2023-10-23 19:59:21,191 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,192 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=25, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 MultiCorpus: 966 train + 219 dev + 204 test sentences
 - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Train:  966 sentences
2023-10-23 19:59:21,193         (train_with_dev=False, train_with_test=False)
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Training Params:
2023-10-23 19:59:21,193  - learning_rate: "5e-05" 
2023-10-23 19:59:21,193  - mini_batch_size: "8"
2023-10-23 19:59:21,193  - max_epochs: "10"
2023-10-23 19:59:21,193  - shuffle: "True"
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Plugins:
2023-10-23 19:59:21,193  - TensorboardLogger
2023-10-23 19:59:21,193  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 19:59:21,193  - metric: "('micro avg', 'f1-score')"
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Computation:
2023-10-23 19:59:21,193  - compute on device: cuda:0
2023-10-23 19:59:21,193  - embedding storage: none
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:21,193 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 19:59:22,177 epoch 1 - iter 12/121 - loss 3.07959071 - time (sec): 0.98 - samples/sec: 2340.27 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:59:23,275 epoch 1 - iter 24/121 - loss 2.38609019 - time (sec): 2.08 - samples/sec: 2474.23 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:59:24,277 epoch 1 - iter 36/121 - loss 1.84215632 - time (sec): 3.08 - samples/sec: 2425.53 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:59:25,346 epoch 1 - iter 48/121 - loss 1.52491414 - time (sec): 4.15 - samples/sec: 2395.32 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:59:26,459 epoch 1 - iter 60/121 - loss 1.35065987 - time (sec): 5.27 - samples/sec: 2361.06 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:59:27,555 epoch 1 - iter 72/121 - loss 1.22720738 - time (sec): 6.36 - samples/sec: 2319.60 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:59:28,645 epoch 1 - iter 84/121 - loss 1.10984601 - time (sec): 7.45 - samples/sec: 2318.37 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:59:29,702 epoch 1 - iter 96/121 - loss 1.01430418 - time (sec): 8.51 - samples/sec: 2318.42 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:59:30,869 epoch 1 - iter 108/121 - loss 0.93461040 - time (sec): 9.67 - samples/sec: 2291.36 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:59:31,861 epoch 1 - iter 120/121 - loss 0.86737349 - time (sec): 10.67 - samples/sec: 2295.52 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:59:31,937 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:31,938 EPOCH 1 done: loss 0.8603 - lr: 0.000049
2023-10-23 19:59:32,764 DEV : loss 0.19693243503570557 - f1-score (micro avg)  0.6116
2023-10-23 19:59:32,768 saving best model
2023-10-23 19:59:33,244 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:34,297 epoch 2 - iter 12/121 - loss 0.21980535 - time (sec): 1.05 - samples/sec: 2376.67 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:59:35,399 epoch 2 - iter 24/121 - loss 0.20510598 - time (sec): 2.15 - samples/sec: 2293.52 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:59:36,442 epoch 2 - iter 36/121 - loss 0.20010149 - time (sec): 3.20 - samples/sec: 2343.54 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:59:37,464 epoch 2 - iter 48/121 - loss 0.20045052 - time (sec): 4.22 - samples/sec: 2342.73 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:59:38,564 epoch 2 - iter 60/121 - loss 0.18472354 - time (sec): 5.32 - samples/sec: 2318.48 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:59:39,630 epoch 2 - iter 72/121 - loss 0.16871403 - time (sec): 6.38 - samples/sec: 2303.89 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:59:40,703 epoch 2 - iter 84/121 - loss 0.16894935 - time (sec): 7.46 - samples/sec: 2314.11 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:59:41,781 epoch 2 - iter 96/121 - loss 0.16727768 - time (sec): 8.54 - samples/sec: 2306.80 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:59:42,794 epoch 2 - iter 108/121 - loss 0.16175313 - time (sec): 9.55 - samples/sec: 2314.72 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:59:43,835 epoch 2 - iter 120/121 - loss 0.16392006 - time (sec): 10.59 - samples/sec: 2316.97 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:59:43,918 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:43,918 EPOCH 2 done: loss 0.1657 - lr: 0.000045
2023-10-23 19:59:44,611 DEV : loss 0.13358022272586823 - f1-score (micro avg)  0.7915
2023-10-23 19:59:44,615 saving best model
2023-10-23 19:59:45,308 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:46,293 epoch 3 - iter 12/121 - loss 0.07053205 - time (sec): 0.98 - samples/sec: 2325.21 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:59:47,376 epoch 3 - iter 24/121 - loss 0.08748616 - time (sec): 2.07 - samples/sec: 2216.18 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:59:48,539 epoch 3 - iter 36/121 - loss 0.08503074 - time (sec): 3.23 - samples/sec: 2253.63 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:59:49,609 epoch 3 - iter 48/121 - loss 0.08134210 - time (sec): 4.30 - samples/sec: 2238.74 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:59:50,663 epoch 3 - iter 60/121 - loss 0.09072919 - time (sec): 5.35 - samples/sec: 2301.36 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:59:51,729 epoch 3 - iter 72/121 - loss 0.09249330 - time (sec): 6.42 - samples/sec: 2266.79 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:59:52,847 epoch 3 - iter 84/121 - loss 0.09443135 - time (sec): 7.54 - samples/sec: 2284.59 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:59:53,867 epoch 3 - iter 96/121 - loss 0.09325762 - time (sec): 8.56 - samples/sec: 2281.48 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:59:54,922 epoch 3 - iter 108/121 - loss 0.09097686 - time (sec): 9.61 - samples/sec: 2278.31 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:59:56,031 epoch 3 - iter 120/121 - loss 0.09128076 - time (sec): 10.72 - samples/sec: 2290.73 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:59:56,114 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:56,114 EPOCH 3 done: loss 0.0910 - lr: 0.000039
2023-10-23 19:59:56,807 DEV : loss 0.1323053240776062 - f1-score (micro avg)  0.8106
2023-10-23 19:59:56,811 saving best model
2023-10-23 19:59:57,406 ----------------------------------------------------------------------------------------------------
2023-10-23 19:59:58,417 epoch 4 - iter 12/121 - loss 0.05092027 - time (sec): 1.01 - samples/sec: 2312.39 - lr: 0.000038 - momentum: 0.000000
2023-10-23 19:59:59,520 epoch 4 - iter 24/121 - loss 0.06212240 - time (sec): 2.11 - samples/sec: 2304.30 - lr: 0.000038 - momentum: 0.000000
2023-10-23 20:00:00,562 epoch 4 - iter 36/121 - loss 0.05852911 - time (sec): 3.15 - samples/sec: 2276.45 - lr: 0.000037 - momentum: 0.000000
2023-10-23 20:00:01,620 epoch 4 - iter 48/121 - loss 0.06036113 - time (sec): 4.21 - samples/sec: 2270.68 - lr: 0.000037 - momentum: 0.000000
2023-10-23 20:00:02,680 epoch 4 - iter 60/121 - loss 0.05609362 - time (sec): 5.27 - samples/sec: 2276.99 - lr: 0.000036 - momentum: 0.000000
2023-10-23 20:00:03,701 epoch 4 - iter 72/121 - loss 0.05240872 - time (sec): 6.29 - samples/sec: 2247.96 - lr: 0.000036 - momentum: 0.000000
2023-10-23 20:00:04,781 epoch 4 - iter 84/121 - loss 0.04834580 - time (sec): 7.37 - samples/sec: 2228.20 - lr: 0.000035 - momentum: 0.000000
2023-10-23 20:00:05,957 epoch 4 - iter 96/121 - loss 0.05473980 - time (sec): 8.55 - samples/sec: 2254.70 - lr: 0.000035 - momentum: 0.000000
2023-10-23 20:00:07,110 epoch 4 - iter 108/121 - loss 0.05895589 - time (sec): 9.70 - samples/sec: 2268.69 - lr: 0.000034 - momentum: 0.000000
2023-10-23 20:00:08,206 epoch 4 - iter 120/121 - loss 0.05978098 - time (sec): 10.80 - samples/sec: 2275.78 - lr: 0.000034 - momentum: 0.000000
2023-10-23 20:00:08,290 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:08,290 EPOCH 4 done: loss 0.0597 - lr: 0.000034
2023-10-23 20:00:08,986 DEV : loss 0.1290253847837448 - f1-score (micro avg)  0.79
2023-10-23 20:00:08,989 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:10,039 epoch 5 - iter 12/121 - loss 0.03430261 - time (sec): 1.05 - samples/sec: 2397.71 - lr: 0.000033 - momentum: 0.000000
2023-10-23 20:00:11,110 epoch 5 - iter 24/121 - loss 0.03113545 - time (sec): 2.12 - samples/sec: 2368.57 - lr: 0.000032 - momentum: 0.000000
2023-10-23 20:00:12,219 epoch 5 - iter 36/121 - loss 0.03389822 - time (sec): 3.23 - samples/sec: 2338.77 - lr: 0.000032 - momentum: 0.000000
2023-10-23 20:00:13,228 epoch 5 - iter 48/121 - loss 0.03500522 - time (sec): 4.24 - samples/sec: 2356.81 - lr: 0.000031 - momentum: 0.000000
2023-10-23 20:00:14,317 epoch 5 - iter 60/121 - loss 0.03690220 - time (sec): 5.33 - samples/sec: 2368.75 - lr: 0.000031 - momentum: 0.000000
2023-10-23 20:00:15,318 epoch 5 - iter 72/121 - loss 0.03710540 - time (sec): 6.33 - samples/sec: 2356.98 - lr: 0.000030 - momentum: 0.000000
2023-10-23 20:00:16,402 epoch 5 - iter 84/121 - loss 0.03808002 - time (sec): 7.41 - samples/sec: 2338.35 - lr: 0.000030 - momentum: 0.000000
2023-10-23 20:00:17,429 epoch 5 - iter 96/121 - loss 0.03712274 - time (sec): 8.44 - samples/sec: 2353.04 - lr: 0.000029 - momentum: 0.000000
2023-10-23 20:00:18,560 epoch 5 - iter 108/121 - loss 0.04007529 - time (sec): 9.57 - samples/sec: 2348.40 - lr: 0.000029 - momentum: 0.000000
2023-10-23 20:00:19,687 epoch 5 - iter 120/121 - loss 0.03992887 - time (sec): 10.70 - samples/sec: 2306.30 - lr: 0.000028 - momentum: 0.000000
2023-10-23 20:00:19,750 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:19,750 EPOCH 5 done: loss 0.0403 - lr: 0.000028
2023-10-23 20:00:20,442 DEV : loss 0.1379198580980301 - f1-score (micro avg)  0.8054
2023-10-23 20:00:20,446 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:21,497 epoch 6 - iter 12/121 - loss 0.02230947 - time (sec): 1.05 - samples/sec: 2505.91 - lr: 0.000027 - momentum: 0.000000
2023-10-23 20:00:22,602 epoch 6 - iter 24/121 - loss 0.02239796 - time (sec): 2.16 - samples/sec: 2310.67 - lr: 0.000027 - momentum: 0.000000
2023-10-23 20:00:23,718 epoch 6 - iter 36/121 - loss 0.02492799 - time (sec): 3.27 - samples/sec: 2321.90 - lr: 0.000026 - momentum: 0.000000
2023-10-23 20:00:24,786 epoch 6 - iter 48/121 - loss 0.02725830 - time (sec): 4.34 - samples/sec: 2340.60 - lr: 0.000026 - momentum: 0.000000
2023-10-23 20:00:25,835 epoch 6 - iter 60/121 - loss 0.02864588 - time (sec): 5.39 - samples/sec: 2306.85 - lr: 0.000025 - momentum: 0.000000
2023-10-23 20:00:26,930 epoch 6 - iter 72/121 - loss 0.02827687 - time (sec): 6.48 - samples/sec: 2279.64 - lr: 0.000025 - momentum: 0.000000
2023-10-23 20:00:27,955 epoch 6 - iter 84/121 - loss 0.02653019 - time (sec): 7.51 - samples/sec: 2295.30 - lr: 0.000024 - momentum: 0.000000
2023-10-23 20:00:29,025 epoch 6 - iter 96/121 - loss 0.02717871 - time (sec): 8.58 - samples/sec: 2282.48 - lr: 0.000024 - momentum: 0.000000
2023-10-23 20:00:30,101 epoch 6 - iter 108/121 - loss 0.02708385 - time (sec): 9.65 - samples/sec: 2275.35 - lr: 0.000023 - momentum: 0.000000
2023-10-23 20:00:31,133 epoch 6 - iter 120/121 - loss 0.02633747 - time (sec): 10.69 - samples/sec: 2298.63 - lr: 0.000022 - momentum: 0.000000
2023-10-23 20:00:31,214 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:31,214 EPOCH 6 done: loss 0.0263 - lr: 0.000022
2023-10-23 20:00:31,913 DEV : loss 0.16080670058727264 - f1-score (micro avg)  0.8258
2023-10-23 20:00:31,917 saving best model
2023-10-23 20:00:32,581 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:33,615 epoch 7 - iter 12/121 - loss 0.02074966 - time (sec): 1.03 - samples/sec: 2311.18 - lr: 0.000022 - momentum: 0.000000
2023-10-23 20:00:34,651 epoch 7 - iter 24/121 - loss 0.01878873 - time (sec): 2.07 - samples/sec: 2223.35 - lr: 0.000021 - momentum: 0.000000
2023-10-23 20:00:35,744 epoch 7 - iter 36/121 - loss 0.01720420 - time (sec): 3.16 - samples/sec: 2200.01 - lr: 0.000021 - momentum: 0.000000
2023-10-23 20:00:36,788 epoch 7 - iter 48/121 - loss 0.01932259 - time (sec): 4.21 - samples/sec: 2202.57 - lr: 0.000020 - momentum: 0.000000
2023-10-23 20:00:37,774 epoch 7 - iter 60/121 - loss 0.01914114 - time (sec): 5.19 - samples/sec: 2224.74 - lr: 0.000020 - momentum: 0.000000
2023-10-23 20:00:38,862 epoch 7 - iter 72/121 - loss 0.01758141 - time (sec): 6.28 - samples/sec: 2271.85 - lr: 0.000019 - momentum: 0.000000
2023-10-23 20:00:40,038 epoch 7 - iter 84/121 - loss 0.01685052 - time (sec): 7.46 - samples/sec: 2281.38 - lr: 0.000019 - momentum: 0.000000
2023-10-23 20:00:41,100 epoch 7 - iter 96/121 - loss 0.01552190 - time (sec): 8.52 - samples/sec: 2280.82 - lr: 0.000018 - momentum: 0.000000
2023-10-23 20:00:42,229 epoch 7 - iter 108/121 - loss 0.01818659 - time (sec): 9.65 - samples/sec: 2287.84 - lr: 0.000017 - momentum: 0.000000
2023-10-23 20:00:43,311 epoch 7 - iter 120/121 - loss 0.01940174 - time (sec): 10.73 - samples/sec: 2296.03 - lr: 0.000017 - momentum: 0.000000
2023-10-23 20:00:43,382 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:43,383 EPOCH 7 done: loss 0.0202 - lr: 0.000017
2023-10-23 20:00:44,081 DEV : loss 0.18020081520080566 - f1-score (micro avg)  0.8294
2023-10-23 20:00:44,085 saving best model
2023-10-23 20:00:44,751 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:45,809 epoch 8 - iter 12/121 - loss 0.01761408 - time (sec): 1.06 - samples/sec: 2348.94 - lr: 0.000016 - momentum: 0.000000
2023-10-23 20:00:46,831 epoch 8 - iter 24/121 - loss 0.02027595 - time (sec): 2.08 - samples/sec: 2350.51 - lr: 0.000016 - momentum: 0.000000
2023-10-23 20:00:47,865 epoch 8 - iter 36/121 - loss 0.01628910 - time (sec): 3.11 - samples/sec: 2452.51 - lr: 0.000015 - momentum: 0.000000
2023-10-23 20:00:48,966 epoch 8 - iter 48/121 - loss 0.01485485 - time (sec): 4.21 - samples/sec: 2394.43 - lr: 0.000015 - momentum: 0.000000
2023-10-23 20:00:49,976 epoch 8 - iter 60/121 - loss 0.01541187 - time (sec): 5.22 - samples/sec: 2367.34 - lr: 0.000014 - momentum: 0.000000
2023-10-23 20:00:51,033 epoch 8 - iter 72/121 - loss 0.01495578 - time (sec): 6.28 - samples/sec: 2338.86 - lr: 0.000014 - momentum: 0.000000
2023-10-23 20:00:52,185 epoch 8 - iter 84/121 - loss 0.01524300 - time (sec): 7.43 - samples/sec: 2310.80 - lr: 0.000013 - momentum: 0.000000
2023-10-23 20:00:53,341 epoch 8 - iter 96/121 - loss 0.01542470 - time (sec): 8.59 - samples/sec: 2315.10 - lr: 0.000013 - momentum: 0.000000
2023-10-23 20:00:54,382 epoch 8 - iter 108/121 - loss 0.01467537 - time (sec): 9.63 - samples/sec: 2314.47 - lr: 0.000012 - momentum: 0.000000
2023-10-23 20:00:55,470 epoch 8 - iter 120/121 - loss 0.01388236 - time (sec): 10.72 - samples/sec: 2299.78 - lr: 0.000011 - momentum: 0.000000
2023-10-23 20:00:55,537 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:55,537 EPOCH 8 done: loss 0.0139 - lr: 0.000011
2023-10-23 20:00:56,237 DEV : loss 0.18324138224124908 - f1-score (micro avg)  0.8216
2023-10-23 20:00:56,241 ----------------------------------------------------------------------------------------------------
2023-10-23 20:00:57,349 epoch 9 - iter 12/121 - loss 0.00782875 - time (sec): 1.11 - samples/sec: 2349.70 - lr: 0.000011 - momentum: 0.000000
2023-10-23 20:00:58,425 epoch 9 - iter 24/121 - loss 0.00702085 - time (sec): 2.18 - samples/sec: 2335.49 - lr: 0.000010 - momentum: 0.000000
2023-10-23 20:00:59,503 epoch 9 - iter 36/121 - loss 0.01311710 - time (sec): 3.26 - samples/sec: 2308.62 - lr: 0.000010 - momentum: 0.000000
2023-10-23 20:01:00,553 epoch 9 - iter 48/121 - loss 0.01076139 - time (sec): 4.31 - samples/sec: 2283.64 - lr: 0.000009 - momentum: 0.000000
2023-10-23 20:01:01,561 epoch 9 - iter 60/121 - loss 0.00924692 - time (sec): 5.32 - samples/sec: 2234.26 - lr: 0.000009 - momentum: 0.000000
2023-10-23 20:01:02,677 epoch 9 - iter 72/121 - loss 0.00840260 - time (sec): 6.44 - samples/sec: 2253.81 - lr: 0.000008 - momentum: 0.000000
2023-10-23 20:01:03,694 epoch 9 - iter 84/121 - loss 0.00870079 - time (sec): 7.45 - samples/sec: 2267.62 - lr: 0.000008 - momentum: 0.000000
2023-10-23 20:01:04,830 epoch 9 - iter 96/121 - loss 0.00802366 - time (sec): 8.59 - samples/sec: 2270.15 - lr: 0.000007 - momentum: 0.000000
2023-10-23 20:01:05,923 epoch 9 - iter 108/121 - loss 0.00812464 - time (sec): 9.68 - samples/sec: 2262.78 - lr: 0.000006 - momentum: 0.000000
2023-10-23 20:01:06,981 epoch 9 - iter 120/121 - loss 0.00750621 - time (sec): 10.74 - samples/sec: 2292.48 - lr: 0.000006 - momentum: 0.000000
2023-10-23 20:01:07,046 ----------------------------------------------------------------------------------------------------
2023-10-23 20:01:07,046 EPOCH 9 done: loss 0.0075 - lr: 0.000006
2023-10-23 20:01:07,751 DEV : loss 0.1951816827058792 - f1-score (micro avg)  0.8374
2023-10-23 20:01:07,755 saving best model
2023-10-23 20:01:08,418 ----------------------------------------------------------------------------------------------------
2023-10-23 20:01:09,526 epoch 10 - iter 12/121 - loss 0.02006047 - time (sec): 1.11 - samples/sec: 2195.41 - lr: 0.000005 - momentum: 0.000000
2023-10-23 20:01:10,545 epoch 10 - iter 24/121 - loss 0.01565914 - time (sec): 2.13 - samples/sec: 2137.48 - lr: 0.000005 - momentum: 0.000000
2023-10-23 20:01:11,598 epoch 10 - iter 36/121 - loss 0.01230843 - time (sec): 3.18 - samples/sec: 2209.25 - lr: 0.000004 - momentum: 0.000000
2023-10-23 20:01:12,729 epoch 10 - iter 48/121 - loss 0.01136140 - time (sec): 4.31 - samples/sec: 2230.78 - lr: 0.000004 - momentum: 0.000000
2023-10-23 20:01:13,739 epoch 10 - iter 60/121 - loss 0.01075316 - time (sec): 5.32 - samples/sec: 2258.11 - lr: 0.000003 - momentum: 0.000000
2023-10-23 20:01:14,788 epoch 10 - iter 72/121 - loss 0.01033628 - time (sec): 6.37 - samples/sec: 2281.18 - lr: 0.000003 - momentum: 0.000000
2023-10-23 20:01:15,930 epoch 10 - iter 84/121 - loss 0.00887929 - time (sec): 7.51 - samples/sec: 2294.81 - lr: 0.000002 - momentum: 0.000000
2023-10-23 20:01:17,033 epoch 10 - iter 96/121 - loss 0.00817613 - time (sec): 8.61 - samples/sec: 2283.21 - lr: 0.000001 - momentum: 0.000000
2023-10-23 20:01:18,109 epoch 10 - iter 108/121 - loss 0.00725123 - time (sec): 9.69 - samples/sec: 2308.58 - lr: 0.000001 - momentum: 0.000000
2023-10-23 20:01:19,161 epoch 10 - iter 120/121 - loss 0.00693442 - time (sec): 10.74 - samples/sec: 2294.35 - lr: 0.000000 - momentum: 0.000000
2023-10-23 20:01:19,225 ----------------------------------------------------------------------------------------------------
2023-10-23 20:01:19,226 EPOCH 10 done: loss 0.0069 - lr: 0.000000
2023-10-23 20:01:19,922 DEV : loss 0.20193332433700562 - f1-score (micro avg)  0.8273
2023-10-23 20:01:20,406 ----------------------------------------------------------------------------------------------------
2023-10-23 20:01:20,407 Loading model from best epoch ...
2023-10-23 20:01:21,963 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-23 20:01:22,823 
Results:
- F-score (micro) 0.8113
- F-score (macro) 0.5613
- Accuracy 0.7049

By class:
              precision    recall  f1-score   support

        pers     0.8803    0.8993    0.8897       139
       scope     0.7929    0.8605    0.8253       129
        work     0.6667    0.7750    0.7168        80
         loc     0.4286    0.3333    0.3750         9
        date     0.0000    0.0000    0.0000         3

   micro avg     0.7880    0.8361    0.8113       360
   macro avg     0.5537    0.5736    0.5613       360
weighted avg     0.7829    0.8361    0.8079       360

2023-10-23 20:01:22,823 ----------------------------------------------------------------------------------------------------