2023-10-24 15:13:44,762 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,763 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 15:13:44,763 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,763 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 15:13:44,763 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,763 Train:  7936 sentences
2023-10-24 15:13:44,763         (train_with_dev=False, train_with_test=False)
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Training Params:
2023-10-24 15:13:44,764  - learning_rate: "3e-05" 
2023-10-24 15:13:44,764  - mini_batch_size: "8"
2023-10-24 15:13:44,764  - max_epochs: "10"
2023-10-24 15:13:44,764  - shuffle: "True"
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Plugins:
2023-10-24 15:13:44,764  - TensorboardLogger
2023-10-24 15:13:44,764  - LinearScheduler | warmup_fraction: '0.1'
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Final evaluation on model from best epoch (best-model.pt)
2023-10-24 15:13:44,764  - metric: "('micro avg', 'f1-score')"
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Computation:
2023-10-24 15:13:44,764  - compute on device: cuda:0
2023-10-24 15:13:44,764  - embedding storage: none
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 ----------------------------------------------------------------------------------------------------
2023-10-24 15:13:44,764 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-24 15:13:52,870 epoch 1 - iter 99/992 - loss 2.00138499 - time (sec): 8.11 - samples/sec: 1940.03 - lr: 0.000003 - momentum: 0.000000
2023-10-24 15:14:00,756 epoch 1 - iter 198/992 - loss 1.19486555 - time (sec): 15.99 - samples/sec: 1939.90 - lr: 0.000006 - momentum: 0.000000
2023-10-24 15:14:08,909 epoch 1 - iter 297/992 - loss 0.87346403 - time (sec): 24.14 - samples/sec: 1963.76 - lr: 0.000009 - momentum: 0.000000
2023-10-24 15:14:17,064 epoch 1 - iter 396/992 - loss 0.69769156 - time (sec): 32.30 - samples/sec: 1961.48 - lr: 0.000012 - momentum: 0.000000
2023-10-24 15:14:25,604 epoch 1 - iter 495/992 - loss 0.58166806 - time (sec): 40.84 - samples/sec: 1973.97 - lr: 0.000015 - momentum: 0.000000
2023-10-24 15:14:33,994 epoch 1 - iter 594/992 - loss 0.50752231 - time (sec): 49.23 - samples/sec: 1971.55 - lr: 0.000018 - momentum: 0.000000
2023-10-24 15:14:42,580 epoch 1 - iter 693/992 - loss 0.45336096 - time (sec): 57.82 - samples/sec: 1963.72 - lr: 0.000021 - momentum: 0.000000
2023-10-24 15:14:51,243 epoch 1 - iter 792/992 - loss 0.41245068 - time (sec): 66.48 - samples/sec: 1965.17 - lr: 0.000024 - momentum: 0.000000
2023-10-24 15:14:59,630 epoch 1 - iter 891/992 - loss 0.38042237 - time (sec): 74.87 - samples/sec: 1966.67 - lr: 0.000027 - momentum: 0.000000
2023-10-24 15:15:07,967 epoch 1 - iter 990/992 - loss 0.35462009 - time (sec): 83.20 - samples/sec: 1967.35 - lr: 0.000030 - momentum: 0.000000
2023-10-24 15:15:08,132 ----------------------------------------------------------------------------------------------------
2023-10-24 15:15:08,132 EPOCH 1 done: loss 0.3542 - lr: 0.000030
2023-10-24 15:15:11,185 DEV : loss 0.0961548462510109 - f1-score (micro avg)  0.7105
2023-10-24 15:15:11,200 saving best model
2023-10-24 15:15:11,755 ----------------------------------------------------------------------------------------------------
2023-10-24 15:15:20,111 epoch 2 - iter 99/992 - loss 0.11640822 - time (sec): 8.35 - samples/sec: 2042.78 - lr: 0.000030 - momentum: 0.000000
2023-10-24 15:15:28,447 epoch 2 - iter 198/992 - loss 0.11616878 - time (sec): 16.69 - samples/sec: 2002.25 - lr: 0.000029 - momentum: 0.000000
2023-10-24 15:15:37,122 epoch 2 - iter 297/992 - loss 0.11115161 - time (sec): 25.37 - samples/sec: 2003.37 - lr: 0.000029 - momentum: 0.000000
2023-10-24 15:15:45,186 epoch 2 - iter 396/992 - loss 0.10710185 - time (sec): 33.43 - samples/sec: 2000.29 - lr: 0.000029 - momentum: 0.000000
2023-10-24 15:15:53,527 epoch 2 - iter 495/992 - loss 0.10512998 - time (sec): 41.77 - samples/sec: 1994.14 - lr: 0.000028 - momentum: 0.000000
2023-10-24 15:16:01,850 epoch 2 - iter 594/992 - loss 0.10552659 - time (sec): 50.09 - samples/sec: 1965.95 - lr: 0.000028 - momentum: 0.000000
2023-10-24 15:16:09,917 epoch 2 - iter 693/992 - loss 0.10493309 - time (sec): 58.16 - samples/sec: 1962.81 - lr: 0.000028 - momentum: 0.000000
2023-10-24 15:16:18,183 epoch 2 - iter 792/992 - loss 0.10434383 - time (sec): 66.43 - samples/sec: 1962.00 - lr: 0.000027 - momentum: 0.000000
2023-10-24 15:16:26,821 epoch 2 - iter 891/992 - loss 0.10270095 - time (sec): 75.07 - samples/sec: 1961.30 - lr: 0.000027 - momentum: 0.000000
2023-10-24 15:16:35,036 epoch 2 - iter 990/992 - loss 0.10121394 - time (sec): 83.28 - samples/sec: 1965.27 - lr: 0.000027 - momentum: 0.000000
2023-10-24 15:16:35,186 ----------------------------------------------------------------------------------------------------
2023-10-24 15:16:35,186 EPOCH 2 done: loss 0.1011 - lr: 0.000027
2023-10-24 15:16:38,599 DEV : loss 0.09430491924285889 - f1-score (micro avg)  0.7529
2023-10-24 15:16:38,614 saving best model
2023-10-24 15:16:39,338 ----------------------------------------------------------------------------------------------------
2023-10-24 15:16:47,529 epoch 3 - iter 99/992 - loss 0.06719236 - time (sec): 8.19 - samples/sec: 1940.21 - lr: 0.000026 - momentum: 0.000000
2023-10-24 15:16:55,855 epoch 3 - iter 198/992 - loss 0.06613133 - time (sec): 16.52 - samples/sec: 1993.65 - lr: 0.000026 - momentum: 0.000000
2023-10-24 15:17:04,381 epoch 3 - iter 297/992 - loss 0.06330398 - time (sec): 25.04 - samples/sec: 1985.65 - lr: 0.000026 - momentum: 0.000000
2023-10-24 15:17:12,671 epoch 3 - iter 396/992 - loss 0.06632455 - time (sec): 33.33 - samples/sec: 1960.17 - lr: 0.000025 - momentum: 0.000000
2023-10-24 15:17:20,731 epoch 3 - iter 495/992 - loss 0.07066014 - time (sec): 41.39 - samples/sec: 1959.36 - lr: 0.000025 - momentum: 0.000000
2023-10-24 15:17:29,327 epoch 3 - iter 594/992 - loss 0.07098366 - time (sec): 49.99 - samples/sec: 1951.79 - lr: 0.000025 - momentum: 0.000000
2023-10-24 15:17:37,244 epoch 3 - iter 693/992 - loss 0.07039656 - time (sec): 57.91 - samples/sec: 1953.94 - lr: 0.000024 - momentum: 0.000000
2023-10-24 15:17:45,665 epoch 3 - iter 792/992 - loss 0.06956794 - time (sec): 66.33 - samples/sec: 1960.93 - lr: 0.000024 - momentum: 0.000000
2023-10-24 15:17:53,989 epoch 3 - iter 891/992 - loss 0.06922567 - time (sec): 74.65 - samples/sec: 1958.25 - lr: 0.000024 - momentum: 0.000000
2023-10-24 15:18:02,727 epoch 3 - iter 990/992 - loss 0.06916264 - time (sec): 83.39 - samples/sec: 1961.66 - lr: 0.000023 - momentum: 0.000000
2023-10-24 15:18:02,917 ----------------------------------------------------------------------------------------------------
2023-10-24 15:18:02,917 EPOCH 3 done: loss 0.0693 - lr: 0.000023
2023-10-24 15:18:06,033 DEV : loss 0.0983629822731018 - f1-score (micro avg)  0.7488
2023-10-24 15:18:06,049 ----------------------------------------------------------------------------------------------------
2023-10-24 15:18:14,336 epoch 4 - iter 99/992 - loss 0.04434730 - time (sec): 8.29 - samples/sec: 2012.20 - lr: 0.000023 - momentum: 0.000000
2023-10-24 15:18:22,782 epoch 4 - iter 198/992 - loss 0.04085860 - time (sec): 16.73 - samples/sec: 1966.74 - lr: 0.000023 - momentum: 0.000000
2023-10-24 15:18:30,640 epoch 4 - iter 297/992 - loss 0.04207446 - time (sec): 24.59 - samples/sec: 1954.17 - lr: 0.000022 - momentum: 0.000000
2023-10-24 15:18:38,789 epoch 4 - iter 396/992 - loss 0.04681766 - time (sec): 32.74 - samples/sec: 1963.82 - lr: 0.000022 - momentum: 0.000000
2023-10-24 15:18:47,334 epoch 4 - iter 495/992 - loss 0.04857690 - time (sec): 41.29 - samples/sec: 1962.60 - lr: 0.000022 - momentum: 0.000000
2023-10-24 15:18:56,652 epoch 4 - iter 594/992 - loss 0.04806280 - time (sec): 50.60 - samples/sec: 1963.48 - lr: 0.000021 - momentum: 0.000000
2023-10-24 15:19:04,615 epoch 4 - iter 693/992 - loss 0.04657590 - time (sec): 58.57 - samples/sec: 1966.76 - lr: 0.000021 - momentum: 0.000000
2023-10-24 15:19:13,077 epoch 4 - iter 792/992 - loss 0.04774712 - time (sec): 67.03 - samples/sec: 1966.19 - lr: 0.000021 - momentum: 0.000000
2023-10-24 15:19:21,518 epoch 4 - iter 891/992 - loss 0.04815205 - time (sec): 75.47 - samples/sec: 1961.15 - lr: 0.000020 - momentum: 0.000000
2023-10-24 15:19:30,005 epoch 4 - iter 990/992 - loss 0.04916499 - time (sec): 83.96 - samples/sec: 1950.19 - lr: 0.000020 - momentum: 0.000000
2023-10-24 15:19:30,145 ----------------------------------------------------------------------------------------------------
2023-10-24 15:19:30,145 EPOCH 4 done: loss 0.0492 - lr: 0.000020
2023-10-24 15:19:33,266 DEV : loss 0.1186017319560051 - f1-score (micro avg)  0.766
2023-10-24 15:19:33,282 saving best model
2023-10-24 15:19:34,070 ----------------------------------------------------------------------------------------------------
2023-10-24 15:19:42,709 epoch 5 - iter 99/992 - loss 0.03958303 - time (sec): 8.64 - samples/sec: 1954.98 - lr: 0.000020 - momentum: 0.000000
2023-10-24 15:19:50,877 epoch 5 - iter 198/992 - loss 0.03820388 - time (sec): 16.81 - samples/sec: 1956.19 - lr: 0.000019 - momentum: 0.000000
2023-10-24 15:19:58,957 epoch 5 - iter 297/992 - loss 0.03759095 - time (sec): 24.89 - samples/sec: 1960.58 - lr: 0.000019 - momentum: 0.000000
2023-10-24 15:20:07,566 epoch 5 - iter 396/992 - loss 0.03671709 - time (sec): 33.49 - samples/sec: 1974.70 - lr: 0.000019 - momentum: 0.000000
2023-10-24 15:20:15,557 epoch 5 - iter 495/992 - loss 0.03795644 - time (sec): 41.49 - samples/sec: 1963.89 - lr: 0.000018 - momentum: 0.000000
2023-10-24 15:20:23,714 epoch 5 - iter 594/992 - loss 0.03754771 - time (sec): 49.64 - samples/sec: 1968.60 - lr: 0.000018 - momentum: 0.000000
2023-10-24 15:20:31,990 epoch 5 - iter 693/992 - loss 0.03701700 - time (sec): 57.92 - samples/sec: 1972.23 - lr: 0.000018 - momentum: 0.000000
2023-10-24 15:20:40,475 epoch 5 - iter 792/992 - loss 0.03754511 - time (sec): 66.40 - samples/sec: 1975.22 - lr: 0.000017 - momentum: 0.000000
2023-10-24 15:20:49,092 epoch 5 - iter 891/992 - loss 0.03754814 - time (sec): 75.02 - samples/sec: 1974.28 - lr: 0.000017 - momentum: 0.000000
2023-10-24 15:20:57,344 epoch 5 - iter 990/992 - loss 0.03819911 - time (sec): 83.27 - samples/sec: 1966.82 - lr: 0.000017 - momentum: 0.000000
2023-10-24 15:20:57,489 ----------------------------------------------------------------------------------------------------
2023-10-24 15:20:57,489 EPOCH 5 done: loss 0.0382 - lr: 0.000017
2023-10-24 15:21:00,612 DEV : loss 0.1500038057565689 - f1-score (micro avg)  0.7716
2023-10-24 15:21:00,627 saving best model
2023-10-24 15:21:01,415 ----------------------------------------------------------------------------------------------------
2023-10-24 15:21:09,674 epoch 6 - iter 99/992 - loss 0.02489554 - time (sec): 8.26 - samples/sec: 1944.65 - lr: 0.000016 - momentum: 0.000000
2023-10-24 15:21:17,831 epoch 6 - iter 198/992 - loss 0.02197168 - time (sec): 16.41 - samples/sec: 1969.28 - lr: 0.000016 - momentum: 0.000000
2023-10-24 15:21:26,440 epoch 6 - iter 297/992 - loss 0.02602124 - time (sec): 25.02 - samples/sec: 1970.79 - lr: 0.000016 - momentum: 0.000000
2023-10-24 15:21:34,700 epoch 6 - iter 396/992 - loss 0.02465442 - time (sec): 33.28 - samples/sec: 1958.95 - lr: 0.000015 - momentum: 0.000000
2023-10-24 15:21:43,130 epoch 6 - iter 495/992 - loss 0.02716845 - time (sec): 41.71 - samples/sec: 1975.40 - lr: 0.000015 - momentum: 0.000000
2023-10-24 15:21:51,299 epoch 6 - iter 594/992 - loss 0.02699725 - time (sec): 49.88 - samples/sec: 1977.15 - lr: 0.000015 - momentum: 0.000000
2023-10-24 15:21:59,606 epoch 6 - iter 693/992 - loss 0.02655613 - time (sec): 58.19 - samples/sec: 1976.09 - lr: 0.000014 - momentum: 0.000000
2023-10-24 15:22:07,766 epoch 6 - iter 792/992 - loss 0.02626525 - time (sec): 66.35 - samples/sec: 1973.44 - lr: 0.000014 - momentum: 0.000000
2023-10-24 15:22:16,581 epoch 6 - iter 891/992 - loss 0.02664702 - time (sec): 75.16 - samples/sec: 1956.18 - lr: 0.000014 - momentum: 0.000000
2023-10-24 15:22:25,007 epoch 6 - iter 990/992 - loss 0.02687875 - time (sec): 83.59 - samples/sec: 1959.53 - lr: 0.000013 - momentum: 0.000000
2023-10-24 15:22:25,140 ----------------------------------------------------------------------------------------------------
2023-10-24 15:22:25,140 EPOCH 6 done: loss 0.0269 - lr: 0.000013
2023-10-24 15:22:28,260 DEV : loss 0.18365593254566193 - f1-score (micro avg)  0.7675
2023-10-24 15:22:28,275 ----------------------------------------------------------------------------------------------------
2023-10-24 15:22:36,688 epoch 7 - iter 99/992 - loss 0.01924589 - time (sec): 8.41 - samples/sec: 2023.57 - lr: 0.000013 - momentum: 0.000000
2023-10-24 15:22:44,992 epoch 7 - iter 198/992 - loss 0.02187669 - time (sec): 16.72 - samples/sec: 1959.39 - lr: 0.000013 - momentum: 0.000000
2023-10-24 15:22:53,153 epoch 7 - iter 297/992 - loss 0.02145695 - time (sec): 24.88 - samples/sec: 1936.89 - lr: 0.000012 - momentum: 0.000000
2023-10-24 15:23:01,187 epoch 7 - iter 396/992 - loss 0.02078135 - time (sec): 32.91 - samples/sec: 1940.16 - lr: 0.000012 - momentum: 0.000000
2023-10-24 15:23:09,352 epoch 7 - iter 495/992 - loss 0.02110910 - time (sec): 41.08 - samples/sec: 1929.42 - lr: 0.000012 - momentum: 0.000000
2023-10-24 15:23:17,649 epoch 7 - iter 594/992 - loss 0.02248657 - time (sec): 49.37 - samples/sec: 1948.38 - lr: 0.000011 - momentum: 0.000000
2023-10-24 15:23:25,983 epoch 7 - iter 693/992 - loss 0.02223240 - time (sec): 57.71 - samples/sec: 1951.52 - lr: 0.000011 - momentum: 0.000000
2023-10-24 15:23:34,185 epoch 7 - iter 792/992 - loss 0.02177442 - time (sec): 65.91 - samples/sec: 1949.07 - lr: 0.000011 - momentum: 0.000000
2023-10-24 15:23:43,231 epoch 7 - iter 891/992 - loss 0.02152618 - time (sec): 74.95 - samples/sec: 1953.49 - lr: 0.000010 - momentum: 0.000000
2023-10-24 15:23:51,601 epoch 7 - iter 990/992 - loss 0.02140999 - time (sec): 83.33 - samples/sec: 1965.40 - lr: 0.000010 - momentum: 0.000000
2023-10-24 15:23:51,748 ----------------------------------------------------------------------------------------------------
2023-10-24 15:23:51,748 EPOCH 7 done: loss 0.0214 - lr: 0.000010
2023-10-24 15:23:54,863 DEV : loss 0.21153658628463745 - f1-score (micro avg)  0.7618
2023-10-24 15:23:54,878 ----------------------------------------------------------------------------------------------------
2023-10-24 15:24:03,108 epoch 8 - iter 99/992 - loss 0.01093374 - time (sec): 8.23 - samples/sec: 2004.96 - lr: 0.000010 - momentum: 0.000000
2023-10-24 15:24:11,138 epoch 8 - iter 198/992 - loss 0.01310924 - time (sec): 16.26 - samples/sec: 1936.95 - lr: 0.000009 - momentum: 0.000000
2023-10-24 15:24:19,358 epoch 8 - iter 297/992 - loss 0.01441408 - time (sec): 24.48 - samples/sec: 1940.68 - lr: 0.000009 - momentum: 0.000000
2023-10-24 15:24:28,043 epoch 8 - iter 396/992 - loss 0.01461590 - time (sec): 33.16 - samples/sec: 1935.65 - lr: 0.000009 - momentum: 0.000000
2023-10-24 15:24:36,832 epoch 8 - iter 495/992 - loss 0.01509641 - time (sec): 41.95 - samples/sec: 1945.22 - lr: 0.000008 - momentum: 0.000000
2023-10-24 15:24:45,127 epoch 8 - iter 594/992 - loss 0.01506859 - time (sec): 50.25 - samples/sec: 1947.58 - lr: 0.000008 - momentum: 0.000000
2023-10-24 15:24:54,112 epoch 8 - iter 693/992 - loss 0.01504122 - time (sec): 59.23 - samples/sec: 1956.47 - lr: 0.000008 - momentum: 0.000000
2023-10-24 15:25:02,153 epoch 8 - iter 792/992 - loss 0.01598623 - time (sec): 67.27 - samples/sec: 1948.08 - lr: 0.000007 - momentum: 0.000000
2023-10-24 15:25:10,479 epoch 8 - iter 891/992 - loss 0.01625220 - time (sec): 75.60 - samples/sec: 1952.55 - lr: 0.000007 - momentum: 0.000000
2023-10-24 15:25:18,505 epoch 8 - iter 990/992 - loss 0.01634153 - time (sec): 83.63 - samples/sec: 1955.26 - lr: 0.000007 - momentum: 0.000000
2023-10-24 15:25:18,705 ----------------------------------------------------------------------------------------------------
2023-10-24 15:25:18,706 EPOCH 8 done: loss 0.0163 - lr: 0.000007
2023-10-24 15:25:21,824 DEV : loss 0.214664027094841 - f1-score (micro avg)  0.7641
2023-10-24 15:25:21,839 ----------------------------------------------------------------------------------------------------
2023-10-24 15:25:30,320 epoch 9 - iter 99/992 - loss 0.00554736 - time (sec): 8.48 - samples/sec: 2033.00 - lr: 0.000006 - momentum: 0.000000
2023-10-24 15:25:38,987 epoch 9 - iter 198/992 - loss 0.00828502 - time (sec): 17.15 - samples/sec: 1982.71 - lr: 0.000006 - momentum: 0.000000
2023-10-24 15:25:47,155 epoch 9 - iter 297/992 - loss 0.00991386 - time (sec): 25.32 - samples/sec: 1992.59 - lr: 0.000006 - momentum: 0.000000
2023-10-24 15:25:55,662 epoch 9 - iter 396/992 - loss 0.00972216 - time (sec): 33.82 - samples/sec: 1976.94 - lr: 0.000005 - momentum: 0.000000
2023-10-24 15:26:03,891 epoch 9 - iter 495/992 - loss 0.00993347 - time (sec): 42.05 - samples/sec: 1975.37 - lr: 0.000005 - momentum: 0.000000
2023-10-24 15:26:12,678 epoch 9 - iter 594/992 - loss 0.01064234 - time (sec): 50.84 - samples/sec: 1976.16 - lr: 0.000005 - momentum: 0.000000
2023-10-24 15:26:20,744 epoch 9 - iter 693/992 - loss 0.01059840 - time (sec): 58.90 - samples/sec: 1972.26 - lr: 0.000004 - momentum: 0.000000
2023-10-24 15:26:28,796 epoch 9 - iter 792/992 - loss 0.01094734 - time (sec): 66.96 - samples/sec: 1967.66 - lr: 0.000004 - momentum: 0.000000
2023-10-24 15:26:36,898 epoch 9 - iter 891/992 - loss 0.01069492 - time (sec): 75.06 - samples/sec: 1964.87 - lr: 0.000004 - momentum: 0.000000
2023-10-24 15:26:45,130 epoch 9 - iter 990/992 - loss 0.01088973 - time (sec): 83.29 - samples/sec: 1965.18 - lr: 0.000003 - momentum: 0.000000
2023-10-24 15:26:45,309 ----------------------------------------------------------------------------------------------------
2023-10-24 15:26:45,309 EPOCH 9 done: loss 0.0109 - lr: 0.000003
2023-10-24 15:26:48,428 DEV : loss 0.22701114416122437 - f1-score (micro avg)  0.7697
2023-10-24 15:26:48,443 ----------------------------------------------------------------------------------------------------
2023-10-24 15:26:56,446 epoch 10 - iter 99/992 - loss 0.00704755 - time (sec): 8.00 - samples/sec: 1986.71 - lr: 0.000003 - momentum: 0.000000
2023-10-24 15:27:04,484 epoch 10 - iter 198/992 - loss 0.00802891 - time (sec): 16.04 - samples/sec: 1989.28 - lr: 0.000003 - momentum: 0.000000
2023-10-24 15:27:13,149 epoch 10 - iter 297/992 - loss 0.00713159 - time (sec): 24.71 - samples/sec: 2001.01 - lr: 0.000002 - momentum: 0.000000
2023-10-24 15:27:21,521 epoch 10 - iter 396/992 - loss 0.00689762 - time (sec): 33.08 - samples/sec: 1985.90 - lr: 0.000002 - momentum: 0.000000
2023-10-24 15:27:29,824 epoch 10 - iter 495/992 - loss 0.00714780 - time (sec): 41.38 - samples/sec: 1986.04 - lr: 0.000002 - momentum: 0.000000
2023-10-24 15:27:38,100 epoch 10 - iter 594/992 - loss 0.00737894 - time (sec): 49.66 - samples/sec: 1992.26 - lr: 0.000001 - momentum: 0.000000
2023-10-24 15:27:46,622 epoch 10 - iter 693/992 - loss 0.00692848 - time (sec): 58.18 - samples/sec: 1969.53 - lr: 0.000001 - momentum: 0.000000
2023-10-24 15:27:54,981 epoch 10 - iter 792/992 - loss 0.00716748 - time (sec): 66.54 - samples/sec: 1965.85 - lr: 0.000001 - momentum: 0.000000
2023-10-24 15:28:03,371 epoch 10 - iter 891/992 - loss 0.00737072 - time (sec): 74.93 - samples/sec: 1964.65 - lr: 0.000000 - momentum: 0.000000
2023-10-24 15:28:11,754 epoch 10 - iter 990/992 - loss 0.00752842 - time (sec): 83.31 - samples/sec: 1962.95 - lr: 0.000000 - momentum: 0.000000
2023-10-24 15:28:11,961 ----------------------------------------------------------------------------------------------------
2023-10-24 15:28:11,961 EPOCH 10 done: loss 0.0076 - lr: 0.000000
2023-10-24 15:28:15,064 DEV : loss 0.23377303779125214 - f1-score (micro avg)  0.7682
2023-10-24 15:28:15,642 ----------------------------------------------------------------------------------------------------
2023-10-24 15:28:15,642 Loading model from best epoch ...
2023-10-24 15:28:17,450 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 15:28:20,523 
Results:
- F-score (micro) 0.7766
- F-score (macro) 0.7019
- Accuracy 0.6524

By class:
              precision    recall  f1-score   support

         LOC     0.8214    0.8214    0.8214       655
         PER     0.7339    0.8161    0.7728       223
         ORG     0.6250    0.4331    0.5116       127

   micro avg     0.7820    0.7711    0.7766      1005
   macro avg     0.7267    0.6902    0.7019      1005
weighted avg     0.7771    0.7711    0.7715      1005

2023-10-24 15:28:20,523 ----------------------------------------------------------------------------------------------------