2023-10-24 16:04:44,877 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,878 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()
)"
2023-10-24 16:04:44,878 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,878 MultiCorpus: 7936 train + 992 dev + 992 test sentences
 - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/fr
2023-10-24 16:04:44,878 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,878 Train:  7936 sentences
2023-10-24 16:04:44,878         (train_with_dev=False, train_with_test=False)
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Training Params:
2023-10-24 16:04:44,879  - learning_rate: "5e-05" 
2023-10-24 16:04:44,879  - mini_batch_size: "4"
2023-10-24 16:04:44,879  - max_epochs: "10"
2023-10-24 16:04:44,879  - shuffle: "True"
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Plugins:
2023-10-24 16:04:44,879  - TensorboardLogger
2023-10-24 16:04:44,879  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 16:04:44,879  - metric: "('micro avg', 'f1-score')"
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Computation:
2023-10-24 16:04:44,879  - compute on device: cuda:0
2023-10-24 16:04:44,879  - embedding storage: none
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 ----------------------------------------------------------------------------------------------------
2023-10-24 16:04:44,879 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 16:04:56,741 epoch 1 - iter 198/1984 - loss 1.30874305 - time (sec): 11.86 - samples/sec: 1327.48 - lr: 0.000005 - momentum: 0.000000
2023-10-24 16:05:08,929 epoch 1 - iter 396/1984 - loss 0.77290785 - time (sec): 24.05 - samples/sec: 1366.71 - lr: 0.000010 - momentum: 0.000000
2023-10-24 16:05:21,110 epoch 1 - iter 594/1984 - loss 0.57572628 - time (sec): 36.23 - samples/sec: 1376.56 - lr: 0.000015 - momentum: 0.000000
2023-10-24 16:05:33,378 epoch 1 - iter 792/1984 - loss 0.46495084 - time (sec): 48.50 - samples/sec: 1393.71 - lr: 0.000020 - momentum: 0.000000
2023-10-24 16:05:45,281 epoch 1 - iter 990/1984 - loss 0.40496031 - time (sec): 60.40 - samples/sec: 1372.95 - lr: 0.000025 - momentum: 0.000000
2023-10-24 16:05:57,339 epoch 1 - iter 1188/1984 - loss 0.35918387 - time (sec): 72.46 - samples/sec: 1368.87 - lr: 0.000030 - momentum: 0.000000
2023-10-24 16:06:09,207 epoch 1 - iter 1386/1984 - loss 0.33254399 - time (sec): 84.33 - samples/sec: 1357.26 - lr: 0.000035 - momentum: 0.000000
2023-10-24 16:06:21,228 epoch 1 - iter 1584/1984 - loss 0.30875914 - time (sec): 96.35 - samples/sec: 1352.95 - lr: 0.000040 - momentum: 0.000000
2023-10-24 16:06:33,559 epoch 1 - iter 1782/1984 - loss 0.28915180 - time (sec): 108.68 - samples/sec: 1356.10 - lr: 0.000045 - momentum: 0.000000
2023-10-24 16:06:45,621 epoch 1 - iter 1980/1984 - loss 0.27550886 - time (sec): 120.74 - samples/sec: 1353.99 - lr: 0.000050 - momentum: 0.000000
2023-10-24 16:06:45,883 ----------------------------------------------------------------------------------------------------
2023-10-24 16:06:45,883 EPOCH 1 done: loss 0.2751 - lr: 0.000050
2023-10-24 16:06:48,984 DEV : loss 0.1138407364487648 - f1-score (micro avg)  0.66
2023-10-24 16:06:48,999 saving best model
2023-10-24 16:06:49,463 ----------------------------------------------------------------------------------------------------
2023-10-24 16:07:01,531 epoch 2 - iter 198/1984 - loss 0.11655675 - time (sec): 12.07 - samples/sec: 1378.59 - lr: 0.000049 - momentum: 0.000000
2023-10-24 16:07:13,599 epoch 2 - iter 396/1984 - loss 0.12768765 - time (sec): 24.13 - samples/sec: 1366.33 - lr: 0.000049 - momentum: 0.000000
2023-10-24 16:07:25,662 epoch 2 - iter 594/1984 - loss 0.12928172 - time (sec): 36.20 - samples/sec: 1354.01 - lr: 0.000048 - momentum: 0.000000
2023-10-24 16:07:37,968 epoch 2 - iter 792/1984 - loss 0.12515423 - time (sec): 48.50 - samples/sec: 1358.05 - lr: 0.000048 - momentum: 0.000000
2023-10-24 16:07:50,011 epoch 2 - iter 990/1984 - loss 0.12468271 - time (sec): 60.55 - samples/sec: 1352.43 - lr: 0.000047 - momentum: 0.000000
2023-10-24 16:08:02,219 epoch 2 - iter 1188/1984 - loss 0.12585547 - time (sec): 72.76 - samples/sec: 1350.88 - lr: 0.000047 - momentum: 0.000000
2023-10-24 16:08:14,508 epoch 2 - iter 1386/1984 - loss 0.12536731 - time (sec): 85.04 - samples/sec: 1356.27 - lr: 0.000046 - momentum: 0.000000
2023-10-24 16:08:26,927 epoch 2 - iter 1584/1984 - loss 0.12683513 - time (sec): 97.46 - samples/sec: 1354.08 - lr: 0.000046 - momentum: 0.000000
2023-10-24 16:08:38,923 epoch 2 - iter 1782/1984 - loss 0.12567024 - time (sec): 109.46 - samples/sec: 1349.32 - lr: 0.000045 - momentum: 0.000000
2023-10-24 16:08:50,905 epoch 2 - iter 1980/1984 - loss 0.12355541 - time (sec): 121.44 - samples/sec: 1348.76 - lr: 0.000044 - momentum: 0.000000
2023-10-24 16:08:51,136 ----------------------------------------------------------------------------------------------------
2023-10-24 16:08:51,136 EPOCH 2 done: loss 0.1236 - lr: 0.000044
2023-10-24 16:08:54,244 DEV : loss 0.11781438440084457 - f1-score (micro avg)  0.7224
2023-10-24 16:08:54,259 saving best model
2023-10-24 16:08:54,870 ----------------------------------------------------------------------------------------------------
2023-10-24 16:09:07,592 epoch 3 - iter 198/1984 - loss 0.09570974 - time (sec): 12.72 - samples/sec: 1320.29 - lr: 0.000044 - momentum: 0.000000
2023-10-24 16:09:19,560 epoch 3 - iter 396/1984 - loss 0.09234026 - time (sec): 24.69 - samples/sec: 1318.45 - lr: 0.000043 - momentum: 0.000000
2023-10-24 16:09:31,705 epoch 3 - iter 594/1984 - loss 0.09370577 - time (sec): 36.83 - samples/sec: 1341.85 - lr: 0.000043 - momentum: 0.000000
2023-10-24 16:09:43,846 epoch 3 - iter 792/1984 - loss 0.09168960 - time (sec): 48.97 - samples/sec: 1353.86 - lr: 0.000042 - momentum: 0.000000
2023-10-24 16:09:55,897 epoch 3 - iter 990/1984 - loss 0.09458487 - time (sec): 61.03 - samples/sec: 1343.19 - lr: 0.000042 - momentum: 0.000000
2023-10-24 16:10:08,031 epoch 3 - iter 1188/1984 - loss 0.09320143 - time (sec): 73.16 - samples/sec: 1339.84 - lr: 0.000041 - momentum: 0.000000
2023-10-24 16:10:20,096 epoch 3 - iter 1386/1984 - loss 0.09112387 - time (sec): 85.22 - samples/sec: 1342.96 - lr: 0.000041 - momentum: 0.000000
2023-10-24 16:10:32,057 epoch 3 - iter 1584/1984 - loss 0.09073603 - time (sec): 97.19 - samples/sec: 1343.93 - lr: 0.000040 - momentum: 0.000000
2023-10-24 16:10:44,110 epoch 3 - iter 1782/1984 - loss 0.09058074 - time (sec): 109.24 - samples/sec: 1344.60 - lr: 0.000039 - momentum: 0.000000
2023-10-24 16:10:56,367 epoch 3 - iter 1980/1984 - loss 0.09067995 - time (sec): 121.50 - samples/sec: 1347.52 - lr: 0.000039 - momentum: 0.000000
2023-10-24 16:10:56,599 ----------------------------------------------------------------------------------------------------
2023-10-24 16:10:56,599 EPOCH 3 done: loss 0.0906 - lr: 0.000039
2023-10-24 16:10:59,703 DEV : loss 0.1346270591020584 - f1-score (micro avg)  0.7411
2023-10-24 16:10:59,718 saving best model
2023-10-24 16:11:00,312 ----------------------------------------------------------------------------------------------------
2023-10-24 16:11:12,521 epoch 4 - iter 198/1984 - loss 0.05402007 - time (sec): 12.21 - samples/sec: 1388.06 - lr: 0.000038 - momentum: 0.000000
2023-10-24 16:11:24,580 epoch 4 - iter 396/1984 - loss 0.06102748 - time (sec): 24.27 - samples/sec: 1343.10 - lr: 0.000038 - momentum: 0.000000
2023-10-24 16:11:36,914 epoch 4 - iter 594/1984 - loss 0.06492659 - time (sec): 36.60 - samples/sec: 1366.14 - lr: 0.000037 - momentum: 0.000000
2023-10-24 16:11:48,948 epoch 4 - iter 792/1984 - loss 0.06649210 - time (sec): 48.63 - samples/sec: 1356.46 - lr: 0.000037 - momentum: 0.000000
2023-10-24 16:12:01,047 epoch 4 - iter 990/1984 - loss 0.06862370 - time (sec): 60.73 - samples/sec: 1355.00 - lr: 0.000036 - momentum: 0.000000
2023-10-24 16:12:13,286 epoch 4 - iter 1188/1984 - loss 0.06836085 - time (sec): 72.97 - samples/sec: 1355.36 - lr: 0.000036 - momentum: 0.000000
2023-10-24 16:12:25,253 epoch 4 - iter 1386/1984 - loss 0.06765039 - time (sec): 84.94 - samples/sec: 1349.99 - lr: 0.000035 - momentum: 0.000000
2023-10-24 16:12:37,532 epoch 4 - iter 1584/1984 - loss 0.07146222 - time (sec): 97.22 - samples/sec: 1348.16 - lr: 0.000034 - momentum: 0.000000
2023-10-24 16:12:49,618 epoch 4 - iter 1782/1984 - loss 0.07238990 - time (sec): 109.30 - samples/sec: 1349.96 - lr: 0.000034 - momentum: 0.000000
2023-10-24 16:13:01,723 epoch 4 - iter 1980/1984 - loss 0.07174639 - time (sec): 121.41 - samples/sec: 1348.26 - lr: 0.000033 - momentum: 0.000000
2023-10-24 16:13:01,960 ----------------------------------------------------------------------------------------------------
2023-10-24 16:13:01,960 EPOCH 4 done: loss 0.0716 - lr: 0.000033
2023-10-24 16:13:05,387 DEV : loss 0.1819346696138382 - f1-score (micro avg)  0.7121
2023-10-24 16:13:05,402 ----------------------------------------------------------------------------------------------------
2023-10-24 16:13:17,704 epoch 5 - iter 198/1984 - loss 0.04521262 - time (sec): 12.30 - samples/sec: 1372.08 - lr: 0.000033 - momentum: 0.000000
2023-10-24 16:13:29,758 epoch 5 - iter 396/1984 - loss 0.04965805 - time (sec): 24.35 - samples/sec: 1333.01 - lr: 0.000032 - momentum: 0.000000
2023-10-24 16:13:42,101 epoch 5 - iter 594/1984 - loss 0.05396032 - time (sec): 36.70 - samples/sec: 1348.68 - lr: 0.000032 - momentum: 0.000000
2023-10-24 16:13:54,145 epoch 5 - iter 792/1984 - loss 0.05332345 - time (sec): 48.74 - samples/sec: 1336.01 - lr: 0.000031 - momentum: 0.000000
2023-10-24 16:14:06,219 epoch 5 - iter 990/1984 - loss 0.05289847 - time (sec): 60.82 - samples/sec: 1333.40 - lr: 0.000031 - momentum: 0.000000
2023-10-24 16:14:18,370 epoch 5 - iter 1188/1984 - loss 0.05257156 - time (sec): 72.97 - samples/sec: 1340.50 - lr: 0.000030 - momentum: 0.000000
2023-10-24 16:14:30,344 epoch 5 - iter 1386/1984 - loss 0.05371135 - time (sec): 84.94 - samples/sec: 1336.50 - lr: 0.000029 - momentum: 0.000000
2023-10-24 16:14:42,427 epoch 5 - iter 1584/1984 - loss 0.05289029 - time (sec): 97.02 - samples/sec: 1335.24 - lr: 0.000029 - momentum: 0.000000
2023-10-24 16:14:54,750 epoch 5 - iter 1782/1984 - loss 0.05253860 - time (sec): 109.35 - samples/sec: 1344.21 - lr: 0.000028 - momentum: 0.000000
2023-10-24 16:15:06,900 epoch 5 - iter 1980/1984 - loss 0.05342353 - time (sec): 121.50 - samples/sec: 1347.29 - lr: 0.000028 - momentum: 0.000000
2023-10-24 16:15:07,145 ----------------------------------------------------------------------------------------------------
2023-10-24 16:15:07,145 EPOCH 5 done: loss 0.0534 - lr: 0.000028
2023-10-24 16:15:10,265 DEV : loss 0.1831832379102707 - f1-score (micro avg)  0.7547
2023-10-24 16:15:10,281 saving best model
2023-10-24 16:15:10,863 ----------------------------------------------------------------------------------------------------
2023-10-24 16:15:22,992 epoch 6 - iter 198/1984 - loss 0.04237849 - time (sec): 12.13 - samples/sec: 1337.47 - lr: 0.000027 - momentum: 0.000000
2023-10-24 16:15:35,132 epoch 6 - iter 396/1984 - loss 0.04244041 - time (sec): 24.27 - samples/sec: 1330.21 - lr: 0.000027 - momentum: 0.000000
2023-10-24 16:15:47,336 epoch 6 - iter 594/1984 - loss 0.04119784 - time (sec): 36.47 - samples/sec: 1321.23 - lr: 0.000026 - momentum: 0.000000
2023-10-24 16:15:59,255 epoch 6 - iter 792/1984 - loss 0.03907748 - time (sec): 48.39 - samples/sec: 1322.25 - lr: 0.000026 - momentum: 0.000000
2023-10-24 16:16:11,471 epoch 6 - iter 990/1984 - loss 0.03932677 - time (sec): 60.61 - samples/sec: 1329.87 - lr: 0.000025 - momentum: 0.000000
2023-10-24 16:16:23,682 epoch 6 - iter 1188/1984 - loss 0.03914299 - time (sec): 72.82 - samples/sec: 1346.94 - lr: 0.000024 - momentum: 0.000000
2023-10-24 16:16:35,824 epoch 6 - iter 1386/1984 - loss 0.03960027 - time (sec): 84.96 - samples/sec: 1346.44 - lr: 0.000024 - momentum: 0.000000
2023-10-24 16:16:47,954 epoch 6 - iter 1584/1984 - loss 0.03955263 - time (sec): 97.09 - samples/sec: 1343.36 - lr: 0.000023 - momentum: 0.000000
2023-10-24 16:17:00,498 epoch 6 - iter 1782/1984 - loss 0.03906932 - time (sec): 109.63 - samples/sec: 1338.19 - lr: 0.000023 - momentum: 0.000000
2023-10-24 16:17:12,589 epoch 6 - iter 1980/1984 - loss 0.03897848 - time (sec): 121.73 - samples/sec: 1344.46 - lr: 0.000022 - momentum: 0.000000
2023-10-24 16:17:12,829 ----------------------------------------------------------------------------------------------------
2023-10-24 16:17:12,829 EPOCH 6 done: loss 0.0389 - lr: 0.000022
2023-10-24 16:17:15,940 DEV : loss 0.19957636296749115 - f1-score (micro avg)  0.7514
2023-10-24 16:17:15,955 ----------------------------------------------------------------------------------------------------
2023-10-24 16:17:28,168 epoch 7 - iter 198/1984 - loss 0.02502948 - time (sec): 12.21 - samples/sec: 1380.74 - lr: 0.000022 - momentum: 0.000000
2023-10-24 16:17:40,287 epoch 7 - iter 396/1984 - loss 0.02588075 - time (sec): 24.33 - samples/sec: 1401.14 - lr: 0.000021 - momentum: 0.000000
2023-10-24 16:17:52,407 epoch 7 - iter 594/1984 - loss 0.02615491 - time (sec): 36.45 - samples/sec: 1368.78 - lr: 0.000021 - momentum: 0.000000
2023-10-24 16:18:04,399 epoch 7 - iter 792/1984 - loss 0.02913086 - time (sec): 48.44 - samples/sec: 1355.33 - lr: 0.000020 - momentum: 0.000000
2023-10-24 16:18:16,592 epoch 7 - iter 990/1984 - loss 0.02832750 - time (sec): 60.64 - samples/sec: 1358.80 - lr: 0.000019 - momentum: 0.000000
2023-10-24 16:18:28,567 epoch 7 - iter 1188/1984 - loss 0.02868687 - time (sec): 72.61 - samples/sec: 1354.60 - lr: 0.000019 - momentum: 0.000000
2023-10-24 16:18:40,812 epoch 7 - iter 1386/1984 - loss 0.02776447 - time (sec): 84.86 - samples/sec: 1358.22 - lr: 0.000018 - momentum: 0.000000
2023-10-24 16:18:53,016 epoch 7 - iter 1584/1984 - loss 0.02756283 - time (sec): 97.06 - samples/sec: 1358.28 - lr: 0.000018 - momentum: 0.000000
2023-10-24 16:19:05,288 epoch 7 - iter 1782/1984 - loss 0.02799328 - time (sec): 109.33 - samples/sec: 1357.02 - lr: 0.000017 - momentum: 0.000000
2023-10-24 16:19:17,165 epoch 7 - iter 1980/1984 - loss 0.02831462 - time (sec): 121.21 - samples/sec: 1350.06 - lr: 0.000017 - momentum: 0.000000
2023-10-24 16:19:17,411 ----------------------------------------------------------------------------------------------------
2023-10-24 16:19:17,411 EPOCH 7 done: loss 0.0285 - lr: 0.000017
2023-10-24 16:19:20,522 DEV : loss 0.2192317098379135 - f1-score (micro avg)  0.752
2023-10-24 16:19:20,537 ----------------------------------------------------------------------------------------------------
2023-10-24 16:19:32,740 epoch 8 - iter 198/1984 - loss 0.01571927 - time (sec): 12.20 - samples/sec: 1352.95 - lr: 0.000016 - momentum: 0.000000
2023-10-24 16:19:45,022 epoch 8 - iter 396/1984 - loss 0.02057122 - time (sec): 24.48 - samples/sec: 1364.10 - lr: 0.000016 - momentum: 0.000000
2023-10-24 16:19:57,061 epoch 8 - iter 594/1984 - loss 0.02018865 - time (sec): 36.52 - samples/sec: 1354.89 - lr: 0.000015 - momentum: 0.000000
2023-10-24 16:20:09,359 epoch 8 - iter 792/1984 - loss 0.01942023 - time (sec): 48.82 - samples/sec: 1337.22 - lr: 0.000014 - momentum: 0.000000
2023-10-24 16:20:21,446 epoch 8 - iter 990/1984 - loss 0.01908064 - time (sec): 60.91 - samples/sec: 1341.88 - lr: 0.000014 - momentum: 0.000000
2023-10-24 16:20:33,588 epoch 8 - iter 1188/1984 - loss 0.01893982 - time (sec): 73.05 - samples/sec: 1344.69 - lr: 0.000013 - momentum: 0.000000
2023-10-24 16:20:45,658 epoch 8 - iter 1386/1984 - loss 0.01968258 - time (sec): 85.12 - samples/sec: 1345.13 - lr: 0.000013 - momentum: 0.000000
2023-10-24 16:20:57,835 epoch 8 - iter 1584/1984 - loss 0.01929883 - time (sec): 97.30 - samples/sec: 1347.10 - lr: 0.000012 - momentum: 0.000000
2023-10-24 16:21:09,932 epoch 8 - iter 1782/1984 - loss 0.01879306 - time (sec): 109.39 - samples/sec: 1350.71 - lr: 0.000012 - momentum: 0.000000
2023-10-24 16:21:22,126 epoch 8 - iter 1980/1984 - loss 0.01895222 - time (sec): 121.59 - samples/sec: 1346.49 - lr: 0.000011 - momentum: 0.000000
2023-10-24 16:21:22,360 ----------------------------------------------------------------------------------------------------
2023-10-24 16:21:22,360 EPOCH 8 done: loss 0.0189 - lr: 0.000011
2023-10-24 16:21:25,487 DEV : loss 0.22360068559646606 - f1-score (micro avg)  0.7521
2023-10-24 16:21:25,502 ----------------------------------------------------------------------------------------------------
2023-10-24 16:21:37,492 epoch 9 - iter 198/1984 - loss 0.01775440 - time (sec): 11.99 - samples/sec: 1336.38 - lr: 0.000011 - momentum: 0.000000
2023-10-24 16:21:49,622 epoch 9 - iter 396/1984 - loss 0.01720248 - time (sec): 24.12 - samples/sec: 1342.89 - lr: 0.000010 - momentum: 0.000000
2023-10-24 16:22:01,654 epoch 9 - iter 594/1984 - loss 0.01399946 - time (sec): 36.15 - samples/sec: 1334.74 - lr: 0.000009 - momentum: 0.000000
2023-10-24 16:22:13,714 epoch 9 - iter 792/1984 - loss 0.01448509 - time (sec): 48.21 - samples/sec: 1341.70 - lr: 0.000009 - momentum: 0.000000
2023-10-24 16:22:26,082 epoch 9 - iter 990/1984 - loss 0.01346876 - time (sec): 60.58 - samples/sec: 1345.87 - lr: 0.000008 - momentum: 0.000000
2023-10-24 16:22:38,079 epoch 9 - iter 1188/1984 - loss 0.01320978 - time (sec): 72.58 - samples/sec: 1341.53 - lr: 0.000008 - momentum: 0.000000
2023-10-24 16:22:50,327 epoch 9 - iter 1386/1984 - loss 0.01288739 - time (sec): 84.82 - samples/sec: 1337.84 - lr: 0.000007 - momentum: 0.000000
2023-10-24 16:23:02,743 epoch 9 - iter 1584/1984 - loss 0.01244493 - time (sec): 97.24 - samples/sec: 1346.31 - lr: 0.000007 - momentum: 0.000000
2023-10-24 16:23:14,948 epoch 9 - iter 1782/1984 - loss 0.01309784 - time (sec): 109.44 - samples/sec: 1352.32 - lr: 0.000006 - momentum: 0.000000
2023-10-24 16:23:27,037 epoch 9 - iter 1980/1984 - loss 0.01325666 - time (sec): 121.53 - samples/sec: 1347.10 - lr: 0.000006 - momentum: 0.000000
2023-10-24 16:23:27,275 ----------------------------------------------------------------------------------------------------
2023-10-24 16:23:27,275 EPOCH 9 done: loss 0.0132 - lr: 0.000006
2023-10-24 16:23:30,725 DEV : loss 0.23320023715496063 - f1-score (micro avg)  0.7554
2023-10-24 16:23:30,740 saving best model
2023-10-24 16:23:31,359 ----------------------------------------------------------------------------------------------------
2023-10-24 16:23:43,428 epoch 10 - iter 198/1984 - loss 0.01269146 - time (sec): 12.07 - samples/sec: 1382.28 - lr: 0.000005 - momentum: 0.000000
2023-10-24 16:23:55,427 epoch 10 - iter 396/1984 - loss 0.01140904 - time (sec): 24.07 - samples/sec: 1352.02 - lr: 0.000004 - momentum: 0.000000
2023-10-24 16:24:07,511 epoch 10 - iter 594/1984 - loss 0.01014037 - time (sec): 36.15 - samples/sec: 1356.57 - lr: 0.000004 - momentum: 0.000000
2023-10-24 16:24:20,208 epoch 10 - iter 792/1984 - loss 0.00961988 - time (sec): 48.85 - samples/sec: 1369.07 - lr: 0.000003 - momentum: 0.000000
2023-10-24 16:24:32,356 epoch 10 - iter 990/1984 - loss 0.00934250 - time (sec): 61.00 - samples/sec: 1360.44 - lr: 0.000003 - momentum: 0.000000
2023-10-24 16:24:44,568 epoch 10 - iter 1188/1984 - loss 0.00880262 - time (sec): 73.21 - samples/sec: 1366.91 - lr: 0.000002 - momentum: 0.000000
2023-10-24 16:24:56,562 epoch 10 - iter 1386/1984 - loss 0.00886579 - time (sec): 85.20 - samples/sec: 1360.69 - lr: 0.000002 - momentum: 0.000000
2023-10-24 16:25:08,616 epoch 10 - iter 1584/1984 - loss 0.00840621 - time (sec): 97.26 - samples/sec: 1364.15 - lr: 0.000001 - momentum: 0.000000
2023-10-24 16:25:20,602 epoch 10 - iter 1782/1984 - loss 0.00865685 - time (sec): 109.24 - samples/sec: 1355.92 - lr: 0.000001 - momentum: 0.000000
2023-10-24 16:25:32,569 epoch 10 - iter 1980/1984 - loss 0.00901465 - time (sec): 121.21 - samples/sec: 1349.08 - lr: 0.000000 - momentum: 0.000000
2023-10-24 16:25:32,857 ----------------------------------------------------------------------------------------------------
2023-10-24 16:25:32,857 EPOCH 10 done: loss 0.0090 - lr: 0.000000
2023-10-24 16:25:35,980 DEV : loss 0.25083112716674805 - f1-score (micro avg)  0.7613
2023-10-24 16:25:35,995 saving best model
2023-10-24 16:25:37,068 ----------------------------------------------------------------------------------------------------
2023-10-24 16:25:37,069 Loading model from best epoch ...
2023-10-24 16:25:38,537 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-24 16:25:41,628 
Results:
- F-score (micro) 0.779
- F-score (macro) 0.6989
- Accuracy 0.6605

By class:
              precision    recall  f1-score   support

         LOC     0.8326    0.8504    0.8414       655
         PER     0.6911    0.7623    0.7249       223
         ORG     0.5922    0.4803    0.5304       127

   micro avg     0.7741    0.7841    0.7790      1005
   macro avg     0.7053    0.6977    0.6989      1005
weighted avg     0.7708    0.7841    0.7763      1005

2023-10-24 16:25:41,628 ----------------------------------------------------------------------------------------------------