2023-10-25 12:28:37,998 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 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 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 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 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 Train:  14465 sentences
2023-10-25 12:28:37,999         (train_with_dev=False, train_with_test=False)
2023-10-25 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 Training Params:
2023-10-25 12:28:37,999  - learning_rate: "3e-05" 
2023-10-25 12:28:37,999  - mini_batch_size: "8"
2023-10-25 12:28:37,999  - max_epochs: "10"
2023-10-25 12:28:37,999  - shuffle: "True"
2023-10-25 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 Plugins:
2023-10-25 12:28:37,999  - TensorboardLogger
2023-10-25 12:28:37,999  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 12:28:37,999  - metric: "('micro avg', 'f1-score')"
2023-10-25 12:28:37,999 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:37,999 Computation:
2023-10-25 12:28:37,999  - compute on device: cuda:0
2023-10-25 12:28:37,999  - embedding storage: none
2023-10-25 12:28:38,000 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:38,000 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-25 12:28:38,000 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:38,000 ----------------------------------------------------------------------------------------------------
2023-10-25 12:28:38,000 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 12:28:53,436 epoch 1 - iter 180/1809 - loss 1.32066192 - time (sec): 15.44 - samples/sec: 2398.78 - lr: 0.000003 - momentum: 0.000000
2023-10-25 12:29:09,601 epoch 1 - iter 360/1809 - loss 0.75278801 - time (sec): 31.60 - samples/sec: 2431.30 - lr: 0.000006 - momentum: 0.000000
2023-10-25 12:29:25,308 epoch 1 - iter 540/1809 - loss 0.55980290 - time (sec): 47.31 - samples/sec: 2422.47 - lr: 0.000009 - momentum: 0.000000
2023-10-25 12:29:41,168 epoch 1 - iter 720/1809 - loss 0.45294865 - time (sec): 63.17 - samples/sec: 2423.46 - lr: 0.000012 - momentum: 0.000000
2023-10-25 12:29:57,000 epoch 1 - iter 900/1809 - loss 0.38916200 - time (sec): 79.00 - samples/sec: 2409.00 - lr: 0.000015 - momentum: 0.000000
2023-10-25 12:30:12,872 epoch 1 - iter 1080/1809 - loss 0.34304204 - time (sec): 94.87 - samples/sec: 2402.45 - lr: 0.000018 - momentum: 0.000000
2023-10-25 12:30:28,488 epoch 1 - iter 1260/1809 - loss 0.30889726 - time (sec): 110.49 - samples/sec: 2404.56 - lr: 0.000021 - momentum: 0.000000
2023-10-25 12:30:44,387 epoch 1 - iter 1440/1809 - loss 0.28449702 - time (sec): 126.39 - samples/sec: 2398.06 - lr: 0.000024 - momentum: 0.000000
2023-10-25 12:31:00,218 epoch 1 - iter 1620/1809 - loss 0.26437763 - time (sec): 142.22 - samples/sec: 2391.42 - lr: 0.000027 - momentum: 0.000000
2023-10-25 12:31:16,209 epoch 1 - iter 1800/1809 - loss 0.24798561 - time (sec): 158.21 - samples/sec: 2390.63 - lr: 0.000030 - momentum: 0.000000
2023-10-25 12:31:16,974 ----------------------------------------------------------------------------------------------------
2023-10-25 12:31:16,974 EPOCH 1 done: loss 0.2473 - lr: 0.000030
2023-10-25 12:31:21,487 DEV : loss 0.10075430572032928 - f1-score (micro avg)  0.6039
2023-10-25 12:31:21,509 saving best model
2023-10-25 12:31:22,067 ----------------------------------------------------------------------------------------------------
2023-10-25 12:31:37,430 epoch 2 - iter 180/1809 - loss 0.07768380 - time (sec): 15.36 - samples/sec: 2376.17 - lr: 0.000030 - momentum: 0.000000
2023-10-25 12:31:53,589 epoch 2 - iter 360/1809 - loss 0.07934728 - time (sec): 31.52 - samples/sec: 2340.48 - lr: 0.000029 - momentum: 0.000000
2023-10-25 12:32:09,858 epoch 2 - iter 540/1809 - loss 0.08305144 - time (sec): 47.79 - samples/sec: 2365.38 - lr: 0.000029 - momentum: 0.000000
2023-10-25 12:32:25,618 epoch 2 - iter 720/1809 - loss 0.08318685 - time (sec): 63.55 - samples/sec: 2375.08 - lr: 0.000029 - momentum: 0.000000
2023-10-25 12:32:41,497 epoch 2 - iter 900/1809 - loss 0.08289216 - time (sec): 79.43 - samples/sec: 2379.62 - lr: 0.000028 - momentum: 0.000000
2023-10-25 12:32:57,235 epoch 2 - iter 1080/1809 - loss 0.08295050 - time (sec): 95.17 - samples/sec: 2378.34 - lr: 0.000028 - momentum: 0.000000
2023-10-25 12:33:12,805 epoch 2 - iter 1260/1809 - loss 0.08218539 - time (sec): 110.74 - samples/sec: 2385.51 - lr: 0.000028 - momentum: 0.000000
2023-10-25 12:33:28,522 epoch 2 - iter 1440/1809 - loss 0.08166311 - time (sec): 126.45 - samples/sec: 2390.88 - lr: 0.000027 - momentum: 0.000000
2023-10-25 12:33:44,142 epoch 2 - iter 1620/1809 - loss 0.08087213 - time (sec): 142.07 - samples/sec: 2394.69 - lr: 0.000027 - momentum: 0.000000
2023-10-25 12:34:00,351 epoch 2 - iter 1800/1809 - loss 0.08180993 - time (sec): 158.28 - samples/sec: 2389.13 - lr: 0.000027 - momentum: 0.000000
2023-10-25 12:34:01,173 ----------------------------------------------------------------------------------------------------
2023-10-25 12:34:01,173 EPOCH 2 done: loss 0.0817 - lr: 0.000027
2023-10-25 12:34:06,428 DEV : loss 0.11919340491294861 - f1-score (micro avg)  0.6265
2023-10-25 12:34:06,451 saving best model
2023-10-25 12:34:07,159 ----------------------------------------------------------------------------------------------------
2023-10-25 12:34:22,732 epoch 3 - iter 180/1809 - loss 0.05754362 - time (sec): 15.57 - samples/sec: 2359.02 - lr: 0.000026 - momentum: 0.000000
2023-10-25 12:34:39,144 epoch 3 - iter 360/1809 - loss 0.05445932 - time (sec): 31.98 - samples/sec: 2359.41 - lr: 0.000026 - momentum: 0.000000
2023-10-25 12:34:55,128 epoch 3 - iter 540/1809 - loss 0.10839689 - time (sec): 47.97 - samples/sec: 2375.14 - lr: 0.000026 - momentum: 0.000000
2023-10-25 12:35:10,938 epoch 3 - iter 720/1809 - loss 0.11176576 - time (sec): 63.78 - samples/sec: 2398.12 - lr: 0.000025 - momentum: 0.000000
2023-10-25 12:35:26,644 epoch 3 - iter 900/1809 - loss 0.10133908 - time (sec): 79.48 - samples/sec: 2390.92 - lr: 0.000025 - momentum: 0.000000
2023-10-25 12:35:42,693 epoch 3 - iter 1080/1809 - loss 0.09494598 - time (sec): 95.53 - samples/sec: 2394.48 - lr: 0.000025 - momentum: 0.000000
2023-10-25 12:35:58,527 epoch 3 - iter 1260/1809 - loss 0.08876149 - time (sec): 111.37 - samples/sec: 2396.98 - lr: 0.000024 - momentum: 0.000000
2023-10-25 12:36:14,350 epoch 3 - iter 1440/1809 - loss 0.08488484 - time (sec): 127.19 - samples/sec: 2392.20 - lr: 0.000024 - momentum: 0.000000
2023-10-25 12:36:29,593 epoch 3 - iter 1620/1809 - loss 0.08167938 - time (sec): 142.43 - samples/sec: 2379.70 - lr: 0.000024 - momentum: 0.000000
2023-10-25 12:36:45,814 epoch 3 - iter 1800/1809 - loss 0.08095225 - time (sec): 158.65 - samples/sec: 2381.77 - lr: 0.000023 - momentum: 0.000000
2023-10-25 12:36:46,679 ----------------------------------------------------------------------------------------------------
2023-10-25 12:36:46,680 EPOCH 3 done: loss 0.0808 - lr: 0.000023
2023-10-25 12:36:51,961 DEV : loss 0.17484049499034882 - f1-score (micro avg)  0.6384
2023-10-25 12:36:51,984 saving best model
2023-10-25 12:36:52,764 ----------------------------------------------------------------------------------------------------
2023-10-25 12:37:08,603 epoch 4 - iter 180/1809 - loss 0.03876512 - time (sec): 15.84 - samples/sec: 2387.38 - lr: 0.000023 - momentum: 0.000000
2023-10-25 12:37:24,227 epoch 4 - iter 360/1809 - loss 0.03787875 - time (sec): 31.46 - samples/sec: 2389.93 - lr: 0.000023 - momentum: 0.000000
2023-10-25 12:37:40,405 epoch 4 - iter 540/1809 - loss 0.03825259 - time (sec): 47.64 - samples/sec: 2379.49 - lr: 0.000022 - momentum: 0.000000
2023-10-25 12:37:56,195 epoch 4 - iter 720/1809 - loss 0.03869128 - time (sec): 63.43 - samples/sec: 2376.11 - lr: 0.000022 - momentum: 0.000000
2023-10-25 12:38:12,183 epoch 4 - iter 900/1809 - loss 0.03899276 - time (sec): 79.42 - samples/sec: 2382.59 - lr: 0.000022 - momentum: 0.000000
2023-10-25 12:38:27,874 epoch 4 - iter 1080/1809 - loss 0.04024557 - time (sec): 95.11 - samples/sec: 2388.88 - lr: 0.000021 - momentum: 0.000000
2023-10-25 12:38:43,516 epoch 4 - iter 1260/1809 - loss 0.04175868 - time (sec): 110.75 - samples/sec: 2385.51 - lr: 0.000021 - momentum: 0.000000
2023-10-25 12:38:59,438 epoch 4 - iter 1440/1809 - loss 0.04172356 - time (sec): 126.67 - samples/sec: 2378.74 - lr: 0.000021 - momentum: 0.000000
2023-10-25 12:39:15,161 epoch 4 - iter 1620/1809 - loss 0.04187760 - time (sec): 142.40 - samples/sec: 2379.62 - lr: 0.000020 - momentum: 0.000000
2023-10-25 12:39:31,322 epoch 4 - iter 1800/1809 - loss 0.04269496 - time (sec): 158.56 - samples/sec: 2382.15 - lr: 0.000020 - momentum: 0.000000
2023-10-25 12:39:32,197 ----------------------------------------------------------------------------------------------------
2023-10-25 12:39:32,197 EPOCH 4 done: loss 0.0426 - lr: 0.000020
2023-10-25 12:39:36,946 DEV : loss 0.1871713101863861 - f1-score (micro avg)  0.617
2023-10-25 12:39:36,968 ----------------------------------------------------------------------------------------------------
2023-10-25 12:39:53,069 epoch 5 - iter 180/1809 - loss 0.02777427 - time (sec): 16.10 - samples/sec: 2334.53 - lr: 0.000020 - momentum: 0.000000
2023-10-25 12:40:09,463 epoch 5 - iter 360/1809 - loss 0.02582892 - time (sec): 32.49 - samples/sec: 2352.02 - lr: 0.000019 - momentum: 0.000000
2023-10-25 12:40:25,230 epoch 5 - iter 540/1809 - loss 0.02797722 - time (sec): 48.26 - samples/sec: 2376.31 - lr: 0.000019 - momentum: 0.000000
2023-10-25 12:40:40,871 epoch 5 - iter 720/1809 - loss 0.02666957 - time (sec): 63.90 - samples/sec: 2396.91 - lr: 0.000019 - momentum: 0.000000
2023-10-25 12:40:57,048 epoch 5 - iter 900/1809 - loss 0.02759579 - time (sec): 80.08 - samples/sec: 2390.81 - lr: 0.000018 - momentum: 0.000000
2023-10-25 12:41:12,856 epoch 5 - iter 1080/1809 - loss 0.02814669 - time (sec): 95.89 - samples/sec: 2387.46 - lr: 0.000018 - momentum: 0.000000
2023-10-25 12:41:28,645 epoch 5 - iter 1260/1809 - loss 0.02850952 - time (sec): 111.68 - samples/sec: 2385.17 - lr: 0.000018 - momentum: 0.000000
2023-10-25 12:41:44,229 epoch 5 - iter 1440/1809 - loss 0.02843264 - time (sec): 127.26 - samples/sec: 2391.30 - lr: 0.000017 - momentum: 0.000000
2023-10-25 12:41:59,925 epoch 5 - iter 1620/1809 - loss 0.02870411 - time (sec): 142.96 - samples/sec: 2387.86 - lr: 0.000017 - momentum: 0.000000
2023-10-25 12:42:15,858 epoch 5 - iter 1800/1809 - loss 0.02880197 - time (sec): 158.89 - samples/sec: 2381.32 - lr: 0.000017 - momentum: 0.000000
2023-10-25 12:42:16,584 ----------------------------------------------------------------------------------------------------
2023-10-25 12:42:16,584 EPOCH 5 done: loss 0.0287 - lr: 0.000017
2023-10-25 12:42:21,352 DEV : loss 0.2866155803203583 - f1-score (micro avg)  0.645
2023-10-25 12:42:21,375 saving best model
2023-10-25 12:42:22,152 ----------------------------------------------------------------------------------------------------
2023-10-25 12:42:38,353 epoch 6 - iter 180/1809 - loss 0.01495851 - time (sec): 16.20 - samples/sec: 2401.90 - lr: 0.000016 - momentum: 0.000000
2023-10-25 12:42:54,262 epoch 6 - iter 360/1809 - loss 0.01766455 - time (sec): 32.11 - samples/sec: 2369.80 - lr: 0.000016 - momentum: 0.000000
2023-10-25 12:43:09,989 epoch 6 - iter 540/1809 - loss 0.01859450 - time (sec): 47.84 - samples/sec: 2364.59 - lr: 0.000016 - momentum: 0.000000
2023-10-25 12:43:25,708 epoch 6 - iter 720/1809 - loss 0.01990834 - time (sec): 63.56 - samples/sec: 2393.20 - lr: 0.000015 - momentum: 0.000000
2023-10-25 12:43:41,465 epoch 6 - iter 900/1809 - loss 0.02012503 - time (sec): 79.31 - samples/sec: 2387.22 - lr: 0.000015 - momentum: 0.000000
2023-10-25 12:43:57,375 epoch 6 - iter 1080/1809 - loss 0.02035323 - time (sec): 95.22 - samples/sec: 2388.70 - lr: 0.000015 - momentum: 0.000000
2023-10-25 12:44:13,594 epoch 6 - iter 1260/1809 - loss 0.02009955 - time (sec): 111.44 - samples/sec: 2381.17 - lr: 0.000014 - momentum: 0.000000
2023-10-25 12:44:29,665 epoch 6 - iter 1440/1809 - loss 0.01997538 - time (sec): 127.51 - samples/sec: 2383.47 - lr: 0.000014 - momentum: 0.000000
2023-10-25 12:44:45,501 epoch 6 - iter 1620/1809 - loss 0.01992365 - time (sec): 143.35 - samples/sec: 2380.95 - lr: 0.000014 - momentum: 0.000000
2023-10-25 12:45:01,008 epoch 6 - iter 1800/1809 - loss 0.02013927 - time (sec): 158.86 - samples/sec: 2380.41 - lr: 0.000013 - momentum: 0.000000
2023-10-25 12:45:01,759 ----------------------------------------------------------------------------------------------------
2023-10-25 12:45:01,759 EPOCH 6 done: loss 0.0201 - lr: 0.000013
2023-10-25 12:45:06,544 DEV : loss 0.37807849049568176 - f1-score (micro avg)  0.6363
2023-10-25 12:45:06,567 ----------------------------------------------------------------------------------------------------
2023-10-25 12:45:22,138 epoch 7 - iter 180/1809 - loss 0.01284640 - time (sec): 15.57 - samples/sec: 2403.58 - lr: 0.000013 - momentum: 0.000000
2023-10-25 12:45:37,980 epoch 7 - iter 360/1809 - loss 0.01313214 - time (sec): 31.41 - samples/sec: 2372.35 - lr: 0.000013 - momentum: 0.000000
2023-10-25 12:45:53,544 epoch 7 - iter 540/1809 - loss 0.01317521 - time (sec): 46.98 - samples/sec: 2376.23 - lr: 0.000012 - momentum: 0.000000
2023-10-25 12:46:09,419 epoch 7 - iter 720/1809 - loss 0.01465604 - time (sec): 62.85 - samples/sec: 2375.28 - lr: 0.000012 - momentum: 0.000000
2023-10-25 12:46:25,283 epoch 7 - iter 900/1809 - loss 0.01445898 - time (sec): 78.72 - samples/sec: 2374.15 - lr: 0.000012 - momentum: 0.000000
2023-10-25 12:46:41,406 epoch 7 - iter 1080/1809 - loss 0.01378515 - time (sec): 94.84 - samples/sec: 2381.54 - lr: 0.000011 - momentum: 0.000000
2023-10-25 12:46:57,319 epoch 7 - iter 1260/1809 - loss 0.01405092 - time (sec): 110.75 - samples/sec: 2391.78 - lr: 0.000011 - momentum: 0.000000
2023-10-25 12:47:13,451 epoch 7 - iter 1440/1809 - loss 0.01485727 - time (sec): 126.88 - samples/sec: 2389.04 - lr: 0.000011 - momentum: 0.000000
2023-10-25 12:47:29,366 epoch 7 - iter 1620/1809 - loss 0.01448345 - time (sec): 142.80 - samples/sec: 2383.94 - lr: 0.000010 - momentum: 0.000000
2023-10-25 12:47:45,272 epoch 7 - iter 1800/1809 - loss 0.01468468 - time (sec): 158.70 - samples/sec: 2382.12 - lr: 0.000010 - momentum: 0.000000
2023-10-25 12:47:45,994 ----------------------------------------------------------------------------------------------------
2023-10-25 12:47:45,994 EPOCH 7 done: loss 0.0147 - lr: 0.000010
2023-10-25 12:47:51,314 DEV : loss 0.38382917642593384 - f1-score (micro avg)  0.6421
2023-10-25 12:47:51,337 ----------------------------------------------------------------------------------------------------
2023-10-25 12:48:07,499 epoch 8 - iter 180/1809 - loss 0.00759326 - time (sec): 16.16 - samples/sec: 2409.98 - lr: 0.000010 - momentum: 0.000000
2023-10-25 12:48:23,665 epoch 8 - iter 360/1809 - loss 0.00817682 - time (sec): 32.33 - samples/sec: 2351.45 - lr: 0.000009 - momentum: 0.000000
2023-10-25 12:48:39,685 epoch 8 - iter 540/1809 - loss 0.00774880 - time (sec): 48.35 - samples/sec: 2361.41 - lr: 0.000009 - momentum: 0.000000
2023-10-25 12:48:55,677 epoch 8 - iter 720/1809 - loss 0.00830876 - time (sec): 64.34 - samples/sec: 2375.37 - lr: 0.000009 - momentum: 0.000000
2023-10-25 12:49:11,519 epoch 8 - iter 900/1809 - loss 0.00898372 - time (sec): 80.18 - samples/sec: 2376.67 - lr: 0.000008 - momentum: 0.000000
2023-10-25 12:49:27,154 epoch 8 - iter 1080/1809 - loss 0.00905103 - time (sec): 95.82 - samples/sec: 2364.51 - lr: 0.000008 - momentum: 0.000000
2023-10-25 12:49:42,765 epoch 8 - iter 1260/1809 - loss 0.00901134 - time (sec): 111.43 - samples/sec: 2370.76 - lr: 0.000008 - momentum: 0.000000
2023-10-25 12:49:58,768 epoch 8 - iter 1440/1809 - loss 0.00911879 - time (sec): 127.43 - samples/sec: 2379.44 - lr: 0.000007 - momentum: 0.000000
2023-10-25 12:50:14,163 epoch 8 - iter 1620/1809 - loss 0.00980469 - time (sec): 142.83 - samples/sec: 2378.78 - lr: 0.000007 - momentum: 0.000000
2023-10-25 12:50:30,039 epoch 8 - iter 1800/1809 - loss 0.00951385 - time (sec): 158.70 - samples/sec: 2382.46 - lr: 0.000007 - momentum: 0.000000
2023-10-25 12:50:30,814 ----------------------------------------------------------------------------------------------------
2023-10-25 12:50:30,814 EPOCH 8 done: loss 0.0095 - lr: 0.000007
2023-10-25 12:50:36,114 DEV : loss 0.3850279152393341 - f1-score (micro avg)  0.6606
2023-10-25 12:50:36,137 saving best model
2023-10-25 12:50:36,798 ----------------------------------------------------------------------------------------------------
2023-10-25 12:50:52,245 epoch 9 - iter 180/1809 - loss 0.00647474 - time (sec): 15.45 - samples/sec: 2393.45 - lr: 0.000006 - momentum: 0.000000
2023-10-25 12:51:08,375 epoch 9 - iter 360/1809 - loss 0.00509171 - time (sec): 31.58 - samples/sec: 2400.18 - lr: 0.000006 - momentum: 0.000000
2023-10-25 12:51:24,236 epoch 9 - iter 540/1809 - loss 0.00664059 - time (sec): 47.44 - samples/sec: 2402.03 - lr: 0.000006 - momentum: 0.000000
2023-10-25 12:51:39,708 epoch 9 - iter 720/1809 - loss 0.00626044 - time (sec): 62.91 - samples/sec: 2395.19 - lr: 0.000005 - momentum: 0.000000
2023-10-25 12:51:55,581 epoch 9 - iter 900/1809 - loss 0.00660259 - time (sec): 78.78 - samples/sec: 2392.98 - lr: 0.000005 - momentum: 0.000000
2023-10-25 12:52:12,089 epoch 9 - iter 1080/1809 - loss 0.00656851 - time (sec): 95.29 - samples/sec: 2386.15 - lr: 0.000005 - momentum: 0.000000
2023-10-25 12:52:28,445 epoch 9 - iter 1260/1809 - loss 0.00630130 - time (sec): 111.65 - samples/sec: 2379.83 - lr: 0.000004 - momentum: 0.000000
2023-10-25 12:52:44,518 epoch 9 - iter 1440/1809 - loss 0.00621822 - time (sec): 127.72 - samples/sec: 2384.06 - lr: 0.000004 - momentum: 0.000000
2023-10-25 12:52:59,613 epoch 9 - iter 1620/1809 - loss 0.00603142 - time (sec): 142.81 - samples/sec: 2378.33 - lr: 0.000004 - momentum: 0.000000
2023-10-25 12:53:15,534 epoch 9 - iter 1800/1809 - loss 0.00568062 - time (sec): 158.73 - samples/sec: 2383.07 - lr: 0.000003 - momentum: 0.000000
2023-10-25 12:53:16,303 ----------------------------------------------------------------------------------------------------
2023-10-25 12:53:16,304 EPOCH 9 done: loss 0.0057 - lr: 0.000003
2023-10-25 12:53:21,631 DEV : loss 0.4284880757331848 - f1-score (micro avg)  0.6479
2023-10-25 12:53:21,654 ----------------------------------------------------------------------------------------------------
2023-10-25 12:53:37,461 epoch 10 - iter 180/1809 - loss 0.00257309 - time (sec): 15.81 - samples/sec: 2408.54 - lr: 0.000003 - momentum: 0.000000
2023-10-25 12:53:53,223 epoch 10 - iter 360/1809 - loss 0.00263089 - time (sec): 31.57 - samples/sec: 2405.48 - lr: 0.000003 - momentum: 0.000000
2023-10-25 12:54:09,057 epoch 10 - iter 540/1809 - loss 0.00294215 - time (sec): 47.40 - samples/sec: 2395.49 - lr: 0.000002 - momentum: 0.000000
2023-10-25 12:54:24,791 epoch 10 - iter 720/1809 - loss 0.00342558 - time (sec): 63.14 - samples/sec: 2387.73 - lr: 0.000002 - momentum: 0.000000
2023-10-25 12:54:40,381 epoch 10 - iter 900/1809 - loss 0.00403372 - time (sec): 78.73 - samples/sec: 2379.45 - lr: 0.000002 - momentum: 0.000000
2023-10-25 12:54:56,034 epoch 10 - iter 1080/1809 - loss 0.00393697 - time (sec): 94.38 - samples/sec: 2380.89 - lr: 0.000001 - momentum: 0.000000
2023-10-25 12:55:12,157 epoch 10 - iter 1260/1809 - loss 0.00409778 - time (sec): 110.50 - samples/sec: 2383.26 - lr: 0.000001 - momentum: 0.000000
2023-10-25 12:55:28,481 epoch 10 - iter 1440/1809 - loss 0.00378507 - time (sec): 126.83 - samples/sec: 2385.83 - lr: 0.000001 - momentum: 0.000000
2023-10-25 12:55:44,632 epoch 10 - iter 1620/1809 - loss 0.00378607 - time (sec): 142.98 - samples/sec: 2384.08 - lr: 0.000000 - momentum: 0.000000
2023-10-25 12:56:00,190 epoch 10 - iter 1800/1809 - loss 0.00380232 - time (sec): 158.54 - samples/sec: 2385.62 - lr: 0.000000 - momentum: 0.000000
2023-10-25 12:56:00,899 ----------------------------------------------------------------------------------------------------
2023-10-25 12:56:00,899 EPOCH 10 done: loss 0.0038 - lr: 0.000000
2023-10-25 12:56:06,221 DEV : loss 0.4174613654613495 - f1-score (micro avg)  0.6436
2023-10-25 12:56:06,807 ----------------------------------------------------------------------------------------------------
2023-10-25 12:56:06,808 Loading model from best epoch ...
2023-10-25 12:56:08,576 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 12:56:14,318 
Results:
- F-score (micro) 0.673
- F-score (macro) 0.5346
- Accuracy 0.5199

By class:
              precision    recall  f1-score   support

         loc     0.6676    0.7716    0.7159       591
        pers     0.6022    0.7675    0.6749       357
         org     0.3023    0.1646    0.2131        79

   micro avg     0.6291    0.7235    0.6730      1027
   macro avg     0.5241    0.5679    0.5346      1027
weighted avg     0.6168    0.7235    0.6629      1027

2023-10-25 12:56:14,318 ----------------------------------------------------------------------------------------------------