2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(32001, 128)
        (position_embeddings): Embedding(512, 128)
        (token_type_embeddings): Embedding(2, 128)
        (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): BertEncoder(
        (layer): ModuleList(
          (0-1): 2 x BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (query): Linear(in_features=128, out_features=128, bias=True)
                (key): Linear(in_features=128, out_features=128, bias=True)
                (value): Linear(in_features=128, out_features=128, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=128, out_features=128, bias=True)
                (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=128, out_features=512, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=512, out_features=128, bias=True)
              (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=128, out_features=128, bias=True)
        (activation): Tanh()
      )
    )
  )
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=128, out_features=17, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 MultiCorpus: 1166 train + 165 dev + 415 test sentences
 - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 Train:  1166 sentences
2023-10-19 23:50:48,376         (train_with_dev=False, train_with_test=False)
2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 Training Params:
2023-10-19 23:50:48,376  - learning_rate: "5e-05" 
2023-10-19 23:50:48,376  - mini_batch_size: "4"
2023-10-19 23:50:48,376  - max_epochs: "10"
2023-10-19 23:50:48,376  - shuffle: "True"
2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 Plugins:
2023-10-19 23:50:48,376  - TensorboardLogger
2023-10-19 23:50:48,376  - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 23:50:48,376 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,376 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 23:50:48,377  - metric: "('micro avg', 'f1-score')"
2023-10-19 23:50:48,377 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,377 Computation:
2023-10-19 23:50:48,377  - compute on device: cuda:0
2023-10-19 23:50:48,377  - embedding storage: none
2023-10-19 23:50:48,377 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,377 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-19 23:50:48,377 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,377 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:48,377 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 23:50:48,849 epoch 1 - iter 29/292 - loss 3.22243302 - time (sec): 0.47 - samples/sec: 10161.42 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:50:49,298 epoch 1 - iter 58/292 - loss 3.20624987 - time (sec): 0.92 - samples/sec: 9691.84 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:50:49,810 epoch 1 - iter 87/292 - loss 2.98916980 - time (sec): 1.43 - samples/sec: 9092.76 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:50:50,351 epoch 1 - iter 116/292 - loss 2.77841040 - time (sec): 1.97 - samples/sec: 8888.40 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:50:50,894 epoch 1 - iter 145/292 - loss 2.49252409 - time (sec): 2.52 - samples/sec: 8941.27 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:50:51,414 epoch 1 - iter 174/292 - loss 2.23806067 - time (sec): 3.04 - samples/sec: 8995.83 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:50:51,911 epoch 1 - iter 203/292 - loss 2.03398048 - time (sec): 3.53 - samples/sec: 8989.06 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:50:52,377 epoch 1 - iter 232/292 - loss 1.88035623 - time (sec): 4.00 - samples/sec: 8961.08 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:50:52,826 epoch 1 - iter 261/292 - loss 1.76391667 - time (sec): 4.45 - samples/sec: 8982.97 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:50:53,260 epoch 1 - iter 290/292 - loss 1.69158724 - time (sec): 4.88 - samples/sec: 9056.58 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:50:53,290 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:53,290 EPOCH 1 done: loss 1.6864 - lr: 0.000049
2023-10-19 23:50:53,554 DEV : loss 0.44552409648895264 - f1-score (micro avg)  0.0
2023-10-19 23:50:53,557 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:54,015 epoch 2 - iter 29/292 - loss 0.87211120 - time (sec): 0.46 - samples/sec: 11168.51 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:50:54,452 epoch 2 - iter 58/292 - loss 0.73871272 - time (sec): 0.89 - samples/sec: 10167.41 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:50:54,901 epoch 2 - iter 87/292 - loss 0.70824337 - time (sec): 1.34 - samples/sec: 10229.01 - lr: 0.000048 - momentum: 0.000000
2023-10-19 23:50:55,351 epoch 2 - iter 116/292 - loss 0.69477355 - time (sec): 1.79 - samples/sec: 10281.16 - lr: 0.000048 - momentum: 0.000000
2023-10-19 23:50:55,805 epoch 2 - iter 145/292 - loss 0.67851629 - time (sec): 2.25 - samples/sec: 10058.13 - lr: 0.000047 - momentum: 0.000000
2023-10-19 23:50:56,246 epoch 2 - iter 174/292 - loss 0.65542390 - time (sec): 2.69 - samples/sec: 9932.64 - lr: 0.000047 - momentum: 0.000000
2023-10-19 23:50:56,695 epoch 2 - iter 203/292 - loss 0.61918439 - time (sec): 3.14 - samples/sec: 9942.52 - lr: 0.000046 - momentum: 0.000000
2023-10-19 23:50:57,162 epoch 2 - iter 232/292 - loss 0.60027956 - time (sec): 3.60 - samples/sec: 9989.62 - lr: 0.000046 - momentum: 0.000000
2023-10-19 23:50:57,617 epoch 2 - iter 261/292 - loss 0.59366592 - time (sec): 4.06 - samples/sec: 9841.23 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:50:58,058 epoch 2 - iter 290/292 - loss 0.58070623 - time (sec): 4.50 - samples/sec: 9784.88 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:50:58,093 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:58,093 EPOCH 2 done: loss 0.5773 - lr: 0.000045
2023-10-19 23:50:58,733 DEV : loss 0.37034550309181213 - f1-score (micro avg)  0.0
2023-10-19 23:50:58,737 ----------------------------------------------------------------------------------------------------
2023-10-19 23:50:59,188 epoch 3 - iter 29/292 - loss 0.49497166 - time (sec): 0.45 - samples/sec: 9363.47 - lr: 0.000044 - momentum: 0.000000
2023-10-19 23:50:59,695 epoch 3 - iter 58/292 - loss 0.45692859 - time (sec): 0.96 - samples/sec: 9146.59 - lr: 0.000043 - momentum: 0.000000
2023-10-19 23:51:00,369 epoch 3 - iter 87/292 - loss 0.46560293 - time (sec): 1.63 - samples/sec: 8432.36 - lr: 0.000043 - momentum: 0.000000
2023-10-19 23:51:00,889 epoch 3 - iter 116/292 - loss 0.46387418 - time (sec): 2.15 - samples/sec: 8595.53 - lr: 0.000042 - momentum: 0.000000
2023-10-19 23:51:01,388 epoch 3 - iter 145/292 - loss 0.46052074 - time (sec): 2.65 - samples/sec: 8505.87 - lr: 0.000042 - momentum: 0.000000
2023-10-19 23:51:01,902 epoch 3 - iter 174/292 - loss 0.45427850 - time (sec): 3.16 - samples/sec: 8543.80 - lr: 0.000041 - momentum: 0.000000
2023-10-19 23:51:02,399 epoch 3 - iter 203/292 - loss 0.45002359 - time (sec): 3.66 - samples/sec: 8539.65 - lr: 0.000041 - momentum: 0.000000
2023-10-19 23:51:02,911 epoch 3 - iter 232/292 - loss 0.45747817 - time (sec): 4.17 - samples/sec: 8498.63 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:51:03,449 epoch 3 - iter 261/292 - loss 0.47679930 - time (sec): 4.71 - samples/sec: 8620.27 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:51:03,959 epoch 3 - iter 290/292 - loss 0.46645483 - time (sec): 5.22 - samples/sec: 8468.79 - lr: 0.000039 - momentum: 0.000000
2023-10-19 23:51:03,987 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:03,987 EPOCH 3 done: loss 0.4656 - lr: 0.000039
2023-10-19 23:51:04,637 DEV : loss 0.3335665762424469 - f1-score (micro avg)  0.1153
2023-10-19 23:51:04,641 saving best model
2023-10-19 23:51:04,668 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:05,179 epoch 4 - iter 29/292 - loss 0.36479034 - time (sec): 0.51 - samples/sec: 8697.27 - lr: 0.000038 - momentum: 0.000000
2023-10-19 23:51:05,698 epoch 4 - iter 58/292 - loss 0.38970094 - time (sec): 1.03 - samples/sec: 8388.64 - lr: 0.000038 - momentum: 0.000000
2023-10-19 23:51:06,234 epoch 4 - iter 87/292 - loss 0.40425548 - time (sec): 1.57 - samples/sec: 8111.07 - lr: 0.000037 - momentum: 0.000000
2023-10-19 23:51:06,845 epoch 4 - iter 116/292 - loss 0.45081769 - time (sec): 2.18 - samples/sec: 8130.16 - lr: 0.000037 - momentum: 0.000000
2023-10-19 23:51:07,343 epoch 4 - iter 145/292 - loss 0.45441040 - time (sec): 2.67 - samples/sec: 8108.29 - lr: 0.000036 - momentum: 0.000000
2023-10-19 23:51:07,875 epoch 4 - iter 174/292 - loss 0.44115447 - time (sec): 3.21 - samples/sec: 8102.11 - lr: 0.000036 - momentum: 0.000000
2023-10-19 23:51:08,385 epoch 4 - iter 203/292 - loss 0.42621077 - time (sec): 3.72 - samples/sec: 8051.74 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:51:08,896 epoch 4 - iter 232/292 - loss 0.41895612 - time (sec): 4.23 - samples/sec: 8347.05 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:51:09,341 epoch 4 - iter 261/292 - loss 0.41265617 - time (sec): 4.67 - samples/sec: 8444.46 - lr: 0.000034 - momentum: 0.000000
2023-10-19 23:51:09,789 epoch 4 - iter 290/292 - loss 0.41170960 - time (sec): 5.12 - samples/sec: 8581.60 - lr: 0.000033 - momentum: 0.000000
2023-10-19 23:51:09,825 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:09,825 EPOCH 4 done: loss 0.4088 - lr: 0.000033
2023-10-19 23:51:10,481 DEV : loss 0.3162705600261688 - f1-score (micro avg)  0.2162
2023-10-19 23:51:10,485 saving best model
2023-10-19 23:51:10,520 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:11,041 epoch 5 - iter 29/292 - loss 0.50926460 - time (sec): 0.52 - samples/sec: 9597.61 - lr: 0.000033 - momentum: 0.000000
2023-10-19 23:51:11,518 epoch 5 - iter 58/292 - loss 0.45616295 - time (sec): 1.00 - samples/sec: 9017.33 - lr: 0.000032 - momentum: 0.000000
2023-10-19 23:51:12,037 epoch 5 - iter 87/292 - loss 0.43782986 - time (sec): 1.52 - samples/sec: 8924.53 - lr: 0.000032 - momentum: 0.000000
2023-10-19 23:51:12,560 epoch 5 - iter 116/292 - loss 0.41173822 - time (sec): 2.04 - samples/sec: 9003.12 - lr: 0.000031 - momentum: 0.000000
2023-10-19 23:51:13,088 epoch 5 - iter 145/292 - loss 0.38731710 - time (sec): 2.57 - samples/sec: 8919.24 - lr: 0.000031 - momentum: 0.000000
2023-10-19 23:51:13,589 epoch 5 - iter 174/292 - loss 0.37951709 - time (sec): 3.07 - samples/sec: 8740.64 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:51:14,117 epoch 5 - iter 203/292 - loss 0.37385394 - time (sec): 3.60 - samples/sec: 8738.66 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:51:14,618 epoch 5 - iter 232/292 - loss 0.37845865 - time (sec): 4.10 - samples/sec: 8493.62 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:51:15,148 epoch 5 - iter 261/292 - loss 0.38159206 - time (sec): 4.63 - samples/sec: 8479.81 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:51:15,671 epoch 5 - iter 290/292 - loss 0.38335551 - time (sec): 5.15 - samples/sec: 8584.40 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:51:15,706 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:15,706 EPOCH 5 done: loss 0.3841 - lr: 0.000028
2023-10-19 23:51:16,349 DEV : loss 0.3012464940547943 - f1-score (micro avg)  0.2406
2023-10-19 23:51:16,353 saving best model
2023-10-19 23:51:16,384 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:16,887 epoch 6 - iter 29/292 - loss 0.43425194 - time (sec): 0.50 - samples/sec: 8783.99 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:51:17,383 epoch 6 - iter 58/292 - loss 0.37211198 - time (sec): 1.00 - samples/sec: 8853.67 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:51:17,886 epoch 6 - iter 87/292 - loss 0.36392128 - time (sec): 1.50 - samples/sec: 8853.92 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:51:18,392 epoch 6 - iter 116/292 - loss 0.36352925 - time (sec): 2.01 - samples/sec: 8472.41 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:51:18,826 epoch 6 - iter 145/292 - loss 0.35734890 - time (sec): 2.44 - samples/sec: 8948.74 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:51:19,383 epoch 6 - iter 174/292 - loss 0.37598998 - time (sec): 3.00 - samples/sec: 8953.88 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:51:19,878 epoch 6 - iter 203/292 - loss 0.36568988 - time (sec): 3.49 - samples/sec: 8938.70 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:51:20,384 epoch 6 - iter 232/292 - loss 0.35754127 - time (sec): 4.00 - samples/sec: 8856.18 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:51:20,923 epoch 6 - iter 261/292 - loss 0.34972551 - time (sec): 4.54 - samples/sec: 8896.85 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:51:21,467 epoch 6 - iter 290/292 - loss 0.35017829 - time (sec): 5.08 - samples/sec: 8713.79 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:51:21,499 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:21,499 EPOCH 6 done: loss 0.3499 - lr: 0.000022
2023-10-19 23:51:22,142 DEV : loss 0.2975820004940033 - f1-score (micro avg)  0.27
2023-10-19 23:51:22,146 saving best model
2023-10-19 23:51:22,179 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:22,693 epoch 7 - iter 29/292 - loss 0.31130874 - time (sec): 0.51 - samples/sec: 7832.13 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:51:23,207 epoch 7 - iter 58/292 - loss 0.29123507 - time (sec): 1.03 - samples/sec: 7869.70 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:51:23,702 epoch 7 - iter 87/292 - loss 0.31468314 - time (sec): 1.52 - samples/sec: 8236.11 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:51:24,213 epoch 7 - iter 116/292 - loss 0.35858794 - time (sec): 2.03 - samples/sec: 8265.29 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:51:24,712 epoch 7 - iter 145/292 - loss 0.35125244 - time (sec): 2.53 - samples/sec: 8266.49 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:51:25,229 epoch 7 - iter 174/292 - loss 0.34518322 - time (sec): 3.05 - samples/sec: 8207.41 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:51:25,759 epoch 7 - iter 203/292 - loss 0.34197644 - time (sec): 3.58 - samples/sec: 8331.88 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:51:26,262 epoch 7 - iter 232/292 - loss 0.34787407 - time (sec): 4.08 - samples/sec: 8396.22 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:51:26,800 epoch 7 - iter 261/292 - loss 0.34705316 - time (sec): 4.62 - samples/sec: 8535.47 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:51:27,318 epoch 7 - iter 290/292 - loss 0.33906214 - time (sec): 5.14 - samples/sec: 8608.91 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:51:27,351 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:27,352 EPOCH 7 done: loss 0.3387 - lr: 0.000017
2023-10-19 23:51:27,994 DEV : loss 0.2966740131378174 - f1-score (micro avg)  0.2664
2023-10-19 23:51:27,998 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:28,522 epoch 8 - iter 29/292 - loss 0.39739257 - time (sec): 0.52 - samples/sec: 9467.49 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:51:29,017 epoch 8 - iter 58/292 - loss 0.38110187 - time (sec): 1.02 - samples/sec: 9053.25 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:51:29,542 epoch 8 - iter 87/292 - loss 0.34916080 - time (sec): 1.54 - samples/sec: 8861.46 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:51:30,083 epoch 8 - iter 116/292 - loss 0.32786736 - time (sec): 2.08 - samples/sec: 8718.00 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:51:30,594 epoch 8 - iter 145/292 - loss 0.31442668 - time (sec): 2.60 - samples/sec: 8749.60 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:51:31,083 epoch 8 - iter 174/292 - loss 0.32556301 - time (sec): 3.08 - samples/sec: 8598.95 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:51:31,590 epoch 8 - iter 203/292 - loss 0.31650062 - time (sec): 3.59 - samples/sec: 8557.66 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:51:32,088 epoch 8 - iter 232/292 - loss 0.32518568 - time (sec): 4.09 - samples/sec: 8559.67 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:51:32,607 epoch 8 - iter 261/292 - loss 0.32110044 - time (sec): 4.61 - samples/sec: 8591.37 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:51:33,127 epoch 8 - iter 290/292 - loss 0.31875157 - time (sec): 5.13 - samples/sec: 8615.12 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:51:33,156 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:33,157 EPOCH 8 done: loss 0.3196 - lr: 0.000011
2023-10-19 23:51:33,801 DEV : loss 0.29454272985458374 - f1-score (micro avg)  0.2927
2023-10-19 23:51:33,805 saving best model
2023-10-19 23:51:33,835 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:34,348 epoch 9 - iter 29/292 - loss 0.27518256 - time (sec): 0.51 - samples/sec: 7791.93 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:51:34,873 epoch 9 - iter 58/292 - loss 0.31916693 - time (sec): 1.04 - samples/sec: 7833.79 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:51:35,396 epoch 9 - iter 87/292 - loss 0.31834315 - time (sec): 1.56 - samples/sec: 7902.04 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:51:35,905 epoch 9 - iter 116/292 - loss 0.30432217 - time (sec): 2.07 - samples/sec: 8014.70 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:51:36,408 epoch 9 - iter 145/292 - loss 0.30822599 - time (sec): 2.57 - samples/sec: 8295.55 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:51:36,927 epoch 9 - iter 174/292 - loss 0.30633165 - time (sec): 3.09 - samples/sec: 8457.57 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:51:37,621 epoch 9 - iter 203/292 - loss 0.31159779 - time (sec): 3.79 - samples/sec: 8292.00 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:51:38,156 epoch 9 - iter 232/292 - loss 0.31572775 - time (sec): 4.32 - samples/sec: 8384.78 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:51:38,685 epoch 9 - iter 261/292 - loss 0.31350571 - time (sec): 4.85 - samples/sec: 8353.07 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:51:39,206 epoch 9 - iter 290/292 - loss 0.31464480 - time (sec): 5.37 - samples/sec: 8228.25 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:51:39,238 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:39,238 EPOCH 9 done: loss 0.3138 - lr: 0.000006
2023-10-19 23:51:39,883 DEV : loss 0.2971099317073822 - f1-score (micro avg)  0.2857
2023-10-19 23:51:39,887 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:40,404 epoch 10 - iter 29/292 - loss 0.25483032 - time (sec): 0.52 - samples/sec: 9758.96 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:51:40,923 epoch 10 - iter 58/292 - loss 0.28927603 - time (sec): 1.04 - samples/sec: 8883.05 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:51:41,413 epoch 10 - iter 87/292 - loss 0.29004341 - time (sec): 1.53 - samples/sec: 8884.57 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:51:41,945 epoch 10 - iter 116/292 - loss 0.28359765 - time (sec): 2.06 - samples/sec: 8828.65 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:51:42,452 epoch 10 - iter 145/292 - loss 0.30454639 - time (sec): 2.56 - samples/sec: 8816.49 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:51:42,913 epoch 10 - iter 174/292 - loss 0.30780996 - time (sec): 3.03 - samples/sec: 8855.00 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:51:43,316 epoch 10 - iter 203/292 - loss 0.31045815 - time (sec): 3.43 - samples/sec: 8830.02 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:51:43,759 epoch 10 - iter 232/292 - loss 0.30187865 - time (sec): 3.87 - samples/sec: 9022.93 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:51:44,210 epoch 10 - iter 261/292 - loss 0.30851920 - time (sec): 4.32 - samples/sec: 9230.63 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:51:44,648 epoch 10 - iter 290/292 - loss 0.30888921 - time (sec): 4.76 - samples/sec: 9285.01 - lr: 0.000000 - momentum: 0.000000
2023-10-19 23:51:44,678 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:44,679 EPOCH 10 done: loss 0.3095 - lr: 0.000000
2023-10-19 23:51:45,340 DEV : loss 0.2977375388145447 - f1-score (micro avg)  0.2915
2023-10-19 23:51:45,372 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:45,373 Loading model from best epoch ...
2023-10-19 23:51:45,446 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-19 23:51:46,362 
Results:
- F-score (micro) 0.3418
- F-score (macro) 0.1805
- Accuracy 0.2161

By class:
              precision    recall  f1-score   support

         PER     0.3663    0.3621    0.3642       348
         LOC     0.3010    0.4406    0.3577       261
         ORG     0.0000    0.0000    0.0000        52
   HumanProd     0.0000    0.0000    0.0000        22

   micro avg     0.3315    0.3529    0.3418       683
   macro avg     0.1668    0.2007    0.1805       683
weighted avg     0.3017    0.3529    0.3222       683

2023-10-19 23:51:46,363 ----------------------------------------------------------------------------------------------------