2023-10-25 16:18:00,357 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,358 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=13, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
 - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Train:  14465 sentences
2023-10-25 16:18:00,359         (train_with_dev=False, train_with_test=False)
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Training Params:
2023-10-25 16:18:00,359  - learning_rate: "5e-05" 
2023-10-25 16:18:00,359  - mini_batch_size: "4"
2023-10-25 16:18:00,359  - max_epochs: "10"
2023-10-25 16:18:00,359  - shuffle: "True"
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Plugins:
2023-10-25 16:18:00,359  - TensorboardLogger
2023-10-25 16:18:00,359  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 16:18:00,359  - metric: "('micro avg', 'f1-score')"
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Computation:
2023-10-25 16:18:00,359  - compute on device: cuda:0
2023-10-25 16:18:00,359  - embedding storage: none
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 ----------------------------------------------------------------------------------------------------
2023-10-25 16:18:00,359 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 16:18:22,857 epoch 1 - iter 361/3617 - loss 0.98721839 - time (sec): 22.50 - samples/sec: 1664.55 - lr: 0.000005 - momentum: 0.000000
2023-10-25 16:18:45,720 epoch 1 - iter 722/3617 - loss 0.56997509 - time (sec): 45.36 - samples/sec: 1684.75 - lr: 0.000010 - momentum: 0.000000
2023-10-25 16:19:08,178 epoch 1 - iter 1083/3617 - loss 0.42947665 - time (sec): 67.82 - samples/sec: 1669.91 - lr: 0.000015 - momentum: 0.000000
2023-10-25 16:19:30,856 epoch 1 - iter 1444/3617 - loss 0.34909939 - time (sec): 90.50 - samples/sec: 1678.64 - lr: 0.000020 - momentum: 0.000000
2023-10-25 16:19:53,548 epoch 1 - iter 1805/3617 - loss 0.30295916 - time (sec): 113.19 - samples/sec: 1677.11 - lr: 0.000025 - momentum: 0.000000
2023-10-25 16:20:16,240 epoch 1 - iter 2166/3617 - loss 0.27214151 - time (sec): 135.88 - samples/sec: 1684.86 - lr: 0.000030 - momentum: 0.000000
2023-10-25 16:20:38,797 epoch 1 - iter 2527/3617 - loss 0.25109284 - time (sec): 158.44 - samples/sec: 1682.20 - lr: 0.000035 - momentum: 0.000000
2023-10-25 16:21:01,498 epoch 1 - iter 2888/3617 - loss 0.23564479 - time (sec): 181.14 - samples/sec: 1683.93 - lr: 0.000040 - momentum: 0.000000
2023-10-25 16:21:24,087 epoch 1 - iter 3249/3617 - loss 0.22390402 - time (sec): 203.73 - samples/sec: 1680.45 - lr: 0.000045 - momentum: 0.000000
2023-10-25 16:21:46,423 epoch 1 - iter 3610/3617 - loss 0.21417050 - time (sec): 226.06 - samples/sec: 1677.12 - lr: 0.000050 - momentum: 0.000000
2023-10-25 16:21:46,872 ----------------------------------------------------------------------------------------------------
2023-10-25 16:21:46,873 EPOCH 1 done: loss 0.2139 - lr: 0.000050
2023-10-25 16:21:51,373 DEV : loss 0.1173805445432663 - f1-score (micro avg)  0.5928
2023-10-25 16:21:51,394 saving best model
2023-10-25 16:21:51,945 ----------------------------------------------------------------------------------------------------
2023-10-25 16:22:14,928 epoch 2 - iter 361/3617 - loss 0.11371088 - time (sec): 22.98 - samples/sec: 1698.15 - lr: 0.000049 - momentum: 0.000000
2023-10-25 16:22:37,559 epoch 2 - iter 722/3617 - loss 0.11014365 - time (sec): 45.61 - samples/sec: 1676.19 - lr: 0.000049 - momentum: 0.000000
2023-10-25 16:23:00,367 epoch 2 - iter 1083/3617 - loss 0.10881076 - time (sec): 68.42 - samples/sec: 1668.81 - lr: 0.000048 - momentum: 0.000000
2023-10-25 16:23:23,009 epoch 2 - iter 1444/3617 - loss 0.10813684 - time (sec): 91.06 - samples/sec: 1673.56 - lr: 0.000048 - momentum: 0.000000
2023-10-25 16:23:45,565 epoch 2 - iter 1805/3617 - loss 0.10693539 - time (sec): 113.62 - samples/sec: 1661.67 - lr: 0.000047 - momentum: 0.000000
2023-10-25 16:24:08,644 epoch 2 - iter 2166/3617 - loss 0.10638248 - time (sec): 136.70 - samples/sec: 1677.19 - lr: 0.000047 - momentum: 0.000000
2023-10-25 16:24:31,270 epoch 2 - iter 2527/3617 - loss 0.10544641 - time (sec): 159.32 - samples/sec: 1672.56 - lr: 0.000046 - momentum: 0.000000
2023-10-25 16:24:54,391 epoch 2 - iter 2888/3617 - loss 0.10605920 - time (sec): 182.45 - samples/sec: 1666.72 - lr: 0.000046 - momentum: 0.000000
2023-10-25 16:25:17,015 epoch 2 - iter 3249/3617 - loss 0.10581619 - time (sec): 205.07 - samples/sec: 1670.42 - lr: 0.000045 - momentum: 0.000000
2023-10-25 16:25:39,603 epoch 2 - iter 3610/3617 - loss 0.10642989 - time (sec): 227.66 - samples/sec: 1665.97 - lr: 0.000044 - momentum: 0.000000
2023-10-25 16:25:40,033 ----------------------------------------------------------------------------------------------------
2023-10-25 16:25:40,033 EPOCH 2 done: loss 0.1064 - lr: 0.000044
2023-10-25 16:25:44,767 DEV : loss 0.12259281426668167 - f1-score (micro avg)  0.5151
2023-10-25 16:25:44,790 ----------------------------------------------------------------------------------------------------
2023-10-25 16:26:07,266 epoch 3 - iter 361/3617 - loss 0.07575995 - time (sec): 22.48 - samples/sec: 1670.01 - lr: 0.000044 - momentum: 0.000000
2023-10-25 16:26:30,145 epoch 3 - iter 722/3617 - loss 0.07769008 - time (sec): 45.35 - samples/sec: 1678.96 - lr: 0.000043 - momentum: 0.000000
2023-10-25 16:26:52,861 epoch 3 - iter 1083/3617 - loss 0.07934303 - time (sec): 68.07 - samples/sec: 1684.63 - lr: 0.000043 - momentum: 0.000000
2023-10-25 16:27:15,407 epoch 3 - iter 1444/3617 - loss 0.08201725 - time (sec): 90.62 - samples/sec: 1671.59 - lr: 0.000042 - momentum: 0.000000
2023-10-25 16:27:38,068 epoch 3 - iter 1805/3617 - loss 0.08413864 - time (sec): 113.28 - samples/sec: 1671.83 - lr: 0.000042 - momentum: 0.000000
2023-10-25 16:28:00,588 epoch 3 - iter 2166/3617 - loss 0.08234846 - time (sec): 135.80 - samples/sec: 1678.32 - lr: 0.000041 - momentum: 0.000000
2023-10-25 16:28:23,268 epoch 3 - iter 2527/3617 - loss 0.08197610 - time (sec): 158.48 - samples/sec: 1680.92 - lr: 0.000041 - momentum: 0.000000
2023-10-25 16:28:45,562 epoch 3 - iter 2888/3617 - loss 0.08211964 - time (sec): 180.77 - samples/sec: 1675.98 - lr: 0.000040 - momentum: 0.000000
2023-10-25 16:29:08,559 epoch 3 - iter 3249/3617 - loss 0.08210844 - time (sec): 203.77 - samples/sec: 1677.64 - lr: 0.000039 - momentum: 0.000000
2023-10-25 16:29:31,049 epoch 3 - iter 3610/3617 - loss 0.08220886 - time (sec): 226.26 - samples/sec: 1675.52 - lr: 0.000039 - momentum: 0.000000
2023-10-25 16:29:31,512 ----------------------------------------------------------------------------------------------------
2023-10-25 16:29:31,513 EPOCH 3 done: loss 0.0822 - lr: 0.000039
2023-10-25 16:29:36,772 DEV : loss 0.22915546596050262 - f1-score (micro avg)  0.6111
2023-10-25 16:29:36,794 saving best model
2023-10-25 16:29:37,445 ----------------------------------------------------------------------------------------------------
2023-10-25 16:30:00,261 epoch 4 - iter 361/3617 - loss 0.05161137 - time (sec): 22.81 - samples/sec: 1693.39 - lr: 0.000038 - momentum: 0.000000
2023-10-25 16:30:22,792 epoch 4 - iter 722/3617 - loss 0.05675682 - time (sec): 45.35 - samples/sec: 1702.28 - lr: 0.000038 - momentum: 0.000000
2023-10-25 16:30:45,543 epoch 4 - iter 1083/3617 - loss 0.05633822 - time (sec): 68.10 - samples/sec: 1701.43 - lr: 0.000037 - momentum: 0.000000
2023-10-25 16:31:08,137 epoch 4 - iter 1444/3617 - loss 0.05836208 - time (sec): 90.69 - samples/sec: 1674.64 - lr: 0.000037 - momentum: 0.000000
2023-10-25 16:31:30,671 epoch 4 - iter 1805/3617 - loss 0.05808428 - time (sec): 113.22 - samples/sec: 1669.96 - lr: 0.000036 - momentum: 0.000000
2023-10-25 16:31:53,629 epoch 4 - iter 2166/3617 - loss 0.05945872 - time (sec): 136.18 - samples/sec: 1682.21 - lr: 0.000036 - momentum: 0.000000
2023-10-25 16:32:16,372 epoch 4 - iter 2527/3617 - loss 0.05987102 - time (sec): 158.93 - samples/sec: 1682.29 - lr: 0.000035 - momentum: 0.000000
2023-10-25 16:32:38,940 epoch 4 - iter 2888/3617 - loss 0.06229445 - time (sec): 181.49 - samples/sec: 1679.33 - lr: 0.000034 - momentum: 0.000000
2023-10-25 16:33:01,490 epoch 4 - iter 3249/3617 - loss 0.06184988 - time (sec): 204.04 - samples/sec: 1677.22 - lr: 0.000034 - momentum: 0.000000
2023-10-25 16:33:23,989 epoch 4 - iter 3610/3617 - loss 0.06154159 - time (sec): 226.54 - samples/sec: 1673.55 - lr: 0.000033 - momentum: 0.000000
2023-10-25 16:33:24,442 ----------------------------------------------------------------------------------------------------
2023-10-25 16:33:24,442 EPOCH 4 done: loss 0.0615 - lr: 0.000033
2023-10-25 16:33:29,699 DEV : loss 0.2458053082227707 - f1-score (micro avg)  0.6126
2023-10-25 16:33:29,720 saving best model
2023-10-25 16:33:30,419 ----------------------------------------------------------------------------------------------------
2023-10-25 16:33:53,141 epoch 5 - iter 361/3617 - loss 0.03679615 - time (sec): 22.72 - samples/sec: 1636.48 - lr: 0.000033 - momentum: 0.000000
2023-10-25 16:34:15,545 epoch 5 - iter 722/3617 - loss 0.03349966 - time (sec): 45.13 - samples/sec: 1643.87 - lr: 0.000032 - momentum: 0.000000
2023-10-25 16:34:38,200 epoch 5 - iter 1083/3617 - loss 0.03405818 - time (sec): 67.78 - samples/sec: 1655.79 - lr: 0.000032 - momentum: 0.000000
2023-10-25 16:35:00,655 epoch 5 - iter 1444/3617 - loss 0.03703588 - time (sec): 90.23 - samples/sec: 1659.92 - lr: 0.000031 - momentum: 0.000000
2023-10-25 16:35:23,213 epoch 5 - iter 1805/3617 - loss 0.04191627 - time (sec): 112.79 - samples/sec: 1665.63 - lr: 0.000031 - momentum: 0.000000
2023-10-25 16:35:45,708 epoch 5 - iter 2166/3617 - loss 0.04211938 - time (sec): 135.29 - samples/sec: 1659.86 - lr: 0.000030 - momentum: 0.000000
2023-10-25 16:36:08,304 epoch 5 - iter 2527/3617 - loss 0.04356578 - time (sec): 157.88 - samples/sec: 1658.25 - lr: 0.000029 - momentum: 0.000000
2023-10-25 16:36:31,295 epoch 5 - iter 2888/3617 - loss 0.04317565 - time (sec): 180.87 - samples/sec: 1673.08 - lr: 0.000029 - momentum: 0.000000
2023-10-25 16:36:53,829 epoch 5 - iter 3249/3617 - loss 0.04414571 - time (sec): 203.41 - samples/sec: 1668.42 - lr: 0.000028 - momentum: 0.000000
2023-10-25 16:37:16,685 epoch 5 - iter 3610/3617 - loss 0.04383334 - time (sec): 226.27 - samples/sec: 1676.42 - lr: 0.000028 - momentum: 0.000000
2023-10-25 16:37:17,090 ----------------------------------------------------------------------------------------------------
2023-10-25 16:37:17,090 EPOCH 5 done: loss 0.0439 - lr: 0.000028
2023-10-25 16:37:22,367 DEV : loss 0.29450729489326477 - f1-score (micro avg)  0.6228
2023-10-25 16:37:22,389 saving best model
2023-10-25 16:37:23,094 ----------------------------------------------------------------------------------------------------
2023-10-25 16:37:45,762 epoch 6 - iter 361/3617 - loss 0.02401422 - time (sec): 22.67 - samples/sec: 1686.95 - lr: 0.000027 - momentum: 0.000000
2023-10-25 16:38:08,579 epoch 6 - iter 722/3617 - loss 0.02513291 - time (sec): 45.48 - samples/sec: 1662.53 - lr: 0.000027 - momentum: 0.000000
2023-10-25 16:38:31,531 epoch 6 - iter 1083/3617 - loss 0.02688665 - time (sec): 68.44 - samples/sec: 1693.79 - lr: 0.000026 - momentum: 0.000000
2023-10-25 16:38:53,910 epoch 6 - iter 1444/3617 - loss 0.02741538 - time (sec): 90.81 - samples/sec: 1683.32 - lr: 0.000026 - momentum: 0.000000
2023-10-25 16:39:16,700 epoch 6 - iter 1805/3617 - loss 0.02832321 - time (sec): 113.61 - samples/sec: 1689.63 - lr: 0.000025 - momentum: 0.000000
2023-10-25 16:39:39,108 epoch 6 - iter 2166/3617 - loss 0.02884619 - time (sec): 136.01 - samples/sec: 1688.38 - lr: 0.000024 - momentum: 0.000000
2023-10-25 16:40:01,861 epoch 6 - iter 2527/3617 - loss 0.02937217 - time (sec): 158.77 - samples/sec: 1686.15 - lr: 0.000024 - momentum: 0.000000
2023-10-25 16:40:24,473 epoch 6 - iter 2888/3617 - loss 0.03055198 - time (sec): 181.38 - samples/sec: 1681.50 - lr: 0.000023 - momentum: 0.000000
2023-10-25 16:40:46,890 epoch 6 - iter 3249/3617 - loss 0.03075395 - time (sec): 203.80 - samples/sec: 1673.96 - lr: 0.000023 - momentum: 0.000000
2023-10-25 16:41:09,565 epoch 6 - iter 3610/3617 - loss 0.03165445 - time (sec): 226.47 - samples/sec: 1674.14 - lr: 0.000022 - momentum: 0.000000
2023-10-25 16:41:10,008 ----------------------------------------------------------------------------------------------------
2023-10-25 16:41:10,008 EPOCH 6 done: loss 0.0316 - lr: 0.000022
2023-10-25 16:41:15,282 DEV : loss 0.31113916635513306 - f1-score (micro avg)  0.6275
2023-10-25 16:41:15,304 saving best model
2023-10-25 16:41:16,055 ----------------------------------------------------------------------------------------------------
2023-10-25 16:41:38,656 epoch 7 - iter 361/3617 - loss 0.01966350 - time (sec): 22.60 - samples/sec: 1685.33 - lr: 0.000022 - momentum: 0.000000
2023-10-25 16:42:01,294 epoch 7 - iter 722/3617 - loss 0.02181364 - time (sec): 45.24 - samples/sec: 1689.13 - lr: 0.000021 - momentum: 0.000000
2023-10-25 16:42:24,009 epoch 7 - iter 1083/3617 - loss 0.02052075 - time (sec): 67.95 - samples/sec: 1682.75 - lr: 0.000021 - momentum: 0.000000
2023-10-25 16:42:46,833 epoch 7 - iter 1444/3617 - loss 0.02198526 - time (sec): 90.78 - samples/sec: 1691.60 - lr: 0.000020 - momentum: 0.000000
2023-10-25 16:43:09,244 epoch 7 - iter 1805/3617 - loss 0.02198388 - time (sec): 113.19 - samples/sec: 1682.17 - lr: 0.000019 - momentum: 0.000000
2023-10-25 16:43:31,998 epoch 7 - iter 2166/3617 - loss 0.02099104 - time (sec): 135.94 - samples/sec: 1687.85 - lr: 0.000019 - momentum: 0.000000
2023-10-25 16:43:54,612 epoch 7 - iter 2527/3617 - loss 0.02101164 - time (sec): 158.56 - samples/sec: 1687.44 - lr: 0.000018 - momentum: 0.000000
2023-10-25 16:44:17,265 epoch 7 - iter 2888/3617 - loss 0.02107248 - time (sec): 181.21 - samples/sec: 1680.63 - lr: 0.000018 - momentum: 0.000000
2023-10-25 16:44:40,039 epoch 7 - iter 3249/3617 - loss 0.02067048 - time (sec): 203.98 - samples/sec: 1675.79 - lr: 0.000017 - momentum: 0.000000
2023-10-25 16:45:02,575 epoch 7 - iter 3610/3617 - loss 0.02054673 - time (sec): 226.52 - samples/sec: 1674.01 - lr: 0.000017 - momentum: 0.000000
2023-10-25 16:45:03,027 ----------------------------------------------------------------------------------------------------
2023-10-25 16:45:03,027 EPOCH 7 done: loss 0.0206 - lr: 0.000017
2023-10-25 16:45:07,782 DEV : loss 0.3365882337093353 - f1-score (micro avg)  0.6271
2023-10-25 16:45:07,804 ----------------------------------------------------------------------------------------------------
2023-10-25 16:45:30,470 epoch 8 - iter 361/3617 - loss 0.01421589 - time (sec): 22.67 - samples/sec: 1710.89 - lr: 0.000016 - momentum: 0.000000
2023-10-25 16:45:53,207 epoch 8 - iter 722/3617 - loss 0.01334565 - time (sec): 45.40 - samples/sec: 1682.77 - lr: 0.000016 - momentum: 0.000000
2023-10-25 16:46:15,832 epoch 8 - iter 1083/3617 - loss 0.01298190 - time (sec): 68.03 - samples/sec: 1685.59 - lr: 0.000015 - momentum: 0.000000
2023-10-25 16:46:38,501 epoch 8 - iter 1444/3617 - loss 0.01355953 - time (sec): 90.70 - samples/sec: 1678.39 - lr: 0.000014 - momentum: 0.000000
2023-10-25 16:47:01,119 epoch 8 - iter 1805/3617 - loss 0.01318574 - time (sec): 113.31 - samples/sec: 1673.05 - lr: 0.000014 - momentum: 0.000000
2023-10-25 16:47:23,681 epoch 8 - iter 2166/3617 - loss 0.01290110 - time (sec): 135.88 - samples/sec: 1674.03 - lr: 0.000013 - momentum: 0.000000
2023-10-25 16:47:46,238 epoch 8 - iter 2527/3617 - loss 0.01331098 - time (sec): 158.43 - samples/sec: 1672.50 - lr: 0.000013 - momentum: 0.000000
2023-10-25 16:48:09,195 epoch 8 - iter 2888/3617 - loss 0.01356070 - time (sec): 181.39 - samples/sec: 1662.42 - lr: 0.000012 - momentum: 0.000000
2023-10-25 16:48:32,130 epoch 8 - iter 3249/3617 - loss 0.01314274 - time (sec): 204.33 - samples/sec: 1670.42 - lr: 0.000012 - momentum: 0.000000
2023-10-25 16:48:54,868 epoch 8 - iter 3610/3617 - loss 0.01341847 - time (sec): 227.06 - samples/sec: 1670.28 - lr: 0.000011 - momentum: 0.000000
2023-10-25 16:48:55,285 ----------------------------------------------------------------------------------------------------
2023-10-25 16:48:55,285 EPOCH 8 done: loss 0.0134 - lr: 0.000011
2023-10-25 16:49:00,055 DEV : loss 0.40507254004478455 - f1-score (micro avg)  0.6314
2023-10-25 16:49:00,077 saving best model
2023-10-25 16:49:00,828 ----------------------------------------------------------------------------------------------------
2023-10-25 16:49:23,521 epoch 9 - iter 361/3617 - loss 0.00754713 - time (sec): 22.69 - samples/sec: 1713.09 - lr: 0.000011 - momentum: 0.000000
2023-10-25 16:49:45,939 epoch 9 - iter 722/3617 - loss 0.01019330 - time (sec): 45.11 - samples/sec: 1669.29 - lr: 0.000010 - momentum: 0.000000
2023-10-25 16:50:08,674 epoch 9 - iter 1083/3617 - loss 0.00909325 - time (sec): 67.84 - samples/sec: 1678.55 - lr: 0.000009 - momentum: 0.000000
2023-10-25 16:50:31,541 epoch 9 - iter 1444/3617 - loss 0.00920364 - time (sec): 90.71 - samples/sec: 1677.07 - lr: 0.000009 - momentum: 0.000000
2023-10-25 16:50:54,228 epoch 9 - iter 1805/3617 - loss 0.00936195 - time (sec): 113.40 - samples/sec: 1685.90 - lr: 0.000008 - momentum: 0.000000
2023-10-25 16:51:16,646 epoch 9 - iter 2166/3617 - loss 0.00947121 - time (sec): 135.82 - samples/sec: 1674.45 - lr: 0.000008 - momentum: 0.000000
2023-10-25 16:51:39,304 epoch 9 - iter 2527/3617 - loss 0.00953719 - time (sec): 158.48 - samples/sec: 1668.32 - lr: 0.000007 - momentum: 0.000000
2023-10-25 16:52:02,093 epoch 9 - iter 2888/3617 - loss 0.00923108 - time (sec): 181.26 - samples/sec: 1673.08 - lr: 0.000007 - momentum: 0.000000
2023-10-25 16:52:24,810 epoch 9 - iter 3249/3617 - loss 0.00883401 - time (sec): 203.98 - samples/sec: 1673.03 - lr: 0.000006 - momentum: 0.000000
2023-10-25 16:52:47,507 epoch 9 - iter 3610/3617 - loss 0.00869020 - time (sec): 226.68 - samples/sec: 1673.24 - lr: 0.000006 - momentum: 0.000000
2023-10-25 16:52:47,929 ----------------------------------------------------------------------------------------------------
2023-10-25 16:52:47,929 EPOCH 9 done: loss 0.0087 - lr: 0.000006
2023-10-25 16:52:53,216 DEV : loss 0.3974364399909973 - f1-score (micro avg)  0.6335
2023-10-25 16:52:53,238 saving best model
2023-10-25 16:52:53,901 ----------------------------------------------------------------------------------------------------
2023-10-25 16:53:16,928 epoch 10 - iter 361/3617 - loss 0.00451968 - time (sec): 23.03 - samples/sec: 1742.22 - lr: 0.000005 - momentum: 0.000000
2023-10-25 16:53:39,365 epoch 10 - iter 722/3617 - loss 0.00518291 - time (sec): 45.46 - samples/sec: 1692.54 - lr: 0.000004 - momentum: 0.000000
2023-10-25 16:54:01,876 epoch 10 - iter 1083/3617 - loss 0.00458772 - time (sec): 67.97 - samples/sec: 1681.79 - lr: 0.000004 - momentum: 0.000000
2023-10-25 16:54:24,404 epoch 10 - iter 1444/3617 - loss 0.00486760 - time (sec): 90.50 - samples/sec: 1676.06 - lr: 0.000003 - momentum: 0.000000
2023-10-25 16:54:47,079 epoch 10 - iter 1805/3617 - loss 0.00489244 - time (sec): 113.18 - samples/sec: 1670.27 - lr: 0.000003 - momentum: 0.000000
2023-10-25 16:55:09,930 epoch 10 - iter 2166/3617 - loss 0.00530223 - time (sec): 136.03 - samples/sec: 1676.93 - lr: 0.000002 - momentum: 0.000000
2023-10-25 16:55:32,746 epoch 10 - iter 2527/3617 - loss 0.00531784 - time (sec): 158.84 - samples/sec: 1675.88 - lr: 0.000002 - momentum: 0.000000
2023-10-25 16:55:55,505 epoch 10 - iter 2888/3617 - loss 0.00516961 - time (sec): 181.60 - samples/sec: 1679.56 - lr: 0.000001 - momentum: 0.000000
2023-10-25 16:56:17,939 epoch 10 - iter 3249/3617 - loss 0.00499057 - time (sec): 204.04 - samples/sec: 1673.16 - lr: 0.000001 - momentum: 0.000000
2023-10-25 16:56:40,508 epoch 10 - iter 3610/3617 - loss 0.00490336 - time (sec): 226.61 - samples/sec: 1673.80 - lr: 0.000000 - momentum: 0.000000
2023-10-25 16:56:40,926 ----------------------------------------------------------------------------------------------------
2023-10-25 16:56:40,927 EPOCH 10 done: loss 0.0049 - lr: 0.000000
2023-10-25 16:56:46,237 DEV : loss 0.41693753004074097 - f1-score (micro avg)  0.6372
2023-10-25 16:56:46,259 saving best model
2023-10-25 16:56:47,509 ----------------------------------------------------------------------------------------------------
2023-10-25 16:56:47,510 Loading model from best epoch ...
2023-10-25 16:56:49,299 SequenceTagger predicts: Dictionary with 13 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
2023-10-25 16:56:55,016 
Results:
- F-score (micro) 0.6271
- F-score (macro) 0.4748
- Accuracy 0.4707

By class:
              precision    recall  f1-score   support

         loc     0.6173    0.7259    0.6672       591
        pers     0.5689    0.7171    0.6344       357
         org     0.2000    0.0886    0.1228        79

   micro avg     0.5864    0.6738    0.6271      1027
   macro avg     0.4621    0.5105    0.4748      1027
weighted avg     0.5684    0.6738    0.6139      1027

2023-10-25 16:56:55,016 ----------------------------------------------------------------------------------------------------