2023-10-23 22:30:17,229 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 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 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 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 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 Train:  3575 sentences
2023-10-23 22:30:17,230         (train_with_dev=False, train_with_test=False)
2023-10-23 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 Training Params:
2023-10-23 22:30:17,230  - learning_rate: "5e-05" 
2023-10-23 22:30:17,230  - mini_batch_size: "8"
2023-10-23 22:30:17,230  - max_epochs: "10"
2023-10-23 22:30:17,230  - shuffle: "True"
2023-10-23 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 Plugins:
2023-10-23 22:30:17,230  - TensorboardLogger
2023-10-23 22:30:17,230  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 22:30:17,230  - metric: "('micro avg', 'f1-score')"
2023-10-23 22:30:17,230 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,230 Computation:
2023-10-23 22:30:17,230  - compute on device: cuda:0
2023-10-23 22:30:17,230  - embedding storage: none
2023-10-23 22:30:17,231 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,231 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-23 22:30:17,231 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,231 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:17,231 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 22:30:21,267 epoch 1 - iter 44/447 - loss 2.61747162 - time (sec): 4.04 - samples/sec: 2035.61 - lr: 0.000005 - momentum: 0.000000
2023-10-23 22:30:25,388 epoch 1 - iter 88/447 - loss 1.60840445 - time (sec): 8.16 - samples/sec: 2091.49 - lr: 0.000010 - momentum: 0.000000
2023-10-23 22:30:29,288 epoch 1 - iter 132/447 - loss 1.22488104 - time (sec): 12.06 - samples/sec: 2090.31 - lr: 0.000015 - momentum: 0.000000
2023-10-23 22:30:33,068 epoch 1 - iter 176/447 - loss 1.02876906 - time (sec): 15.84 - samples/sec: 2108.24 - lr: 0.000020 - momentum: 0.000000
2023-10-23 22:30:36,953 epoch 1 - iter 220/447 - loss 0.87744594 - time (sec): 19.72 - samples/sec: 2129.38 - lr: 0.000024 - momentum: 0.000000
2023-10-23 22:30:40,666 epoch 1 - iter 264/447 - loss 0.77450690 - time (sec): 23.43 - samples/sec: 2142.27 - lr: 0.000029 - momentum: 0.000000
2023-10-23 22:30:44,600 epoch 1 - iter 308/447 - loss 0.69356769 - time (sec): 27.37 - samples/sec: 2149.59 - lr: 0.000034 - momentum: 0.000000
2023-10-23 22:30:48,495 epoch 1 - iter 352/447 - loss 0.62969553 - time (sec): 31.26 - samples/sec: 2153.68 - lr: 0.000039 - momentum: 0.000000
2023-10-23 22:30:52,331 epoch 1 - iter 396/447 - loss 0.58382135 - time (sec): 35.10 - samples/sec: 2154.72 - lr: 0.000044 - momentum: 0.000000
2023-10-23 22:30:56,593 epoch 1 - iter 440/447 - loss 0.53971211 - time (sec): 39.36 - samples/sec: 2158.94 - lr: 0.000049 - momentum: 0.000000
2023-10-23 22:30:57,344 ----------------------------------------------------------------------------------------------------
2023-10-23 22:30:57,344 EPOCH 1 done: loss 0.5354 - lr: 0.000049
2023-10-23 22:31:02,145 DEV : loss 0.14619310200214386 - f1-score (micro avg)  0.6262
2023-10-23 22:31:02,165 saving best model
2023-10-23 22:31:02,636 ----------------------------------------------------------------------------------------------------
2023-10-23 22:31:06,348 epoch 2 - iter 44/447 - loss 0.13529306 - time (sec): 3.71 - samples/sec: 2152.18 - lr: 0.000049 - momentum: 0.000000
2023-10-23 22:31:10,178 epoch 2 - iter 88/447 - loss 0.14040657 - time (sec): 7.54 - samples/sec: 2231.49 - lr: 0.000049 - momentum: 0.000000
2023-10-23 22:31:14,578 epoch 2 - iter 132/447 - loss 0.14036495 - time (sec): 11.94 - samples/sec: 2176.35 - lr: 0.000048 - momentum: 0.000000
2023-10-23 22:31:18,453 epoch 2 - iter 176/447 - loss 0.14258655 - time (sec): 15.82 - samples/sec: 2166.64 - lr: 0.000048 - momentum: 0.000000
2023-10-23 22:31:22,524 epoch 2 - iter 220/447 - loss 0.14221669 - time (sec): 19.89 - samples/sec: 2156.71 - lr: 0.000047 - momentum: 0.000000
2023-10-23 22:31:26,576 epoch 2 - iter 264/447 - loss 0.13370512 - time (sec): 23.94 - samples/sec: 2131.60 - lr: 0.000047 - momentum: 0.000000
2023-10-23 22:31:30,355 epoch 2 - iter 308/447 - loss 0.13477548 - time (sec): 27.72 - samples/sec: 2134.27 - lr: 0.000046 - momentum: 0.000000
2023-10-23 22:31:34,090 epoch 2 - iter 352/447 - loss 0.13109257 - time (sec): 31.45 - samples/sec: 2127.08 - lr: 0.000046 - momentum: 0.000000
2023-10-23 22:31:38,417 epoch 2 - iter 396/447 - loss 0.13099059 - time (sec): 35.78 - samples/sec: 2127.77 - lr: 0.000045 - momentum: 0.000000
2023-10-23 22:31:42,421 epoch 2 - iter 440/447 - loss 0.12705414 - time (sec): 39.78 - samples/sec: 2138.94 - lr: 0.000045 - momentum: 0.000000
2023-10-23 22:31:43,024 ----------------------------------------------------------------------------------------------------
2023-10-23 22:31:43,024 EPOCH 2 done: loss 0.1267 - lr: 0.000045
2023-10-23 22:31:49,495 DEV : loss 0.13422338664531708 - f1-score (micro avg)  0.6981
2023-10-23 22:31:49,516 saving best model
2023-10-23 22:31:50,207 ----------------------------------------------------------------------------------------------------
2023-10-23 22:31:54,081 epoch 3 - iter 44/447 - loss 0.06517716 - time (sec): 3.87 - samples/sec: 2019.03 - lr: 0.000044 - momentum: 0.000000
2023-10-23 22:31:58,238 epoch 3 - iter 88/447 - loss 0.06909628 - time (sec): 8.03 - samples/sec: 2017.65 - lr: 0.000043 - momentum: 0.000000
2023-10-23 22:32:01,998 epoch 3 - iter 132/447 - loss 0.06970190 - time (sec): 11.79 - samples/sec: 2077.66 - lr: 0.000043 - momentum: 0.000000
2023-10-23 22:32:06,132 epoch 3 - iter 176/447 - loss 0.07724232 - time (sec): 15.92 - samples/sec: 2113.01 - lr: 0.000042 - momentum: 0.000000
2023-10-23 22:32:09,840 epoch 3 - iter 220/447 - loss 0.07409603 - time (sec): 19.63 - samples/sec: 2092.92 - lr: 0.000042 - momentum: 0.000000
2023-10-23 22:32:14,305 epoch 3 - iter 264/447 - loss 0.07522591 - time (sec): 24.10 - samples/sec: 2087.35 - lr: 0.000041 - momentum: 0.000000
2023-10-23 22:32:18,612 epoch 3 - iter 308/447 - loss 0.07450279 - time (sec): 28.40 - samples/sec: 2095.97 - lr: 0.000041 - momentum: 0.000000
2023-10-23 22:32:22,409 epoch 3 - iter 352/447 - loss 0.07276381 - time (sec): 32.20 - samples/sec: 2114.52 - lr: 0.000040 - momentum: 0.000000
2023-10-23 22:32:26,239 epoch 3 - iter 396/447 - loss 0.07476661 - time (sec): 36.03 - samples/sec: 2124.32 - lr: 0.000040 - momentum: 0.000000
2023-10-23 22:32:30,277 epoch 3 - iter 440/447 - loss 0.07597918 - time (sec): 40.07 - samples/sec: 2127.19 - lr: 0.000039 - momentum: 0.000000
2023-10-23 22:32:30,858 ----------------------------------------------------------------------------------------------------
2023-10-23 22:32:30,859 EPOCH 3 done: loss 0.0758 - lr: 0.000039
2023-10-23 22:32:37,348 DEV : loss 0.13163481652736664 - f1-score (micro avg)  0.7203
2023-10-23 22:32:37,368 saving best model
2023-10-23 22:32:37,995 ----------------------------------------------------------------------------------------------------
2023-10-23 22:32:41,892 epoch 4 - iter 44/447 - loss 0.04397609 - time (sec): 3.90 - samples/sec: 2153.22 - lr: 0.000038 - momentum: 0.000000
2023-10-23 22:32:45,651 epoch 4 - iter 88/447 - loss 0.04709654 - time (sec): 7.66 - samples/sec: 2137.42 - lr: 0.000038 - momentum: 0.000000
2023-10-23 22:32:49,533 epoch 4 - iter 132/447 - loss 0.04593196 - time (sec): 11.54 - samples/sec: 2166.47 - lr: 0.000037 - momentum: 0.000000
2023-10-23 22:32:53,857 epoch 4 - iter 176/447 - loss 0.04818047 - time (sec): 15.86 - samples/sec: 2160.62 - lr: 0.000037 - momentum: 0.000000
2023-10-23 22:32:58,108 epoch 4 - iter 220/447 - loss 0.04713671 - time (sec): 20.11 - samples/sec: 2134.79 - lr: 0.000036 - momentum: 0.000000
2023-10-23 22:33:01,959 epoch 4 - iter 264/447 - loss 0.04951053 - time (sec): 23.96 - samples/sec: 2136.25 - lr: 0.000036 - momentum: 0.000000
2023-10-23 22:33:05,688 epoch 4 - iter 308/447 - loss 0.04805972 - time (sec): 27.69 - samples/sec: 2144.03 - lr: 0.000035 - momentum: 0.000000
2023-10-23 22:33:09,695 epoch 4 - iter 352/447 - loss 0.04776840 - time (sec): 31.70 - samples/sec: 2140.57 - lr: 0.000035 - momentum: 0.000000
2023-10-23 22:33:13,577 epoch 4 - iter 396/447 - loss 0.04732331 - time (sec): 35.58 - samples/sec: 2137.75 - lr: 0.000034 - momentum: 0.000000
2023-10-23 22:33:17,808 epoch 4 - iter 440/447 - loss 0.04667565 - time (sec): 39.81 - samples/sec: 2138.30 - lr: 0.000033 - momentum: 0.000000
2023-10-23 22:33:18,478 ----------------------------------------------------------------------------------------------------
2023-10-23 22:33:18,479 EPOCH 4 done: loss 0.0468 - lr: 0.000033
2023-10-23 22:33:24,957 DEV : loss 0.15146000683307648 - f1-score (micro avg)  0.739
2023-10-23 22:33:24,977 saving best model
2023-10-23 22:33:25,573 ----------------------------------------------------------------------------------------------------
2023-10-23 22:33:29,808 epoch 5 - iter 44/447 - loss 0.01668860 - time (sec): 4.23 - samples/sec: 2114.97 - lr: 0.000033 - momentum: 0.000000
2023-10-23 22:33:33,878 epoch 5 - iter 88/447 - loss 0.02476922 - time (sec): 8.30 - samples/sec: 2093.66 - lr: 0.000032 - momentum: 0.000000
2023-10-23 22:33:37,628 epoch 5 - iter 132/447 - loss 0.02649246 - time (sec): 12.05 - samples/sec: 2115.90 - lr: 0.000032 - momentum: 0.000000
2023-10-23 22:33:41,750 epoch 5 - iter 176/447 - loss 0.03062251 - time (sec): 16.18 - samples/sec: 2133.69 - lr: 0.000031 - momentum: 0.000000
2023-10-23 22:33:46,044 epoch 5 - iter 220/447 - loss 0.02841129 - time (sec): 20.47 - samples/sec: 2159.21 - lr: 0.000031 - momentum: 0.000000
2023-10-23 22:33:49,757 epoch 5 - iter 264/447 - loss 0.02981830 - time (sec): 24.18 - samples/sec: 2148.21 - lr: 0.000030 - momentum: 0.000000
2023-10-23 22:33:53,930 epoch 5 - iter 308/447 - loss 0.03059182 - time (sec): 28.36 - samples/sec: 2136.13 - lr: 0.000030 - momentum: 0.000000
2023-10-23 22:33:57,668 epoch 5 - iter 352/447 - loss 0.03094377 - time (sec): 32.09 - samples/sec: 2139.50 - lr: 0.000029 - momentum: 0.000000
2023-10-23 22:34:01,555 epoch 5 - iter 396/447 - loss 0.02981108 - time (sec): 35.98 - samples/sec: 2131.11 - lr: 0.000028 - momentum: 0.000000
2023-10-23 22:34:05,425 epoch 5 - iter 440/447 - loss 0.02945931 - time (sec): 39.85 - samples/sec: 2135.15 - lr: 0.000028 - momentum: 0.000000
2023-10-23 22:34:06,116 ----------------------------------------------------------------------------------------------------
2023-10-23 22:34:06,117 EPOCH 5 done: loss 0.0293 - lr: 0.000028
2023-10-23 22:34:12,590 DEV : loss 0.22155629098415375 - f1-score (micro avg)  0.7493
2023-10-23 22:34:12,611 saving best model
2023-10-23 22:34:13,209 ----------------------------------------------------------------------------------------------------
2023-10-23 22:34:16,768 epoch 6 - iter 44/447 - loss 0.01815000 - time (sec): 3.56 - samples/sec: 2090.34 - lr: 0.000027 - momentum: 0.000000
2023-10-23 22:34:20,690 epoch 6 - iter 88/447 - loss 0.01807258 - time (sec): 7.48 - samples/sec: 2124.94 - lr: 0.000027 - momentum: 0.000000
2023-10-23 22:34:24,827 epoch 6 - iter 132/447 - loss 0.02179131 - time (sec): 11.62 - samples/sec: 2158.82 - lr: 0.000026 - momentum: 0.000000
2023-10-23 22:34:28,893 epoch 6 - iter 176/447 - loss 0.02160888 - time (sec): 15.68 - samples/sec: 2146.17 - lr: 0.000026 - momentum: 0.000000
2023-10-23 22:34:33,305 epoch 6 - iter 220/447 - loss 0.02172418 - time (sec): 20.09 - samples/sec: 2147.11 - lr: 0.000025 - momentum: 0.000000
2023-10-23 22:34:37,007 epoch 6 - iter 264/447 - loss 0.02170470 - time (sec): 23.80 - samples/sec: 2151.46 - lr: 0.000025 - momentum: 0.000000
2023-10-23 22:34:41,178 epoch 6 - iter 308/447 - loss 0.02234828 - time (sec): 27.97 - samples/sec: 2144.67 - lr: 0.000024 - momentum: 0.000000
2023-10-23 22:34:45,340 epoch 6 - iter 352/447 - loss 0.02114853 - time (sec): 32.13 - samples/sec: 2131.89 - lr: 0.000023 - momentum: 0.000000
2023-10-23 22:34:49,332 epoch 6 - iter 396/447 - loss 0.02105417 - time (sec): 36.12 - samples/sec: 2125.31 - lr: 0.000023 - momentum: 0.000000
2023-10-23 22:34:53,202 epoch 6 - iter 440/447 - loss 0.01999840 - time (sec): 39.99 - samples/sec: 2126.53 - lr: 0.000022 - momentum: 0.000000
2023-10-23 22:34:53,908 ----------------------------------------------------------------------------------------------------
2023-10-23 22:34:53,908 EPOCH 6 done: loss 0.0199 - lr: 0.000022
2023-10-23 22:35:00,402 DEV : loss 0.2293727993965149 - f1-score (micro avg)  0.7686
2023-10-23 22:35:00,423 saving best model
2023-10-23 22:35:01,014 ----------------------------------------------------------------------------------------------------
2023-10-23 22:35:05,341 epoch 7 - iter 44/447 - loss 0.00980116 - time (sec): 4.33 - samples/sec: 2168.37 - lr: 0.000022 - momentum: 0.000000
2023-10-23 22:35:09,245 epoch 7 - iter 88/447 - loss 0.01146217 - time (sec): 8.23 - samples/sec: 2133.32 - lr: 0.000021 - momentum: 0.000000
2023-10-23 22:35:13,013 epoch 7 - iter 132/447 - loss 0.01089331 - time (sec): 12.00 - samples/sec: 2113.50 - lr: 0.000021 - momentum: 0.000000
2023-10-23 22:35:16,734 epoch 7 - iter 176/447 - loss 0.01100412 - time (sec): 15.72 - samples/sec: 2103.62 - lr: 0.000020 - momentum: 0.000000
2023-10-23 22:35:20,770 epoch 7 - iter 220/447 - loss 0.01260891 - time (sec): 19.76 - samples/sec: 2113.68 - lr: 0.000020 - momentum: 0.000000
2023-10-23 22:35:24,654 epoch 7 - iter 264/447 - loss 0.01499648 - time (sec): 23.64 - samples/sec: 2103.53 - lr: 0.000019 - momentum: 0.000000
2023-10-23 22:35:28,932 epoch 7 - iter 308/447 - loss 0.01520584 - time (sec): 27.92 - samples/sec: 2115.87 - lr: 0.000018 - momentum: 0.000000
2023-10-23 22:35:33,256 epoch 7 - iter 352/447 - loss 0.01474127 - time (sec): 32.24 - samples/sec: 2134.52 - lr: 0.000018 - momentum: 0.000000
2023-10-23 22:35:37,126 epoch 7 - iter 396/447 - loss 0.01433985 - time (sec): 36.11 - samples/sec: 2131.72 - lr: 0.000017 - momentum: 0.000000
2023-10-23 22:35:40,902 epoch 7 - iter 440/447 - loss 0.01344578 - time (sec): 39.89 - samples/sec: 2131.24 - lr: 0.000017 - momentum: 0.000000
2023-10-23 22:35:41,529 ----------------------------------------------------------------------------------------------------
2023-10-23 22:35:41,529 EPOCH 7 done: loss 0.0133 - lr: 0.000017
2023-10-23 22:35:48,021 DEV : loss 0.2617715001106262 - f1-score (micro avg)  0.7712
2023-10-23 22:35:48,042 saving best model
2023-10-23 22:35:48,634 ----------------------------------------------------------------------------------------------------
2023-10-23 22:35:52,644 epoch 8 - iter 44/447 - loss 0.00739272 - time (sec): 4.01 - samples/sec: 2124.55 - lr: 0.000016 - momentum: 0.000000
2023-10-23 22:35:56,893 epoch 8 - iter 88/447 - loss 0.00595935 - time (sec): 8.26 - samples/sec: 2069.00 - lr: 0.000016 - momentum: 0.000000
2023-10-23 22:36:00,775 epoch 8 - iter 132/447 - loss 0.00894853 - time (sec): 12.14 - samples/sec: 2110.05 - lr: 0.000015 - momentum: 0.000000
2023-10-23 22:36:05,398 epoch 8 - iter 176/447 - loss 0.00734796 - time (sec): 16.76 - samples/sec: 2104.25 - lr: 0.000015 - momentum: 0.000000
2023-10-23 22:36:09,056 epoch 8 - iter 220/447 - loss 0.00672069 - time (sec): 20.42 - samples/sec: 2108.20 - lr: 0.000014 - momentum: 0.000000
2023-10-23 22:36:12,942 epoch 8 - iter 264/447 - loss 0.00679148 - time (sec): 24.31 - samples/sec: 2124.47 - lr: 0.000013 - momentum: 0.000000
2023-10-23 22:36:16,667 epoch 8 - iter 308/447 - loss 0.00768702 - time (sec): 28.03 - samples/sec: 2133.16 - lr: 0.000013 - momentum: 0.000000
2023-10-23 22:36:20,306 epoch 8 - iter 352/447 - loss 0.00760444 - time (sec): 31.67 - samples/sec: 2125.31 - lr: 0.000012 - momentum: 0.000000
2023-10-23 22:36:24,266 epoch 8 - iter 396/447 - loss 0.00734192 - time (sec): 35.63 - samples/sec: 2129.40 - lr: 0.000012 - momentum: 0.000000
2023-10-23 22:36:28,646 epoch 8 - iter 440/447 - loss 0.00806862 - time (sec): 40.01 - samples/sec: 2128.80 - lr: 0.000011 - momentum: 0.000000
2023-10-23 22:36:29,337 ----------------------------------------------------------------------------------------------------
2023-10-23 22:36:29,337 EPOCH 8 done: loss 0.0080 - lr: 0.000011
2023-10-23 22:36:35,571 DEV : loss 0.2736358642578125 - f1-score (micro avg)  0.7733
2023-10-23 22:36:35,592 saving best model
2023-10-23 22:36:36,185 ----------------------------------------------------------------------------------------------------
2023-10-23 22:36:39,878 epoch 9 - iter 44/447 - loss 0.00454046 - time (sec): 3.69 - samples/sec: 2163.58 - lr: 0.000011 - momentum: 0.000000
2023-10-23 22:36:44,012 epoch 9 - iter 88/447 - loss 0.00391630 - time (sec): 7.83 - samples/sec: 2060.42 - lr: 0.000010 - momentum: 0.000000
2023-10-23 22:36:47,842 epoch 9 - iter 132/447 - loss 0.00352831 - time (sec): 11.66 - samples/sec: 2119.86 - lr: 0.000010 - momentum: 0.000000
2023-10-23 22:36:51,495 epoch 9 - iter 176/447 - loss 0.00324014 - time (sec): 15.31 - samples/sec: 2143.80 - lr: 0.000009 - momentum: 0.000000
2023-10-23 22:36:55,486 epoch 9 - iter 220/447 - loss 0.00376207 - time (sec): 19.30 - samples/sec: 2145.27 - lr: 0.000008 - momentum: 0.000000
2023-10-23 22:36:59,856 epoch 9 - iter 264/447 - loss 0.00521423 - time (sec): 23.67 - samples/sec: 2153.42 - lr: 0.000008 - momentum: 0.000000
2023-10-23 22:37:03,961 epoch 9 - iter 308/447 - loss 0.00537886 - time (sec): 27.77 - samples/sec: 2146.14 - lr: 0.000007 - momentum: 0.000000
2023-10-23 22:37:08,356 epoch 9 - iter 352/447 - loss 0.00484718 - time (sec): 32.17 - samples/sec: 2142.65 - lr: 0.000007 - momentum: 0.000000
2023-10-23 22:37:12,275 epoch 9 - iter 396/447 - loss 0.00487190 - time (sec): 36.09 - samples/sec: 2132.68 - lr: 0.000006 - momentum: 0.000000
2023-10-23 22:37:16,222 epoch 9 - iter 440/447 - loss 0.00525891 - time (sec): 40.04 - samples/sec: 2131.23 - lr: 0.000006 - momentum: 0.000000
2023-10-23 22:37:16,845 ----------------------------------------------------------------------------------------------------
2023-10-23 22:37:16,846 EPOCH 9 done: loss 0.0052 - lr: 0.000006
2023-10-23 22:37:23,060 DEV : loss 0.2881031036376953 - f1-score (micro avg)  0.7758
2023-10-23 22:37:23,081 saving best model
2023-10-23 22:37:23,683 ----------------------------------------------------------------------------------------------------
2023-10-23 22:37:27,975 epoch 10 - iter 44/447 - loss 0.00315695 - time (sec): 4.29 - samples/sec: 2066.95 - lr: 0.000005 - momentum: 0.000000
2023-10-23 22:37:32,248 epoch 10 - iter 88/447 - loss 0.00274169 - time (sec): 8.56 - samples/sec: 2001.47 - lr: 0.000005 - momentum: 0.000000
2023-10-23 22:37:35,940 epoch 10 - iter 132/447 - loss 0.00183972 - time (sec): 12.26 - samples/sec: 2099.04 - lr: 0.000004 - momentum: 0.000000
2023-10-23 22:37:40,088 epoch 10 - iter 176/447 - loss 0.00256280 - time (sec): 16.40 - samples/sec: 2122.84 - lr: 0.000003 - momentum: 0.000000
2023-10-23 22:37:43,873 epoch 10 - iter 220/447 - loss 0.00354318 - time (sec): 20.19 - samples/sec: 2121.91 - lr: 0.000003 - momentum: 0.000000
2023-10-23 22:37:47,546 epoch 10 - iter 264/447 - loss 0.00354710 - time (sec): 23.86 - samples/sec: 2127.10 - lr: 0.000002 - momentum: 0.000000
2023-10-23 22:37:51,706 epoch 10 - iter 308/447 - loss 0.00327233 - time (sec): 28.02 - samples/sec: 2126.72 - lr: 0.000002 - momentum: 0.000000
2023-10-23 22:37:55,430 epoch 10 - iter 352/447 - loss 0.00332028 - time (sec): 31.75 - samples/sec: 2116.46 - lr: 0.000001 - momentum: 0.000000
2023-10-23 22:37:59,496 epoch 10 - iter 396/447 - loss 0.00374741 - time (sec): 35.81 - samples/sec: 2124.40 - lr: 0.000001 - momentum: 0.000000
2023-10-23 22:38:03,509 epoch 10 - iter 440/447 - loss 0.00354295 - time (sec): 39.82 - samples/sec: 2115.19 - lr: 0.000000 - momentum: 0.000000
2023-10-23 22:38:04,545 ----------------------------------------------------------------------------------------------------
2023-10-23 22:38:04,546 EPOCH 10 done: loss 0.0035 - lr: 0.000000
2023-10-23 22:38:10,759 DEV : loss 0.2901349365711212 - f1-score (micro avg)  0.7753
2023-10-23 22:38:11,256 ----------------------------------------------------------------------------------------------------
2023-10-23 22:38:11,257 Loading model from best epoch ...
2023-10-23 22:38:13,012 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 22:38:17,859 
Results:
- F-score (micro) 0.751
- F-score (macro) 0.6724
- Accuracy 0.6218

By class:
              precision    recall  f1-score   support

         loc     0.8395    0.8423    0.8409       596
        pers     0.6658    0.7778    0.7175       333
         org     0.5588    0.4318    0.4872       132
        prod     0.6531    0.4848    0.5565        66
        time     0.7451    0.7755    0.7600        49

   micro avg     0.7468    0.7551    0.7510      1176
   macro avg     0.6925    0.6624    0.6724      1176
weighted avg     0.7444    0.7551    0.7469      1176

2023-10-23 22:38:17,859 ----------------------------------------------------------------------------------------------------