2023-10-25 17:25:12,830 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,831 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 17:25:12,831 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 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 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Train:  14465 sentences
2023-10-25 17:25:12,832         (train_with_dev=False, train_with_test=False)
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Training Params:
2023-10-25 17:25:12,832  - learning_rate: "5e-05" 
2023-10-25 17:25:12,832  - mini_batch_size: "8"
2023-10-25 17:25:12,832  - max_epochs: "10"
2023-10-25 17:25:12,832  - shuffle: "True"
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Plugins:
2023-10-25 17:25:12,832  - TensorboardLogger
2023-10-25 17:25:12,832  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 17:25:12,832  - metric: "('micro avg', 'f1-score')"
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Computation:
2023-10-25 17:25:12,832  - compute on device: cuda:0
2023-10-25 17:25:12,832  - embedding storage: none
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 ----------------------------------------------------------------------------------------------------
2023-10-25 17:25:12,832 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 17:25:28,883 epoch 1 - iter 180/1809 - loss 1.08867170 - time (sec): 16.05 - samples/sec: 2407.65 - lr: 0.000005 - momentum: 0.000000
2023-10-25 17:25:44,521 epoch 1 - iter 360/1809 - loss 0.65004327 - time (sec): 31.69 - samples/sec: 2416.98 - lr: 0.000010 - momentum: 0.000000
2023-10-25 17:26:00,346 epoch 1 - iter 540/1809 - loss 0.48753569 - time (sec): 47.51 - samples/sec: 2407.41 - lr: 0.000015 - momentum: 0.000000
2023-10-25 17:26:15,761 epoch 1 - iter 720/1809 - loss 0.39766425 - time (sec): 62.93 - samples/sec: 2421.92 - lr: 0.000020 - momentum: 0.000000
2023-10-25 17:26:31,459 epoch 1 - iter 900/1809 - loss 0.34169738 - time (sec): 78.63 - samples/sec: 2408.69 - lr: 0.000025 - momentum: 0.000000
2023-10-25 17:26:47,241 epoch 1 - iter 1080/1809 - loss 0.30530543 - time (sec): 94.41 - samples/sec: 2400.17 - lr: 0.000030 - momentum: 0.000000
2023-10-25 17:27:03,504 epoch 1 - iter 1260/1809 - loss 0.27539034 - time (sec): 110.67 - samples/sec: 2397.75 - lr: 0.000035 - momentum: 0.000000
2023-10-25 17:27:19,006 epoch 1 - iter 1440/1809 - loss 0.25487372 - time (sec): 126.17 - samples/sec: 2394.96 - lr: 0.000040 - momentum: 0.000000
2023-10-25 17:27:35,047 epoch 1 - iter 1620/1809 - loss 0.23807391 - time (sec): 142.21 - samples/sec: 2389.53 - lr: 0.000045 - momentum: 0.000000
2023-10-25 17:27:51,142 epoch 1 - iter 1800/1809 - loss 0.22438103 - time (sec): 158.31 - samples/sec: 2389.71 - lr: 0.000050 - momentum: 0.000000
2023-10-25 17:27:51,843 ----------------------------------------------------------------------------------------------------
2023-10-25 17:27:51,843 EPOCH 1 done: loss 0.2237 - lr: 0.000050
2023-10-25 17:27:56,354 DEV : loss 0.11131972819566727 - f1-score (micro avg)  0.5998
2023-10-25 17:27:56,377 saving best model
2023-10-25 17:27:56,928 ----------------------------------------------------------------------------------------------------
2023-10-25 17:28:12,813 epoch 2 - iter 180/1809 - loss 0.08088650 - time (sec): 15.88 - samples/sec: 2358.09 - lr: 0.000049 - momentum: 0.000000
2023-10-25 17:28:28,596 epoch 2 - iter 360/1809 - loss 0.08543964 - time (sec): 31.67 - samples/sec: 2357.98 - lr: 0.000049 - momentum: 0.000000
2023-10-25 17:28:44,265 epoch 2 - iter 540/1809 - loss 0.08544855 - time (sec): 47.34 - samples/sec: 2378.99 - lr: 0.000048 - momentum: 0.000000
2023-10-25 17:28:59,984 epoch 2 - iter 720/1809 - loss 0.08766095 - time (sec): 63.06 - samples/sec: 2384.45 - lr: 0.000048 - momentum: 0.000000
2023-10-25 17:29:16,164 epoch 2 - iter 900/1809 - loss 0.08687484 - time (sec): 79.23 - samples/sec: 2399.84 - lr: 0.000047 - momentum: 0.000000
2023-10-25 17:29:31,913 epoch 2 - iter 1080/1809 - loss 0.08737062 - time (sec): 94.98 - samples/sec: 2401.58 - lr: 0.000047 - momentum: 0.000000
2023-10-25 17:29:47,549 epoch 2 - iter 1260/1809 - loss 0.08575598 - time (sec): 110.62 - samples/sec: 2399.66 - lr: 0.000046 - momentum: 0.000000
2023-10-25 17:30:03,603 epoch 2 - iter 1440/1809 - loss 0.08550450 - time (sec): 126.67 - samples/sec: 2395.66 - lr: 0.000046 - momentum: 0.000000
2023-10-25 17:30:19,491 epoch 2 - iter 1620/1809 - loss 0.08602069 - time (sec): 142.56 - samples/sec: 2392.68 - lr: 0.000045 - momentum: 0.000000
2023-10-25 17:30:35,371 epoch 2 - iter 1800/1809 - loss 0.08584415 - time (sec): 158.44 - samples/sec: 2389.42 - lr: 0.000044 - momentum: 0.000000
2023-10-25 17:30:36,066 ----------------------------------------------------------------------------------------------------
2023-10-25 17:30:36,066 EPOCH 2 done: loss 0.0859 - lr: 0.000044
2023-10-25 17:30:41,320 DEV : loss 0.14367857575416565 - f1-score (micro avg)  0.621
2023-10-25 17:30:41,343 saving best model
2023-10-25 17:30:42,046 ----------------------------------------------------------------------------------------------------
2023-10-25 17:30:57,826 epoch 3 - iter 180/1809 - loss 0.06105910 - time (sec): 15.78 - samples/sec: 2444.97 - lr: 0.000044 - momentum: 0.000000
2023-10-25 17:31:14,553 epoch 3 - iter 360/1809 - loss 0.06291567 - time (sec): 32.51 - samples/sec: 2454.20 - lr: 0.000043 - momentum: 0.000000
2023-10-25 17:31:30,567 epoch 3 - iter 540/1809 - loss 0.05939069 - time (sec): 48.52 - samples/sec: 2434.77 - lr: 0.000043 - momentum: 0.000000
2023-10-25 17:31:46,426 epoch 3 - iter 720/1809 - loss 0.06189798 - time (sec): 64.38 - samples/sec: 2420.88 - lr: 0.000042 - momentum: 0.000000
2023-10-25 17:32:02,072 epoch 3 - iter 900/1809 - loss 0.06226376 - time (sec): 80.02 - samples/sec: 2408.22 - lr: 0.000042 - momentum: 0.000000
2023-10-25 17:32:17,628 epoch 3 - iter 1080/1809 - loss 0.06229431 - time (sec): 95.58 - samples/sec: 2403.38 - lr: 0.000041 - momentum: 0.000000
2023-10-25 17:32:33,396 epoch 3 - iter 1260/1809 - loss 0.06309156 - time (sec): 111.35 - samples/sec: 2401.39 - lr: 0.000041 - momentum: 0.000000
2023-10-25 17:32:49,252 epoch 3 - iter 1440/1809 - loss 0.06334011 - time (sec): 127.20 - samples/sec: 2389.92 - lr: 0.000040 - momentum: 0.000000
2023-10-25 17:33:05,170 epoch 3 - iter 1620/1809 - loss 0.06299930 - time (sec): 143.12 - samples/sec: 2384.04 - lr: 0.000039 - momentum: 0.000000
2023-10-25 17:33:20,601 epoch 3 - iter 1800/1809 - loss 0.06268902 - time (sec): 158.55 - samples/sec: 2385.99 - lr: 0.000039 - momentum: 0.000000
2023-10-25 17:33:21,442 ----------------------------------------------------------------------------------------------------
2023-10-25 17:33:21,442 EPOCH 3 done: loss 0.0626 - lr: 0.000039
2023-10-25 17:33:26,209 DEV : loss 0.16750071942806244 - f1-score (micro avg)  0.6271
2023-10-25 17:33:26,232 saving best model
2023-10-25 17:33:27,448 ----------------------------------------------------------------------------------------------------
2023-10-25 17:33:43,590 epoch 4 - iter 180/1809 - loss 0.04454260 - time (sec): 16.14 - samples/sec: 2370.51 - lr: 0.000038 - momentum: 0.000000
2023-10-25 17:33:59,289 epoch 4 - iter 360/1809 - loss 0.04376843 - time (sec): 31.84 - samples/sec: 2384.31 - lr: 0.000038 - momentum: 0.000000
2023-10-25 17:34:15,317 epoch 4 - iter 540/1809 - loss 0.04208892 - time (sec): 47.87 - samples/sec: 2401.85 - lr: 0.000037 - momentum: 0.000000
2023-10-25 17:34:31,148 epoch 4 - iter 720/1809 - loss 0.04219370 - time (sec): 63.70 - samples/sec: 2412.85 - lr: 0.000037 - momentum: 0.000000
2023-10-25 17:34:46,949 epoch 4 - iter 900/1809 - loss 0.04300031 - time (sec): 79.50 - samples/sec: 2412.83 - lr: 0.000036 - momentum: 0.000000
2023-10-25 17:35:02,757 epoch 4 - iter 1080/1809 - loss 0.04422396 - time (sec): 95.31 - samples/sec: 2397.75 - lr: 0.000036 - momentum: 0.000000
2023-10-25 17:35:18,399 epoch 4 - iter 1260/1809 - loss 0.04338815 - time (sec): 110.95 - samples/sec: 2391.32 - lr: 0.000035 - momentum: 0.000000
2023-10-25 17:35:34,237 epoch 4 - iter 1440/1809 - loss 0.04365612 - time (sec): 126.79 - samples/sec: 2388.41 - lr: 0.000034 - momentum: 0.000000
2023-10-25 17:35:49,818 epoch 4 - iter 1620/1809 - loss 0.04436943 - time (sec): 142.37 - samples/sec: 2386.02 - lr: 0.000034 - momentum: 0.000000
2023-10-25 17:36:05,768 epoch 4 - iter 1800/1809 - loss 0.04471372 - time (sec): 158.32 - samples/sec: 2388.70 - lr: 0.000033 - momentum: 0.000000
2023-10-25 17:36:06,615 ----------------------------------------------------------------------------------------------------
2023-10-25 17:36:06,615 EPOCH 4 done: loss 0.0448 - lr: 0.000033
2023-10-25 17:36:11,377 DEV : loss 0.21365126967430115 - f1-score (micro avg)  0.6119
2023-10-25 17:36:11,400 ----------------------------------------------------------------------------------------------------
2023-10-25 17:36:27,342 epoch 5 - iter 180/1809 - loss 0.02797797 - time (sec): 15.94 - samples/sec: 2446.04 - lr: 0.000033 - momentum: 0.000000
2023-10-25 17:36:43,491 epoch 5 - iter 360/1809 - loss 0.02861473 - time (sec): 32.09 - samples/sec: 2410.53 - lr: 0.000032 - momentum: 0.000000
2023-10-25 17:36:59,285 epoch 5 - iter 540/1809 - loss 0.02970454 - time (sec): 47.88 - samples/sec: 2406.82 - lr: 0.000032 - momentum: 0.000000
2023-10-25 17:37:14,595 epoch 5 - iter 720/1809 - loss 0.03017154 - time (sec): 63.19 - samples/sec: 2383.00 - lr: 0.000031 - momentum: 0.000000
2023-10-25 17:37:30,823 epoch 5 - iter 900/1809 - loss 0.02993842 - time (sec): 79.42 - samples/sec: 2390.07 - lr: 0.000031 - momentum: 0.000000
2023-10-25 17:37:47,071 epoch 5 - iter 1080/1809 - loss 0.03036229 - time (sec): 95.67 - samples/sec: 2389.07 - lr: 0.000030 - momentum: 0.000000
2023-10-25 17:38:02,683 epoch 5 - iter 1260/1809 - loss 0.03032083 - time (sec): 111.28 - samples/sec: 2380.89 - lr: 0.000029 - momentum: 0.000000
2023-10-25 17:38:18,242 epoch 5 - iter 1440/1809 - loss 0.03017265 - time (sec): 126.84 - samples/sec: 2381.62 - lr: 0.000029 - momentum: 0.000000
2023-10-25 17:38:34,319 epoch 5 - iter 1620/1809 - loss 0.03017571 - time (sec): 142.92 - samples/sec: 2368.45 - lr: 0.000028 - momentum: 0.000000
2023-10-25 17:38:50,611 epoch 5 - iter 1800/1809 - loss 0.02982099 - time (sec): 159.21 - samples/sec: 2376.76 - lr: 0.000028 - momentum: 0.000000
2023-10-25 17:38:51,342 ----------------------------------------------------------------------------------------------------
2023-10-25 17:38:51,342 EPOCH 5 done: loss 0.0299 - lr: 0.000028
2023-10-25 17:38:56,115 DEV : loss 0.2786865830421448 - f1-score (micro avg)  0.6472
2023-10-25 17:38:56,139 saving best model
2023-10-25 17:38:56,860 ----------------------------------------------------------------------------------------------------
2023-10-25 17:39:12,505 epoch 6 - iter 180/1809 - loss 0.01698871 - time (sec): 15.64 - samples/sec: 2353.61 - lr: 0.000027 - momentum: 0.000000
2023-10-25 17:39:28,137 epoch 6 - iter 360/1809 - loss 0.01883337 - time (sec): 31.28 - samples/sec: 2382.83 - lr: 0.000027 - momentum: 0.000000
2023-10-25 17:39:44,244 epoch 6 - iter 540/1809 - loss 0.02197274 - time (sec): 47.38 - samples/sec: 2391.47 - lr: 0.000026 - momentum: 0.000000
2023-10-25 17:39:59,902 epoch 6 - iter 720/1809 - loss 0.02290012 - time (sec): 63.04 - samples/sec: 2395.80 - lr: 0.000026 - momentum: 0.000000
2023-10-25 17:40:16,174 epoch 6 - iter 900/1809 - loss 0.02254507 - time (sec): 79.31 - samples/sec: 2378.20 - lr: 0.000025 - momentum: 0.000000
2023-10-25 17:40:31,791 epoch 6 - iter 1080/1809 - loss 0.02233300 - time (sec): 94.93 - samples/sec: 2375.99 - lr: 0.000024 - momentum: 0.000000
2023-10-25 17:40:47,376 epoch 6 - iter 1260/1809 - loss 0.02223982 - time (sec): 110.51 - samples/sec: 2371.40 - lr: 0.000024 - momentum: 0.000000
2023-10-25 17:41:03,399 epoch 6 - iter 1440/1809 - loss 0.02230768 - time (sec): 126.54 - samples/sec: 2379.75 - lr: 0.000023 - momentum: 0.000000
2023-10-25 17:41:19,391 epoch 6 - iter 1620/1809 - loss 0.02169893 - time (sec): 142.53 - samples/sec: 2382.79 - lr: 0.000023 - momentum: 0.000000
2023-10-25 17:41:35,589 epoch 6 - iter 1800/1809 - loss 0.02156452 - time (sec): 158.73 - samples/sec: 2382.82 - lr: 0.000022 - momentum: 0.000000
2023-10-25 17:41:36,334 ----------------------------------------------------------------------------------------------------
2023-10-25 17:41:36,334 EPOCH 6 done: loss 0.0216 - lr: 0.000022
2023-10-25 17:41:41,614 DEV : loss 0.36510854959487915 - f1-score (micro avg)  0.6298
2023-10-25 17:41:41,637 ----------------------------------------------------------------------------------------------------
2023-10-25 17:41:57,608 epoch 7 - iter 180/1809 - loss 0.02022287 - time (sec): 15.97 - samples/sec: 2400.72 - lr: 0.000022 - momentum: 0.000000
2023-10-25 17:42:13,475 epoch 7 - iter 360/1809 - loss 0.02033749 - time (sec): 31.84 - samples/sec: 2400.51 - lr: 0.000021 - momentum: 0.000000
2023-10-25 17:42:29,613 epoch 7 - iter 540/1809 - loss 0.02001745 - time (sec): 47.98 - samples/sec: 2407.10 - lr: 0.000021 - momentum: 0.000000
2023-10-25 17:42:45,451 epoch 7 - iter 720/1809 - loss 0.01848045 - time (sec): 63.81 - samples/sec: 2415.31 - lr: 0.000020 - momentum: 0.000000
2023-10-25 17:43:00,702 epoch 7 - iter 900/1809 - loss 0.01690827 - time (sec): 79.06 - samples/sec: 2403.90 - lr: 0.000019 - momentum: 0.000000
2023-10-25 17:43:16,683 epoch 7 - iter 1080/1809 - loss 0.01639987 - time (sec): 95.05 - samples/sec: 2384.14 - lr: 0.000019 - momentum: 0.000000
2023-10-25 17:43:32,462 epoch 7 - iter 1260/1809 - loss 0.01694441 - time (sec): 110.82 - samples/sec: 2375.78 - lr: 0.000018 - momentum: 0.000000
2023-10-25 17:43:48,583 epoch 7 - iter 1440/1809 - loss 0.01604881 - time (sec): 126.95 - samples/sec: 2373.46 - lr: 0.000018 - momentum: 0.000000
2023-10-25 17:44:04,373 epoch 7 - iter 1620/1809 - loss 0.01596925 - time (sec): 142.74 - samples/sec: 2380.20 - lr: 0.000017 - momentum: 0.000000
2023-10-25 17:44:20,312 epoch 7 - iter 1800/1809 - loss 0.01571324 - time (sec): 158.67 - samples/sec: 2384.33 - lr: 0.000017 - momentum: 0.000000
2023-10-25 17:44:21,026 ----------------------------------------------------------------------------------------------------
2023-10-25 17:44:21,026 EPOCH 7 done: loss 0.0157 - lr: 0.000017
2023-10-25 17:44:26,345 DEV : loss 0.3604075312614441 - f1-score (micro avg)  0.6238
2023-10-25 17:44:26,368 ----------------------------------------------------------------------------------------------------
2023-10-25 17:44:42,092 epoch 8 - iter 180/1809 - loss 0.00997516 - time (sec): 15.72 - samples/sec: 2339.27 - lr: 0.000016 - momentum: 0.000000
2023-10-25 17:44:57,918 epoch 8 - iter 360/1809 - loss 0.01105999 - time (sec): 31.55 - samples/sec: 2358.40 - lr: 0.000016 - momentum: 0.000000
2023-10-25 17:45:13,718 epoch 8 - iter 540/1809 - loss 0.01121835 - time (sec): 47.35 - samples/sec: 2355.37 - lr: 0.000015 - momentum: 0.000000
2023-10-25 17:45:29,687 epoch 8 - iter 720/1809 - loss 0.01185460 - time (sec): 63.32 - samples/sec: 2359.55 - lr: 0.000014 - momentum: 0.000000
2023-10-25 17:45:45,573 epoch 8 - iter 900/1809 - loss 0.01093216 - time (sec): 79.20 - samples/sec: 2365.07 - lr: 0.000014 - momentum: 0.000000
2023-10-25 17:46:01,155 epoch 8 - iter 1080/1809 - loss 0.01026454 - time (sec): 94.79 - samples/sec: 2366.17 - lr: 0.000013 - momentum: 0.000000
2023-10-25 17:46:16,917 epoch 8 - iter 1260/1809 - loss 0.00974729 - time (sec): 110.55 - samples/sec: 2370.48 - lr: 0.000013 - momentum: 0.000000
2023-10-25 17:46:32,383 epoch 8 - iter 1440/1809 - loss 0.00942034 - time (sec): 126.01 - samples/sec: 2370.26 - lr: 0.000012 - momentum: 0.000000
2023-10-25 17:46:48,687 epoch 8 - iter 1620/1809 - loss 0.01013871 - time (sec): 142.32 - samples/sec: 2373.81 - lr: 0.000012 - momentum: 0.000000
2023-10-25 17:47:05,389 epoch 8 - iter 1800/1809 - loss 0.01001323 - time (sec): 159.02 - samples/sec: 2378.22 - lr: 0.000011 - momentum: 0.000000
2023-10-25 17:47:06,147 ----------------------------------------------------------------------------------------------------
2023-10-25 17:47:06,147 EPOCH 8 done: loss 0.0101 - lr: 0.000011
2023-10-25 17:47:11,459 DEV : loss 0.3776438534259796 - f1-score (micro avg)  0.649
2023-10-25 17:47:11,482 saving best model
2023-10-25 17:47:12,162 ----------------------------------------------------------------------------------------------------
2023-10-25 17:47:28,015 epoch 9 - iter 180/1809 - loss 0.00806189 - time (sec): 15.85 - samples/sec: 2396.31 - lr: 0.000011 - momentum: 0.000000
2023-10-25 17:47:43,744 epoch 9 - iter 360/1809 - loss 0.00786294 - time (sec): 31.58 - samples/sec: 2414.19 - lr: 0.000010 - momentum: 0.000000
2023-10-25 17:47:59,740 epoch 9 - iter 540/1809 - loss 0.00779681 - time (sec): 47.58 - samples/sec: 2404.36 - lr: 0.000009 - momentum: 0.000000
2023-10-25 17:48:15,611 epoch 9 - iter 720/1809 - loss 0.00824623 - time (sec): 63.45 - samples/sec: 2391.40 - lr: 0.000009 - momentum: 0.000000
2023-10-25 17:48:31,872 epoch 9 - iter 900/1809 - loss 0.00749187 - time (sec): 79.71 - samples/sec: 2379.55 - lr: 0.000008 - momentum: 0.000000
2023-10-25 17:48:47,559 epoch 9 - iter 1080/1809 - loss 0.00729148 - time (sec): 95.40 - samples/sec: 2381.02 - lr: 0.000008 - momentum: 0.000000
2023-10-25 17:49:03,417 epoch 9 - iter 1260/1809 - loss 0.00706207 - time (sec): 111.25 - samples/sec: 2374.16 - lr: 0.000007 - momentum: 0.000000
2023-10-25 17:49:19,068 epoch 9 - iter 1440/1809 - loss 0.00684409 - time (sec): 126.90 - samples/sec: 2373.51 - lr: 0.000007 - momentum: 0.000000
2023-10-25 17:49:34,617 epoch 9 - iter 1620/1809 - loss 0.00687108 - time (sec): 142.45 - samples/sec: 2378.28 - lr: 0.000006 - momentum: 0.000000
2023-10-25 17:49:50,728 epoch 9 - iter 1800/1809 - loss 0.00658565 - time (sec): 158.56 - samples/sec: 2381.77 - lr: 0.000006 - momentum: 0.000000
2023-10-25 17:49:51,725 ----------------------------------------------------------------------------------------------------
2023-10-25 17:49:51,725 EPOCH 9 done: loss 0.0067 - lr: 0.000006
2023-10-25 17:49:56,514 DEV : loss 0.3927135467529297 - f1-score (micro avg)  0.6399
2023-10-25 17:49:56,538 ----------------------------------------------------------------------------------------------------
2023-10-25 17:50:12,657 epoch 10 - iter 180/1809 - loss 0.00422793 - time (sec): 16.12 - samples/sec: 2350.66 - lr: 0.000005 - momentum: 0.000000
2023-10-25 17:50:28,618 epoch 10 - iter 360/1809 - loss 0.00339541 - time (sec): 32.08 - samples/sec: 2385.59 - lr: 0.000004 - momentum: 0.000000
2023-10-25 17:50:44,793 epoch 10 - iter 540/1809 - loss 0.00334334 - time (sec): 48.25 - samples/sec: 2373.68 - lr: 0.000004 - momentum: 0.000000
2023-10-25 17:51:00,624 epoch 10 - iter 720/1809 - loss 0.00349222 - time (sec): 64.09 - samples/sec: 2368.92 - lr: 0.000003 - momentum: 0.000000
2023-10-25 17:51:16,681 epoch 10 - iter 900/1809 - loss 0.00336080 - time (sec): 80.14 - samples/sec: 2376.57 - lr: 0.000003 - momentum: 0.000000
2023-10-25 17:51:32,495 epoch 10 - iter 1080/1809 - loss 0.00320549 - time (sec): 95.96 - samples/sec: 2379.97 - lr: 0.000002 - momentum: 0.000000
2023-10-25 17:51:48,151 epoch 10 - iter 1260/1809 - loss 0.00327382 - time (sec): 111.61 - samples/sec: 2376.20 - lr: 0.000002 - momentum: 0.000000
2023-10-25 17:52:04,075 epoch 10 - iter 1440/1809 - loss 0.00335080 - time (sec): 127.54 - samples/sec: 2378.32 - lr: 0.000001 - momentum: 0.000000
2023-10-25 17:52:20,274 epoch 10 - iter 1620/1809 - loss 0.00332977 - time (sec): 143.74 - samples/sec: 2380.65 - lr: 0.000001 - momentum: 0.000000
2023-10-25 17:52:35,875 epoch 10 - iter 1800/1809 - loss 0.00380800 - time (sec): 159.34 - samples/sec: 2375.32 - lr: 0.000000 - momentum: 0.000000
2023-10-25 17:52:36,617 ----------------------------------------------------------------------------------------------------
2023-10-25 17:52:36,617 EPOCH 10 done: loss 0.0038 - lr: 0.000000
2023-10-25 17:52:41,399 DEV : loss 0.4173244535923004 - f1-score (micro avg)  0.6413
2023-10-25 17:52:41,977 ----------------------------------------------------------------------------------------------------
2023-10-25 17:52:41,978 Loading model from best epoch ...
2023-10-25 17:52:43,747 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 17:52:50,008 
Results:
- F-score (micro) 0.6409
- F-score (macro) 0.4973
- Accuracy 0.4862

By class:
              precision    recall  f1-score   support

         loc     0.6403    0.7259    0.6804       591
        pers     0.5885    0.7451    0.6576       357
         org     0.1961    0.1266    0.1538        79

   micro avg     0.6010    0.6865    0.6409      1027
   macro avg     0.4750    0.5325    0.4973      1027
weighted avg     0.5881    0.6865    0.6320      1027

2023-10-25 17:52:50,008 ----------------------------------------------------------------------------------------------------