2023-10-23 19:28:08,429 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,430 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(
          (0-11): 12 x 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 19:28:08,430 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 MultiCorpus: 1214 train + 266 dev + 251 test sentences
 - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-23 19:28:08,431 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 Train:  1214 sentences
2023-10-23 19:28:08,431         (train_with_dev=False, train_with_test=False)
2023-10-23 19:28:08,431 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 Training Params:
2023-10-23 19:28:08,431  - learning_rate: "5e-05" 
2023-10-23 19:28:08,431  - mini_batch_size: "8"
2023-10-23 19:28:08,431  - max_epochs: "10"
2023-10-23 19:28:08,431  - shuffle: "True"
2023-10-23 19:28:08,431 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 Plugins:
2023-10-23 19:28:08,431  - TensorboardLogger
2023-10-23 19:28:08,431  - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 19:28:08,431 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 19:28:08,431  - metric: "('micro avg', 'f1-score')"
2023-10-23 19:28:08,431 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,431 Computation:
2023-10-23 19:28:08,431  - compute on device: cuda:0
2023-10-23 19:28:08,431  - embedding storage: none
2023-10-23 19:28:08,432 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,432 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-23 19:28:08,432 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,432 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:08,432 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 19:28:09,278 epoch 1 - iter 15/152 - loss 3.10648646 - time (sec): 0.84 - samples/sec: 3984.83 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:28:10,112 epoch 1 - iter 30/152 - loss 2.33164226 - time (sec): 1.68 - samples/sec: 3693.19 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:28:10,967 epoch 1 - iter 45/152 - loss 1.82550350 - time (sec): 2.53 - samples/sec: 3578.86 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:28:11,839 epoch 1 - iter 60/152 - loss 1.51983686 - time (sec): 3.41 - samples/sec: 3628.68 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:28:12,657 epoch 1 - iter 75/152 - loss 1.30217273 - time (sec): 4.22 - samples/sec: 3693.90 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:28:13,510 epoch 1 - iter 90/152 - loss 1.12831185 - time (sec): 5.08 - samples/sec: 3746.55 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:28:14,342 epoch 1 - iter 105/152 - loss 1.01865170 - time (sec): 5.91 - samples/sec: 3713.99 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:28:15,186 epoch 1 - iter 120/152 - loss 0.92895552 - time (sec): 6.75 - samples/sec: 3684.10 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:28:16,042 epoch 1 - iter 135/152 - loss 0.85596346 - time (sec): 7.61 - samples/sec: 3628.83 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:28:16,909 epoch 1 - iter 150/152 - loss 0.79169534 - time (sec): 8.48 - samples/sec: 3615.90 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:28:17,000 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:17,000 EPOCH 1 done: loss 0.7869 - lr: 0.000049
2023-10-23 19:28:17,675 DEV : loss 0.17555871605873108 - f1-score (micro avg)  0.7241
2023-10-23 19:28:17,685 saving best model
2023-10-23 19:28:18,082 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:18,959 epoch 2 - iter 15/152 - loss 0.23088170 - time (sec): 0.88 - samples/sec: 3778.61 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:28:19,787 epoch 2 - iter 30/152 - loss 0.18940597 - time (sec): 1.70 - samples/sec: 3699.68 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:28:20,663 epoch 2 - iter 45/152 - loss 0.17596696 - time (sec): 2.58 - samples/sec: 3611.36 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:28:21,527 epoch 2 - iter 60/152 - loss 0.17248666 - time (sec): 3.44 - samples/sec: 3642.05 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:28:22,396 epoch 2 - iter 75/152 - loss 0.15126558 - time (sec): 4.31 - samples/sec: 3622.59 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:28:23,265 epoch 2 - iter 90/152 - loss 0.13949180 - time (sec): 5.18 - samples/sec: 3644.41 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:28:24,125 epoch 2 - iter 105/152 - loss 0.13155953 - time (sec): 6.04 - samples/sec: 3625.26 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:28:24,985 epoch 2 - iter 120/152 - loss 0.13163124 - time (sec): 6.90 - samples/sec: 3570.07 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:28:25,857 epoch 2 - iter 135/152 - loss 0.12690132 - time (sec): 7.77 - samples/sec: 3584.31 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:28:26,710 epoch 2 - iter 150/152 - loss 0.12777232 - time (sec): 8.63 - samples/sec: 3554.88 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:28:26,822 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:26,822 EPOCH 2 done: loss 0.1277 - lr: 0.000045
2023-10-23 19:28:27,736 DEV : loss 0.1446673572063446 - f1-score (micro avg)  0.7878
2023-10-23 19:28:27,743 saving best model
2023-10-23 19:28:28,402 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:29,273 epoch 3 - iter 15/152 - loss 0.08514465 - time (sec): 0.87 - samples/sec: 3710.70 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:28:30,146 epoch 3 - iter 30/152 - loss 0.07536261 - time (sec): 1.74 - samples/sec: 3563.02 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:28:31,015 epoch 3 - iter 45/152 - loss 0.08092261 - time (sec): 2.61 - samples/sec: 3611.93 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:28:31,878 epoch 3 - iter 60/152 - loss 0.08371129 - time (sec): 3.47 - samples/sec: 3540.87 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:28:32,727 epoch 3 - iter 75/152 - loss 0.08306079 - time (sec): 4.32 - samples/sec: 3500.89 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:28:33,570 epoch 3 - iter 90/152 - loss 0.07751458 - time (sec): 5.17 - samples/sec: 3456.61 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:28:34,439 epoch 3 - iter 105/152 - loss 0.07481885 - time (sec): 6.04 - samples/sec: 3443.68 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:28:35,282 epoch 3 - iter 120/152 - loss 0.07386486 - time (sec): 6.88 - samples/sec: 3479.71 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:28:36,163 epoch 3 - iter 135/152 - loss 0.07377200 - time (sec): 7.76 - samples/sec: 3535.31 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:28:37,002 epoch 3 - iter 150/152 - loss 0.07689373 - time (sec): 8.60 - samples/sec: 3572.07 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:28:37,112 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:37,112 EPOCH 3 done: loss 0.0763 - lr: 0.000039
2023-10-23 19:28:37,989 DEV : loss 0.15523318946361542 - f1-score (micro avg)  0.8092
2023-10-23 19:28:37,998 saving best model
2023-10-23 19:28:38,516 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:39,370 epoch 4 - iter 15/152 - loss 0.04245603 - time (sec): 0.85 - samples/sec: 3430.27 - lr: 0.000038 - momentum: 0.000000
2023-10-23 19:28:40,236 epoch 4 - iter 30/152 - loss 0.04183888 - time (sec): 1.72 - samples/sec: 3448.54 - lr: 0.000038 - momentum: 0.000000
2023-10-23 19:28:41,097 epoch 4 - iter 45/152 - loss 0.04138118 - time (sec): 2.58 - samples/sec: 3515.09 - lr: 0.000037 - momentum: 0.000000
2023-10-23 19:28:41,924 epoch 4 - iter 60/152 - loss 0.04323066 - time (sec): 3.41 - samples/sec: 3538.06 - lr: 0.000037 - momentum: 0.000000
2023-10-23 19:28:42,781 epoch 4 - iter 75/152 - loss 0.04776832 - time (sec): 4.26 - samples/sec: 3577.93 - lr: 0.000036 - momentum: 0.000000
2023-10-23 19:28:43,653 epoch 4 - iter 90/152 - loss 0.05529293 - time (sec): 5.14 - samples/sec: 3602.26 - lr: 0.000036 - momentum: 0.000000
2023-10-23 19:28:44,515 epoch 4 - iter 105/152 - loss 0.05509916 - time (sec): 6.00 - samples/sec: 3592.56 - lr: 0.000035 - momentum: 0.000000
2023-10-23 19:28:45,379 epoch 4 - iter 120/152 - loss 0.05794470 - time (sec): 6.86 - samples/sec: 3563.03 - lr: 0.000035 - momentum: 0.000000
2023-10-23 19:28:46,245 epoch 4 - iter 135/152 - loss 0.05422696 - time (sec): 7.73 - samples/sec: 3558.09 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:28:47,078 epoch 4 - iter 150/152 - loss 0.05209033 - time (sec): 8.56 - samples/sec: 3576.31 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:28:47,190 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:47,190 EPOCH 4 done: loss 0.0519 - lr: 0.000034
2023-10-23 19:28:48,085 DEV : loss 0.18392440676689148 - f1-score (micro avg)  0.8079
2023-10-23 19:28:48,093 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:49,006 epoch 5 - iter 15/152 - loss 0.04447125 - time (sec): 0.91 - samples/sec: 3358.25 - lr: 0.000033 - momentum: 0.000000
2023-10-23 19:28:49,766 epoch 5 - iter 30/152 - loss 0.04714366 - time (sec): 1.67 - samples/sec: 3627.35 - lr: 0.000032 - momentum: 0.000000
2023-10-23 19:28:50,536 epoch 5 - iter 45/152 - loss 0.04987880 - time (sec): 2.44 - samples/sec: 3739.89 - lr: 0.000032 - momentum: 0.000000
2023-10-23 19:28:51,306 epoch 5 - iter 60/152 - loss 0.04607296 - time (sec): 3.21 - samples/sec: 3900.27 - lr: 0.000031 - momentum: 0.000000
2023-10-23 19:28:52,069 epoch 5 - iter 75/152 - loss 0.03822405 - time (sec): 3.98 - samples/sec: 3888.83 - lr: 0.000031 - momentum: 0.000000
2023-10-23 19:28:52,850 epoch 5 - iter 90/152 - loss 0.03458092 - time (sec): 4.76 - samples/sec: 3895.36 - lr: 0.000030 - momentum: 0.000000
2023-10-23 19:28:53,619 epoch 5 - iter 105/152 - loss 0.03789100 - time (sec): 5.53 - samples/sec: 3850.24 - lr: 0.000030 - momentum: 0.000000
2023-10-23 19:28:54,504 epoch 5 - iter 120/152 - loss 0.03788481 - time (sec): 6.41 - samples/sec: 3810.44 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:28:55,276 epoch 5 - iter 135/152 - loss 0.03869103 - time (sec): 7.18 - samples/sec: 3801.36 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:28:56,063 epoch 5 - iter 150/152 - loss 0.03797828 - time (sec): 7.97 - samples/sec: 3826.56 - lr: 0.000028 - momentum: 0.000000
2023-10-23 19:28:56,164 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:56,165 EPOCH 5 done: loss 0.0375 - lr: 0.000028
2023-10-23 19:28:57,041 DEV : loss 0.20153838396072388 - f1-score (micro avg)  0.8371
2023-10-23 19:28:57,048 saving best model
2023-10-23 19:28:57,549 ----------------------------------------------------------------------------------------------------
2023-10-23 19:28:58,346 epoch 6 - iter 15/152 - loss 0.02879222 - time (sec): 0.80 - samples/sec: 4192.02 - lr: 0.000027 - momentum: 0.000000
2023-10-23 19:28:59,112 epoch 6 - iter 30/152 - loss 0.02821820 - time (sec): 1.56 - samples/sec: 4051.47 - lr: 0.000027 - momentum: 0.000000
2023-10-23 19:28:59,871 epoch 6 - iter 45/152 - loss 0.02466846 - time (sec): 2.32 - samples/sec: 4034.06 - lr: 0.000026 - momentum: 0.000000
2023-10-23 19:29:00,634 epoch 6 - iter 60/152 - loss 0.02314493 - time (sec): 3.08 - samples/sec: 4016.79 - lr: 0.000026 - momentum: 0.000000
2023-10-23 19:29:01,388 epoch 6 - iter 75/152 - loss 0.02224728 - time (sec): 3.84 - samples/sec: 4013.33 - lr: 0.000025 - momentum: 0.000000
2023-10-23 19:29:02,171 epoch 6 - iter 90/152 - loss 0.02816283 - time (sec): 4.62 - samples/sec: 4012.09 - lr: 0.000025 - momentum: 0.000000
2023-10-23 19:29:02,946 epoch 6 - iter 105/152 - loss 0.02704570 - time (sec): 5.40 - samples/sec: 4043.38 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:29:03,723 epoch 6 - iter 120/152 - loss 0.02486045 - time (sec): 6.17 - samples/sec: 4044.02 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:29:04,503 epoch 6 - iter 135/152 - loss 0.02530614 - time (sec): 6.95 - samples/sec: 4011.16 - lr: 0.000023 - momentum: 0.000000
2023-10-23 19:29:05,287 epoch 6 - iter 150/152 - loss 0.02764711 - time (sec): 7.74 - samples/sec: 3969.18 - lr: 0.000022 - momentum: 0.000000
2023-10-23 19:29:05,383 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:05,384 EPOCH 6 done: loss 0.0281 - lr: 0.000022
2023-10-23 19:29:06,278 DEV : loss 0.20378239452838898 - f1-score (micro avg)  0.8225
2023-10-23 19:29:06,285 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:07,178 epoch 7 - iter 15/152 - loss 0.02113138 - time (sec): 0.89 - samples/sec: 3354.88 - lr: 0.000022 - momentum: 0.000000
2023-10-23 19:29:07,950 epoch 7 - iter 30/152 - loss 0.02628674 - time (sec): 1.66 - samples/sec: 3661.29 - lr: 0.000021 - momentum: 0.000000
2023-10-23 19:29:08,724 epoch 7 - iter 45/152 - loss 0.02140093 - time (sec): 2.44 - samples/sec: 3788.69 - lr: 0.000021 - momentum: 0.000000
2023-10-23 19:29:09,516 epoch 7 - iter 60/152 - loss 0.02213689 - time (sec): 3.23 - samples/sec: 3695.13 - lr: 0.000020 - momentum: 0.000000
2023-10-23 19:29:10,387 epoch 7 - iter 75/152 - loss 0.01950359 - time (sec): 4.10 - samples/sec: 3670.30 - lr: 0.000020 - momentum: 0.000000
2023-10-23 19:29:11,171 epoch 7 - iter 90/152 - loss 0.01677011 - time (sec): 4.88 - samples/sec: 3791.03 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:29:11,947 epoch 7 - iter 105/152 - loss 0.01741335 - time (sec): 5.66 - samples/sec: 3818.79 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:29:12,733 epoch 7 - iter 120/152 - loss 0.02038706 - time (sec): 6.45 - samples/sec: 3805.18 - lr: 0.000018 - momentum: 0.000000
2023-10-23 19:29:13,537 epoch 7 - iter 135/152 - loss 0.02097207 - time (sec): 7.25 - samples/sec: 3790.29 - lr: 0.000017 - momentum: 0.000000
2023-10-23 19:29:14,313 epoch 7 - iter 150/152 - loss 0.01937167 - time (sec): 8.03 - samples/sec: 3822.64 - lr: 0.000017 - momentum: 0.000000
2023-10-23 19:29:14,412 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:14,412 EPOCH 7 done: loss 0.0192 - lr: 0.000017
2023-10-23 19:29:15,329 DEV : loss 0.20130547881126404 - f1-score (micro avg)  0.8427
2023-10-23 19:29:15,336 saving best model
2023-10-23 19:29:15,855 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:16,759 epoch 8 - iter 15/152 - loss 0.02170272 - time (sec): 0.90 - samples/sec: 3254.23 - lr: 0.000016 - momentum: 0.000000
2023-10-23 19:29:17,577 epoch 8 - iter 30/152 - loss 0.01763891 - time (sec): 1.72 - samples/sec: 3485.37 - lr: 0.000016 - momentum: 0.000000
2023-10-23 19:29:18,366 epoch 8 - iter 45/152 - loss 0.01238472 - time (sec): 2.51 - samples/sec: 3551.52 - lr: 0.000015 - momentum: 0.000000
2023-10-23 19:29:19,139 epoch 8 - iter 60/152 - loss 0.01226530 - time (sec): 3.28 - samples/sec: 3663.76 - lr: 0.000015 - momentum: 0.000000
2023-10-23 19:29:19,914 epoch 8 - iter 75/152 - loss 0.01160501 - time (sec): 4.06 - samples/sec: 3778.54 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:29:20,684 epoch 8 - iter 90/152 - loss 0.01177711 - time (sec): 4.83 - samples/sec: 3841.11 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:29:21,460 epoch 8 - iter 105/152 - loss 0.01087581 - time (sec): 5.60 - samples/sec: 3813.59 - lr: 0.000013 - momentum: 0.000000
2023-10-23 19:29:22,244 epoch 8 - iter 120/152 - loss 0.01153989 - time (sec): 6.39 - samples/sec: 3857.68 - lr: 0.000012 - momentum: 0.000000
2023-10-23 19:29:23,036 epoch 8 - iter 135/152 - loss 0.01255713 - time (sec): 7.18 - samples/sec: 3823.39 - lr: 0.000012 - momentum: 0.000000
2023-10-23 19:29:23,834 epoch 8 - iter 150/152 - loss 0.01303708 - time (sec): 7.98 - samples/sec: 3843.33 - lr: 0.000011 - momentum: 0.000000
2023-10-23 19:29:23,932 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:23,932 EPOCH 8 done: loss 0.0129 - lr: 0.000011
2023-10-23 19:29:24,810 DEV : loss 0.21092796325683594 - f1-score (micro avg)  0.8456
2023-10-23 19:29:24,817 saving best model
2023-10-23 19:29:25,320 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:26,175 epoch 9 - iter 15/152 - loss 0.00011508 - time (sec): 0.85 - samples/sec: 3724.58 - lr: 0.000011 - momentum: 0.000000
2023-10-23 19:29:26,962 epoch 9 - iter 30/152 - loss 0.00278332 - time (sec): 1.64 - samples/sec: 3656.76 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:29:27,751 epoch 9 - iter 45/152 - loss 0.00818942 - time (sec): 2.43 - samples/sec: 3757.98 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:29:28,521 epoch 9 - iter 60/152 - loss 0.00722370 - time (sec): 3.20 - samples/sec: 3761.30 - lr: 0.000009 - momentum: 0.000000
2023-10-23 19:29:29,292 epoch 9 - iter 75/152 - loss 0.01017300 - time (sec): 3.97 - samples/sec: 3843.65 - lr: 0.000009 - momentum: 0.000000
2023-10-23 19:29:30,082 epoch 9 - iter 90/152 - loss 0.00876407 - time (sec): 4.76 - samples/sec: 3900.72 - lr: 0.000008 - momentum: 0.000000
2023-10-23 19:29:30,903 epoch 9 - iter 105/152 - loss 0.00762758 - time (sec): 5.58 - samples/sec: 3907.45 - lr: 0.000007 - momentum: 0.000000
2023-10-23 19:29:31,827 epoch 9 - iter 120/152 - loss 0.01050398 - time (sec): 6.51 - samples/sec: 3823.95 - lr: 0.000007 - momentum: 0.000000
2023-10-23 19:29:32,700 epoch 9 - iter 135/152 - loss 0.01066733 - time (sec): 7.38 - samples/sec: 3763.03 - lr: 0.000006 - momentum: 0.000000
2023-10-23 19:29:33,502 epoch 9 - iter 150/152 - loss 0.01058936 - time (sec): 8.18 - samples/sec: 3748.94 - lr: 0.000006 - momentum: 0.000000
2023-10-23 19:29:33,608 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:33,609 EPOCH 9 done: loss 0.0105 - lr: 0.000006
2023-10-23 19:29:34,499 DEV : loss 0.2129676789045334 - f1-score (micro avg)  0.8442
2023-10-23 19:29:34,506 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:35,338 epoch 10 - iter 15/152 - loss 0.00005689 - time (sec): 0.83 - samples/sec: 3348.89 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:29:36,118 epoch 10 - iter 30/152 - loss 0.00575367 - time (sec): 1.61 - samples/sec: 3943.53 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:29:36,896 epoch 10 - iter 45/152 - loss 0.00850168 - time (sec): 2.39 - samples/sec: 3940.24 - lr: 0.000004 - momentum: 0.000000
2023-10-23 19:29:37,678 epoch 10 - iter 60/152 - loss 0.00671911 - time (sec): 3.17 - samples/sec: 4078.92 - lr: 0.000004 - momentum: 0.000000
2023-10-23 19:29:38,439 epoch 10 - iter 75/152 - loss 0.00697453 - time (sec): 3.93 - samples/sec: 4044.19 - lr: 0.000003 - momentum: 0.000000
2023-10-23 19:29:39,263 epoch 10 - iter 90/152 - loss 0.00828962 - time (sec): 4.76 - samples/sec: 3959.63 - lr: 0.000003 - momentum: 0.000000
2023-10-23 19:29:40,055 epoch 10 - iter 105/152 - loss 0.00769316 - time (sec): 5.55 - samples/sec: 3902.67 - lr: 0.000002 - momentum: 0.000000
2023-10-23 19:29:40,824 epoch 10 - iter 120/152 - loss 0.00810457 - time (sec): 6.32 - samples/sec: 3921.56 - lr: 0.000001 - momentum: 0.000000
2023-10-23 19:29:41,642 epoch 10 - iter 135/152 - loss 0.00770051 - time (sec): 7.13 - samples/sec: 3906.11 - lr: 0.000001 - momentum: 0.000000
2023-10-23 19:29:42,439 epoch 10 - iter 150/152 - loss 0.00755195 - time (sec): 7.93 - samples/sec: 3877.78 - lr: 0.000000 - momentum: 0.000000
2023-10-23 19:29:42,535 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:42,535 EPOCH 10 done: loss 0.0075 - lr: 0.000000
2023-10-23 19:29:43,396 DEV : loss 0.21681025624275208 - f1-score (micro avg)  0.85
2023-10-23 19:29:43,403 saving best model
2023-10-23 19:29:44,360 ----------------------------------------------------------------------------------------------------
2023-10-23 19:29:44,361 Loading model from best epoch ...
2023-10-23 19:29:46,174 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
2023-10-23 19:29:47,016 
Results:
- F-score (micro) 0.8253
- F-score (macro) 0.7022
- Accuracy 0.7143

By class:
              precision    recall  f1-score   support

       scope     0.7848    0.8212    0.8026       151
        pers     0.7895    0.9375    0.8571        96
        work     0.8300    0.8737    0.8513        95
        date     0.0000    0.0000    0.0000         3
         loc     1.0000    1.0000    1.0000         3

   micro avg     0.7916    0.8621    0.8253       348
   macro avg     0.6809    0.7265    0.7022       348
weighted avg     0.7935    0.8621    0.8257       348

2023-10-23 19:29:47,016 ----------------------------------------------------------------------------------------------------