2023-10-19 23:42:06,059 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,059 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 23:42:06,059 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,059 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 23:42:06,059 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,059 Train:  1166 sentences
2023-10-19 23:42:06,059         (train_with_dev=False, train_with_test=False)
2023-10-19 23:42:06,059 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,059 Training Params:
2023-10-19 23:42:06,059  - learning_rate: "3e-05" 
2023-10-19 23:42:06,059  - mini_batch_size: "4"
2023-10-19 23:42:06,059  - max_epochs: "10"
2023-10-19 23:42:06,060  - shuffle: "True"
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 Plugins:
2023-10-19 23:42:06,060  - TensorboardLogger
2023-10-19 23:42:06,060  - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 23:42:06,060  - metric: "('micro avg', 'f1-score')"
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 Computation:
2023-10-19 23:42:06,060  - compute on device: cuda:0
2023-10-19 23:42:06,060  - embedding storage: none
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:06,060 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 23:42:06,967 epoch 1 - iter 29/292 - loss 3.08591664 - time (sec): 0.91 - samples/sec: 5239.80 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:42:07,454 epoch 1 - iter 58/292 - loss 3.08024881 - time (sec): 1.39 - samples/sec: 6420.54 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:42:07,977 epoch 1 - iter 87/292 - loss 3.05119373 - time (sec): 1.92 - samples/sec: 7148.76 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:42:08,526 epoch 1 - iter 116/292 - loss 3.00830650 - time (sec): 2.47 - samples/sec: 7672.61 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:42:09,042 epoch 1 - iter 145/292 - loss 2.82533115 - time (sec): 2.98 - samples/sec: 7772.64 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:42:09,539 epoch 1 - iter 174/292 - loss 2.68196572 - time (sec): 3.48 - samples/sec: 7733.92 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:42:10,050 epoch 1 - iter 203/292 - loss 2.53889030 - time (sec): 3.99 - samples/sec: 7571.16 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:42:10,589 epoch 1 - iter 232/292 - loss 2.30235004 - time (sec): 4.53 - samples/sec: 7780.95 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:42:11,108 epoch 1 - iter 261/292 - loss 2.13326537 - time (sec): 5.05 - samples/sec: 7826.92 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:42:11,639 epoch 1 - iter 290/292 - loss 1.97964118 - time (sec): 5.58 - samples/sec: 7947.31 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:42:11,666 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:11,666 EPOCH 1 done: loss 1.9775 - lr: 0.000030
2023-10-19 23:42:12,081 DEV : loss 0.46280646324157715 - f1-score (micro avg)  0.0
2023-10-19 23:42:12,085 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:12,612 epoch 2 - iter 29/292 - loss 0.75100566 - time (sec): 0.53 - samples/sec: 9942.53 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:42:13,156 epoch 2 - iter 58/292 - loss 0.79963907 - time (sec): 1.07 - samples/sec: 9250.93 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:42:13,658 epoch 2 - iter 87/292 - loss 0.77458000 - time (sec): 1.57 - samples/sec: 8957.69 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:42:14,177 epoch 2 - iter 116/292 - loss 0.73709213 - time (sec): 2.09 - samples/sec: 9063.02 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:42:14,696 epoch 2 - iter 145/292 - loss 0.73824341 - time (sec): 2.61 - samples/sec: 8719.67 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:42:15,239 epoch 2 - iter 174/292 - loss 0.70725517 - time (sec): 3.15 - samples/sec: 8521.16 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:42:15,758 epoch 2 - iter 203/292 - loss 0.69621852 - time (sec): 3.67 - samples/sec: 8545.85 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:42:16,275 epoch 2 - iter 232/292 - loss 0.68754116 - time (sec): 4.19 - samples/sec: 8578.64 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:42:16,722 epoch 2 - iter 261/292 - loss 0.67062185 - time (sec): 4.64 - samples/sec: 8662.35 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:42:17,188 epoch 2 - iter 290/292 - loss 0.65439760 - time (sec): 5.10 - samples/sec: 8685.95 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:42:17,214 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:17,214 EPOCH 2 done: loss 0.6545 - lr: 0.000027
2023-10-19 23:42:17,832 DEV : loss 0.4219829738140106 - f1-score (micro avg)  0.0
2023-10-19 23:42:17,836 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:18,310 epoch 3 - iter 29/292 - loss 0.49006854 - time (sec): 0.47 - samples/sec: 9074.56 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:42:18,847 epoch 3 - iter 58/292 - loss 0.73232854 - time (sec): 1.01 - samples/sec: 8510.41 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:42:19,353 epoch 3 - iter 87/292 - loss 0.68251336 - time (sec): 1.52 - samples/sec: 8519.91 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:42:19,875 epoch 3 - iter 116/292 - loss 0.63235067 - time (sec): 2.04 - samples/sec: 8668.90 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:42:20,382 epoch 3 - iter 145/292 - loss 0.62468572 - time (sec): 2.55 - samples/sec: 8392.58 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:42:20,935 epoch 3 - iter 174/292 - loss 0.62606584 - time (sec): 3.10 - samples/sec: 8613.21 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:42:21,480 epoch 3 - iter 203/292 - loss 0.60290014 - time (sec): 3.64 - samples/sec: 8616.36 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:42:22,003 epoch 3 - iter 232/292 - loss 0.59361057 - time (sec): 4.17 - samples/sec: 8458.53 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:42:22,517 epoch 3 - iter 261/292 - loss 0.58612670 - time (sec): 4.68 - samples/sec: 8481.25 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:42:23,030 epoch 3 - iter 290/292 - loss 0.57753323 - time (sec): 5.19 - samples/sec: 8521.11 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:42:23,060 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:23,060 EPOCH 3 done: loss 0.5763 - lr: 0.000023
2023-10-19 23:42:23,827 DEV : loss 0.3529767692089081 - f1-score (micro avg)  0.0
2023-10-19 23:42:23,831 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:24,353 epoch 4 - iter 29/292 - loss 0.49689288 - time (sec): 0.52 - samples/sec: 8422.11 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:42:24,894 epoch 4 - iter 58/292 - loss 0.48782282 - time (sec): 1.06 - samples/sec: 8283.51 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:42:25,397 epoch 4 - iter 87/292 - loss 0.47892406 - time (sec): 1.57 - samples/sec: 8598.67 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:42:25,913 epoch 4 - iter 116/292 - loss 0.47218105 - time (sec): 2.08 - samples/sec: 8481.60 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:42:26,418 epoch 4 - iter 145/292 - loss 0.47202192 - time (sec): 2.59 - samples/sec: 8533.59 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:42:26,959 epoch 4 - iter 174/292 - loss 0.49078431 - time (sec): 3.13 - samples/sec: 8760.33 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:42:27,471 epoch 4 - iter 203/292 - loss 0.49917888 - time (sec): 3.64 - samples/sec: 8606.24 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:42:27,985 epoch 4 - iter 232/292 - loss 0.49683508 - time (sec): 4.15 - samples/sec: 8581.77 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:42:28,526 epoch 4 - iter 261/292 - loss 0.49461759 - time (sec): 4.69 - samples/sec: 8607.84 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:42:29,018 epoch 4 - iter 290/292 - loss 0.48994028 - time (sec): 5.19 - samples/sec: 8493.63 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:42:29,053 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:29,054 EPOCH 4 done: loss 0.4878 - lr: 0.000020
2023-10-19 23:42:29,684 DEV : loss 0.33182382583618164 - f1-score (micro avg)  0.0519
2023-10-19 23:42:29,688 saving best model
2023-10-19 23:42:29,718 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:30,243 epoch 5 - iter 29/292 - loss 0.47860587 - time (sec): 0.52 - samples/sec: 8301.65 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:42:30,758 epoch 5 - iter 58/292 - loss 0.45421070 - time (sec): 1.04 - samples/sec: 8889.91 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:42:31,321 epoch 5 - iter 87/292 - loss 0.50017143 - time (sec): 1.60 - samples/sec: 9120.81 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:42:31,851 epoch 5 - iter 116/292 - loss 0.50574198 - time (sec): 2.13 - samples/sec: 8859.29 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:42:32,349 epoch 5 - iter 145/292 - loss 0.48939797 - time (sec): 2.63 - samples/sec: 8699.48 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:42:32,872 epoch 5 - iter 174/292 - loss 0.47205527 - time (sec): 3.15 - samples/sec: 8561.62 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:42:33,426 epoch 5 - iter 203/292 - loss 0.47253502 - time (sec): 3.71 - samples/sec: 8455.14 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:42:33,921 epoch 5 - iter 232/292 - loss 0.46611011 - time (sec): 4.20 - samples/sec: 8486.53 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:42:34,435 epoch 5 - iter 261/292 - loss 0.45700445 - time (sec): 4.72 - samples/sec: 8402.90 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:42:34,991 epoch 5 - iter 290/292 - loss 0.44717647 - time (sec): 5.27 - samples/sec: 8382.89 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:42:35,027 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:35,027 EPOCH 5 done: loss 0.4469 - lr: 0.000017
2023-10-19 23:42:35,658 DEV : loss 0.329159677028656 - f1-score (micro avg)  0.11
2023-10-19 23:42:35,661 saving best model
2023-10-19 23:42:35,693 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:36,237 epoch 6 - iter 29/292 - loss 0.45931813 - time (sec): 0.54 - samples/sec: 9314.72 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:42:36,754 epoch 6 - iter 58/292 - loss 0.42547849 - time (sec): 1.06 - samples/sec: 8689.77 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:42:37,317 epoch 6 - iter 87/292 - loss 0.47113410 - time (sec): 1.62 - samples/sec: 8916.09 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:42:37,839 epoch 6 - iter 116/292 - loss 0.46155777 - time (sec): 2.15 - samples/sec: 8628.72 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:42:38,402 epoch 6 - iter 145/292 - loss 0.45884388 - time (sec): 2.71 - samples/sec: 8457.57 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:42:38,917 epoch 6 - iter 174/292 - loss 0.44123585 - time (sec): 3.22 - samples/sec: 8597.19 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:42:39,456 epoch 6 - iter 203/292 - loss 0.42472976 - time (sec): 3.76 - samples/sec: 8436.29 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:42:39,973 epoch 6 - iter 232/292 - loss 0.42486810 - time (sec): 4.28 - samples/sec: 8330.37 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:42:40,492 epoch 6 - iter 261/292 - loss 0.42696152 - time (sec): 4.80 - samples/sec: 8374.98 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:42:40,995 epoch 6 - iter 290/292 - loss 0.42408929 - time (sec): 5.30 - samples/sec: 8364.21 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:42:41,020 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:41,020 EPOCH 6 done: loss 0.4244 - lr: 0.000013
2023-10-19 23:42:41,649 DEV : loss 0.32003137469291687 - f1-score (micro avg)  0.152
2023-10-19 23:42:41,652 saving best model
2023-10-19 23:42:41,684 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:42,226 epoch 7 - iter 29/292 - loss 0.37862602 - time (sec): 0.54 - samples/sec: 9870.25 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:42:42,716 epoch 7 - iter 58/292 - loss 0.40722645 - time (sec): 1.03 - samples/sec: 9014.41 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:42:43,225 epoch 7 - iter 87/292 - loss 0.40708103 - time (sec): 1.54 - samples/sec: 8485.94 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:42:43,749 epoch 7 - iter 116/292 - loss 0.38567811 - time (sec): 2.06 - samples/sec: 8628.47 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:42:44,255 epoch 7 - iter 145/292 - loss 0.38065430 - time (sec): 2.57 - samples/sec: 8677.84 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:42:44,729 epoch 7 - iter 174/292 - loss 0.39464854 - time (sec): 3.04 - samples/sec: 8592.58 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:42:45,199 epoch 7 - iter 203/292 - loss 0.39435703 - time (sec): 3.51 - samples/sec: 8462.62 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:42:45,716 epoch 7 - iter 232/292 - loss 0.41885136 - time (sec): 4.03 - samples/sec: 8568.32 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:42:46,250 epoch 7 - iter 261/292 - loss 0.40635836 - time (sec): 4.56 - samples/sec: 8629.52 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:42:46,796 epoch 7 - iter 290/292 - loss 0.40642788 - time (sec): 5.11 - samples/sec: 8648.25 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:42:46,827 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:46,827 EPOCH 7 done: loss 0.4068 - lr: 0.000010
2023-10-19 23:42:47,470 DEV : loss 0.3101561963558197 - f1-score (micro avg)  0.1771
2023-10-19 23:42:47,474 saving best model
2023-10-19 23:42:47,505 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:48,025 epoch 8 - iter 29/292 - loss 0.39692250 - time (sec): 0.52 - samples/sec: 8387.53 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:42:48,555 epoch 8 - iter 58/292 - loss 0.40211436 - time (sec): 1.05 - samples/sec: 8139.94 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:42:49,109 epoch 8 - iter 87/292 - loss 0.37946836 - time (sec): 1.60 - samples/sec: 8053.82 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:42:49,638 epoch 8 - iter 116/292 - loss 0.37436871 - time (sec): 2.13 - samples/sec: 8028.81 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:42:50,165 epoch 8 - iter 145/292 - loss 0.38320782 - time (sec): 2.66 - samples/sec: 8267.49 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:42:50,661 epoch 8 - iter 174/292 - loss 0.37239817 - time (sec): 3.16 - samples/sec: 8175.80 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:42:51,161 epoch 8 - iter 203/292 - loss 0.38670704 - time (sec): 3.66 - samples/sec: 8324.35 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:42:51,691 epoch 8 - iter 232/292 - loss 0.40156103 - time (sec): 4.19 - samples/sec: 8530.79 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:42:52,196 epoch 8 - iter 261/292 - loss 0.40115704 - time (sec): 4.69 - samples/sec: 8501.21 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:42:52,760 epoch 8 - iter 290/292 - loss 0.39705366 - time (sec): 5.25 - samples/sec: 8409.61 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:42:52,798 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:52,799 EPOCH 8 done: loss 0.3972 - lr: 0.000007
2023-10-19 23:42:53,436 DEV : loss 0.3071003556251526 - f1-score (micro avg)  0.1917
2023-10-19 23:42:53,440 saving best model
2023-10-19 23:42:53,472 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:53,940 epoch 9 - iter 29/292 - loss 0.29746546 - time (sec): 0.47 - samples/sec: 10070.18 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:42:54,409 epoch 9 - iter 58/292 - loss 0.35506392 - time (sec): 0.94 - samples/sec: 9508.66 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:42:54,886 epoch 9 - iter 87/292 - loss 0.35396730 - time (sec): 1.41 - samples/sec: 9629.12 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:42:55,379 epoch 9 - iter 116/292 - loss 0.36343270 - time (sec): 1.91 - samples/sec: 9125.81 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:42:55,864 epoch 9 - iter 145/292 - loss 0.36432377 - time (sec): 2.39 - samples/sec: 9111.20 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:42:56,392 epoch 9 - iter 174/292 - loss 0.36168872 - time (sec): 2.92 - samples/sec: 9146.51 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:42:56,978 epoch 9 - iter 203/292 - loss 0.36858999 - time (sec): 3.51 - samples/sec: 9023.83 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:42:57,502 epoch 9 - iter 232/292 - loss 0.37232179 - time (sec): 4.03 - samples/sec: 8917.92 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:42:58,036 epoch 9 - iter 261/292 - loss 0.38336928 - time (sec): 4.56 - samples/sec: 8912.37 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:42:58,512 epoch 9 - iter 290/292 - loss 0.38695651 - time (sec): 5.04 - samples/sec: 8793.24 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:42:58,539 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:58,539 EPOCH 9 done: loss 0.3876 - lr: 0.000003
2023-10-19 23:42:59,308 DEV : loss 0.3116590082645416 - f1-score (micro avg)  0.1842
2023-10-19 23:42:59,312 ----------------------------------------------------------------------------------------------------
2023-10-19 23:42:59,844 epoch 10 - iter 29/292 - loss 0.28754311 - time (sec): 0.53 - samples/sec: 8273.26 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:43:00,349 epoch 10 - iter 58/292 - loss 0.32926331 - time (sec): 1.04 - samples/sec: 8670.32 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:43:00,849 epoch 10 - iter 87/292 - loss 0.36191922 - time (sec): 1.54 - samples/sec: 8343.15 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:43:01,357 epoch 10 - iter 116/292 - loss 0.38321652 - time (sec): 2.04 - samples/sec: 8290.88 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:43:01,851 epoch 10 - iter 145/292 - loss 0.40004916 - time (sec): 2.54 - samples/sec: 8267.04 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:43:02,355 epoch 10 - iter 174/292 - loss 0.38579499 - time (sec): 3.04 - samples/sec: 8332.74 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:43:02,866 epoch 10 - iter 203/292 - loss 0.37548323 - time (sec): 3.55 - samples/sec: 8364.88 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:43:03,398 epoch 10 - iter 232/292 - loss 0.37611261 - time (sec): 4.08 - samples/sec: 8522.01 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:43:03,915 epoch 10 - iter 261/292 - loss 0.37076893 - time (sec): 4.60 - samples/sec: 8506.28 - lr: 0.000000 - momentum: 0.000000
2023-10-19 23:43:04,459 epoch 10 - iter 290/292 - loss 0.39272161 - time (sec): 5.15 - samples/sec: 8606.84 - lr: 0.000000 - momentum: 0.000000
2023-10-19 23:43:04,488 ----------------------------------------------------------------------------------------------------
2023-10-19 23:43:04,488 EPOCH 10 done: loss 0.3923 - lr: 0.000000
2023-10-19 23:43:05,128 DEV : loss 0.3108135163784027 - f1-score (micro avg)  0.1927
2023-10-19 23:43:05,132 saving best model
2023-10-19 23:43:05,190 ----------------------------------------------------------------------------------------------------
2023-10-19 23:43:05,190 Loading model from best epoch ...
2023-10-19 23:43:05,263 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 23:43:06,146 
Results:
- F-score (micro) 0.2063
- F-score (macro) 0.1109
- Accuracy 0.1194

By class:
              precision    recall  f1-score   support

         PER     0.2196    0.1868    0.2019       348
         LOC     0.2460    0.2375    0.2417       261
         ORG     0.0000    0.0000    0.0000        52
   HumanProd     0.0000    0.0000    0.0000        22

   micro avg     0.2318    0.1859    0.2063       683
   macro avg     0.1164    0.1061    0.1109       683
weighted avg     0.2059    0.1859    0.1952       683

2023-10-19 23:43:06,146 ----------------------------------------------------------------------------------------------------