2023-10-25 08:00:15,628 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,629 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 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 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 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Train:  14465 sentences
2023-10-25 08:00:15,630         (train_with_dev=False, train_with_test=False)
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Training Params:
2023-10-25 08:00:15,630  - learning_rate: "3e-05" 
2023-10-25 08:00:15,630  - mini_batch_size: "8"
2023-10-25 08:00:15,630  - max_epochs: "10"
2023-10-25 08:00:15,630  - shuffle: "True"
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Plugins:
2023-10-25 08:00:15,630  - TensorboardLogger
2023-10-25 08:00:15,630  - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 08:00:15,630  - metric: "('micro avg', 'f1-score')"
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Computation:
2023-10-25 08:00:15,630  - compute on device: cuda:0
2023-10-25 08:00:15,630  - embedding storage: none
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 ----------------------------------------------------------------------------------------------------
2023-10-25 08:00:15,630 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 08:00:31,579 epoch 1 - iter 180/1809 - loss 1.59994791 - time (sec): 15.95 - samples/sec: 2365.16 - lr: 0.000003 - momentum: 0.000000
2023-10-25 08:00:46,626 epoch 1 - iter 360/1809 - loss 0.90942152 - time (sec): 31.00 - samples/sec: 2420.21 - lr: 0.000006 - momentum: 0.000000
2023-10-25 08:01:02,121 epoch 1 - iter 540/1809 - loss 0.65057194 - time (sec): 46.49 - samples/sec: 2437.06 - lr: 0.000009 - momentum: 0.000000
2023-10-25 08:01:17,548 epoch 1 - iter 720/1809 - loss 0.52234297 - time (sec): 61.92 - samples/sec: 2445.01 - lr: 0.000012 - momentum: 0.000000
2023-10-25 08:01:32,921 epoch 1 - iter 900/1809 - loss 0.44356097 - time (sec): 77.29 - samples/sec: 2440.72 - lr: 0.000015 - momentum: 0.000000
2023-10-25 08:01:48,608 epoch 1 - iter 1080/1809 - loss 0.38806485 - time (sec): 92.98 - samples/sec: 2438.35 - lr: 0.000018 - momentum: 0.000000
2023-10-25 08:02:04,004 epoch 1 - iter 1260/1809 - loss 0.34665146 - time (sec): 108.37 - samples/sec: 2444.01 - lr: 0.000021 - momentum: 0.000000
2023-10-25 08:02:19,487 epoch 1 - iter 1440/1809 - loss 0.31692748 - time (sec): 123.86 - samples/sec: 2440.98 - lr: 0.000024 - momentum: 0.000000
2023-10-25 08:02:35,196 epoch 1 - iter 1620/1809 - loss 0.29267973 - time (sec): 139.57 - samples/sec: 2437.07 - lr: 0.000027 - momentum: 0.000000
2023-10-25 08:02:50,837 epoch 1 - iter 1800/1809 - loss 0.27406237 - time (sec): 155.21 - samples/sec: 2436.52 - lr: 0.000030 - momentum: 0.000000
2023-10-25 08:02:51,583 ----------------------------------------------------------------------------------------------------
2023-10-25 08:02:51,583 EPOCH 1 done: loss 0.2733 - lr: 0.000030
2023-10-25 08:02:56,022 DEV : loss 0.11878068745136261 - f1-score (micro avg)  0.6243
2023-10-25 08:02:56,043 saving best model
2023-10-25 08:02:56,600 ----------------------------------------------------------------------------------------------------
2023-10-25 08:03:12,137 epoch 2 - iter 180/1809 - loss 0.08520146 - time (sec): 15.54 - samples/sec: 2457.95 - lr: 0.000030 - momentum: 0.000000
2023-10-25 08:03:28,446 epoch 2 - iter 360/1809 - loss 0.09154462 - time (sec): 31.84 - samples/sec: 2418.86 - lr: 0.000029 - momentum: 0.000000
2023-10-25 08:03:44,444 epoch 2 - iter 540/1809 - loss 0.09248862 - time (sec): 47.84 - samples/sec: 2412.53 - lr: 0.000029 - momentum: 0.000000
2023-10-25 08:04:00,307 epoch 2 - iter 720/1809 - loss 0.08973269 - time (sec): 63.71 - samples/sec: 2404.62 - lr: 0.000029 - momentum: 0.000000
2023-10-25 08:04:16,033 epoch 2 - iter 900/1809 - loss 0.08876132 - time (sec): 79.43 - samples/sec: 2403.58 - lr: 0.000028 - momentum: 0.000000
2023-10-25 08:04:31,870 epoch 2 - iter 1080/1809 - loss 0.08756439 - time (sec): 95.27 - samples/sec: 2394.03 - lr: 0.000028 - momentum: 0.000000
2023-10-25 08:04:47,396 epoch 2 - iter 1260/1809 - loss 0.08711257 - time (sec): 110.79 - samples/sec: 2393.13 - lr: 0.000028 - momentum: 0.000000
2023-10-25 08:05:03,398 epoch 2 - iter 1440/1809 - loss 0.08478479 - time (sec): 126.80 - samples/sec: 2393.23 - lr: 0.000027 - momentum: 0.000000
2023-10-25 08:05:19,435 epoch 2 - iter 1620/1809 - loss 0.08360993 - time (sec): 142.83 - samples/sec: 2388.17 - lr: 0.000027 - momentum: 0.000000
2023-10-25 08:05:34,900 epoch 2 - iter 1800/1809 - loss 0.08306504 - time (sec): 158.30 - samples/sec: 2388.83 - lr: 0.000027 - momentum: 0.000000
2023-10-25 08:05:35,628 ----------------------------------------------------------------------------------------------------
2023-10-25 08:05:35,629 EPOCH 2 done: loss 0.0831 - lr: 0.000027
2023-10-25 08:05:40,837 DEV : loss 0.13267631828784943 - f1-score (micro avg)  0.6358
2023-10-25 08:05:40,859 saving best model
2023-10-25 08:05:41,675 ----------------------------------------------------------------------------------------------------
2023-10-25 08:05:57,585 epoch 3 - iter 180/1809 - loss 0.06089348 - time (sec): 15.91 - samples/sec: 2355.16 - lr: 0.000026 - momentum: 0.000000
2023-10-25 08:06:13,768 epoch 3 - iter 360/1809 - loss 0.06038894 - time (sec): 32.09 - samples/sec: 2360.88 - lr: 0.000026 - momentum: 0.000000
2023-10-25 08:06:29,084 epoch 3 - iter 540/1809 - loss 0.05526036 - time (sec): 47.41 - samples/sec: 2389.71 - lr: 0.000026 - momentum: 0.000000
2023-10-25 08:06:44,661 epoch 3 - iter 720/1809 - loss 0.05749612 - time (sec): 62.98 - samples/sec: 2390.73 - lr: 0.000025 - momentum: 0.000000
2023-10-25 08:07:00,404 epoch 3 - iter 900/1809 - loss 0.05617974 - time (sec): 78.73 - samples/sec: 2403.04 - lr: 0.000025 - momentum: 0.000000
2023-10-25 08:07:16,708 epoch 3 - iter 1080/1809 - loss 0.05706057 - time (sec): 95.03 - samples/sec: 2404.56 - lr: 0.000025 - momentum: 0.000000
2023-10-25 08:07:32,106 epoch 3 - iter 1260/1809 - loss 0.05724190 - time (sec): 110.43 - samples/sec: 2401.49 - lr: 0.000024 - momentum: 0.000000
2023-10-25 08:07:48,254 epoch 3 - iter 1440/1809 - loss 0.05718478 - time (sec): 126.58 - samples/sec: 2408.93 - lr: 0.000024 - momentum: 0.000000
2023-10-25 08:08:04,408 epoch 3 - iter 1620/1809 - loss 0.05826610 - time (sec): 142.73 - samples/sec: 2395.50 - lr: 0.000024 - momentum: 0.000000
2023-10-25 08:08:19,957 epoch 3 - iter 1800/1809 - loss 0.05919743 - time (sec): 158.28 - samples/sec: 2391.38 - lr: 0.000023 - momentum: 0.000000
2023-10-25 08:08:20,676 ----------------------------------------------------------------------------------------------------
2023-10-25 08:08:20,676 EPOCH 3 done: loss 0.0592 - lr: 0.000023
2023-10-25 08:08:25,440 DEV : loss 0.1354532539844513 - f1-score (micro avg)  0.6314
2023-10-25 08:08:25,462 ----------------------------------------------------------------------------------------------------
2023-10-25 08:08:41,845 epoch 4 - iter 180/1809 - loss 0.03568652 - time (sec): 16.38 - samples/sec: 2312.63 - lr: 0.000023 - momentum: 0.000000
2023-10-25 08:08:58,273 epoch 4 - iter 360/1809 - loss 0.03716226 - time (sec): 32.81 - samples/sec: 2346.64 - lr: 0.000023 - momentum: 0.000000
2023-10-25 08:09:13,745 epoch 4 - iter 540/1809 - loss 0.03968774 - time (sec): 48.28 - samples/sec: 2347.42 - lr: 0.000022 - momentum: 0.000000
2023-10-25 08:09:29,537 epoch 4 - iter 720/1809 - loss 0.04000489 - time (sec): 64.07 - samples/sec: 2355.52 - lr: 0.000022 - momentum: 0.000000
2023-10-25 08:09:45,388 epoch 4 - iter 900/1809 - loss 0.03962584 - time (sec): 79.93 - samples/sec: 2362.15 - lr: 0.000022 - momentum: 0.000000
2023-10-25 08:10:01,321 epoch 4 - iter 1080/1809 - loss 0.03940596 - time (sec): 95.86 - samples/sec: 2371.85 - lr: 0.000021 - momentum: 0.000000
2023-10-25 08:10:17,098 epoch 4 - iter 1260/1809 - loss 0.04055800 - time (sec): 111.64 - samples/sec: 2371.02 - lr: 0.000021 - momentum: 0.000000
2023-10-25 08:10:32,621 epoch 4 - iter 1440/1809 - loss 0.04022573 - time (sec): 127.16 - samples/sec: 2373.19 - lr: 0.000021 - momentum: 0.000000
2023-10-25 08:10:48,660 epoch 4 - iter 1620/1809 - loss 0.04065113 - time (sec): 143.20 - samples/sec: 2370.71 - lr: 0.000020 - momentum: 0.000000
2023-10-25 08:11:04,972 epoch 4 - iter 1800/1809 - loss 0.04133841 - time (sec): 159.51 - samples/sec: 2370.42 - lr: 0.000020 - momentum: 0.000000
2023-10-25 08:11:05,824 ----------------------------------------------------------------------------------------------------
2023-10-25 08:11:05,824 EPOCH 4 done: loss 0.0414 - lr: 0.000020
2023-10-25 08:11:10,594 DEV : loss 0.2289542257785797 - f1-score (micro avg)  0.6386
2023-10-25 08:11:10,616 saving best model
2023-10-25 08:11:11,305 ----------------------------------------------------------------------------------------------------
2023-10-25 08:11:26,893 epoch 5 - iter 180/1809 - loss 0.02492765 - time (sec): 15.59 - samples/sec: 2342.07 - lr: 0.000020 - momentum: 0.000000
2023-10-25 08:11:42,990 epoch 5 - iter 360/1809 - loss 0.02595936 - time (sec): 31.68 - samples/sec: 2334.66 - lr: 0.000019 - momentum: 0.000000
2023-10-25 08:11:58,875 epoch 5 - iter 540/1809 - loss 0.02591071 - time (sec): 47.57 - samples/sec: 2350.63 - lr: 0.000019 - momentum: 0.000000
2023-10-25 08:12:14,762 epoch 5 - iter 720/1809 - loss 0.02549117 - time (sec): 63.46 - samples/sec: 2358.16 - lr: 0.000019 - momentum: 0.000000
2023-10-25 08:12:30,706 epoch 5 - iter 900/1809 - loss 0.02448476 - time (sec): 79.40 - samples/sec: 2376.53 - lr: 0.000018 - momentum: 0.000000
2023-10-25 08:12:46,502 epoch 5 - iter 1080/1809 - loss 0.02533076 - time (sec): 95.20 - samples/sec: 2368.81 - lr: 0.000018 - momentum: 0.000000
2023-10-25 08:13:02,210 epoch 5 - iter 1260/1809 - loss 0.02562868 - time (sec): 110.90 - samples/sec: 2367.94 - lr: 0.000018 - momentum: 0.000000
2023-10-25 08:13:18,742 epoch 5 - iter 1440/1809 - loss 0.02590139 - time (sec): 127.44 - samples/sec: 2370.63 - lr: 0.000017 - momentum: 0.000000
2023-10-25 08:13:34,484 epoch 5 - iter 1620/1809 - loss 0.02625493 - time (sec): 143.18 - samples/sec: 2370.26 - lr: 0.000017 - momentum: 0.000000
2023-10-25 08:13:50,871 epoch 5 - iter 1800/1809 - loss 0.02688381 - time (sec): 159.57 - samples/sec: 2371.05 - lr: 0.000017 - momentum: 0.000000
2023-10-25 08:13:51,555 ----------------------------------------------------------------------------------------------------
2023-10-25 08:13:51,555 EPOCH 5 done: loss 0.0269 - lr: 0.000017
2023-10-25 08:13:56,313 DEV : loss 0.26100045442581177 - f1-score (micro avg)  0.6625
2023-10-25 08:13:56,335 saving best model
2023-10-25 08:13:57,053 ----------------------------------------------------------------------------------------------------
2023-10-25 08:14:12,919 epoch 6 - iter 180/1809 - loss 0.01378039 - time (sec): 15.86 - samples/sec: 2282.43 - lr: 0.000016 - momentum: 0.000000
2023-10-25 08:14:28,961 epoch 6 - iter 360/1809 - loss 0.01816354 - time (sec): 31.91 - samples/sec: 2360.47 - lr: 0.000016 - momentum: 0.000000
2023-10-25 08:14:45,179 epoch 6 - iter 540/1809 - loss 0.01885418 - time (sec): 48.12 - samples/sec: 2356.04 - lr: 0.000016 - momentum: 0.000000
2023-10-25 08:15:00,786 epoch 6 - iter 720/1809 - loss 0.01972614 - time (sec): 63.73 - samples/sec: 2349.29 - lr: 0.000015 - momentum: 0.000000
2023-10-25 08:15:16,751 epoch 6 - iter 900/1809 - loss 0.01899198 - time (sec): 79.70 - samples/sec: 2361.69 - lr: 0.000015 - momentum: 0.000000
2023-10-25 08:15:32,360 epoch 6 - iter 1080/1809 - loss 0.01852834 - time (sec): 95.31 - samples/sec: 2362.64 - lr: 0.000015 - momentum: 0.000000
2023-10-25 08:15:48,278 epoch 6 - iter 1260/1809 - loss 0.01797562 - time (sec): 111.22 - samples/sec: 2363.36 - lr: 0.000014 - momentum: 0.000000
2023-10-25 08:16:04,333 epoch 6 - iter 1440/1809 - loss 0.01764648 - time (sec): 127.28 - samples/sec: 2373.74 - lr: 0.000014 - momentum: 0.000000
2023-10-25 08:16:20,288 epoch 6 - iter 1620/1809 - loss 0.01787887 - time (sec): 143.23 - samples/sec: 2372.76 - lr: 0.000014 - momentum: 0.000000
2023-10-25 08:16:36,075 epoch 6 - iter 1800/1809 - loss 0.01811722 - time (sec): 159.02 - samples/sec: 2376.53 - lr: 0.000013 - momentum: 0.000000
2023-10-25 08:16:36,858 ----------------------------------------------------------------------------------------------------
2023-10-25 08:16:36,858 EPOCH 6 done: loss 0.0182 - lr: 0.000013
2023-10-25 08:16:42,101 DEV : loss 0.3313358724117279 - f1-score (micro avg)  0.6553
2023-10-25 08:16:42,123 ----------------------------------------------------------------------------------------------------
2023-10-25 08:16:57,953 epoch 7 - iter 180/1809 - loss 0.00872843 - time (sec): 15.83 - samples/sec: 2415.85 - lr: 0.000013 - momentum: 0.000000
2023-10-25 08:17:13,241 epoch 7 - iter 360/1809 - loss 0.00854091 - time (sec): 31.12 - samples/sec: 2417.71 - lr: 0.000013 - momentum: 0.000000
2023-10-25 08:17:29,025 epoch 7 - iter 540/1809 - loss 0.01084116 - time (sec): 46.90 - samples/sec: 2397.20 - lr: 0.000012 - momentum: 0.000000
2023-10-25 08:17:44,926 epoch 7 - iter 720/1809 - loss 0.01304482 - time (sec): 62.80 - samples/sec: 2399.67 - lr: 0.000012 - momentum: 0.000000
2023-10-25 08:18:01,388 epoch 7 - iter 900/1809 - loss 0.01267124 - time (sec): 79.26 - samples/sec: 2410.58 - lr: 0.000012 - momentum: 0.000000
2023-10-25 08:18:16,849 epoch 7 - iter 1080/1809 - loss 0.01242008 - time (sec): 94.73 - samples/sec: 2406.32 - lr: 0.000011 - momentum: 0.000000
2023-10-25 08:18:33,141 epoch 7 - iter 1260/1809 - loss 0.01230193 - time (sec): 111.02 - samples/sec: 2391.84 - lr: 0.000011 - momentum: 0.000000
2023-10-25 08:18:48,939 epoch 7 - iter 1440/1809 - loss 0.01248631 - time (sec): 126.82 - samples/sec: 2391.04 - lr: 0.000011 - momentum: 0.000000
2023-10-25 08:19:04,921 epoch 7 - iter 1620/1809 - loss 0.01261317 - time (sec): 142.80 - samples/sec: 2390.66 - lr: 0.000010 - momentum: 0.000000
2023-10-25 08:19:20,957 epoch 7 - iter 1800/1809 - loss 0.01276577 - time (sec): 158.83 - samples/sec: 2380.11 - lr: 0.000010 - momentum: 0.000000
2023-10-25 08:19:21,677 ----------------------------------------------------------------------------------------------------
2023-10-25 08:19:21,677 EPOCH 7 done: loss 0.0127 - lr: 0.000010
2023-10-25 08:19:26,940 DEV : loss 0.36011332273483276 - f1-score (micro avg)  0.6616
2023-10-25 08:19:26,962 ----------------------------------------------------------------------------------------------------
2023-10-25 08:19:43,149 epoch 8 - iter 180/1809 - loss 0.00761376 - time (sec): 16.19 - samples/sec: 2367.10 - lr: 0.000010 - momentum: 0.000000
2023-10-25 08:19:59,316 epoch 8 - iter 360/1809 - loss 0.00758239 - time (sec): 32.35 - samples/sec: 2344.06 - lr: 0.000009 - momentum: 0.000000
2023-10-25 08:20:15,488 epoch 8 - iter 540/1809 - loss 0.00857590 - time (sec): 48.52 - samples/sec: 2374.72 - lr: 0.000009 - momentum: 0.000000
2023-10-25 08:20:30,539 epoch 8 - iter 720/1809 - loss 0.00895513 - time (sec): 63.58 - samples/sec: 2393.92 - lr: 0.000009 - momentum: 0.000000
2023-10-25 08:20:46,448 epoch 8 - iter 900/1809 - loss 0.00825738 - time (sec): 79.49 - samples/sec: 2390.01 - lr: 0.000008 - momentum: 0.000000
2023-10-25 08:21:02,541 epoch 8 - iter 1080/1809 - loss 0.00881305 - time (sec): 95.58 - samples/sec: 2386.85 - lr: 0.000008 - momentum: 0.000000
2023-10-25 08:21:18,012 epoch 8 - iter 1260/1809 - loss 0.00882209 - time (sec): 111.05 - samples/sec: 2382.50 - lr: 0.000008 - momentum: 0.000000
2023-10-25 08:21:34,428 epoch 8 - iter 1440/1809 - loss 0.00827827 - time (sec): 127.47 - samples/sec: 2379.38 - lr: 0.000007 - momentum: 0.000000
2023-10-25 08:21:50,011 epoch 8 - iter 1620/1809 - loss 0.00824322 - time (sec): 143.05 - samples/sec: 2380.33 - lr: 0.000007 - momentum: 0.000000
2023-10-25 08:22:05,668 epoch 8 - iter 1800/1809 - loss 0.00850028 - time (sec): 158.70 - samples/sec: 2383.21 - lr: 0.000007 - momentum: 0.000000
2023-10-25 08:22:06,376 ----------------------------------------------------------------------------------------------------
2023-10-25 08:22:06,376 EPOCH 8 done: loss 0.0086 - lr: 0.000007
2023-10-25 08:22:11,644 DEV : loss 0.39194777607917786 - f1-score (micro avg)  0.6577
2023-10-25 08:22:11,666 ----------------------------------------------------------------------------------------------------
2023-10-25 08:22:28,097 epoch 9 - iter 180/1809 - loss 0.00369902 - time (sec): 16.43 - samples/sec: 2368.97 - lr: 0.000006 - momentum: 0.000000
2023-10-25 08:22:44,007 epoch 9 - iter 360/1809 - loss 0.00469730 - time (sec): 32.34 - samples/sec: 2414.47 - lr: 0.000006 - momentum: 0.000000
2023-10-25 08:22:59,689 epoch 9 - iter 540/1809 - loss 0.00431458 - time (sec): 48.02 - samples/sec: 2412.11 - lr: 0.000006 - momentum: 0.000000
2023-10-25 08:23:15,295 epoch 9 - iter 720/1809 - loss 0.00481666 - time (sec): 63.63 - samples/sec: 2391.66 - lr: 0.000005 - momentum: 0.000000
2023-10-25 08:23:31,490 epoch 9 - iter 900/1809 - loss 0.00493696 - time (sec): 79.82 - samples/sec: 2402.05 - lr: 0.000005 - momentum: 0.000000
2023-10-25 08:23:47,176 epoch 9 - iter 1080/1809 - loss 0.00523981 - time (sec): 95.51 - samples/sec: 2394.12 - lr: 0.000005 - momentum: 0.000000
2023-10-25 08:24:02,926 epoch 9 - iter 1260/1809 - loss 0.00497472 - time (sec): 111.26 - samples/sec: 2386.83 - lr: 0.000004 - momentum: 0.000000
2023-10-25 08:24:18,624 epoch 9 - iter 1440/1809 - loss 0.00565406 - time (sec): 126.96 - samples/sec: 2386.65 - lr: 0.000004 - momentum: 0.000000
2023-10-25 08:24:34,491 epoch 9 - iter 1620/1809 - loss 0.00563871 - time (sec): 142.82 - samples/sec: 2386.99 - lr: 0.000004 - momentum: 0.000000
2023-10-25 08:24:50,211 epoch 9 - iter 1800/1809 - loss 0.00567494 - time (sec): 158.54 - samples/sec: 2383.99 - lr: 0.000003 - momentum: 0.000000
2023-10-25 08:24:51,042 ----------------------------------------------------------------------------------------------------
2023-10-25 08:24:51,043 EPOCH 9 done: loss 0.0057 - lr: 0.000003
2023-10-25 08:24:55,799 DEV : loss 0.393858402967453 - f1-score (micro avg)  0.6654
2023-10-25 08:24:55,821 saving best model
2023-10-25 08:24:56,521 ----------------------------------------------------------------------------------------------------
2023-10-25 08:25:12,728 epoch 10 - iter 180/1809 - loss 0.00196544 - time (sec): 16.21 - samples/sec: 2353.56 - lr: 0.000003 - momentum: 0.000000
2023-10-25 08:25:28,376 epoch 10 - iter 360/1809 - loss 0.00228683 - time (sec): 31.85 - samples/sec: 2391.48 - lr: 0.000003 - momentum: 0.000000
2023-10-25 08:25:44,475 epoch 10 - iter 540/1809 - loss 0.00299234 - time (sec): 47.95 - samples/sec: 2361.65 - lr: 0.000002 - momentum: 0.000000
2023-10-25 08:26:00,434 epoch 10 - iter 720/1809 - loss 0.00293109 - time (sec): 63.91 - samples/sec: 2370.47 - lr: 0.000002 - momentum: 0.000000
2023-10-25 08:26:16,100 epoch 10 - iter 900/1809 - loss 0.00302326 - time (sec): 79.58 - samples/sec: 2361.79 - lr: 0.000002 - momentum: 0.000000
2023-10-25 08:26:31,796 epoch 10 - iter 1080/1809 - loss 0.00327400 - time (sec): 95.27 - samples/sec: 2365.70 - lr: 0.000001 - momentum: 0.000000
2023-10-25 08:26:47,735 epoch 10 - iter 1260/1809 - loss 0.00338707 - time (sec): 111.21 - samples/sec: 2357.01 - lr: 0.000001 - momentum: 0.000000
2023-10-25 08:27:03,951 epoch 10 - iter 1440/1809 - loss 0.00361125 - time (sec): 127.43 - samples/sec: 2361.94 - lr: 0.000001 - momentum: 0.000000
2023-10-25 08:27:20,042 epoch 10 - iter 1620/1809 - loss 0.00365904 - time (sec): 143.52 - samples/sec: 2367.04 - lr: 0.000000 - momentum: 0.000000
2023-10-25 08:27:36,103 epoch 10 - iter 1800/1809 - loss 0.00356670 - time (sec): 159.58 - samples/sec: 2371.48 - lr: 0.000000 - momentum: 0.000000
2023-10-25 08:27:36,804 ----------------------------------------------------------------------------------------------------
2023-10-25 08:27:36,804 EPOCH 10 done: loss 0.0036 - lr: 0.000000
2023-10-25 08:27:41,566 DEV : loss 0.40507274866104126 - f1-score (micro avg)  0.6612
2023-10-25 08:27:42,142 ----------------------------------------------------------------------------------------------------
2023-10-25 08:27:42,143 Loading model from best epoch ...
2023-10-25 08:27:44,091 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 08:27:50,312 
Results:
- F-score (micro) 0.6545
- F-score (macro) 0.5095
- Accuracy 0.4987

By class:
              precision    recall  f1-score   support

         loc     0.6376    0.7919    0.7064       591
        pers     0.5787    0.7619    0.6578       357
         org     0.1791    0.1519    0.1644        79

   micro avg     0.5917    0.7322    0.6545      1027
   macro avg     0.4651    0.5686    0.5095      1027
weighted avg     0.5819    0.7322    0.6478      1027

2023-10-25 08:27:50,312 ----------------------------------------------------------------------------------------------------