2023-10-23 22:49:30,395 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 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 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 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 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 Train:  3575 sentences
2023-10-23 22:49:30,396         (train_with_dev=False, train_with_test=False)
2023-10-23 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 Training Params:
2023-10-23 22:49:30,396  - learning_rate: "5e-05" 
2023-10-23 22:49:30,396  - mini_batch_size: "4"
2023-10-23 22:49:30,396  - max_epochs: "10"
2023-10-23 22:49:30,396  - shuffle: "True"
2023-10-23 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 Plugins:
2023-10-23 22:49:30,396  - TensorboardLogger
2023-10-23 22:49:30,396  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 22:49:30,396  - metric: "('micro avg', 'f1-score')"
2023-10-23 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,396 Computation:
2023-10-23 22:49:30,396  - compute on device: cuda:0
2023-10-23 22:49:30,396  - embedding storage: none
2023-10-23 22:49:30,396 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,397 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-23 22:49:30,397 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,397 ----------------------------------------------------------------------------------------------------
2023-10-23 22:49:30,397 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 22:49:36,155 epoch 1 - iter 89/894 - loss 1.89230113 - time (sec): 5.76 - samples/sec: 1568.36 - lr: 0.000005 - momentum: 0.000000
2023-10-23 22:49:41,729 epoch 1 - iter 178/894 - loss 1.23768734 - time (sec): 11.33 - samples/sec: 1548.16 - lr: 0.000010 - momentum: 0.000000
2023-10-23 22:49:47,374 epoch 1 - iter 267/894 - loss 0.95322455 - time (sec): 16.98 - samples/sec: 1551.87 - lr: 0.000015 - momentum: 0.000000
2023-10-23 22:49:52,890 epoch 1 - iter 356/894 - loss 0.79934855 - time (sec): 22.49 - samples/sec: 1549.24 - lr: 0.000020 - momentum: 0.000000
2023-10-23 22:49:58,835 epoch 1 - iter 445/894 - loss 0.68662881 - time (sec): 28.44 - samples/sec: 1552.64 - lr: 0.000025 - momentum: 0.000000
2023-10-23 22:50:04,386 epoch 1 - iter 534/894 - loss 0.61468447 - time (sec): 33.99 - samples/sec: 1538.57 - lr: 0.000030 - momentum: 0.000000
2023-10-23 22:50:09,991 epoch 1 - iter 623/894 - loss 0.56293072 - time (sec): 39.59 - samples/sec: 1526.39 - lr: 0.000035 - momentum: 0.000000
2023-10-23 22:50:15,496 epoch 1 - iter 712/894 - loss 0.52064238 - time (sec): 45.10 - samples/sec: 1510.27 - lr: 0.000040 - momentum: 0.000000
2023-10-23 22:50:21,261 epoch 1 - iter 801/894 - loss 0.48300698 - time (sec): 50.86 - samples/sec: 1525.07 - lr: 0.000045 - momentum: 0.000000
2023-10-23 22:50:26,941 epoch 1 - iter 890/894 - loss 0.45116414 - time (sec): 56.54 - samples/sec: 1526.00 - lr: 0.000050 - momentum: 0.000000
2023-10-23 22:50:27,178 ----------------------------------------------------------------------------------------------------
2023-10-23 22:50:27,179 EPOCH 1 done: loss 0.4508 - lr: 0.000050
2023-10-23 22:50:32,016 DEV : loss 0.20658902823925018 - f1-score (micro avg)  0.6099
2023-10-23 22:50:32,036 saving best model
2023-10-23 22:50:32,505 ----------------------------------------------------------------------------------------------------
2023-10-23 22:50:38,267 epoch 2 - iter 89/894 - loss 0.15434962 - time (sec): 5.76 - samples/sec: 1489.64 - lr: 0.000049 - momentum: 0.000000
2023-10-23 22:50:43,999 epoch 2 - iter 178/894 - loss 0.17011126 - time (sec): 11.49 - samples/sec: 1526.50 - lr: 0.000049 - momentum: 0.000000
2023-10-23 22:50:49,620 epoch 2 - iter 267/894 - loss 0.16331287 - time (sec): 17.11 - samples/sec: 1509.50 - lr: 0.000048 - momentum: 0.000000
2023-10-23 22:50:55,433 epoch 2 - iter 356/894 - loss 0.15935409 - time (sec): 22.93 - samples/sec: 1523.36 - lr: 0.000048 - momentum: 0.000000
2023-10-23 22:51:01,011 epoch 2 - iter 445/894 - loss 0.15771296 - time (sec): 28.50 - samples/sec: 1518.48 - lr: 0.000047 - momentum: 0.000000
2023-10-23 22:51:06,621 epoch 2 - iter 534/894 - loss 0.15628055 - time (sec): 34.12 - samples/sec: 1518.62 - lr: 0.000047 - momentum: 0.000000
2023-10-23 22:51:12,176 epoch 2 - iter 623/894 - loss 0.15337233 - time (sec): 39.67 - samples/sec: 1515.60 - lr: 0.000046 - momentum: 0.000000
2023-10-23 22:51:17,915 epoch 2 - iter 712/894 - loss 0.14878889 - time (sec): 45.41 - samples/sec: 1526.53 - lr: 0.000046 - momentum: 0.000000
2023-10-23 22:51:23,512 epoch 2 - iter 801/894 - loss 0.14702059 - time (sec): 51.01 - samples/sec: 1520.68 - lr: 0.000045 - momentum: 0.000000
2023-10-23 22:51:29,174 epoch 2 - iter 890/894 - loss 0.14567783 - time (sec): 56.67 - samples/sec: 1521.37 - lr: 0.000044 - momentum: 0.000000
2023-10-23 22:51:29,414 ----------------------------------------------------------------------------------------------------
2023-10-23 22:51:29,414 EPOCH 2 done: loss 0.1465 - lr: 0.000044
2023-10-23 22:51:35,915 DEV : loss 0.17153306305408478 - f1-score (micro avg)  0.6876
2023-10-23 22:51:35,936 saving best model
2023-10-23 22:51:36,525 ----------------------------------------------------------------------------------------------------
2023-10-23 22:51:42,471 epoch 3 - iter 89/894 - loss 0.11549407 - time (sec): 5.94 - samples/sec: 1624.10 - lr: 0.000044 - momentum: 0.000000
2023-10-23 22:51:48,118 epoch 3 - iter 178/894 - loss 0.10047040 - time (sec): 11.59 - samples/sec: 1614.35 - lr: 0.000043 - momentum: 0.000000
2023-10-23 22:51:53,800 epoch 3 - iter 267/894 - loss 0.10381143 - time (sec): 17.27 - samples/sec: 1594.33 - lr: 0.000043 - momentum: 0.000000
2023-10-23 22:51:59,265 epoch 3 - iter 356/894 - loss 0.09976007 - time (sec): 22.74 - samples/sec: 1563.08 - lr: 0.000042 - momentum: 0.000000
2023-10-23 22:52:05,191 epoch 3 - iter 445/894 - loss 0.09852416 - time (sec): 28.66 - samples/sec: 1567.70 - lr: 0.000042 - momentum: 0.000000
2023-10-23 22:52:11,121 epoch 3 - iter 534/894 - loss 0.09587092 - time (sec): 34.59 - samples/sec: 1572.55 - lr: 0.000041 - momentum: 0.000000
2023-10-23 22:52:16,611 epoch 3 - iter 623/894 - loss 0.09686006 - time (sec): 40.08 - samples/sec: 1551.20 - lr: 0.000041 - momentum: 0.000000
2023-10-23 22:52:22,100 epoch 3 - iter 712/894 - loss 0.09757567 - time (sec): 45.57 - samples/sec: 1533.14 - lr: 0.000040 - momentum: 0.000000
2023-10-23 22:52:27,745 epoch 3 - iter 801/894 - loss 0.09644605 - time (sec): 51.22 - samples/sec: 1536.12 - lr: 0.000039 - momentum: 0.000000
2023-10-23 22:52:33,154 epoch 3 - iter 890/894 - loss 0.09578227 - time (sec): 56.63 - samples/sec: 1521.18 - lr: 0.000039 - momentum: 0.000000
2023-10-23 22:52:33,398 ----------------------------------------------------------------------------------------------------
2023-10-23 22:52:33,398 EPOCH 3 done: loss 0.0958 - lr: 0.000039
2023-10-23 22:52:39,875 DEV : loss 0.19253584742546082 - f1-score (micro avg)  0.6924
2023-10-23 22:52:39,895 saving best model
2023-10-23 22:52:40,469 ----------------------------------------------------------------------------------------------------
2023-10-23 22:52:46,035 epoch 4 - iter 89/894 - loss 0.05340071 - time (sec): 5.57 - samples/sec: 1522.95 - lr: 0.000038 - momentum: 0.000000
2023-10-23 22:52:51,880 epoch 4 - iter 178/894 - loss 0.06546909 - time (sec): 11.41 - samples/sec: 1556.05 - lr: 0.000038 - momentum: 0.000000
2023-10-23 22:52:57,704 epoch 4 - iter 267/894 - loss 0.06397801 - time (sec): 17.23 - samples/sec: 1550.01 - lr: 0.000037 - momentum: 0.000000
2023-10-23 22:53:03,184 epoch 4 - iter 356/894 - loss 0.06168127 - time (sec): 22.71 - samples/sec: 1511.94 - lr: 0.000037 - momentum: 0.000000
2023-10-23 22:53:09,248 epoch 4 - iter 445/894 - loss 0.06400375 - time (sec): 28.78 - samples/sec: 1527.61 - lr: 0.000036 - momentum: 0.000000
2023-10-23 22:53:14,803 epoch 4 - iter 534/894 - loss 0.06406170 - time (sec): 34.33 - samples/sec: 1512.72 - lr: 0.000036 - momentum: 0.000000
2023-10-23 22:53:20,518 epoch 4 - iter 623/894 - loss 0.06767318 - time (sec): 40.05 - samples/sec: 1530.84 - lr: 0.000035 - momentum: 0.000000
2023-10-23 22:53:26,118 epoch 4 - iter 712/894 - loss 0.06818413 - time (sec): 45.65 - samples/sec: 1527.17 - lr: 0.000034 - momentum: 0.000000
2023-10-23 22:53:31,676 epoch 4 - iter 801/894 - loss 0.06652914 - time (sec): 51.21 - samples/sec: 1525.97 - lr: 0.000034 - momentum: 0.000000
2023-10-23 22:53:37,205 epoch 4 - iter 890/894 - loss 0.06661341 - time (sec): 56.74 - samples/sec: 1517.64 - lr: 0.000033 - momentum: 0.000000
2023-10-23 22:53:37,460 ----------------------------------------------------------------------------------------------------
2023-10-23 22:53:37,460 EPOCH 4 done: loss 0.0667 - lr: 0.000033
2023-10-23 22:53:43,960 DEV : loss 0.22617001831531525 - f1-score (micro avg)  0.732
2023-10-23 22:53:43,981 saving best model
2023-10-23 22:53:44,563 ----------------------------------------------------------------------------------------------------
2023-10-23 22:53:50,150 epoch 5 - iter 89/894 - loss 0.03847375 - time (sec): 5.59 - samples/sec: 1548.11 - lr: 0.000033 - momentum: 0.000000
2023-10-23 22:53:56,003 epoch 5 - iter 178/894 - loss 0.04130081 - time (sec): 11.44 - samples/sec: 1543.93 - lr: 0.000032 - momentum: 0.000000
2023-10-23 22:54:01,533 epoch 5 - iter 267/894 - loss 0.04400346 - time (sec): 16.97 - samples/sec: 1523.98 - lr: 0.000032 - momentum: 0.000000
2023-10-23 22:54:07,074 epoch 5 - iter 356/894 - loss 0.04504201 - time (sec): 22.51 - samples/sec: 1515.87 - lr: 0.000031 - momentum: 0.000000
2023-10-23 22:54:12,796 epoch 5 - iter 445/894 - loss 0.04515784 - time (sec): 28.23 - samples/sec: 1509.00 - lr: 0.000031 - momentum: 0.000000
2023-10-23 22:54:18,507 epoch 5 - iter 534/894 - loss 0.04312426 - time (sec): 33.94 - samples/sec: 1507.17 - lr: 0.000030 - momentum: 0.000000
2023-10-23 22:54:24,019 epoch 5 - iter 623/894 - loss 0.04439914 - time (sec): 39.45 - samples/sec: 1507.54 - lr: 0.000029 - momentum: 0.000000
2023-10-23 22:54:29,902 epoch 5 - iter 712/894 - loss 0.04626351 - time (sec): 45.34 - samples/sec: 1516.83 - lr: 0.000029 - momentum: 0.000000
2023-10-23 22:54:35,470 epoch 5 - iter 801/894 - loss 0.04521734 - time (sec): 50.91 - samples/sec: 1521.82 - lr: 0.000028 - momentum: 0.000000
2023-10-23 22:54:41,097 epoch 5 - iter 890/894 - loss 0.04347528 - time (sec): 56.53 - samples/sec: 1522.53 - lr: 0.000028 - momentum: 0.000000
2023-10-23 22:54:41,362 ----------------------------------------------------------------------------------------------------
2023-10-23 22:54:41,362 EPOCH 5 done: loss 0.0436 - lr: 0.000028
2023-10-23 22:54:47,838 DEV : loss 0.22702528536319733 - f1-score (micro avg)  0.7545
2023-10-23 22:54:47,858 saving best model
2023-10-23 22:54:48,441 ----------------------------------------------------------------------------------------------------
2023-10-23 22:54:54,178 epoch 6 - iter 89/894 - loss 0.02705068 - time (sec): 5.74 - samples/sec: 1466.90 - lr: 0.000027 - momentum: 0.000000
2023-10-23 22:54:59,948 epoch 6 - iter 178/894 - loss 0.02543707 - time (sec): 11.51 - samples/sec: 1485.52 - lr: 0.000027 - momentum: 0.000000
2023-10-23 22:55:05,992 epoch 6 - iter 267/894 - loss 0.02928149 - time (sec): 17.55 - samples/sec: 1533.87 - lr: 0.000026 - momentum: 0.000000
2023-10-23 22:55:11,509 epoch 6 - iter 356/894 - loss 0.03037954 - time (sec): 23.07 - samples/sec: 1527.13 - lr: 0.000026 - momentum: 0.000000
2023-10-23 22:55:17,078 epoch 6 - iter 445/894 - loss 0.03095994 - time (sec): 28.64 - samples/sec: 1521.48 - lr: 0.000025 - momentum: 0.000000
2023-10-23 22:55:22,726 epoch 6 - iter 534/894 - loss 0.02994244 - time (sec): 34.28 - samples/sec: 1518.85 - lr: 0.000024 - momentum: 0.000000
2023-10-23 22:55:28,164 epoch 6 - iter 623/894 - loss 0.03058719 - time (sec): 39.72 - samples/sec: 1508.59 - lr: 0.000024 - momentum: 0.000000
2023-10-23 22:55:33,615 epoch 6 - iter 712/894 - loss 0.03030287 - time (sec): 45.17 - samples/sec: 1504.23 - lr: 0.000023 - momentum: 0.000000
2023-10-23 22:55:39,332 epoch 6 - iter 801/894 - loss 0.02985015 - time (sec): 50.89 - samples/sec: 1509.85 - lr: 0.000023 - momentum: 0.000000
2023-10-23 22:55:45,019 epoch 6 - iter 890/894 - loss 0.02948320 - time (sec): 56.58 - samples/sec: 1523.21 - lr: 0.000022 - momentum: 0.000000
2023-10-23 22:55:45,264 ----------------------------------------------------------------------------------------------------
2023-10-23 22:55:45,264 EPOCH 6 done: loss 0.0294 - lr: 0.000022
2023-10-23 22:55:51,747 DEV : loss 0.26115021109580994 - f1-score (micro avg)  0.7395
2023-10-23 22:55:51,767 ----------------------------------------------------------------------------------------------------
2023-10-23 22:55:57,666 epoch 7 - iter 89/894 - loss 0.01502691 - time (sec): 5.90 - samples/sec: 1560.68 - lr: 0.000022 - momentum: 0.000000
2023-10-23 22:56:03,318 epoch 7 - iter 178/894 - loss 0.02355773 - time (sec): 11.55 - samples/sec: 1543.95 - lr: 0.000021 - momentum: 0.000000
2023-10-23 22:56:08,854 epoch 7 - iter 267/894 - loss 0.02081776 - time (sec): 17.09 - samples/sec: 1526.58 - lr: 0.000021 - momentum: 0.000000
2023-10-23 22:56:14,634 epoch 7 - iter 356/894 - loss 0.02157166 - time (sec): 22.87 - samples/sec: 1562.10 - lr: 0.000020 - momentum: 0.000000
2023-10-23 22:56:20,252 epoch 7 - iter 445/894 - loss 0.02168071 - time (sec): 28.48 - samples/sec: 1541.80 - lr: 0.000019 - momentum: 0.000000
2023-10-23 22:56:25,970 epoch 7 - iter 534/894 - loss 0.01981735 - time (sec): 34.20 - samples/sec: 1533.84 - lr: 0.000019 - momentum: 0.000000
2023-10-23 22:56:31,600 epoch 7 - iter 623/894 - loss 0.02156934 - time (sec): 39.83 - samples/sec: 1534.52 - lr: 0.000018 - momentum: 0.000000
2023-10-23 22:56:37,370 epoch 7 - iter 712/894 - loss 0.02161565 - time (sec): 45.60 - samples/sec: 1541.51 - lr: 0.000018 - momentum: 0.000000
2023-10-23 22:56:43,079 epoch 7 - iter 801/894 - loss 0.02136584 - time (sec): 51.31 - samples/sec: 1536.33 - lr: 0.000017 - momentum: 0.000000
2023-10-23 22:56:48,442 epoch 7 - iter 890/894 - loss 0.02065920 - time (sec): 56.67 - samples/sec: 1521.22 - lr: 0.000017 - momentum: 0.000000
2023-10-23 22:56:48,681 ----------------------------------------------------------------------------------------------------
2023-10-23 22:56:48,681 EPOCH 7 done: loss 0.0206 - lr: 0.000017
2023-10-23 22:56:55,183 DEV : loss 0.26584720611572266 - f1-score (micro avg)  0.755
2023-10-23 22:56:55,203 saving best model
2023-10-23 22:56:55,785 ----------------------------------------------------------------------------------------------------
2023-10-23 22:57:01,368 epoch 8 - iter 89/894 - loss 0.01810547 - time (sec): 5.58 - samples/sec: 1535.70 - lr: 0.000016 - momentum: 0.000000
2023-10-23 22:57:07,270 epoch 8 - iter 178/894 - loss 0.01401670 - time (sec): 11.48 - samples/sec: 1550.83 - lr: 0.000016 - momentum: 0.000000
2023-10-23 22:57:12,806 epoch 8 - iter 267/894 - loss 0.01102657 - time (sec): 17.02 - samples/sec: 1540.87 - lr: 0.000015 - momentum: 0.000000
2023-10-23 22:57:18,438 epoch 8 - iter 356/894 - loss 0.01297886 - time (sec): 22.65 - samples/sec: 1510.22 - lr: 0.000014 - momentum: 0.000000
2023-10-23 22:57:24,046 epoch 8 - iter 445/894 - loss 0.01401949 - time (sec): 28.26 - samples/sec: 1507.99 - lr: 0.000014 - momentum: 0.000000
2023-10-23 22:57:29,518 epoch 8 - iter 534/894 - loss 0.01265375 - time (sec): 33.73 - samples/sec: 1503.43 - lr: 0.000013 - momentum: 0.000000
2023-10-23 22:57:35,357 epoch 8 - iter 623/894 - loss 0.01275932 - time (sec): 39.57 - samples/sec: 1516.55 - lr: 0.000013 - momentum: 0.000000
2023-10-23 22:57:41,261 epoch 8 - iter 712/894 - loss 0.01174535 - time (sec): 45.47 - samples/sec: 1524.32 - lr: 0.000012 - momentum: 0.000000
2023-10-23 22:57:46,854 epoch 8 - iter 801/894 - loss 0.01245907 - time (sec): 51.07 - samples/sec: 1528.48 - lr: 0.000012 - momentum: 0.000000
2023-10-23 22:57:52,395 epoch 8 - iter 890/894 - loss 0.01185428 - time (sec): 56.61 - samples/sec: 1523.16 - lr: 0.000011 - momentum: 0.000000
2023-10-23 22:57:52,640 ----------------------------------------------------------------------------------------------------
2023-10-23 22:57:52,640 EPOCH 8 done: loss 0.0121 - lr: 0.000011
2023-10-23 22:57:59,144 DEV : loss 0.2595275938510895 - f1-score (micro avg)  0.7686
2023-10-23 22:57:59,165 saving best model
2023-10-23 22:57:59,748 ----------------------------------------------------------------------------------------------------
2023-10-23 22:58:05,352 epoch 9 - iter 89/894 - loss 0.01175348 - time (sec): 5.60 - samples/sec: 1497.38 - lr: 0.000011 - momentum: 0.000000
2023-10-23 22:58:11,152 epoch 9 - iter 178/894 - loss 0.00798146 - time (sec): 11.40 - samples/sec: 1518.95 - lr: 0.000010 - momentum: 0.000000
2023-10-23 22:58:16,871 epoch 9 - iter 267/894 - loss 0.00715061 - time (sec): 17.12 - samples/sec: 1546.45 - lr: 0.000009 - momentum: 0.000000
2023-10-23 22:58:22,431 epoch 9 - iter 356/894 - loss 0.00696113 - time (sec): 22.68 - samples/sec: 1527.76 - lr: 0.000009 - momentum: 0.000000
2023-10-23 22:58:27,985 epoch 9 - iter 445/894 - loss 0.00575510 - time (sec): 28.24 - samples/sec: 1524.56 - lr: 0.000008 - momentum: 0.000000
2023-10-23 22:58:33,621 epoch 9 - iter 534/894 - loss 0.00572485 - time (sec): 33.87 - samples/sec: 1515.62 - lr: 0.000008 - momentum: 0.000000
2023-10-23 22:58:39,174 epoch 9 - iter 623/894 - loss 0.00639103 - time (sec): 39.42 - samples/sec: 1516.00 - lr: 0.000007 - momentum: 0.000000
2023-10-23 22:58:45,197 epoch 9 - iter 712/894 - loss 0.00630826 - time (sec): 45.45 - samples/sec: 1532.85 - lr: 0.000007 - momentum: 0.000000
2023-10-23 22:58:50,684 epoch 9 - iter 801/894 - loss 0.00607735 - time (sec): 50.94 - samples/sec: 1521.19 - lr: 0.000006 - momentum: 0.000000
2023-10-23 22:58:56,358 epoch 9 - iter 890/894 - loss 0.00584459 - time (sec): 56.61 - samples/sec: 1519.82 - lr: 0.000006 - momentum: 0.000000
2023-10-23 22:58:56,610 ----------------------------------------------------------------------------------------------------
2023-10-23 22:58:56,610 EPOCH 9 done: loss 0.0058 - lr: 0.000006
2023-10-23 22:59:02,842 DEV : loss 0.2801297605037689 - f1-score (micro avg)  0.7709
2023-10-23 22:59:02,862 saving best model
2023-10-23 22:59:03,447 ----------------------------------------------------------------------------------------------------
2023-10-23 22:59:08,960 epoch 10 - iter 89/894 - loss 0.00751582 - time (sec): 5.51 - samples/sec: 1457.49 - lr: 0.000005 - momentum: 0.000000
2023-10-23 22:59:14,726 epoch 10 - iter 178/894 - loss 0.00514737 - time (sec): 11.28 - samples/sec: 1426.06 - lr: 0.000004 - momentum: 0.000000
2023-10-23 22:59:20,482 epoch 10 - iter 267/894 - loss 0.00386344 - time (sec): 17.03 - samples/sec: 1472.62 - lr: 0.000004 - momentum: 0.000000
2023-10-23 22:59:26,373 epoch 10 - iter 356/894 - loss 0.00357614 - time (sec): 22.92 - samples/sec: 1491.44 - lr: 0.000003 - momentum: 0.000000
2023-10-23 22:59:32,181 epoch 10 - iter 445/894 - loss 0.00379262 - time (sec): 28.73 - samples/sec: 1513.79 - lr: 0.000003 - momentum: 0.000000
2023-10-23 22:59:37,772 epoch 10 - iter 534/894 - loss 0.00335340 - time (sec): 34.32 - samples/sec: 1505.86 - lr: 0.000002 - momentum: 0.000000
2023-10-23 22:59:43,297 epoch 10 - iter 623/894 - loss 0.00404005 - time (sec): 39.85 - samples/sec: 1497.43 - lr: 0.000002 - momentum: 0.000000
2023-10-23 22:59:48,901 epoch 10 - iter 712/894 - loss 0.00415591 - time (sec): 45.45 - samples/sec: 1505.67 - lr: 0.000001 - momentum: 0.000000
2023-10-23 22:59:54,556 epoch 10 - iter 801/894 - loss 0.00448379 - time (sec): 51.11 - samples/sec: 1509.84 - lr: 0.000001 - momentum: 0.000000
2023-10-23 23:00:00,418 epoch 10 - iter 890/894 - loss 0.00481143 - time (sec): 56.97 - samples/sec: 1511.26 - lr: 0.000000 - momentum: 0.000000
2023-10-23 23:00:00,668 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:00,668 EPOCH 10 done: loss 0.0048 - lr: 0.000000
2023-10-23 23:00:06,899 DEV : loss 0.2858913242816925 - f1-score (micro avg)  0.7746
2023-10-23 23:00:06,919 saving best model
2023-10-23 23:00:07,980 ----------------------------------------------------------------------------------------------------
2023-10-23 23:00:07,980 Loading model from best epoch ...
2023-10-23 23:00:09,643 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 23:00:14,469 
Results:
- F-score (micro) 0.7476
- F-score (macro) 0.6761
- Accuracy 0.6143

By class:
              precision    recall  f1-score   support

         loc     0.8271    0.8507    0.8387       596
        pers     0.6623    0.7538    0.7051       333
         org     0.5268    0.4470    0.4836       132
        prod     0.7674    0.5000    0.6055        66
        time     0.7400    0.7551    0.7475        49

   micro avg     0.7410    0.7543    0.7476      1176
   macro avg     0.7047    0.6613    0.6761      1176
weighted avg     0.7397    0.7543    0.7441      1176

2023-10-23 23:00:14,470 ----------------------------------------------------------------------------------------------------