2023-10-24 10:30:21,441 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,442 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 10:30:21,442 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,442 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 10:30:21,442 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,442 Train:  5901 sentences
2023-10-24 10:30:21,442         (train_with_dev=False, train_with_test=False)
2023-10-24 10:30:21,442 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,442 Training Params:
2023-10-24 10:30:21,442  - learning_rate: "3e-05" 
2023-10-24 10:30:21,442  - mini_batch_size: "4"
2023-10-24 10:30:21,442  - max_epochs: "10"
2023-10-24 10:30:21,443  - shuffle: "True"
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 Plugins:
2023-10-24 10:30:21,443  - TensorboardLogger
2023-10-24 10:30:21,443  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 10:30:21,443  - metric: "('micro avg', 'f1-score')"
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 Computation:
2023-10-24 10:30:21,443  - compute on device: cuda:0
2023-10-24 10:30:21,443  - embedding storage: none
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 ----------------------------------------------------------------------------------------------------
2023-10-24 10:30:21,443 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 10:30:30,685 epoch 1 - iter 147/1476 - loss 1.95486685 - time (sec): 9.24 - samples/sec: 1731.50 - lr: 0.000003 - momentum: 0.000000
2023-10-24 10:30:39,970 epoch 1 - iter 294/1476 - loss 1.26204596 - time (sec): 18.53 - samples/sec: 1712.28 - lr: 0.000006 - momentum: 0.000000
2023-10-24 10:30:49,068 epoch 1 - iter 441/1476 - loss 1.01783980 - time (sec): 27.62 - samples/sec: 1664.50 - lr: 0.000009 - momentum: 0.000000
2023-10-24 10:30:58,969 epoch 1 - iter 588/1476 - loss 0.82960997 - time (sec): 37.53 - samples/sec: 1720.25 - lr: 0.000012 - momentum: 0.000000
2023-10-24 10:31:09,389 epoch 1 - iter 735/1476 - loss 0.69238553 - time (sec): 47.95 - samples/sec: 1760.88 - lr: 0.000015 - momentum: 0.000000
2023-10-24 10:31:18,839 epoch 1 - iter 882/1476 - loss 0.61723371 - time (sec): 57.40 - samples/sec: 1758.66 - lr: 0.000018 - momentum: 0.000000
2023-10-24 10:31:28,128 epoch 1 - iter 1029/1476 - loss 0.55914623 - time (sec): 66.68 - samples/sec: 1750.72 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:31:37,986 epoch 1 - iter 1176/1476 - loss 0.51214581 - time (sec): 76.54 - samples/sec: 1748.28 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:31:47,268 epoch 1 - iter 1323/1476 - loss 0.47688361 - time (sec): 85.82 - samples/sec: 1743.62 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:31:56,801 epoch 1 - iter 1470/1476 - loss 0.44429417 - time (sec): 95.36 - samples/sec: 1740.14 - lr: 0.000030 - momentum: 0.000000
2023-10-24 10:31:57,149 ----------------------------------------------------------------------------------------------------
2023-10-24 10:31:57,150 EPOCH 1 done: loss 0.4435 - lr: 0.000030
2023-10-24 10:32:03,446 DEV : loss 0.1300630122423172 - f1-score (micro avg)  0.7315
2023-10-24 10:32:03,467 saving best model
2023-10-24 10:32:04,027 ----------------------------------------------------------------------------------------------------
2023-10-24 10:32:13,594 epoch 2 - iter 147/1476 - loss 0.09774384 - time (sec): 9.57 - samples/sec: 1764.56 - lr: 0.000030 - momentum: 0.000000
2023-10-24 10:32:22,802 epoch 2 - iter 294/1476 - loss 0.12373892 - time (sec): 18.77 - samples/sec: 1717.04 - lr: 0.000029 - momentum: 0.000000
2023-10-24 10:32:31,998 epoch 2 - iter 441/1476 - loss 0.13775868 - time (sec): 27.97 - samples/sec: 1678.40 - lr: 0.000029 - momentum: 0.000000
2023-10-24 10:32:41,763 epoch 2 - iter 588/1476 - loss 0.12915200 - time (sec): 37.74 - samples/sec: 1702.64 - lr: 0.000029 - momentum: 0.000000
2023-10-24 10:32:51,061 epoch 2 - iter 735/1476 - loss 0.12918783 - time (sec): 47.03 - samples/sec: 1692.83 - lr: 0.000028 - momentum: 0.000000
2023-10-24 10:33:00,686 epoch 2 - iter 882/1476 - loss 0.12958345 - time (sec): 56.66 - samples/sec: 1704.04 - lr: 0.000028 - momentum: 0.000000
2023-10-24 10:33:09,743 epoch 2 - iter 1029/1476 - loss 0.12887412 - time (sec): 65.71 - samples/sec: 1691.48 - lr: 0.000028 - momentum: 0.000000
2023-10-24 10:33:19,759 epoch 2 - iter 1176/1476 - loss 0.12754934 - time (sec): 75.73 - samples/sec: 1725.62 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:33:29,648 epoch 2 - iter 1323/1476 - loss 0.12821778 - time (sec): 85.62 - samples/sec: 1726.78 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:33:39,650 epoch 2 - iter 1470/1476 - loss 0.12716691 - time (sec): 95.62 - samples/sec: 1735.61 - lr: 0.000027 - momentum: 0.000000
2023-10-24 10:33:39,996 ----------------------------------------------------------------------------------------------------
2023-10-24 10:33:39,997 EPOCH 2 done: loss 0.1270 - lr: 0.000027
2023-10-24 10:33:48,525 DEV : loss 0.13529355823993683 - f1-score (micro avg)  0.7895
2023-10-24 10:33:48,546 saving best model
2023-10-24 10:33:49,250 ----------------------------------------------------------------------------------------------------
2023-10-24 10:33:58,610 epoch 3 - iter 147/1476 - loss 0.06413979 - time (sec): 9.36 - samples/sec: 1629.69 - lr: 0.000026 - momentum: 0.000000
2023-10-24 10:34:08,613 epoch 3 - iter 294/1476 - loss 0.08008883 - time (sec): 19.36 - samples/sec: 1719.49 - lr: 0.000026 - momentum: 0.000000
2023-10-24 10:34:18,091 epoch 3 - iter 441/1476 - loss 0.07801843 - time (sec): 28.84 - samples/sec: 1704.77 - lr: 0.000026 - momentum: 0.000000
2023-10-24 10:34:27,913 epoch 3 - iter 588/1476 - loss 0.07393475 - time (sec): 38.66 - samples/sec: 1742.86 - lr: 0.000025 - momentum: 0.000000
2023-10-24 10:34:37,183 epoch 3 - iter 735/1476 - loss 0.07460277 - time (sec): 47.93 - samples/sec: 1724.93 - lr: 0.000025 - momentum: 0.000000
2023-10-24 10:34:46,875 epoch 3 - iter 882/1476 - loss 0.07823560 - time (sec): 57.62 - samples/sec: 1735.79 - lr: 0.000025 - momentum: 0.000000
2023-10-24 10:34:56,414 epoch 3 - iter 1029/1476 - loss 0.07661923 - time (sec): 67.16 - samples/sec: 1731.96 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:35:05,800 epoch 3 - iter 1176/1476 - loss 0.07755315 - time (sec): 76.55 - samples/sec: 1727.99 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:35:15,765 epoch 3 - iter 1323/1476 - loss 0.07765157 - time (sec): 86.51 - samples/sec: 1744.74 - lr: 0.000024 - momentum: 0.000000
2023-10-24 10:35:24,956 epoch 3 - iter 1470/1476 - loss 0.07767577 - time (sec): 95.70 - samples/sec: 1735.25 - lr: 0.000023 - momentum: 0.000000
2023-10-24 10:35:25,291 ----------------------------------------------------------------------------------------------------
2023-10-24 10:35:25,291 EPOCH 3 done: loss 0.0777 - lr: 0.000023
2023-10-24 10:35:33,788 DEV : loss 0.1414514034986496 - f1-score (micro avg)  0.8064
2023-10-24 10:35:33,809 saving best model
2023-10-24 10:35:34,565 ----------------------------------------------------------------------------------------------------
2023-10-24 10:35:44,207 epoch 4 - iter 147/1476 - loss 0.05130159 - time (sec): 9.64 - samples/sec: 1746.38 - lr: 0.000023 - momentum: 0.000000
2023-10-24 10:35:53,931 epoch 4 - iter 294/1476 - loss 0.04892145 - time (sec): 19.36 - samples/sec: 1811.41 - lr: 0.000023 - momentum: 0.000000
2023-10-24 10:36:03,580 epoch 4 - iter 441/1476 - loss 0.04776918 - time (sec): 29.01 - samples/sec: 1782.70 - lr: 0.000022 - momentum: 0.000000
2023-10-24 10:36:13,245 epoch 4 - iter 588/1476 - loss 0.04668210 - time (sec): 38.68 - samples/sec: 1746.47 - lr: 0.000022 - momentum: 0.000000
2023-10-24 10:36:22,993 epoch 4 - iter 735/1476 - loss 0.04560696 - time (sec): 48.43 - samples/sec: 1754.83 - lr: 0.000022 - momentum: 0.000000
2023-10-24 10:36:32,409 epoch 4 - iter 882/1476 - loss 0.04633596 - time (sec): 57.84 - samples/sec: 1747.73 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:36:42,394 epoch 4 - iter 1029/1476 - loss 0.04952081 - time (sec): 67.83 - samples/sec: 1755.06 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:36:51,859 epoch 4 - iter 1176/1476 - loss 0.05327110 - time (sec): 77.29 - samples/sec: 1744.99 - lr: 0.000021 - momentum: 0.000000
2023-10-24 10:37:01,316 epoch 4 - iter 1323/1476 - loss 0.05312525 - time (sec): 86.75 - samples/sec: 1738.37 - lr: 0.000020 - momentum: 0.000000
2023-10-24 10:37:10,558 epoch 4 - iter 1470/1476 - loss 0.05433269 - time (sec): 95.99 - samples/sec: 1726.40 - lr: 0.000020 - momentum: 0.000000
2023-10-24 10:37:10,926 ----------------------------------------------------------------------------------------------------
2023-10-24 10:37:10,926 EPOCH 4 done: loss 0.0545 - lr: 0.000020
2023-10-24 10:37:19,428 DEV : loss 0.17535756528377533 - f1-score (micro avg)  0.8202
2023-10-24 10:37:19,449 saving best model
2023-10-24 10:37:20,150 ----------------------------------------------------------------------------------------------------
2023-10-24 10:37:29,883 epoch 5 - iter 147/1476 - loss 0.03243990 - time (sec): 9.73 - samples/sec: 1742.69 - lr: 0.000020 - momentum: 0.000000
2023-10-24 10:37:39,519 epoch 5 - iter 294/1476 - loss 0.04635094 - time (sec): 19.37 - samples/sec: 1773.97 - lr: 0.000019 - momentum: 0.000000
2023-10-24 10:37:49,362 epoch 5 - iter 441/1476 - loss 0.04025634 - time (sec): 29.21 - samples/sec: 1779.48 - lr: 0.000019 - momentum: 0.000000
2023-10-24 10:37:58,525 epoch 5 - iter 588/1476 - loss 0.03809557 - time (sec): 38.37 - samples/sec: 1749.42 - lr: 0.000019 - momentum: 0.000000
2023-10-24 10:38:08,520 epoch 5 - iter 735/1476 - loss 0.03722634 - time (sec): 48.37 - samples/sec: 1747.98 - lr: 0.000018 - momentum: 0.000000
2023-10-24 10:38:17,615 epoch 5 - iter 882/1476 - loss 0.03652541 - time (sec): 57.46 - samples/sec: 1725.74 - lr: 0.000018 - momentum: 0.000000
2023-10-24 10:38:26,667 epoch 5 - iter 1029/1476 - loss 0.03632487 - time (sec): 66.52 - samples/sec: 1721.17 - lr: 0.000018 - momentum: 0.000000
2023-10-24 10:38:35,997 epoch 5 - iter 1176/1476 - loss 0.03493445 - time (sec): 75.85 - samples/sec: 1706.50 - lr: 0.000017 - momentum: 0.000000
2023-10-24 10:38:45,476 epoch 5 - iter 1323/1476 - loss 0.03543690 - time (sec): 85.33 - samples/sec: 1712.30 - lr: 0.000017 - momentum: 0.000000
2023-10-24 10:38:55,831 epoch 5 - iter 1470/1476 - loss 0.03603493 - time (sec): 95.68 - samples/sec: 1734.96 - lr: 0.000017 - momentum: 0.000000
2023-10-24 10:38:56,171 ----------------------------------------------------------------------------------------------------
2023-10-24 10:38:56,172 EPOCH 5 done: loss 0.0362 - lr: 0.000017
2023-10-24 10:39:04,666 DEV : loss 0.18856941163539886 - f1-score (micro avg)  0.8052
2023-10-24 10:39:04,687 ----------------------------------------------------------------------------------------------------
2023-10-24 10:39:14,450 epoch 6 - iter 147/1476 - loss 0.03138711 - time (sec): 9.76 - samples/sec: 1826.14 - lr: 0.000016 - momentum: 0.000000
2023-10-24 10:39:24,003 epoch 6 - iter 294/1476 - loss 0.02845150 - time (sec): 19.31 - samples/sec: 1750.17 - lr: 0.000016 - momentum: 0.000000
2023-10-24 10:39:33,538 epoch 6 - iter 441/1476 - loss 0.02731184 - time (sec): 28.85 - samples/sec: 1735.88 - lr: 0.000016 - momentum: 0.000000
2023-10-24 10:39:43,120 epoch 6 - iter 588/1476 - loss 0.02757989 - time (sec): 38.43 - samples/sec: 1737.16 - lr: 0.000015 - momentum: 0.000000
2023-10-24 10:39:52,417 epoch 6 - iter 735/1476 - loss 0.02426912 - time (sec): 47.73 - samples/sec: 1730.41 - lr: 0.000015 - momentum: 0.000000
2023-10-24 10:40:02,130 epoch 6 - iter 882/1476 - loss 0.02398610 - time (sec): 57.44 - samples/sec: 1740.41 - lr: 0.000015 - momentum: 0.000000
2023-10-24 10:40:11,398 epoch 6 - iter 1029/1476 - loss 0.02369056 - time (sec): 66.71 - samples/sec: 1723.81 - lr: 0.000014 - momentum: 0.000000
2023-10-24 10:40:20,772 epoch 6 - iter 1176/1476 - loss 0.02397182 - time (sec): 76.08 - samples/sec: 1726.11 - lr: 0.000014 - momentum: 0.000000
2023-10-24 10:40:30,870 epoch 6 - iter 1323/1476 - loss 0.02409287 - time (sec): 86.18 - samples/sec: 1738.85 - lr: 0.000014 - momentum: 0.000000
2023-10-24 10:40:40,391 epoch 6 - iter 1470/1476 - loss 0.02429223 - time (sec): 95.70 - samples/sec: 1733.92 - lr: 0.000013 - momentum: 0.000000
2023-10-24 10:40:40,734 ----------------------------------------------------------------------------------------------------
2023-10-24 10:40:40,735 EPOCH 6 done: loss 0.0242 - lr: 0.000013
2023-10-24 10:40:49,251 DEV : loss 0.1976252794265747 - f1-score (micro avg)  0.8181
2023-10-24 10:40:49,272 ----------------------------------------------------------------------------------------------------
2023-10-24 10:40:58,821 epoch 7 - iter 147/1476 - loss 0.02416041 - time (sec): 9.55 - samples/sec: 1720.61 - lr: 0.000013 - momentum: 0.000000
2023-10-24 10:41:08,314 epoch 7 - iter 294/1476 - loss 0.02557096 - time (sec): 19.04 - samples/sec: 1705.97 - lr: 0.000013 - momentum: 0.000000
2023-10-24 10:41:18,019 epoch 7 - iter 441/1476 - loss 0.02401158 - time (sec): 28.75 - samples/sec: 1731.71 - lr: 0.000012 - momentum: 0.000000
2023-10-24 10:41:27,278 epoch 7 - iter 588/1476 - loss 0.02052173 - time (sec): 38.01 - samples/sec: 1714.38 - lr: 0.000012 - momentum: 0.000000
2023-10-24 10:41:36,455 epoch 7 - iter 735/1476 - loss 0.01942122 - time (sec): 47.18 - samples/sec: 1703.48 - lr: 0.000012 - momentum: 0.000000
2023-10-24 10:41:46,543 epoch 7 - iter 882/1476 - loss 0.01902328 - time (sec): 57.27 - samples/sec: 1730.36 - lr: 0.000011 - momentum: 0.000000
2023-10-24 10:41:56,034 epoch 7 - iter 1029/1476 - loss 0.01808307 - time (sec): 66.76 - samples/sec: 1730.74 - lr: 0.000011 - momentum: 0.000000
2023-10-24 10:42:05,699 epoch 7 - iter 1176/1476 - loss 0.01833467 - time (sec): 76.43 - samples/sec: 1730.68 - lr: 0.000011 - momentum: 0.000000
2023-10-24 10:42:15,348 epoch 7 - iter 1323/1476 - loss 0.01730497 - time (sec): 86.08 - samples/sec: 1734.66 - lr: 0.000010 - momentum: 0.000000
2023-10-24 10:42:24,846 epoch 7 - iter 1470/1476 - loss 0.01857979 - time (sec): 95.57 - samples/sec: 1734.74 - lr: 0.000010 - momentum: 0.000000
2023-10-24 10:42:25,221 ----------------------------------------------------------------------------------------------------
2023-10-24 10:42:25,221 EPOCH 7 done: loss 0.0186 - lr: 0.000010
2023-10-24 10:42:33,760 DEV : loss 0.2103830873966217 - f1-score (micro avg)  0.8275
2023-10-24 10:42:33,781 saving best model
2023-10-24 10:42:34,480 ----------------------------------------------------------------------------------------------------
2023-10-24 10:42:43,884 epoch 8 - iter 147/1476 - loss 0.01365644 - time (sec): 9.40 - samples/sec: 1696.78 - lr: 0.000010 - momentum: 0.000000
2023-10-24 10:42:53,017 epoch 8 - iter 294/1476 - loss 0.01467945 - time (sec): 18.54 - samples/sec: 1658.43 - lr: 0.000009 - momentum: 0.000000
2023-10-24 10:43:03,240 epoch 8 - iter 441/1476 - loss 0.01419339 - time (sec): 28.76 - samples/sec: 1760.03 - lr: 0.000009 - momentum: 0.000000
2023-10-24 10:43:12,794 epoch 8 - iter 588/1476 - loss 0.01139119 - time (sec): 38.31 - samples/sec: 1760.19 - lr: 0.000009 - momentum: 0.000000
2023-10-24 10:43:22,562 epoch 8 - iter 735/1476 - loss 0.01070596 - time (sec): 48.08 - samples/sec: 1754.76 - lr: 0.000008 - momentum: 0.000000
2023-10-24 10:43:32,626 epoch 8 - iter 882/1476 - loss 0.01177176 - time (sec): 58.15 - samples/sec: 1762.34 - lr: 0.000008 - momentum: 0.000000
2023-10-24 10:43:41,858 epoch 8 - iter 1029/1476 - loss 0.01286942 - time (sec): 67.38 - samples/sec: 1742.60 - lr: 0.000008 - momentum: 0.000000
2023-10-24 10:43:51,105 epoch 8 - iter 1176/1476 - loss 0.01221774 - time (sec): 76.62 - samples/sec: 1735.10 - lr: 0.000007 - momentum: 0.000000
2023-10-24 10:44:00,445 epoch 8 - iter 1323/1476 - loss 0.01176144 - time (sec): 85.96 - samples/sec: 1731.26 - lr: 0.000007 - momentum: 0.000000
2023-10-24 10:44:10,081 epoch 8 - iter 1470/1476 - loss 0.01227108 - time (sec): 95.60 - samples/sec: 1733.60 - lr: 0.000007 - momentum: 0.000000
2023-10-24 10:44:10,447 ----------------------------------------------------------------------------------------------------
2023-10-24 10:44:10,447 EPOCH 8 done: loss 0.0123 - lr: 0.000007
2023-10-24 10:44:19,008 DEV : loss 0.2190389633178711 - f1-score (micro avg)  0.827
2023-10-24 10:44:19,029 ----------------------------------------------------------------------------------------------------
2023-10-24 10:44:28,424 epoch 9 - iter 147/1476 - loss 0.00656723 - time (sec): 9.39 - samples/sec: 1692.09 - lr: 0.000006 - momentum: 0.000000
2023-10-24 10:44:38,241 epoch 9 - iter 294/1476 - loss 0.00522978 - time (sec): 19.21 - samples/sec: 1767.71 - lr: 0.000006 - momentum: 0.000000
2023-10-24 10:44:47,503 epoch 9 - iter 441/1476 - loss 0.00478950 - time (sec): 28.47 - samples/sec: 1720.95 - lr: 0.000006 - momentum: 0.000000
2023-10-24 10:44:56,695 epoch 9 - iter 588/1476 - loss 0.00468800 - time (sec): 37.66 - samples/sec: 1698.76 - lr: 0.000005 - momentum: 0.000000
2023-10-24 10:45:05,920 epoch 9 - iter 735/1476 - loss 0.00606865 - time (sec): 46.89 - samples/sec: 1700.29 - lr: 0.000005 - momentum: 0.000000
2023-10-24 10:45:15,342 epoch 9 - iter 882/1476 - loss 0.00622321 - time (sec): 56.31 - samples/sec: 1699.13 - lr: 0.000005 - momentum: 0.000000
2023-10-24 10:45:24,857 epoch 9 - iter 1029/1476 - loss 0.00584308 - time (sec): 65.83 - samples/sec: 1709.37 - lr: 0.000004 - momentum: 0.000000
2023-10-24 10:45:34,881 epoch 9 - iter 1176/1476 - loss 0.00648079 - time (sec): 75.85 - samples/sec: 1730.03 - lr: 0.000004 - momentum: 0.000000
2023-10-24 10:45:45,039 epoch 9 - iter 1323/1476 - loss 0.00662559 - time (sec): 86.01 - samples/sec: 1738.06 - lr: 0.000004 - momentum: 0.000000
2023-10-24 10:45:54,542 epoch 9 - iter 1470/1476 - loss 0.00685200 - time (sec): 95.51 - samples/sec: 1737.40 - lr: 0.000003 - momentum: 0.000000
2023-10-24 10:45:54,884 ----------------------------------------------------------------------------------------------------
2023-10-24 10:45:54,885 EPOCH 9 done: loss 0.0068 - lr: 0.000003
2023-10-24 10:46:03,440 DEV : loss 0.22385086119174957 - f1-score (micro avg)  0.8342
2023-10-24 10:46:03,462 saving best model
2023-10-24 10:46:04,162 ----------------------------------------------------------------------------------------------------
2023-10-24 10:46:13,588 epoch 10 - iter 147/1476 - loss 0.00352151 - time (sec): 9.42 - samples/sec: 1718.97 - lr: 0.000003 - momentum: 0.000000
2023-10-24 10:46:22,961 epoch 10 - iter 294/1476 - loss 0.00446608 - time (sec): 18.80 - samples/sec: 1702.67 - lr: 0.000003 - momentum: 0.000000
2023-10-24 10:46:32,841 epoch 10 - iter 441/1476 - loss 0.00470680 - time (sec): 28.68 - samples/sec: 1742.15 - lr: 0.000002 - momentum: 0.000000
2023-10-24 10:46:42,528 epoch 10 - iter 588/1476 - loss 0.00484924 - time (sec): 38.36 - samples/sec: 1761.90 - lr: 0.000002 - momentum: 0.000000
2023-10-24 10:46:52,776 epoch 10 - iter 735/1476 - loss 0.00598633 - time (sec): 48.61 - samples/sec: 1776.90 - lr: 0.000002 - momentum: 0.000000
2023-10-24 10:47:02,222 epoch 10 - iter 882/1476 - loss 0.00629805 - time (sec): 58.06 - samples/sec: 1762.31 - lr: 0.000001 - momentum: 0.000000
2023-10-24 10:47:12,020 epoch 10 - iter 1029/1476 - loss 0.00622798 - time (sec): 67.86 - samples/sec: 1757.82 - lr: 0.000001 - momentum: 0.000000
2023-10-24 10:47:21,170 epoch 10 - iter 1176/1476 - loss 0.00617265 - time (sec): 77.01 - samples/sec: 1743.69 - lr: 0.000001 - momentum: 0.000000
2023-10-24 10:47:30,350 epoch 10 - iter 1323/1476 - loss 0.00592236 - time (sec): 86.19 - samples/sec: 1734.52 - lr: 0.000000 - momentum: 0.000000
2023-10-24 10:47:39,701 epoch 10 - iter 1470/1476 - loss 0.00547473 - time (sec): 95.54 - samples/sec: 1736.26 - lr: 0.000000 - momentum: 0.000000
2023-10-24 10:47:40,046 ----------------------------------------------------------------------------------------------------
2023-10-24 10:47:40,046 EPOCH 10 done: loss 0.0055 - lr: 0.000000
2023-10-24 10:47:48,614 DEV : loss 0.22415557503700256 - f1-score (micro avg)  0.8404
2023-10-24 10:47:48,636 saving best model
2023-10-24 10:47:49,932 ----------------------------------------------------------------------------------------------------
2023-10-24 10:47:49,932 Loading model from best epoch ...
2023-10-24 10:47:51,801 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 10:47:58,484 
Results:
- F-score (micro) 0.7974
- F-score (macro) 0.7083
- Accuracy 0.6897

By class:
              precision    recall  f1-score   support

         loc     0.8366    0.8893    0.8621       858
        pers     0.7656    0.7784    0.7719       537
         org     0.5882    0.6061    0.5970       132
        prod     0.7018    0.6557    0.6780        61
        time     0.5873    0.6852    0.6325        54

   micro avg     0.7806    0.8149    0.7974      1642
   macro avg     0.6959    0.7229    0.7083      1642
weighted avg     0.7802    0.8149    0.7969      1642

2023-10-24 10:47:58,485 ----------------------------------------------------------------------------------------------------