2023-10-23 21:21:30,456 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,457 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 21:21:30,457 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,457 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 21:21:30,457 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,457 Train:  3575 sentences
2023-10-23 21:21:30,457         (train_with_dev=False, train_with_test=False)
2023-10-23 21:21:30,457 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,457 Training Params:
2023-10-23 21:21:30,457  - learning_rate: "3e-05" 
2023-10-23 21:21:30,457  - mini_batch_size: "4"
2023-10-23 21:21:30,457  - max_epochs: "10"
2023-10-23 21:21:30,457  - shuffle: "True"
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 Plugins:
2023-10-23 21:21:30,458  - TensorboardLogger
2023-10-23 21:21:30,458  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 21:21:30,458  - metric: "('micro avg', 'f1-score')"
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 Computation:
2023-10-23 21:21:30,458  - compute on device: cuda:0
2023-10-23 21:21:30,458  - embedding storage: none
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 ----------------------------------------------------------------------------------------------------
2023-10-23 21:21:30,458 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 21:21:35,957 epoch 1 - iter 89/894 - loss 2.21664487 - time (sec): 5.50 - samples/sec: 1523.65 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:21:41,733 epoch 1 - iter 178/894 - loss 1.33031967 - time (sec): 11.27 - samples/sec: 1548.64 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:21:47,322 epoch 1 - iter 267/894 - loss 1.02761727 - time (sec): 16.86 - samples/sec: 1558.12 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:21:52,888 epoch 1 - iter 356/894 - loss 0.85080042 - time (sec): 22.43 - samples/sec: 1560.61 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:21:58,685 epoch 1 - iter 445/894 - loss 0.74598055 - time (sec): 28.23 - samples/sec: 1565.20 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:22:04,296 epoch 1 - iter 534/894 - loss 0.67330125 - time (sec): 33.84 - samples/sec: 1557.07 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:22:09,966 epoch 1 - iter 623/894 - loss 0.61339427 - time (sec): 39.51 - samples/sec: 1548.21 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:22:15,476 epoch 1 - iter 712/894 - loss 0.56491664 - time (sec): 45.02 - samples/sec: 1547.50 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:22:21,077 epoch 1 - iter 801/894 - loss 0.52761211 - time (sec): 50.62 - samples/sec: 1541.15 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:22:26,797 epoch 1 - iter 890/894 - loss 0.49680906 - time (sec): 56.34 - samples/sec: 1528.78 - lr: 0.000030 - momentum: 0.000000
2023-10-23 21:22:27,043 ----------------------------------------------------------------------------------------------------
2023-10-23 21:22:27,043 EPOCH 1 done: loss 0.4947 - lr: 0.000030
2023-10-23 21:22:31,863 DEV : loss 0.1481543481349945 - f1-score (micro avg)  0.6598
2023-10-23 21:22:31,883 saving best model
2023-10-23 21:22:32,350 ----------------------------------------------------------------------------------------------------
2023-10-23 21:22:38,121 epoch 2 - iter 89/894 - loss 0.17708347 - time (sec): 5.77 - samples/sec: 1644.56 - lr: 0.000030 - momentum: 0.000000
2023-10-23 21:22:43,647 epoch 2 - iter 178/894 - loss 0.17307608 - time (sec): 11.30 - samples/sec: 1556.96 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:22:49,452 epoch 2 - iter 267/894 - loss 0.15463895 - time (sec): 17.10 - samples/sec: 1572.23 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:22:55,050 epoch 2 - iter 356/894 - loss 0.14758882 - time (sec): 22.70 - samples/sec: 1557.85 - lr: 0.000029 - momentum: 0.000000
2023-10-23 21:23:00,620 epoch 2 - iter 445/894 - loss 0.14968602 - time (sec): 28.27 - samples/sec: 1554.22 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:23:06,260 epoch 2 - iter 534/894 - loss 0.14924781 - time (sec): 33.91 - samples/sec: 1543.18 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:23:11,750 epoch 2 - iter 623/894 - loss 0.14556656 - time (sec): 39.40 - samples/sec: 1540.00 - lr: 0.000028 - momentum: 0.000000
2023-10-23 21:23:17,236 epoch 2 - iter 712/894 - loss 0.14492055 - time (sec): 44.88 - samples/sec: 1531.25 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:23:23,139 epoch 2 - iter 801/894 - loss 0.14248077 - time (sec): 50.79 - samples/sec: 1540.25 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:23:28,702 epoch 2 - iter 890/894 - loss 0.14341120 - time (sec): 56.35 - samples/sec: 1528.57 - lr: 0.000027 - momentum: 0.000000
2023-10-23 21:23:28,955 ----------------------------------------------------------------------------------------------------
2023-10-23 21:23:28,955 EPOCH 2 done: loss 0.1432 - lr: 0.000027
2023-10-23 21:23:35,410 DEV : loss 0.16756634414196014 - f1-score (micro avg)  0.686
2023-10-23 21:23:35,430 saving best model
2023-10-23 21:23:36,027 ----------------------------------------------------------------------------------------------------
2023-10-23 21:23:42,076 epoch 3 - iter 89/894 - loss 0.07202634 - time (sec): 6.05 - samples/sec: 1740.28 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:23:47,728 epoch 3 - iter 178/894 - loss 0.08210135 - time (sec): 11.70 - samples/sec: 1636.27 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:23:53,320 epoch 3 - iter 267/894 - loss 0.08942123 - time (sec): 17.29 - samples/sec: 1592.06 - lr: 0.000026 - momentum: 0.000000
2023-10-23 21:23:58,906 epoch 3 - iter 356/894 - loss 0.08248351 - time (sec): 22.88 - samples/sec: 1560.39 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:24:04,612 epoch 3 - iter 445/894 - loss 0.08206964 - time (sec): 28.58 - samples/sec: 1547.29 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:24:10,207 epoch 3 - iter 534/894 - loss 0.08479942 - time (sec): 34.18 - samples/sec: 1547.26 - lr: 0.000025 - momentum: 0.000000
2023-10-23 21:24:15,857 epoch 3 - iter 623/894 - loss 0.08185387 - time (sec): 39.83 - samples/sec: 1557.23 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:24:21,255 epoch 3 - iter 712/894 - loss 0.08050106 - time (sec): 45.23 - samples/sec: 1531.85 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:24:26,934 epoch 3 - iter 801/894 - loss 0.08377902 - time (sec): 50.91 - samples/sec: 1526.36 - lr: 0.000024 - momentum: 0.000000
2023-10-23 21:24:32,544 epoch 3 - iter 890/894 - loss 0.08294752 - time (sec): 56.52 - samples/sec: 1527.26 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:24:32,776 ----------------------------------------------------------------------------------------------------
2023-10-23 21:24:32,776 EPOCH 3 done: loss 0.0827 - lr: 0.000023
2023-10-23 21:24:39,253 DEV : loss 0.18027736246585846 - f1-score (micro avg)  0.7222
2023-10-23 21:24:39,273 saving best model
2023-10-23 21:24:39,864 ----------------------------------------------------------------------------------------------------
2023-10-23 21:24:45,407 epoch 4 - iter 89/894 - loss 0.04271264 - time (sec): 5.54 - samples/sec: 1527.69 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:24:50,971 epoch 4 - iter 178/894 - loss 0.05003284 - time (sec): 11.11 - samples/sec: 1532.92 - lr: 0.000023 - momentum: 0.000000
2023-10-23 21:24:56,717 epoch 4 - iter 267/894 - loss 0.04645080 - time (sec): 16.85 - samples/sec: 1556.89 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:25:02,380 epoch 4 - iter 356/894 - loss 0.04895070 - time (sec): 22.52 - samples/sec: 1537.54 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:25:08,261 epoch 4 - iter 445/894 - loss 0.04925683 - time (sec): 28.40 - samples/sec: 1558.22 - lr: 0.000022 - momentum: 0.000000
2023-10-23 21:25:13,823 epoch 4 - iter 534/894 - loss 0.05485294 - time (sec): 33.96 - samples/sec: 1542.54 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:25:19,366 epoch 4 - iter 623/894 - loss 0.05445647 - time (sec): 39.50 - samples/sec: 1531.79 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:25:24,826 epoch 4 - iter 712/894 - loss 0.05558929 - time (sec): 44.96 - samples/sec: 1516.15 - lr: 0.000021 - momentum: 0.000000
2023-10-23 21:25:30,589 epoch 4 - iter 801/894 - loss 0.05569812 - time (sec): 50.72 - samples/sec: 1516.91 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:25:36,393 epoch 4 - iter 890/894 - loss 0.05395194 - time (sec): 56.53 - samples/sec: 1526.24 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:25:36,624 ----------------------------------------------------------------------------------------------------
2023-10-23 21:25:36,625 EPOCH 4 done: loss 0.0543 - lr: 0.000020
2023-10-23 21:25:43,133 DEV : loss 0.19269603490829468 - f1-score (micro avg)  0.7635
2023-10-23 21:25:43,153 saving best model
2023-10-23 21:25:43,753 ----------------------------------------------------------------------------------------------------
2023-10-23 21:25:49,397 epoch 5 - iter 89/894 - loss 0.04613190 - time (sec): 5.64 - samples/sec: 1539.22 - lr: 0.000020 - momentum: 0.000000
2023-10-23 21:25:55,377 epoch 5 - iter 178/894 - loss 0.04206252 - time (sec): 11.62 - samples/sec: 1624.43 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:26:00,952 epoch 5 - iter 267/894 - loss 0.03516016 - time (sec): 17.20 - samples/sec: 1576.75 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:26:06,711 epoch 5 - iter 356/894 - loss 0.03286165 - time (sec): 22.96 - samples/sec: 1573.64 - lr: 0.000019 - momentum: 0.000000
2023-10-23 21:26:12,286 epoch 5 - iter 445/894 - loss 0.03370259 - time (sec): 28.53 - samples/sec: 1561.28 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:26:17,963 epoch 5 - iter 534/894 - loss 0.03464729 - time (sec): 34.21 - samples/sec: 1551.36 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:26:23,726 epoch 5 - iter 623/894 - loss 0.03428769 - time (sec): 39.97 - samples/sec: 1545.26 - lr: 0.000018 - momentum: 0.000000
2023-10-23 21:26:29,269 epoch 5 - iter 712/894 - loss 0.03634000 - time (sec): 45.52 - samples/sec: 1528.85 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:26:35,025 epoch 5 - iter 801/894 - loss 0.03738652 - time (sec): 51.27 - samples/sec: 1528.26 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:26:40,464 epoch 5 - iter 890/894 - loss 0.03658564 - time (sec): 56.71 - samples/sec: 1519.86 - lr: 0.000017 - momentum: 0.000000
2023-10-23 21:26:40,710 ----------------------------------------------------------------------------------------------------
2023-10-23 21:26:40,710 EPOCH 5 done: loss 0.0367 - lr: 0.000017
2023-10-23 21:26:47,225 DEV : loss 0.19243519008159637 - f1-score (micro avg)  0.7571
2023-10-23 21:26:47,245 ----------------------------------------------------------------------------------------------------
2023-10-23 21:26:53,171 epoch 6 - iter 89/894 - loss 0.01488108 - time (sec): 5.93 - samples/sec: 1589.90 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:26:58,559 epoch 6 - iter 178/894 - loss 0.02507305 - time (sec): 11.31 - samples/sec: 1492.30 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:27:04,219 epoch 6 - iter 267/894 - loss 0.02660050 - time (sec): 16.97 - samples/sec: 1514.85 - lr: 0.000016 - momentum: 0.000000
2023-10-23 21:27:10,264 epoch 6 - iter 356/894 - loss 0.02304923 - time (sec): 23.02 - samples/sec: 1526.25 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:27:15,928 epoch 6 - iter 445/894 - loss 0.02395097 - time (sec): 28.68 - samples/sec: 1518.59 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:27:21,500 epoch 6 - iter 534/894 - loss 0.02312750 - time (sec): 34.25 - samples/sec: 1514.25 - lr: 0.000015 - momentum: 0.000000
2023-10-23 21:27:26,995 epoch 6 - iter 623/894 - loss 0.02395946 - time (sec): 39.75 - samples/sec: 1504.16 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:27:32,503 epoch 6 - iter 712/894 - loss 0.02320612 - time (sec): 45.26 - samples/sec: 1509.94 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:27:38,101 epoch 6 - iter 801/894 - loss 0.02250887 - time (sec): 50.86 - samples/sec: 1520.80 - lr: 0.000014 - momentum: 0.000000
2023-10-23 21:27:43,863 epoch 6 - iter 890/894 - loss 0.02277949 - time (sec): 56.62 - samples/sec: 1522.19 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:27:44,111 ----------------------------------------------------------------------------------------------------
2023-10-23 21:27:44,111 EPOCH 6 done: loss 0.0227 - lr: 0.000013
2023-10-23 21:27:50,618 DEV : loss 0.2726885974407196 - f1-score (micro avg)  0.7458
2023-10-23 21:27:50,639 ----------------------------------------------------------------------------------------------------
2023-10-23 21:27:56,471 epoch 7 - iter 89/894 - loss 0.01202364 - time (sec): 5.83 - samples/sec: 1583.99 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:28:02,569 epoch 7 - iter 178/894 - loss 0.01669844 - time (sec): 11.93 - samples/sec: 1590.98 - lr: 0.000013 - momentum: 0.000000
2023-10-23 21:28:08,156 epoch 7 - iter 267/894 - loss 0.01475230 - time (sec): 17.52 - samples/sec: 1574.38 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:28:13,665 epoch 7 - iter 356/894 - loss 0.01339422 - time (sec): 23.02 - samples/sec: 1538.11 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:28:19,314 epoch 7 - iter 445/894 - loss 0.01478419 - time (sec): 28.67 - samples/sec: 1518.67 - lr: 0.000012 - momentum: 0.000000
2023-10-23 21:28:24,952 epoch 7 - iter 534/894 - loss 0.01540978 - time (sec): 34.31 - samples/sec: 1519.79 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:28:30,561 epoch 7 - iter 623/894 - loss 0.01527742 - time (sec): 39.92 - samples/sec: 1526.87 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:28:36,196 epoch 7 - iter 712/894 - loss 0.01519423 - time (sec): 45.56 - samples/sec: 1521.04 - lr: 0.000011 - momentum: 0.000000
2023-10-23 21:28:41,775 epoch 7 - iter 801/894 - loss 0.01588042 - time (sec): 51.14 - samples/sec: 1520.45 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:28:47,386 epoch 7 - iter 890/894 - loss 0.01506212 - time (sec): 56.75 - samples/sec: 1518.15 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:28:47,656 ----------------------------------------------------------------------------------------------------
2023-10-23 21:28:47,657 EPOCH 7 done: loss 0.0153 - lr: 0.000010
2023-10-23 21:28:54,151 DEV : loss 0.2593619227409363 - f1-score (micro avg)  0.7681
2023-10-23 21:28:54,171 saving best model
2023-10-23 21:28:54,771 ----------------------------------------------------------------------------------------------------
2023-10-23 21:29:00,547 epoch 8 - iter 89/894 - loss 0.01205340 - time (sec): 5.77 - samples/sec: 1505.27 - lr: 0.000010 - momentum: 0.000000
2023-10-23 21:29:06,066 epoch 8 - iter 178/894 - loss 0.01236707 - time (sec): 11.29 - samples/sec: 1492.63 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:29:11,754 epoch 8 - iter 267/894 - loss 0.00992080 - time (sec): 16.98 - samples/sec: 1498.04 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:29:17,249 epoch 8 - iter 356/894 - loss 0.00995604 - time (sec): 22.48 - samples/sec: 1484.55 - lr: 0.000009 - momentum: 0.000000
2023-10-23 21:29:22,953 epoch 8 - iter 445/894 - loss 0.01027724 - time (sec): 28.18 - samples/sec: 1484.35 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:29:28,531 epoch 8 - iter 534/894 - loss 0.00935046 - time (sec): 33.76 - samples/sec: 1491.26 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:29:34,441 epoch 8 - iter 623/894 - loss 0.01009927 - time (sec): 39.67 - samples/sec: 1508.32 - lr: 0.000008 - momentum: 0.000000
2023-10-23 21:29:40,012 epoch 8 - iter 712/894 - loss 0.01012031 - time (sec): 45.24 - samples/sec: 1499.94 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:29:45,715 epoch 8 - iter 801/894 - loss 0.01002887 - time (sec): 50.94 - samples/sec: 1513.77 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:29:51,485 epoch 8 - iter 890/894 - loss 0.00972871 - time (sec): 56.71 - samples/sec: 1519.80 - lr: 0.000007 - momentum: 0.000000
2023-10-23 21:29:51,727 ----------------------------------------------------------------------------------------------------
2023-10-23 21:29:51,728 EPOCH 8 done: loss 0.0097 - lr: 0.000007
2023-10-23 21:29:58,241 DEV : loss 0.27069804072380066 - f1-score (micro avg)  0.7757
2023-10-23 21:29:58,261 saving best model
2023-10-23 21:29:58,854 ----------------------------------------------------------------------------------------------------
2023-10-23 21:30:04,344 epoch 9 - iter 89/894 - loss 0.00394006 - time (sec): 5.49 - samples/sec: 1434.06 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:30:10,325 epoch 9 - iter 178/894 - loss 0.00797501 - time (sec): 11.47 - samples/sec: 1558.94 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:30:16,052 epoch 9 - iter 267/894 - loss 0.00619020 - time (sec): 17.20 - samples/sec: 1553.30 - lr: 0.000006 - momentum: 0.000000
2023-10-23 21:30:21,716 epoch 9 - iter 356/894 - loss 0.00643612 - time (sec): 22.86 - samples/sec: 1549.09 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:30:27,475 epoch 9 - iter 445/894 - loss 0.00778558 - time (sec): 28.62 - samples/sec: 1544.90 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:30:33,413 epoch 9 - iter 534/894 - loss 0.00814245 - time (sec): 34.56 - samples/sec: 1544.30 - lr: 0.000005 - momentum: 0.000000
2023-10-23 21:30:38,995 epoch 9 - iter 623/894 - loss 0.00794589 - time (sec): 40.14 - samples/sec: 1538.36 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:30:44,474 epoch 9 - iter 712/894 - loss 0.00766539 - time (sec): 45.62 - samples/sec: 1523.76 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:30:49,952 epoch 9 - iter 801/894 - loss 0.00726590 - time (sec): 51.10 - samples/sec: 1511.71 - lr: 0.000004 - momentum: 0.000000
2023-10-23 21:30:55,592 epoch 9 - iter 890/894 - loss 0.00734059 - time (sec): 56.74 - samples/sec: 1517.12 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:30:55,841 ----------------------------------------------------------------------------------------------------
2023-10-23 21:30:55,841 EPOCH 9 done: loss 0.0073 - lr: 0.000003
2023-10-23 21:31:02,068 DEV : loss 0.2792131006717682 - f1-score (micro avg)  0.7783
2023-10-23 21:31:02,089 saving best model
2023-10-23 21:31:02,684 ----------------------------------------------------------------------------------------------------
2023-10-23 21:31:08,637 epoch 10 - iter 89/894 - loss 0.00337450 - time (sec): 5.95 - samples/sec: 1563.46 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:31:14,533 epoch 10 - iter 178/894 - loss 0.00493983 - time (sec): 11.85 - samples/sec: 1498.08 - lr: 0.000003 - momentum: 0.000000
2023-10-23 21:31:20,499 epoch 10 - iter 267/894 - loss 0.00387315 - time (sec): 17.81 - samples/sec: 1549.82 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:31:26,020 epoch 10 - iter 356/894 - loss 0.00316311 - time (sec): 23.33 - samples/sec: 1531.19 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:31:31,606 epoch 10 - iter 445/894 - loss 0.00345817 - time (sec): 28.92 - samples/sec: 1520.25 - lr: 0.000002 - momentum: 0.000000
2023-10-23 21:31:37,261 epoch 10 - iter 534/894 - loss 0.00498121 - time (sec): 34.58 - samples/sec: 1528.01 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:31:42,794 epoch 10 - iter 623/894 - loss 0.00480233 - time (sec): 40.11 - samples/sec: 1520.50 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:31:48,587 epoch 10 - iter 712/894 - loss 0.00498084 - time (sec): 45.90 - samples/sec: 1530.48 - lr: 0.000001 - momentum: 0.000000
2023-10-23 21:31:54,056 epoch 10 - iter 801/894 - loss 0.00461055 - time (sec): 51.37 - samples/sec: 1513.87 - lr: 0.000000 - momentum: 0.000000
2023-10-23 21:31:59,716 epoch 10 - iter 890/894 - loss 0.00466250 - time (sec): 57.03 - samples/sec: 1512.46 - lr: 0.000000 - momentum: 0.000000
2023-10-23 21:31:59,949 ----------------------------------------------------------------------------------------------------
2023-10-23 21:31:59,949 EPOCH 10 done: loss 0.0047 - lr: 0.000000
2023-10-23 21:32:06,205 DEV : loss 0.2752907872200012 - f1-score (micro avg)  0.7757
2023-10-23 21:32:06,712 ----------------------------------------------------------------------------------------------------
2023-10-23 21:32:06,713 Loading model from best epoch ...
2023-10-23 21:32:08,410 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 21:32:13,254 
Results:
- F-score (micro) 0.7561
- F-score (macro) 0.6654
- Accuracy 0.6236

By class:
              precision    recall  f1-score   support

         loc     0.8444    0.8557    0.8500       596
        pers     0.6882    0.7688    0.7262       333
         org     0.5437    0.4242    0.4766       132
        prod     0.6800    0.5152    0.5862        66
        time     0.7273    0.6531    0.6882        49

   micro avg     0.7570    0.7551    0.7561      1176
   macro avg     0.6967    0.6434    0.6654      1176
weighted avg     0.7523    0.7551    0.7515      1176

2023-10-23 21:32:13,255 ----------------------------------------------------------------------------------------------------