2023-10-23 21:43:27,817 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,818 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=21, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-23 21:43:27,818 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
 - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Train:  3575 sentences
2023-10-23 21:43:27,819         (train_with_dev=False, train_with_test=False)
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Training Params:
2023-10-23 21:43:27,819  - learning_rate: "3e-05" 
2023-10-23 21:43:27,819  - mini_batch_size: "8"
2023-10-23 21:43:27,819  - max_epochs: "10"
2023-10-23 21:43:27,819  - shuffle: "True"
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Plugins:
2023-10-23 21:43:27,819  - TensorboardLogger
2023-10-23 21:43:27,819  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 21:43:27,819  - metric: "('micro avg', 'f1-score')"
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Computation:
2023-10-23 21:43:27,819  - compute on device: cuda:0
2023-10-23 21:43:27,819  - embedding storage: none
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 ----------------------------------------------------------------------------------------------------
2023-10-23 21:43:27,819 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 21:43:31,549 epoch 1 - iter 44/447 - loss 2.59736907 - time (sec): 3.73 - samples/sec: 2232.32 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:43:35,682 epoch 1 - iter 88/447 - loss 1.66480304 - time (sec): 7.86 - samples/sec: 2185.19 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:43:39,656 epoch 1 - iter 132/447 - loss 1.26020851 - time (sec): 11.84 - samples/sec: 2198.48 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:43:43,583 epoch 1 - iter 176/447 - loss 1.03511087 - time (sec): 15.76 - samples/sec: 2203.99 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:43:47,775 epoch 1 - iter 220/447 - loss 0.89283125 - time (sec): 19.95 - samples/sec: 2194.86 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:43:51,681 epoch 1 - iter 264/447 - loss 0.80764086 - time (sec): 23.86 - samples/sec: 2180.36 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:43:55,776 epoch 1 - iter 308/447 - loss 0.73311634 - time (sec): 27.96 - samples/sec: 2167.82 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:43:59,480 epoch 1 - iter 352/447 - loss 0.67644386 - time (sec): 31.66 - samples/sec: 2169.32 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:44:03,410 epoch 1 - iter 396/447 - loss 0.62981661 - time (sec): 35.59 - samples/sec: 2163.10 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:44:07,550 epoch 1 - iter 440/447 - loss 0.59048312 - time (sec): 39.73 - samples/sec: 2145.47 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:44:08,172 ----------------------------------------------------------------------------------------------------
2023-10-23 21:44:08,172 EPOCH 1 done: loss 0.5849 - lr: 0.000029
2023-10-23 21:44:13,024 DEV : loss 0.15741746127605438 - f1-score (micro avg)  0.6304
2023-10-23 21:44:13,044 saving best model
2023-10-23 21:44:13,611 ----------------------------------------------------------------------------------------------------
2023-10-23 21:44:17,779 epoch 2 - iter 44/447 - loss 0.18063276 - time (sec): 4.17 - samples/sec: 2257.14 - lr: 0.000030 - momentum: 0.000000
2023-10-23 21:44:21,569 epoch 2 - iter 88/447 - loss 0.18528584 - time (sec): 7.96 - samples/sec: 2187.93 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:44:25,757 epoch 2 - iter 132/447 - loss 0.16599237 - time (sec): 12.15 - samples/sec: 2182.35 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:44:29,711 epoch 2 - iter 176/447 - loss 0.15670000 - time (sec): 16.10 - samples/sec: 2169.31 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:44:33,587 epoch 2 - iter 220/447 - loss 0.15648904 - time (sec): 19.98 - samples/sec: 2181.11 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:44:37,531 epoch 2 - iter 264/447 - loss 0.15443719 - time (sec): 23.92 - samples/sec: 2157.18 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:44:41,316 epoch 2 - iter 308/447 - loss 0.14760432 - time (sec): 27.70 - samples/sec: 2166.92 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:44:45,037 epoch 2 - iter 352/447 - loss 0.14586645 - time (sec): 31.43 - samples/sec: 2162.64 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:44:49,356 epoch 2 - iter 396/447 - loss 0.14259641 - time (sec): 35.74 - samples/sec: 2167.87 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:44:53,194 epoch 2 - iter 440/447 - loss 0.14126909 - time (sec): 39.58 - samples/sec: 2155.17 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:44:53,795 ----------------------------------------------------------------------------------------------------
2023-10-23 21:44:53,795 EPOCH 2 done: loss 0.1402 - lr: 0.000027
2023-10-23 21:45:00,267 DEV : loss 0.13381491601467133 - f1-score (micro avg)  0.7117
2023-10-23 21:45:00,287 saving best model
2023-10-23 21:45:00,985 ----------------------------------------------------------------------------------------------------
2023-10-23 21:45:05,601 epoch 3 - iter 44/447 - loss 0.06751128 - time (sec): 4.62 - samples/sec: 2259.03 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:45:09,604 epoch 3 - iter 88/447 - loss 0.07069500 - time (sec): 8.62 - samples/sec: 2206.18 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:45:13,531 epoch 3 - iter 132/447 - loss 0.07976465 - time (sec): 12.55 - samples/sec: 2175.25 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:45:17,346 epoch 3 - iter 176/447 - loss 0.07651757 - time (sec): 16.36 - samples/sec: 2160.96 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:45:21,434 epoch 3 - iter 220/447 - loss 0.07807169 - time (sec): 20.45 - samples/sec: 2136.55 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:45:25,359 epoch 3 - iter 264/447 - loss 0.07678230 - time (sec): 24.37 - samples/sec: 2141.63 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:45:29,201 epoch 3 - iter 308/447 - loss 0.07502733 - time (sec): 28.22 - samples/sec: 2169.75 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:45:32,828 epoch 3 - iter 352/447 - loss 0.07417559 - time (sec): 31.84 - samples/sec: 2155.29 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:45:36,858 epoch 3 - iter 396/447 - loss 0.07690418 - time (sec): 35.87 - samples/sec: 2139.50 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:45:40,794 epoch 3 - iter 440/447 - loss 0.07512869 - time (sec): 39.81 - samples/sec: 2144.65 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:45:41,344 ----------------------------------------------------------------------------------------------------
2023-10-23 21:45:41,344 EPOCH 3 done: loss 0.0747 - lr: 0.000023
2023-10-23 21:45:47,862 DEV : loss 0.1403728574514389 - f1-score (micro avg)  0.7576
2023-10-23 21:45:47,882 saving best model
2023-10-23 21:45:48,534 ----------------------------------------------------------------------------------------------------
2023-10-23 21:45:52,383 epoch 4 - iter 44/447 - loss 0.04429873 - time (sec): 3.85 - samples/sec: 2190.16 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:45:56,211 epoch 4 - iter 88/447 - loss 0.05556305 - time (sec): 7.68 - samples/sec: 2182.82 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:46:00,413 epoch 4 - iter 132/447 - loss 0.04771936 - time (sec): 11.88 - samples/sec: 2185.70 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:46:04,432 epoch 4 - iter 176/447 - loss 0.04763457 - time (sec): 15.90 - samples/sec: 2148.76 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:46:08,771 epoch 4 - iter 220/447 - loss 0.04883475 - time (sec): 20.24 - samples/sec: 2164.09 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:46:12,638 epoch 4 - iter 264/447 - loss 0.05042629 - time (sec): 24.10 - samples/sec: 2149.11 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:46:16,490 epoch 4 - iter 308/447 - loss 0.04933331 - time (sec): 27.95 - samples/sec: 2138.45 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:46:20,184 epoch 4 - iter 352/447 - loss 0.04993052 - time (sec): 31.65 - samples/sec: 2134.04 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:46:24,364 epoch 4 - iter 396/447 - loss 0.05054757 - time (sec): 35.83 - samples/sec: 2125.87 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:46:28,318 epoch 4 - iter 440/447 - loss 0.04943137 - time (sec): 39.78 - samples/sec: 2133.38 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:46:29,180 ----------------------------------------------------------------------------------------------------
2023-10-23 21:46:29,180 EPOCH 4 done: loss 0.0495 - lr: 0.000020
2023-10-23 21:46:35,657 DEV : loss 0.15535356104373932 - f1-score (micro avg)  0.7538
2023-10-23 21:46:35,677 ----------------------------------------------------------------------------------------------------
2023-10-23 21:46:39,548 epoch 5 - iter 44/447 - loss 0.03078265 - time (sec): 3.87 - samples/sec: 2225.40 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:46:44,002 epoch 5 - iter 88/447 - loss 0.03386077 - time (sec): 8.32 - samples/sec: 2240.13 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:46:47,844 epoch 5 - iter 132/447 - loss 0.02800467 - time (sec): 12.17 - samples/sec: 2207.49 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:46:51,925 epoch 5 - iter 176/447 - loss 0.02859791 - time (sec): 16.25 - samples/sec: 2192.30 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:46:55,830 epoch 5 - iter 220/447 - loss 0.02933140 - time (sec): 20.15 - samples/sec: 2186.28 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:46:59,903 epoch 5 - iter 264/447 - loss 0.03168646 - time (sec): 24.22 - samples/sec: 2165.59 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:47:04,063 epoch 5 - iter 308/447 - loss 0.03078826 - time (sec): 28.38 - samples/sec: 2153.17 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:47:07,934 epoch 5 - iter 352/447 - loss 0.03164438 - time (sec): 32.26 - samples/sec: 2137.69 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:47:11,983 epoch 5 - iter 396/447 - loss 0.03204700 - time (sec): 36.30 - samples/sec: 2133.66 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:47:15,699 epoch 5 - iter 440/447 - loss 0.03119195 - time (sec): 40.02 - samples/sec: 2133.16 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:47:16,246 ----------------------------------------------------------------------------------------------------
2023-10-23 21:47:16,246 EPOCH 5 done: loss 0.0309 - lr: 0.000017
2023-10-23 21:47:22,748 DEV : loss 0.19321992993354797 - f1-score (micro avg)  0.7672
2023-10-23 21:47:22,769 saving best model
2023-10-23 21:47:23,478 ----------------------------------------------------------------------------------------------------
2023-10-23 21:47:27,940 epoch 6 - iter 44/447 - loss 0.02741518 - time (sec): 4.46 - samples/sec: 2090.87 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:47:31,462 epoch 6 - iter 88/447 - loss 0.02648322 - time (sec): 7.98 - samples/sec: 2098.54 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:47:35,446 epoch 6 - iter 132/447 - loss 0.02696457 - time (sec): 11.97 - samples/sec: 2118.34 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:47:40,129 epoch 6 - iter 176/447 - loss 0.02361068 - time (sec): 16.65 - samples/sec: 2081.86 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:47:44,245 epoch 6 - iter 220/447 - loss 0.02276207 - time (sec): 20.77 - samples/sec: 2080.13 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:47:48,072 epoch 6 - iter 264/447 - loss 0.02276839 - time (sec): 24.59 - samples/sec: 2086.22 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:47:51,854 epoch 6 - iter 308/447 - loss 0.02374098 - time (sec): 28.37 - samples/sec: 2087.49 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:47:55,586 epoch 6 - iter 352/447 - loss 0.02378282 - time (sec): 32.11 - samples/sec: 2108.41 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:47:59,400 epoch 6 - iter 396/447 - loss 0.02305597 - time (sec): 35.92 - samples/sec: 2122.86 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:48:03,543 epoch 6 - iter 440/447 - loss 0.02262792 - time (sec): 40.06 - samples/sec: 2126.09 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:48:04,170 ----------------------------------------------------------------------------------------------------
2023-10-23 21:48:04,170 EPOCH 6 done: loss 0.0228 - lr: 0.000013
2023-10-23 21:48:10,648 DEV : loss 0.2212265431880951 - f1-score (micro avg)  0.7681
2023-10-23 21:48:10,668 saving best model
2023-10-23 21:48:11,380 ----------------------------------------------------------------------------------------------------
2023-10-23 21:48:15,630 epoch 7 - iter 44/447 - loss 0.02011576 - time (sec): 4.25 - samples/sec: 2161.60 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:48:20,236 epoch 7 - iter 88/447 - loss 0.02058168 - time (sec): 8.86 - samples/sec: 2129.94 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:48:24,023 epoch 7 - iter 132/447 - loss 0.01673971 - time (sec): 12.64 - samples/sec: 2161.41 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:48:27,774 epoch 7 - iter 176/447 - loss 0.01674535 - time (sec): 16.39 - samples/sec: 2137.16 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:48:31,840 epoch 7 - iter 220/447 - loss 0.01634720 - time (sec): 20.46 - samples/sec: 2107.89 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:48:35,738 epoch 7 - iter 264/447 - loss 0.01512947 - time (sec): 24.36 - samples/sec: 2110.43 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:48:39,714 epoch 7 - iter 308/447 - loss 0.01474730 - time (sec): 28.33 - samples/sec: 2126.89 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:48:43,633 epoch 7 - iter 352/447 - loss 0.01413429 - time (sec): 32.25 - samples/sec: 2123.06 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:48:47,542 epoch 7 - iter 396/447 - loss 0.01551299 - time (sec): 36.16 - samples/sec: 2132.18 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:48:51,431 epoch 7 - iter 440/447 - loss 0.01500511 - time (sec): 40.05 - samples/sec: 2128.34 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:48:52,048 ----------------------------------------------------------------------------------------------------
2023-10-23 21:48:52,049 EPOCH 7 done: loss 0.0151 - lr: 0.000010
2023-10-23 21:48:58,550 DEV : loss 0.20411019027233124 - f1-score (micro avg)  0.7805
2023-10-23 21:48:58,570 saving best model
2023-10-23 21:48:59,286 ----------------------------------------------------------------------------------------------------
2023-10-23 21:49:03,512 epoch 8 - iter 44/447 - loss 0.01270864 - time (sec): 4.23 - samples/sec: 2032.12 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:49:07,306 epoch 8 - iter 88/447 - loss 0.01253401 - time (sec): 8.02 - samples/sec: 2083.82 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:49:11,270 epoch 8 - iter 132/447 - loss 0.01166606 - time (sec): 11.98 - samples/sec: 2081.78 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:49:15,017 epoch 8 - iter 176/447 - loss 0.01169154 - time (sec): 15.73 - samples/sec: 2096.62 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:49:19,083 epoch 8 - iter 220/447 - loss 0.01146001 - time (sec): 19.80 - samples/sec: 2091.88 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:49:22,864 epoch 8 - iter 264/447 - loss 0.01101559 - time (sec): 23.58 - samples/sec: 2107.80 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:49:27,278 epoch 8 - iter 308/447 - loss 0.01131528 - time (sec): 27.99 - samples/sec: 2116.82 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:49:31,122 epoch 8 - iter 352/447 - loss 0.01058721 - time (sec): 31.84 - samples/sec: 2113.39 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:49:35,175 epoch 8 - iter 396/447 - loss 0.01001339 - time (sec): 35.89 - samples/sec: 2129.54 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:49:39,230 epoch 8 - iter 440/447 - loss 0.00967542 - time (sec): 39.94 - samples/sec: 2134.83 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:49:39,875 ----------------------------------------------------------------------------------------------------
2023-10-23 21:49:39,876 EPOCH 8 done: loss 0.0095 - lr: 0.000007
2023-10-23 21:49:46,389 DEV : loss 0.225086510181427 - f1-score (micro avg)  0.7789
2023-10-23 21:49:46,409 ----------------------------------------------------------------------------------------------------
2023-10-23 21:49:50,173 epoch 9 - iter 44/447 - loss 0.00403557 - time (sec): 3.76 - samples/sec: 2081.58 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:49:54,550 epoch 9 - iter 88/447 - loss 0.00765470 - time (sec): 8.14 - samples/sec: 2163.07 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:49:58,621 epoch 9 - iter 132/447 - loss 0.00920501 - time (sec): 12.21 - samples/sec: 2172.70 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:50:02,655 epoch 9 - iter 176/447 - loss 0.00917938 - time (sec): 16.24 - samples/sec: 2153.71 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:50:06,801 epoch 9 - iter 220/447 - loss 0.00894625 - time (sec): 20.39 - samples/sec: 2138.41 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:50:11,253 epoch 9 - iter 264/447 - loss 0.00790337 - time (sec): 24.84 - samples/sec: 2127.58 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:50:15,046 epoch 9 - iter 308/447 - loss 0.00736902 - time (sec): 28.64 - samples/sec: 2131.12 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:50:18,757 epoch 9 - iter 352/447 - loss 0.00748375 - time (sec): 32.35 - samples/sec: 2130.89 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:50:22,404 epoch 9 - iter 396/447 - loss 0.00686718 - time (sec): 35.99 - samples/sec: 2128.26 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:50:26,194 epoch 9 - iter 440/447 - loss 0.00697380 - time (sec): 39.78 - samples/sec: 2134.97 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:50:26,915 ----------------------------------------------------------------------------------------------------
2023-10-23 21:50:26,916 EPOCH 9 done: loss 0.0068 - lr: 0.000003
2023-10-23 21:50:33,435 DEV : loss 0.23983320593833923 - f1-score (micro avg)  0.7897
2023-10-23 21:50:33,456 saving best model
2023-10-23 21:50:34,253 ----------------------------------------------------------------------------------------------------
2023-10-23 21:50:38,619 epoch 10 - iter 44/447 - loss 0.00392863 - time (sec): 4.37 - samples/sec: 2090.26 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:50:42,547 epoch 10 - iter 88/447 - loss 0.00267496 - time (sec): 8.29 - samples/sec: 2111.21 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:50:46,964 epoch 10 - iter 132/447 - loss 0.00256060 - time (sec): 12.71 - samples/sec: 2134.72 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:50:50,766 epoch 10 - iter 176/447 - loss 0.00265105 - time (sec): 16.51 - samples/sec: 2144.00 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:50:54,684 epoch 10 - iter 220/447 - loss 0.00294022 - time (sec): 20.43 - samples/sec: 2130.59 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:50:58,612 epoch 10 - iter 264/447 - loss 0.00407805 - time (sec): 24.36 - samples/sec: 2146.37 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:51:02,387 epoch 10 - iter 308/447 - loss 0.00366515 - time (sec): 28.13 - samples/sec: 2145.46 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:51:06,524 epoch 10 - iter 352/447 - loss 0.00414494 - time (sec): 32.27 - samples/sec: 2151.05 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:51:10,214 epoch 10 - iter 396/447 - loss 0.00427295 - time (sec): 35.96 - samples/sec: 2143.80 - lr: 0.000000 - momentum: 0.000000
2023-10-23 21:51:14,104 epoch 10 - iter 440/447 - loss 0.00403470 - time (sec): 39.85 - samples/sec: 2138.07 - lr: 0.000000 - momentum: 0.000000
2023-10-23 21:51:14,719 ----------------------------------------------------------------------------------------------------
2023-10-23 21:51:14,719 EPOCH 10 done: loss 0.0040 - lr: 0.000000
2023-10-23 21:51:20,939 DEV : loss 0.24832327663898468 - f1-score (micro avg)  0.7863
2023-10-23 21:51:21,516 ----------------------------------------------------------------------------------------------------
2023-10-23 21:51:21,517 Loading model from best epoch ...
2023-10-23 21:51:23,587 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
2023-10-23 21:51:28,141 
Results:
- F-score (micro) 0.7529
- F-score (macro) 0.664
- Accuracy 0.6222

By class:
              precision    recall  f1-score   support

         loc     0.8486    0.8557    0.8521       596
        pers     0.6675    0.7658    0.7133       333
         org     0.5254    0.4697    0.4960       132
        prod     0.6977    0.4545    0.5505        66
        time     0.7234    0.6939    0.7083        49

   micro avg     0.7481    0.7577    0.7529      1176
   macro avg     0.6925    0.6479    0.6640      1176
weighted avg     0.7474    0.7577    0.7499      1176

2023-10-23 21:51:28,141 ----------------------------------------------------------------------------------------------------