11610622704029083 - f1-score (micro avg)  0.7619
2023-10-24 19:11:11,586 saving best model
2023-10-24 19:11:12,225 ----------------------------------------------------------------------------------------------------
2023-10-24 19:11:20,827 epoch 5 - iter 99/992 - loss 0.03961834 - time (sec): 8.60 - samples/sec: 1958.57 - lr: 0.000033 - momentum: 0.000000
2023-10-24 19:11:28,982 epoch 5 - iter 198/992 - loss 0.03534589 - time (sec): 16.76 - samples/sec: 1969.79 - lr: 0.000032 - momentum: 0.000000
2023-10-24 19:11:37,315 epoch 5 - iter 297/992 - loss 0.03749801 - time (sec): 25.09 - samples/sec: 1981.88 - lr: 0.000032 - momentum: 0.000000
2023-10-24 19:11:46,151 epoch 5 - iter 396/992 - loss 0.03528151 - time (sec): 33.93 - samples/sec: 1983.96 - lr: 0.000031 - momentum: 0.000000
2023-10-24 19:11:54,365 epoch 5 - iter 495/992 - loss 0.03519979 - time (sec): 42.14 - samples/sec: 1974.45 - lr: 0.000031 - momentum: 0.000000
2023-10-24 19:12:02,429 epoch 5 - iter 594/992 - loss 0.03550820 - time (sec): 50.20 - samples/sec: 1968.78 - lr: 0.000030 - momentum: 0.000000
2023-10-24 19:12:10,603 epoch 5 - iter 693/992 - loss 0.03597362 - time (sec): 58.38 - samples/sec: 1964.72 - lr: 0.000029 - momentum: 0.000000
2023-10-24 19:12:18,946 epoch 5 - iter 792/992 - loss 0.03569118 - time (sec): 66.72 - samples/sec: 1969.04 - lr: 0.000029 - momentum: 0.000000
2023-10-24 19:12:27,035 epoch 5 - iter 891/992 - loss 0.03582242 - time (sec): 74.81 - samples/sec: 1962.92 - lr: 0.000028 - momentum: 0.000000
2023-10-24 19:12:35,694 epoch 5 - iter 990/992 - loss 0.03556779 - time (sec): 83.47 - samples/sec: 1960.31 - lr: 0.000028 - momentum: 0.000000
2023-10-24 19:12:35,875 ----------------------------------------------------------------------------------------------------
2023-10-24 19:12:35,875 EPOCH 5 done: loss 0.0356 - lr: 0.000028
2023-10-24 19:12:38,999 DEV : loss 0.1716771423816681 - f1-score (micro avg)  0.7426
2023-10-24 19:12:39,014 ----------------------------------------------------------------------------------------------------
2023-10-24 19:12:47,355 epoch 6 - iter 99/992 - loss 0.03224386 - time (sec): 8.34 - samples/sec: 1942.30 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:12:55,447 epoch 6 - iter 198/992 - loss 0.03197562 - time (sec): 16.43 - samples/sec: 1959.18 - lr: 0.000027 - momentum: 0.000000
2023-10-24 19:13:03,799 epoch 6 - iter 297/992 - loss 0.02965185 - time (sec): 24.78 - samples/sec: 1979.69 - lr: 0.000026 - momentum: 0.000000
2023-10-24 19:13:11,914 epoch 6 - iter 396/992 - loss 0.03043814 - time (sec): 32.90 - samples/sec: 1967.10 - lr: 0.000026 - momentum: 0.000000
2023-10-24 19:13:20,509 epoch 6 - iter 495/992 - loss 0.02992723 - time (sec): 41.49 - samples/sec: 1974.57 - lr: 0.000025 - momentum: 0.000000
2023-10-24 19:13:28,982 epoch 6 - iter 594/992 - loss 0.02978050 - time (sec): 49.97 - samples/sec: 1954.97 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:13:37,482 epoch 6 - iter 693/992 - loss 0.02928196 - time (sec): 58.47 - samples/sec: 1959.29 - lr: 0.000024 - momentum: 0.000000
2023-10-24 19:13:45,576 epoch 6 - iter 792/992 - loss 0.02952635 - time (sec): 66.56 - samples/sec: 1960.59 - lr: 0.000023 - momentum: 0.000000
2023-10-24 19:13:54,224 epoch 6 - iter 891/992 - loss 0.02912377 - time (sec): 75.21 - samples/sec: 1950.02 - lr: 0.000023 - momentum: 0.000000
2023-10-24 19:14:02,690 epoch 6 - iter 990/992 - loss 0.02939295 - time (sec): 83.68 - samples/sec: 1956.57 - lr: 0.000022 - momentum: 0.000000
2023-10-24 19:14:02,850 ----------------------------------------------------------------------------------------------------
2023-10-24 19:14:02,850 EPOCH 6 done: loss 0.0294 - lr: 0.000022
2023-10-24 19:14:05,972 DEV : loss 0.192485511302948 - f1-score (micro avg)  0.7462
2023-10-24 19:14:05,987 ----------------------------------------------------------------------------------------------------
2023-10-24 19:14:14,813 epoch 7 - iter 99/992 - loss 0.02045973 - time (sec): 8.83 - samples/sec: 1989.11 - lr: 0.000022 - momentum: 0.000000
2023-10-24 19:14:23,135 epoch 7 - iter 198/992 - loss 0.01981631 - time (sec): 17.15 - samples/sec: 1998.22 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:14:31,271 epoch 7 - iter 297/992 - loss 0.01923823 - time (sec): 25.28 - samples/sec: 2001.59 - lr: 0.000021 - momentum: 0.000000
2023-10-24 19:14:39,735 epoch 7 - iter 396/992 - loss 0.02020709 - time (sec): 33.75 - samples/sec: 1983.61 - lr: 0.000020 - momentum: 0.000000
2023-10-24 19:14:47,975 epoch 7 - iter 495/992 - loss 0.02153825 - time (sec): 41.99 - samples/sec: 1978.07 - lr: 0.000019 - momentum: 0.000000
2023-10-24 19:14:56,108 epoch 7 - iter 594/992 - loss 0.02042658 - time (sec): 50.12 - samples/sec: 1972.49 - lr: 0.000019 - momentum: 0.000000
2023-10-24 19:15:04,294 epoch 7 - iter 693/992 - loss 0.02067326 - time (sec): 58.31 - samples/sec: 1965.88 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:15:12,571 epoch 7 - iter 792/992 - loss 0.02092512 - time (sec): 66.58 - samples/sec: 1965.47 - lr: 0.000018 - momentum: 0.000000
2023-10-24 19:15:20,891 epoch 7 - iter 891/992 - loss 0.02067809 - time (sec): 74.90 - samples/sec: 1968.70 - lr: 0.000017 - momentum: 0.000000
2023-10-24 19:15:29,114 epoch 7 - iter 990/992 - loss 0.02076980 - time (sec): 83.13 - samples/sec: 1968.12 - lr: 0.000017 - momentum: 0.000000
2023-10-24 19:15:29,378 ----------------------------------------------------------------------------------------------------
2023-10-24 19:15:29,378 EPOCH 7 done: loss 0.0208 - lr: 0.000017
2023-10-24 19:15:32,489 DEV : loss 0.21390925347805023 - f1-score (micro avg)  0.7568
2023-10-24 19:15:32,504 ----------------------------------------------------------------------------------------------------
2023-10-24 19:15:40,895 epoch 8 - iter 99/992 - loss 0.01235834 - time (sec): 8.39 - samples/sec: 1954.00 - lr: 0.000016 - momentum: 0.000000
2023-10-24 19:15:49,494 epoch 8 - iter 198/992 - loss 0.01284679 - time (sec): 16.99 - samples/sec: 1975.32 - lr: 0.000016 - momentum: 0.000000
2023-10-24 19:15:57,663 epoch 8 - iter 297/992 - loss 0.01202123 - time (sec): 25.16 - samples/sec: 1980.96 - lr: 0.000015 - momentum: 0.000000
2023-10-24 19:16:05,831 epoch 8 - iter 396/992 - loss 0.01338066 - time (sec): 33.33 - samples/sec: 1985.64 - lr: 0.000014 - momentum: 0.000000
2023-10-24 19:16:14,383 epoch 8 - iter 495/992 - loss 0.01427779 - time (sec): 41.88 - samples/sec: 1991.53 - lr: 0.000014 - momentum: 0.000000
2023-10-24 19:16:22,512 epoch 8 - iter 594/992 - loss 0.01426704 - time (sec): 50.01 - samples/sec: 1990.06 - lr: 0.000013 - momentum: 0.000000
2023-10-24 19:16:31,092 epoch 8 - iter 693/992 - loss 0.01503984 - time (sec): 58.59 - samples/sec: 1974.64 - lr: 0.000013 - momentum: 0.000000
2023-10-24 19:16:39,618 epoch 8 - iter 792/992 - loss 0.01476754 - time (sec): 67.11 - samples/sec: 1956.26 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:16:48,166 epoch 8 - iter 891/992 - loss 0.01433965 - time (sec): 75.66 - samples/sec: 1958.05 - lr: 0.000012 - momentum: 0.000000
2023-10-24 19:16:56,116 epoch 8 - iter 990/992 - loss 0.01439873 - time (sec): 83.61 - samples/sec: 1957.13 - lr: 0.000011 - momentum: 0.000000
2023-10-24 19:16:56,266 ----------------------------------------------------------------------------------------------------
2023-10-24 19:16:56,266 EPOCH 8 done: loss 0.0144 - lr: 0.000011
2023-10-24 19:16:59,394 DEV : loss 0.2170470654964447 - f1-score (micro avg)  0.7653
2023-10-24 19:16:59,409 saving best model
2023-10-24 19:16:59,998 ----------------------------------------------------------------------------------------------------
2023-10-24 19:17:08,452 epoch 9 - iter 99/992 - loss 0.01523691 - time (sec): 8.45 - samples/sec: 1956.81 - lr: 0.000011 - momentum: 0.000000
2023-10-24 19:17:16,335 epoch 9 - iter 198/992 - loss 0.01371175 - time (sec): 16.34 - samples/sec: 1973.01 - lr: 0.000010 - momentum: 0.000000
2023-10-24 19:17:25,129 epoch 9 - iter 297/992 - loss 0.01112734 - time (sec): 25.13 - samples/sec: 1961.09 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:17:33,617 epoch 9 - iter 396/992 - loss 0.01101364 - time (sec): 33.62 - samples/sec: 1954.71 - lr: 0.000009 - momentum: 0.000000
2023-10-24 19:17:41,740 epoch 9 - iter 495/992 - loss 0.01020473 - time (sec): 41.74 - samples/sec: 1971.57 - lr: 0.000008 - momentum: 0.000000
2023-10-24 19:17:49,783 epoch 9 - iter 594/992 - loss 0.00941962 - time (sec): 49.78 - samples/sec: 1965.69 - lr: 0.000008 - momentum: 0.000000
2023-10-24 19:17:58,224 epoch 9 - iter 693/992 - loss 0.00898993 - time (sec): 58.23 - samples/sec: 1968.14 - lr: 0.000007 - momentum: 0.000000
2023-10-24 19:18:06,525 epoch 9 - iter 792/992 - loss 0.00910924 - time (sec): 66.53 - samples/sec: 1970.28 - lr: 0.000007 - momentum: 0.000000
2023-10-24 19:18:15,185 epoch 9 - iter 891/992 - loss 0.00928332 - time (sec): 75.19 - samples/sec: 1961.67 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:18:23,413 epoch 9 - iter 990/992 - loss 0.00916308 - time (sec): 83.41 - samples/sec: 1962.06 - lr: 0.000006 - momentum: 0.000000
2023-10-24 19:18:23,585 ----------------------------------------------------------------------------------------------------
2023-10-24 19:18:23,585 EPOCH 9 done: loss 0.0092 - lr: 0.000006
2023-10-24 19:18:26,698 DEV : loss 0.2309696227312088 - f1-score (micro avg)  0.761
2023-10-24 19:18:26,713 ----------------------------------------------------------------------------------------------------
2023-10-24 19:18:34,965 epoch 10 - iter 99/992 - loss 0.00331234 - time (sec): 8.25 - samples/sec: 1929.01 - lr: 0.000005 - momentum: 0.000000
2023-10-24 19:18:43,239 epoch 10 - iter 198/992 - loss 0.00499297 - time (sec): 16.52 - samples/sec: 1982.26 - lr: 0.000004 - momentum: 0.000000
2023-10-24 19:18:51,539 epoch 10 - iter 297/992 - loss 0.00567139 - time (sec): 24.82 - samples/sec: 1956.99 - lr: 0.000004 - momentum: 0.000000
2023-10-24 19:18:59,907 epoch 10 - iter 396/992 - loss 0.00588887 - time (sec): 33.19 - samples/sec: 1963.07 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:19:08,519 epoch 10 - iter 495/992 - loss 0.00578750 - time (sec): 41.80 - samples/sec: 1954.56 - lr: 0.000003 - momentum: 0.000000
2023-10-24 19:19:17,405 epoch 10 - iter 594/992 - loss 0.00603662 - time (sec): 50.69 - samples/sec: 1943.26 - lr: 0.000002 - momentum: 0.000000
2023-10-24 19:19:25,492 epoch 10 - iter 693/992 - loss 0.00581652 - time (sec): 58.78 - samples/sec: 1950.26 - lr: 0.000002 - momentum: 0.000000
2023-10-24 19:19:33,597 epoch 10 - iter 792/992 - loss 0.00565761 - time (sec): 66.88 - samples/sec: 1952.72 - lr: 0.000001 - momentum: 0.000000
2023-10-24 19:19:42,061 epoch 10 - iter 891/992 - loss 0.00628280 - time (sec): 75.35 - samples/sec: 1961.00 - lr: 0.000001 - momentum: 0.000000
2023-10-24 19:19:50,323 epoch 10 - iter 990/992 - loss 0.00648941 - time (sec): 83.61 - samples/sec: 1958.09 - lr: 0.000000 - momentum: 0.000000
2023-10-24 19:19:50,484 ----------------------------------------------------------------------------------------------------
2023-10-24 19:19:50,484 EPOCH 10 done: loss 0.0065 - lr: 0.000000
2023-10-24 19:19:53,602 DEV : loss 0.24162988364696503 - f1-score (micro avg)  0.7665
2023-10-24 19:19:53,617 saving best model
2023-10-24 19:19:54,685 ----------------------------------------------------------------------------------------------------
2023-10-24 19:19:54,686 Loading model from best epoch ...
2023-10-24 19:19:56,216 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 19:19:59,296 
Results:
- F-score (micro) 0.7905
- F-score (macro) 0.6954
- Accuracy 0.6762

By class:
              precision    recall  f1-score   support

         LOC     0.8430    0.8687    0.8556       655
         PER     0.7020    0.8027    0.7490       223
         ORG     0.5843    0.4094    0.4815       127

   micro avg     0.7851    0.7960    0.7905      1005
   macro avg     0.7097    0.6936    0.6954      1005
weighted avg     0.7790    0.7960    0.7847      1005

2023-10-24 19:19:59,296 ----------------------------------------------------------------------------------------------------