2023-10-24 10:48:14,850 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,851 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()
)"
2023-10-24 10:48:14,852 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,852 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
 - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
2023-10-24 10:48:14,852 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,852 Train:  5901 sentences
2023-10-24 10:48:14,852         (train_with_dev=False, train_with_test=False)
2023-10-24 10:48:14,852 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,852 Training Params:
2023-10-24 10:48:14,852  - learning_rate: "5e-05" 
2023-10-24 10:48:14,852  - mini_batch_size: "4"
2023-10-24 10:48:14,852  - max_epochs: "10"
2023-10-24 10:48:14,852  - shuffle: "True"
2023-10-24 10:48:14,852 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,852 Plugins:
2023-10-24 10:48:14,852  - TensorboardLogger
2023-10-24 10:48:14,852  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 10:48:14,852 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,852 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 10:48:14,853  - metric: "('micro avg', 'f1-score')"
2023-10-24 10:48:14,853 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,853 Computation:
2023-10-24 10:48:14,853  - compute on device: cuda:0
2023-10-24 10:48:14,853  - embedding storage: none
2023-10-24 10:48:14,853 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,853 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-24 10:48:14,853 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,853 ----------------------------------------------------------------------------------------------------
2023-10-24 10:48:14,853 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 10:48:24,098 epoch 1 - iter 147/1476 - loss 1.65586929 - time (sec): 9.24 - samples/sec: 1730.95 - lr: 0.000005 - momentum: 0.000000
2023-10-24 10:48:33,391 epoch 1 - iter 294/1476 - loss 1.07991837 - time (sec): 18.54 - samples/sec: 1711.24 - lr: 0.000010 - momentum: 0.000000
2023-10-24 10:48:42,499 epoch 1 - iter 441/1476 - loss 0.87315512 - time (sec): 27.65 - samples/sec: 1663.26 - lr: 0.000015 - momentum: 0.000000
2023-10-24 10:48:52,399 epoch 1 - iter 588/1476 - loss 0.70884012 - time (sec): 37.55 - samples/sec: 1719.32 - lr: 0.000020 - momentum: 0.000000
2023-10-24 10:49:02,834 epoch 1 - iter 735/1476 - loss 0.59023179 - time (sec): 47.98 - samples/sec: 1759.57 - lr: 0.000025 - momentum: 0.000000
2023-10-24 10:49:12,304 epoch 1 - iter 882/1476 - loss 0.52815123 - time (sec): 57.45 - samples/sec: 1756.99 - lr: 0.000030 - momentum: 0.000000
2023-10-24 10:49:21,617 epoch 1 - iter 1029/1476 - loss 0.48116891 - time (sec): 66.76 - samples/sec: 1748.66 - lr: 0.000035 - momentum: 0.000000
2023-10-24 10:49:31,462 epoch 1 - iter 1176/1476 - loss 0.44141868 - time (sec): 76.61 - samples/sec: 1746.77 - lr: 0.000040 - momentum: 0.000000
2023-10-24 10:49:40,743 epoch 1 - iter 1323/1476 - loss 0.41530887 - time (sec): 85.89 - samples/sec: 1742.31 - lr: 0.000045 - momentum: 0.000000
2023-10-24 10:49:50,281 epoch 1 - iter 1470/1476 - loss 0.38978126 - time (sec): 95.43 - samples/sec: 1738.88 - lr: 0.000050 - momentum: 0.000000
2023-10-24 10:49:50,628 ----------------------------------------------------------------------------------------------------
2023-10-24 10:49:50,629 EPOCH 1 done: loss 0.3891 - lr: 0.000050
2023-10-24 10:49:56,936 DEV : loss 0.13457921147346497 - f1-score (micro avg)  0.7234
2023-10-24 10:49:56,958 saving best model
2023-10-24 10:49:57,516 ----------------------------------------------------------------------------------------------------
2023-10-24 10:50:07,080 epoch 2 - iter 147/1476 - loss 0.12059972 - time (sec): 9.56 - samples/sec: 1765.14 - lr: 0.000049 - momentum: 0.000000
2023-10-24 10:50:16,285 epoch 2 - iter 294/1476 - loss 0.13797220 - time (sec): 18.77 - samples/sec: 1717.67 - lr: 0.000049 - momentum: 0.000000
2023-10-24 10:50:25,463 epoch 2 - iter 441/1476 - loss 0.14905127 - time (sec): 27.95 - samples/sec: 1679.87 - lr: 0.000048 - momentum: 0.000000
2023-10-24 10:50:35,219 epoch 2 - iter 588/1476 - loss 0.14142829 - time (sec): 37.70 - samples/sec: 1704.17 - lr: 0.000048 - momentum: 0.000000
2023-10-24 10:50:44,511 epoch 2 - iter 735/1476 - loss 0.13962946 - time (sec): 46.99 - samples/sec: 1694.23 - lr: 0.000047 - momentum: 0.000000
2023-10-24 10:50:54,152 epoch 2 - iter 882/1476 - loss 0.13959635 - time (sec): 56.63 - samples/sec: 1704.74 - lr: 0.000047 - momentum: 0.000000
2023-10-24 10:51:03,232 epoch 2 - iter 1029/1476 - loss 0.14077252 - time (sec): 65.71 - samples/sec: 1691.49 - lr: 0.000046 - momentum: 0.000000
2023-10-24 10:51:13,264 epoch 2 - iter 1176/1476 - loss 0.13763429 - time (sec): 75.75 - samples/sec: 1725.25 - lr: 0.000046 - momentum: 0.000000
2023-10-24 10:51:23,146 epoch 2 - iter 1323/1476 - loss 0.13938057 - time (sec): 85.63 - samples/sec: 1726.60 - lr: 0.000045 - momentum: 0.000000
2023-10-24 10:51:33,145 epoch 2 - iter 1470/1476 - loss 0.13778830 - time (sec): 95.63 - samples/sec: 1735.50 - lr: 0.000044 - momentum: 0.000000
2023-10-24 10:51:33,492 ----------------------------------------------------------------------------------------------------
2023-10-24 10:51:33,492 EPOCH 2 done: loss 0.1379 - lr: 0.000044
2023-10-24 10:51:42,008 DEV : loss 0.14209164679050446 - f1-score (micro avg)  0.7784
2023-10-24 10:51:42,029 saving best model
2023-10-24 10:51:42,735 ----------------------------------------------------------------------------------------------------
2023-10-24 10:51:52,069 epoch 3 - iter 147/1476 - loss 0.08832162 - time (sec): 9.33 - samples/sec: 1634.07 - lr: 0.000044 - momentum: 0.000000
2023-10-24 10:52:02,054 epoch 3 - iter 294/1476 - loss 0.08724963 - time (sec): 19.32 - samples/sec: 1723.32 - lr: 0.000043 - momentum: 0.000000
2023-10-24 10:52:11,502 epoch 3 - iter 441/1476 - loss 0.08766214 - time (sec): 28.77 - samples/sec: 1709.11 - lr: 0.000043 - momentum: 0.000000
2023-10-24 10:52:21,316 epoch 3 - iter 588/1476 - loss 0.08283332 - time (sec): 38.58 - samples/sec: 1746.55 - lr: 0.000042 - momentum: 0.000000
2023-10-24 10:52:30,589 epoch 3 - iter 735/1476 - loss 0.08143414 - time (sec): 47.85 - samples/sec: 1727.76 - lr: 0.000042 - momentum: 0.000000
2023-10-24 10:52:40,282 epoch 3 - iter 882/1476 - loss 0.08342790 - time (sec): 57.55 - samples/sec: 1738.12 - lr: 0.000041 - momentum: 0.000000
2023-10-24 10:52:49,830 epoch 3 - iter 1029/1476 - loss 0.08223349 - time (sec): 67.09 - samples/sec: 1733.72 - lr: 0.000041 - momentum: 0.000000
2023-10-24 10:52:59,223 epoch 3 - iter 1176/1476 - loss 0.08468750 - time (sec): 76.49 - samples/sec: 1729.40 - lr: 0.000040 - momentum: 0.000000
2023-10-24 10:53:09,193 epoch 3 - iter 1323/1476 - loss 0.09646163 - time (sec): 86.46 - samples/sec: 1745.87 - lr: 0.000039 - momentum: 0.000000
2023-10-24 10:53:18,392 epoch 3 - iter 1470/1476 - loss 0.09593820 - time (sec): 95.66 - samples/sec: 1736.12 - lr: 0.000039 - momentum: 0.000000
2023-10-24 10:53:18,728 ----------------------------------------------------------------------------------------------------
2023-10-24 10:53:18,728 EPOCH 3 done: loss 0.0959 - lr: 0.000039
2023-10-24 10:53:27,143 DEV : loss 0.2701607942581177 - f1-score (micro avg)  0.763
2023-10-24 10:53:27,165 ----------------------------------------------------------------------------------------------------
2023-10-24 10:53:36,810 epoch 4 - iter 147/1476 - loss 0.12417453 - time (sec): 9.64 - samples/sec: 1745.60 - lr: 0.000038 - momentum: 0.000000
2023-10-24 10:53:46,534 epoch 4 - iter 294/1476 - loss 0.12118589 - time (sec): 19.37 - samples/sec: 1811.03 - lr: 0.000038 - momentum: 0.000000
2023-10-24 10:53:56,194 epoch 4 - iter 441/1476 - loss 0.10852964 - time (sec): 29.03 - samples/sec: 1781.74 - lr: 0.000037 - momentum: 0.000000
2023-10-24 10:54:05,524 epoch 4 - iter 588/1476 - loss 0.09519935 - time (sec): 38.36 - samples/sec: 1761.04 - lr: 0.000037 - momentum: 0.000000
2023-10-24 10:54:15,280 epoch 4 - iter 735/1476 - loss 0.09097434 - time (sec): 48.11 - samples/sec: 1766.24 - lr: 0.000036 - momentum: 0.000000
2023-10-24 10:54:24,715 epoch 4 - iter 882/1476 - loss 0.08614100 - time (sec): 57.55 - samples/sec: 1756.63 - lr: 0.000036 - momentum: 0.000000
2023-10-24 10:54:34,696 epoch 4 - iter 1029/1476 - loss 0.09487861 - time (sec): 67.53 - samples/sec: 1762.79 - lr: 0.000035 - momentum: 0.000000
2023-10-24 10:54:44,167 epoch 4 - iter 1176/1476 - loss 0.09394085 - time (sec): 77.00 - samples/sec: 1751.57 - lr: 0.000034 - momentum: 0.000000
2023-10-24 10:54:53,633 epoch 4 - iter 1323/1476 - loss 0.09504047 - time (sec): 86.47 - samples/sec: 1744.04 - lr: 0.000034 - momentum: 0.000000
2023-10-24 10:55:02,882 epoch 4 - iter 1470/1476 - loss 0.09448577 - time (sec): 95.72 - samples/sec: 1731.37 - lr: 0.000033 - momentum: 0.000000
2023-10-24 10:55:03,250 ----------------------------------------------------------------------------------------------------
2023-10-24 10:55:03,251 EPOCH 4 done: loss 0.0948 - lr: 0.000033
2023-10-24 10:55:11,668 DEV : loss 0.27863532304763794 - f1-score (micro avg)  0.7293
2023-10-24 10:55:11,689 ----------------------------------------------------------------------------------------------------
2023-10-24 10:55:21,448 epoch 5 - iter 147/1476 - loss 0.07291799 - time (sec): 9.76 - samples/sec: 1737.92 - lr: 0.000033 - momentum: 0.000000
2023-10-24 10:55:31,095 epoch 5 - iter 294/1476 - loss 0.11773689 - time (sec): 19.40 - samples/sec: 1770.59 - lr: 0.000032 - momentum: 0.000000
2023-10-24 10:55:40,949 epoch 5 - iter 441/1476 - loss 0.09833702 - time (sec): 29.26 - samples/sec: 1776.56 - lr: 0.000032 - momentum: 0.000000
2023-10-24 10:55:50,119 epoch 5 - iter 588/1476 - loss 0.08337112 - time (sec): 38.43 - samples/sec: 1746.88 - lr: 0.000031 - momentum: 0.000000
2023-10-24 10:56:00,122 epoch 5 - iter 735/1476 - loss 0.08978486 - time (sec): 48.43 - samples/sec: 1745.69 - lr: 0.000031 - momentum: 0.000000
2023-10-24 10:56:09,225 epoch 5 - iter 882/1476 - loss 0.08167065 - time (sec): 57.54 - samples/sec: 1723.59 - lr: 0.000030 - momentum: 0.000000
2023-10-24 10:56:18,288 epoch 5 - iter 1029/1476 - loss 0.07871689 - time (sec): 66.60 - samples/sec: 1719.04 - lr: 0.000029 - momentum: 0.000000
2023-10-24 10:56:27,625 epoch 5 - iter 1176/1476 - loss 0.07299931 - time (sec): 75.93 - samples/sec: 1704.49 - lr: 0.000029 - momentum: 0.000000
2023-10-24 10:56:37,116 epoch 5 - iter 1323/1476 - loss 0.07223057 - time (sec): 85.43 - samples/sec: 1710.28 - lr: 0.000028 - momentum: 0.000000
2023-10-24 10:56:47,474 epoch 5 - iter 1470/1476 - loss 0.07846900 - time (sec): 95.78 - samples/sec: 1733.07 - lr: 0.000028 - momentum: 0.000000
2023-10-24 10:56:47,814 ----------------------------------------------------------------------------------------------------
2023-10-24 10:56:47,815 EPOCH 5 done: loss 0.0784 - lr: 0.000028
2023-10-24 10:56:56,241 DEV : loss 0.25809499621391296 - f1-score (micro avg)  0.7499
2023-10-24 10:56:56,262 ----------------------------------------------------------------------------------------------------
2023-10-24 10:57:06,035 epoch 6 - iter 147/1476 - loss 0.05313087 - time (sec): 9.77 - samples/sec: 1824.29 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:57:15,603 epoch 6 - iter 294/1476 - loss 0.05439273 - time (sec): 19.34 - samples/sec: 1747.91 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:57:25,156 epoch 6 - iter 441/1476 - loss 0.04903707 - time (sec): 28.89 - samples/sec: 1733.35 - lr: 0.000026 - momentum: 0.000000
2023-10-24 10:57:34,744 epoch 6 - iter 588/1476 - loss 0.05877384 - time (sec): 38.48 - samples/sec: 1734.92 - lr: 0.000026 - momentum: 0.000000
2023-10-24 10:57:44,061 epoch 6 - iter 735/1476 - loss 0.05051822 - time (sec): 47.80 - samples/sec: 1727.89 - lr: 0.000025 - momentum: 0.000000
2023-10-24 10:57:53,790 epoch 6 - iter 882/1476 - loss 0.04679481 - time (sec): 57.53 - samples/sec: 1737.86 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:58:03,065 epoch 6 - iter 1029/1476 - loss 0.04646404 - time (sec): 66.80 - samples/sec: 1721.46 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:58:12,451 epoch 6 - iter 1176/1476 - loss 0.05002079 - time (sec): 76.19 - samples/sec: 1723.74 - lr: 0.000023 - momentum: 0.000000
2023-10-24 10:58:22,558 epoch 6 - iter 1323/1476 - loss 0.06170524 - time (sec): 86.30 - samples/sec: 1736.56 - lr: 0.000023 - momentum: 0.000000
2023-10-24 10:58:32,083 epoch 6 - iter 1470/1476 - loss 0.06160170 - time (sec): 95.82 - samples/sec: 1731.81 - lr: 0.000022 - momentum: 0.000000
2023-10-24 10:58:32,426 ----------------------------------------------------------------------------------------------------
2023-10-24 10:58:32,427 EPOCH 6 done: loss 0.0614 - lr: 0.000022
2023-10-24 10:58:40,876 DEV : loss 0.2634078860282898 - f1-score (micro avg)  0.772
2023-10-24 10:58:40,897 ----------------------------------------------------------------------------------------------------
2023-10-24 10:58:50,465 epoch 7 - iter 147/1476 - loss 0.04507495 - time (sec): 9.57 - samples/sec: 1717.08 - lr: 0.000022 - momentum: 0.000000
2023-10-24 10:58:59,978 epoch 7 - iter 294/1476 - loss 0.04197351 - time (sec): 19.08 - samples/sec: 1702.46 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:59:09,686 epoch 7 - iter 441/1476 - loss 0.06505740 - time (sec): 28.79 - samples/sec: 1729.16 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:59:18,963 epoch 7 - iter 588/1476 - loss 0.05418034 - time (sec): 38.07 - samples/sec: 1711.68 - lr: 0.000020 - momentum: 0.000000
2023-10-24 10:59:28,157 epoch 7 - iter 735/1476 - loss 0.04622712 - time (sec): 47.26 - samples/sec: 1700.72 - lr: 0.000019 - momentum: 0.000000
2023-10-24 10:59:38,265 epoch 7 - iter 882/1476 - loss 0.05893413 - time (sec): 57.37 - samples/sec: 1727.44 - lr: 0.000019 - momentum: 0.000000
2023-10-24 10:59:47,775 epoch 7 - iter 1029/1476 - loss 0.05878999 - time (sec): 66.88 - samples/sec: 1727.73 - lr: 0.000018 - momentum: 0.000000
2023-10-24 10:59:57,450 epoch 7 - iter 1176/1476 - loss 0.05964465 - time (sec): 76.55 - samples/sec: 1727.83 - lr: 0.000018 - momentum: 0.000000
2023-10-24 11:00:07,100 epoch 7 - iter 1323/1476 - loss 0.05826532 - time (sec): 86.20 - samples/sec: 1732.09 - lr: 0.000017 - momentum: 0.000000
2023-10-24 11:00:16,614 epoch 7 - iter 1470/1476 - loss 0.06281126 - time (sec): 95.72 - samples/sec: 1732.15 - lr: 0.000017 - momentum: 0.000000
2023-10-24 11:00:16,990 ----------------------------------------------------------------------------------------------------
2023-10-24 11:00:16,990 EPOCH 7 done: loss 0.0626 - lr: 0.000017
2023-10-24 11:00:25,435 DEV : loss 0.27169960737228394 - f1-score (micro avg)  0.7652
2023-10-24 11:00:25,457 ----------------------------------------------------------------------------------------------------
2023-10-24 11:00:34,865 epoch 8 - iter 147/1476 - loss 0.04542037 - time (sec): 9.41 - samples/sec: 1696.00 - lr: 0.000016 - momentum: 0.000000
2023-10-24 11:00:44,003 epoch 8 - iter 294/1476 - loss 0.02861702 - time (sec): 18.55 - samples/sec: 1657.60 - lr: 0.000016 - momentum: 0.000000
2023-10-24 11:00:54,239 epoch 8 - iter 441/1476 - loss 0.06281701 - time (sec): 28.78 - samples/sec: 1758.67 - lr: 0.000015 - momentum: 0.000000
2023-10-24 11:01:03,793 epoch 8 - iter 588/1476 - loss 0.05883833 - time (sec): 38.34 - samples/sec: 1759.21 - lr: 0.000014 - momentum: 0.000000
2023-10-24 11:01:13,566 epoch 8 - iter 735/1476 - loss 0.05103042 - time (sec): 48.11 - samples/sec: 1753.77 - lr: 0.000014 - momentum: 0.000000
2023-10-24 11:01:23,641 epoch 8 - iter 882/1476 - loss 0.05585751 - time (sec): 58.18 - samples/sec: 1761.22 - lr: 0.000013 - momentum: 0.000000
2023-10-24 11:01:32,886 epoch 8 - iter 1029/1476 - loss 0.05420164 - time (sec): 67.43 - samples/sec: 1741.28 - lr: 0.000013 - momentum: 0.000000
2023-10-24 11:01:42,145 epoch 8 - iter 1176/1476 - loss 0.05014942 - time (sec): 76.69 - samples/sec: 1733.69 - lr: 0.000012 - momentum: 0.000000
2023-10-24 11:01:51,484 epoch 8 - iter 1323/1476 - loss 0.04821620 - time (sec): 86.03 - samples/sec: 1730.02 - lr: 0.000012 - momentum: 0.000000
2023-10-24 11:02:01,128 epoch 8 - iter 1470/1476 - loss 0.04480348 - time (sec): 95.67 - samples/sec: 1732.32 - lr: 0.000011 - momentum: 0.000000
2023-10-24 11:02:01,495 ----------------------------------------------------------------------------------------------------
2023-10-24 11:02:01,495 EPOCH 8 done: loss 0.0447 - lr: 0.000011
2023-10-24 11:02:09,941 DEV : loss 0.30274227261543274 - f1-score (micro avg)  0.7626
2023-10-24 11:02:09,962 ----------------------------------------------------------------------------------------------------
2023-10-24 11:02:19,368 epoch 9 - iter 147/1476 - loss 0.02455183 - time (sec): 9.40 - samples/sec: 1690.22 - lr: 0.000011 - momentum: 0.000000
2023-10-24 11:02:29,184 epoch 9 - iter 294/1476 - loss 0.02908119 - time (sec): 19.22 - samples/sec: 1766.79 - lr: 0.000010 - momentum: 0.000000
2023-10-24 11:02:38,447 epoch 9 - iter 441/1476 - loss 0.03060954 - time (sec): 28.48 - samples/sec: 1720.29 - lr: 0.000009 - momentum: 0.000000
2023-10-24 11:02:47,999 epoch 9 - iter 588/1476 - loss 0.02637177 - time (sec): 38.04 - samples/sec: 1682.20 - lr: 0.000009 - momentum: 0.000000
2023-10-24 11:02:57,224 epoch 9 - iter 735/1476 - loss 0.02532292 - time (sec): 47.26 - samples/sec: 1686.95 - lr: 0.000008 - momentum: 0.000000
2023-10-24 11:03:06,638 epoch 9 - iter 882/1476 - loss 0.02620936 - time (sec): 56.67 - samples/sec: 1688.27 - lr: 0.000008 - momentum: 0.000000
2023-10-24 11:03:16,146 epoch 9 - iter 1029/1476 - loss 0.02456485 - time (sec): 66.18 - samples/sec: 1700.19 - lr: 0.000007 - momentum: 0.000000
2023-10-24 11:03:26,166 epoch 9 - iter 1176/1476 - loss 0.03675836 - time (sec): 76.20 - samples/sec: 1722.03 - lr: 0.000007 - momentum: 0.000000
2023-10-24 11:03:36,323 epoch 9 - iter 1323/1476 - loss 0.04061899 - time (sec): 86.36 - samples/sec: 1730.99 - lr: 0.000006 - momentum: 0.000000
2023-10-24 11:03:45,828 epoch 9 - iter 1470/1476 - loss 0.04002423 - time (sec): 95.86 - samples/sec: 1731.00 - lr: 0.000006 - momentum: 0.000000
2023-10-24 11:03:46,171 ----------------------------------------------------------------------------------------------------
2023-10-24 11:03:46,171 EPOCH 9 done: loss 0.0399 - lr: 0.000006
2023-10-24 11:03:54,596 DEV : loss 0.2963683307170868 - f1-score (micro avg)  0.7703
2023-10-24 11:03:54,618 ----------------------------------------------------------------------------------------------------
2023-10-24 11:04:04,051 epoch 10 - iter 147/1476 - loss 0.02704804 - time (sec): 9.43 - samples/sec: 1717.54 - lr: 0.000005 - momentum: 0.000000
2023-10-24 11:04:13,428 epoch 10 - iter 294/1476 - loss 0.02279645 - time (sec): 18.81 - samples/sec: 1701.66 - lr: 0.000004 - momentum: 0.000000
2023-10-24 11:04:23,321 epoch 10 - iter 441/1476 - loss 0.02018937 - time (sec): 28.70 - samples/sec: 1740.66 - lr: 0.000004 - momentum: 0.000000
2023-10-24 11:04:33,017 epoch 10 - iter 588/1476 - loss 0.02530081 - time (sec): 38.40 - samples/sec: 1760.38 - lr: 0.000003 - momentum: 0.000000
2023-10-24 11:04:43,267 epoch 10 - iter 735/1476 - loss 0.04049497 - time (sec): 48.65 - samples/sec: 1775.63 - lr: 0.000003 - momentum: 0.000000
2023-10-24 11:04:52,714 epoch 10 - iter 882/1476 - loss 0.04282402 - time (sec): 58.10 - samples/sec: 1761.20 - lr: 0.000002 - momentum: 0.000000
2023-10-24 11:05:02,523 epoch 10 - iter 1029/1476 - loss 0.04621028 - time (sec): 67.90 - samples/sec: 1756.59 - lr: 0.000002 - momentum: 0.000000
2023-10-24 11:05:11,678 epoch 10 - iter 1176/1476 - loss 0.04170952 - time (sec): 77.06 - samples/sec: 1742.51 - lr: 0.000001 - momentum: 0.000000
2023-10-24 11:05:20,869 epoch 10 - iter 1323/1476 - loss 0.03916033 - time (sec): 86.25 - samples/sec: 1733.25 - lr: 0.000001 - momentum: 0.000000
2023-10-24 11:05:30,215 epoch 10 - iter 1470/1476 - loss 0.03566834 - time (sec): 95.60 - samples/sec: 1735.21 - lr: 0.000000 - momentum: 0.000000
2023-10-24 11:05:30,559 ----------------------------------------------------------------------------------------------------
2023-10-24 11:05:30,559 EPOCH 10 done: loss 0.0356 - lr: 0.000000
2023-10-24 11:05:39,016 DEV : loss 0.30029311776161194 - f1-score (micro avg)  0.7695
2023-10-24 11:05:39,590 ----------------------------------------------------------------------------------------------------
2023-10-24 11:05:39,590 Loading model from best epoch ...
2023-10-24 11:05:41,453 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-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
2023-10-24 11:05:47,732 
Results:
- F-score (micro) 0.7379
- F-score (macro) 0.6047
- Accuracy 0.6102

By class:
              precision    recall  f1-score   support

         loc     0.8307    0.8520    0.8412       858
        pers     0.6764    0.6927    0.6845       537
         org     0.4410    0.5379    0.4846       132
        time     0.5147    0.6481    0.5738        54
        prod     0.6667    0.3279    0.4396        61

   micro avg     0.7276    0.7485    0.7379      1642
   macro avg     0.6259    0.6117    0.6047      1642
weighted avg     0.7324    0.7485    0.7376      1642

2023-10-24 11:05:47,732 ----------------------------------------------------------------------------------------------------