2023-10-12 08:01:20,925 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,929 Model: "SequenceTagger(
  (embeddings): ByT5Embeddings(
    (model): T5EncoderModel(
      (shared): Embedding(384, 1472)
      (encoder): T5Stack(
        (embed_tokens): Embedding(384, 1472)
        (block): ModuleList(
          (0): T5Block(
            (layer): ModuleList(
              (0): T5LayerSelfAttention(
                (SelfAttention): T5Attention(
                  (q): Linear(in_features=1472, out_features=384, bias=False)
                  (k): Linear(in_features=1472, out_features=384, bias=False)
                  (v): Linear(in_features=1472, out_features=384, bias=False)
                  (o): Linear(in_features=384, out_features=1472, bias=False)
                  (relative_attention_bias): Embedding(32, 6)
                )
                (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (1): T5LayerFF(
                (DenseReluDense): T5DenseGatedActDense(
                  (wi_0): Linear(in_features=1472, out_features=3584, bias=False)
                  (wi_1): Linear(in_features=1472, out_features=3584, bias=False)
                  (wo): Linear(in_features=3584, out_features=1472, bias=False)
                  (dropout): Dropout(p=0.1, inplace=False)
                  (act): NewGELUActivation()
                )
                (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
          )
          (1-11): 11 x T5Block(
            (layer): ModuleList(
              (0): T5LayerSelfAttention(
                (SelfAttention): T5Attention(
                  (q): Linear(in_features=1472, out_features=384, bias=False)
                  (k): Linear(in_features=1472, out_features=384, bias=False)
                  (v): Linear(in_features=1472, out_features=384, bias=False)
                  (o): Linear(in_features=384, out_features=1472, bias=False)
                )
                (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (1): T5LayerFF(
                (DenseReluDense): T5DenseGatedActDense(
                  (wi_0): Linear(in_features=1472, out_features=3584, bias=False)
                  (wi_1): Linear(in_features=1472, out_features=3584, bias=False)
                  (wo): Linear(in_features=3584, out_features=1472, bias=False)
                  (dropout): Dropout(p=0.1, inplace=False)
                  (act): NewGELUActivation()
                )
                (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
          )
        )
        (final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
    )
  )
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=1472, out_features=13, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-12 08:01:20,929 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,930 MultiCorpus: 5777 train + 722 dev + 723 test sentences
 - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
2023-10-12 08:01:20,930 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,930 Train:  5777 sentences
2023-10-12 08:01:20,930         (train_with_dev=False, train_with_test=False)
2023-10-12 08:01:20,930 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,930 Training Params:
2023-10-12 08:01:20,931  - learning_rate: "0.00015" 
2023-10-12 08:01:20,931  - mini_batch_size: "8"
2023-10-12 08:01:20,931  - max_epochs: "10"
2023-10-12 08:01:20,931  - shuffle: "True"
2023-10-12 08:01:20,931 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,931 Plugins:
2023-10-12 08:01:20,931  - TensorboardLogger
2023-10-12 08:01:20,931  - LinearScheduler | warmup_fraction: '0.1'
2023-10-12 08:01:20,931 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,932 Final evaluation on model from best epoch (best-model.pt)
2023-10-12 08:01:20,932  - metric: "('micro avg', 'f1-score')"
2023-10-12 08:01:20,932 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,932 Computation:
2023-10-12 08:01:20,932  - compute on device: cuda:0
2023-10-12 08:01:20,932  - embedding storage: none
2023-10-12 08:01:20,932 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,932 Model training base path: "hmbench-icdar/nl-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-3"
2023-10-12 08:01:20,932 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,932 ----------------------------------------------------------------------------------------------------
2023-10-12 08:01:20,933 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-12 08:02:07,389 epoch 1 - iter 72/723 - loss 2.54132511 - time (sec): 46.45 - samples/sec: 371.47 - lr: 0.000015 - momentum: 0.000000
2023-10-12 08:02:51,483 epoch 1 - iter 144/723 - loss 2.49534387 - time (sec): 90.55 - samples/sec: 380.52 - lr: 0.000030 - momentum: 0.000000
2023-10-12 08:03:34,907 epoch 1 - iter 216/723 - loss 2.33709596 - time (sec): 133.97 - samples/sec: 391.12 - lr: 0.000045 - momentum: 0.000000
2023-10-12 08:04:16,305 epoch 1 - iter 288/723 - loss 2.14306603 - time (sec): 175.37 - samples/sec: 394.95 - lr: 0.000060 - momentum: 0.000000
2023-10-12 08:04:59,362 epoch 1 - iter 360/723 - loss 1.92003995 - time (sec): 218.43 - samples/sec: 399.64 - lr: 0.000074 - momentum: 0.000000
2023-10-12 08:05:39,114 epoch 1 - iter 432/723 - loss 1.70854498 - time (sec): 258.18 - samples/sec: 404.24 - lr: 0.000089 - momentum: 0.000000
2023-10-12 08:06:20,260 epoch 1 - iter 504/723 - loss 1.49829714 - time (sec): 299.32 - samples/sec: 413.09 - lr: 0.000104 - momentum: 0.000000
2023-10-12 08:07:00,496 epoch 1 - iter 576/723 - loss 1.35542792 - time (sec): 339.56 - samples/sec: 411.66 - lr: 0.000119 - momentum: 0.000000
2023-10-12 08:07:40,075 epoch 1 - iter 648/723 - loss 1.22705400 - time (sec): 379.14 - samples/sec: 415.25 - lr: 0.000134 - momentum: 0.000000
2023-10-12 08:08:20,913 epoch 1 - iter 720/723 - loss 1.12090252 - time (sec): 419.98 - samples/sec: 418.02 - lr: 0.000149 - momentum: 0.000000
2023-10-12 08:08:22,176 ----------------------------------------------------------------------------------------------------
2023-10-12 08:08:22,176 EPOCH 1 done: loss 1.1174 - lr: 0.000149
2023-10-12 08:08:42,896 DEV : loss 0.20851875841617584 - f1-score (micro avg)  0.2808
2023-10-12 08:08:42,927 saving best model
2023-10-12 08:08:43,817 ----------------------------------------------------------------------------------------------------
2023-10-12 08:09:22,535 epoch 2 - iter 72/723 - loss 0.16527334 - time (sec): 38.72 - samples/sec: 458.14 - lr: 0.000148 - momentum: 0.000000
2023-10-12 08:10:01,596 epoch 2 - iter 144/723 - loss 0.15920354 - time (sec): 77.78 - samples/sec: 461.01 - lr: 0.000147 - momentum: 0.000000
2023-10-12 08:10:41,275 epoch 2 - iter 216/723 - loss 0.14858254 - time (sec): 117.46 - samples/sec: 457.98 - lr: 0.000145 - momentum: 0.000000
2023-10-12 08:11:22,375 epoch 2 - iter 288/723 - loss 0.14005659 - time (sec): 158.56 - samples/sec: 460.85 - lr: 0.000143 - momentum: 0.000000
2023-10-12 08:12:00,825 epoch 2 - iter 360/723 - loss 0.13472715 - time (sec): 197.01 - samples/sec: 454.09 - lr: 0.000142 - momentum: 0.000000
2023-10-12 08:12:39,735 epoch 2 - iter 432/723 - loss 0.13544588 - time (sec): 235.92 - samples/sec: 449.60 - lr: 0.000140 - momentum: 0.000000
2023-10-12 08:13:20,878 epoch 2 - iter 504/723 - loss 0.13281162 - time (sec): 277.06 - samples/sec: 445.68 - lr: 0.000138 - momentum: 0.000000
2023-10-12 08:14:00,585 epoch 2 - iter 576/723 - loss 0.12972903 - time (sec): 316.77 - samples/sec: 442.83 - lr: 0.000137 - momentum: 0.000000
2023-10-12 08:14:42,263 epoch 2 - iter 648/723 - loss 0.12809968 - time (sec): 358.44 - samples/sec: 441.21 - lr: 0.000135 - momentum: 0.000000
2023-10-12 08:15:23,099 epoch 2 - iter 720/723 - loss 0.12592851 - time (sec): 399.28 - samples/sec: 439.75 - lr: 0.000133 - momentum: 0.000000
2023-10-12 08:15:24,361 ----------------------------------------------------------------------------------------------------
2023-10-12 08:15:24,362 EPOCH 2 done: loss 0.1257 - lr: 0.000133
2023-10-12 08:15:46,454 DEV : loss 0.11041188985109329 - f1-score (micro avg)  0.7636
2023-10-12 08:15:46,485 saving best model
2023-10-12 08:15:49,509 ----------------------------------------------------------------------------------------------------
2023-10-12 08:16:29,070 epoch 3 - iter 72/723 - loss 0.09753042 - time (sec): 39.56 - samples/sec: 443.00 - lr: 0.000132 - momentum: 0.000000
2023-10-12 08:17:08,243 epoch 3 - iter 144/723 - loss 0.09125376 - time (sec): 78.73 - samples/sec: 436.86 - lr: 0.000130 - momentum: 0.000000
2023-10-12 08:17:48,702 epoch 3 - iter 216/723 - loss 0.08108488 - time (sec): 119.19 - samples/sec: 437.59 - lr: 0.000128 - momentum: 0.000000
2023-10-12 08:18:28,176 epoch 3 - iter 288/723 - loss 0.08382117 - time (sec): 158.66 - samples/sec: 429.34 - lr: 0.000127 - momentum: 0.000000
2023-10-12 08:19:08,625 epoch 3 - iter 360/723 - loss 0.08097089 - time (sec): 199.11 - samples/sec: 434.97 - lr: 0.000125 - momentum: 0.000000
2023-10-12 08:19:48,758 epoch 3 - iter 432/723 - loss 0.08001548 - time (sec): 239.25 - samples/sec: 434.92 - lr: 0.000123 - momentum: 0.000000
2023-10-12 08:20:30,650 epoch 3 - iter 504/723 - loss 0.08074185 - time (sec): 281.14 - samples/sec: 435.28 - lr: 0.000122 - momentum: 0.000000
2023-10-12 08:21:11,019 epoch 3 - iter 576/723 - loss 0.07871326 - time (sec): 321.51 - samples/sec: 433.22 - lr: 0.000120 - momentum: 0.000000
2023-10-12 08:21:51,914 epoch 3 - iter 648/723 - loss 0.07725144 - time (sec): 362.40 - samples/sec: 433.28 - lr: 0.000118 - momentum: 0.000000
2023-10-12 08:22:35,378 epoch 3 - iter 720/723 - loss 0.07587084 - time (sec): 405.87 - samples/sec: 432.96 - lr: 0.000117 - momentum: 0.000000
2023-10-12 08:22:36,559 ----------------------------------------------------------------------------------------------------
2023-10-12 08:22:36,559 EPOCH 3 done: loss 0.0760 - lr: 0.000117
2023-10-12 08:22:58,358 DEV : loss 0.07043775916099548 - f1-score (micro avg)  0.8748
2023-10-12 08:22:58,410 saving best model
2023-10-12 08:23:01,442 ----------------------------------------------------------------------------------------------------
2023-10-12 08:23:42,834 epoch 4 - iter 72/723 - loss 0.04801858 - time (sec): 41.39 - samples/sec: 439.25 - lr: 0.000115 - momentum: 0.000000
2023-10-12 08:24:22,770 epoch 4 - iter 144/723 - loss 0.04609664 - time (sec): 81.32 - samples/sec: 436.70 - lr: 0.000113 - momentum: 0.000000
2023-10-12 08:25:02,522 epoch 4 - iter 216/723 - loss 0.05431924 - time (sec): 121.07 - samples/sec: 439.26 - lr: 0.000112 - momentum: 0.000000
2023-10-12 08:25:43,590 epoch 4 - iter 288/723 - loss 0.05298324 - time (sec): 162.14 - samples/sec: 440.08 - lr: 0.000110 - momentum: 0.000000
2023-10-12 08:26:21,973 epoch 4 - iter 360/723 - loss 0.05055245 - time (sec): 200.53 - samples/sec: 439.16 - lr: 0.000108 - momentum: 0.000000
2023-10-12 08:27:00,290 epoch 4 - iter 432/723 - loss 0.05084362 - time (sec): 238.84 - samples/sec: 441.50 - lr: 0.000107 - momentum: 0.000000
2023-10-12 08:27:40,073 epoch 4 - iter 504/723 - loss 0.04984247 - time (sec): 278.63 - samples/sec: 445.33 - lr: 0.000105 - momentum: 0.000000
2023-10-12 08:28:21,188 epoch 4 - iter 576/723 - loss 0.05030850 - time (sec): 319.74 - samples/sec: 441.11 - lr: 0.000103 - momentum: 0.000000
2023-10-12 08:29:00,573 epoch 4 - iter 648/723 - loss 0.05012050 - time (sec): 359.13 - samples/sec: 441.36 - lr: 0.000102 - momentum: 0.000000
2023-10-12 08:29:39,922 epoch 4 - iter 720/723 - loss 0.05042988 - time (sec): 398.47 - samples/sec: 440.78 - lr: 0.000100 - momentum: 0.000000
2023-10-12 08:29:41,107 ----------------------------------------------------------------------------------------------------
2023-10-12 08:29:41,108 EPOCH 4 done: loss 0.0503 - lr: 0.000100
2023-10-12 08:30:01,548 DEV : loss 0.07415352761745453 - f1-score (micro avg)  0.871
2023-10-12 08:30:01,581 ----------------------------------------------------------------------------------------------------
2023-10-12 08:30:40,430 epoch 5 - iter 72/723 - loss 0.02733231 - time (sec): 38.85 - samples/sec: 436.87 - lr: 0.000098 - momentum: 0.000000
2023-10-12 08:31:20,046 epoch 5 - iter 144/723 - loss 0.03866248 - time (sec): 78.46 - samples/sec: 434.61 - lr: 0.000097 - momentum: 0.000000
2023-10-12 08:32:01,229 epoch 5 - iter 216/723 - loss 0.03610868 - time (sec): 119.65 - samples/sec: 436.96 - lr: 0.000095 - momentum: 0.000000
2023-10-12 08:32:40,200 epoch 5 - iter 288/723 - loss 0.03310032 - time (sec): 158.62 - samples/sec: 442.71 - lr: 0.000093 - momentum: 0.000000
2023-10-12 08:33:20,657 epoch 5 - iter 360/723 - loss 0.03469398 - time (sec): 199.07 - samples/sec: 445.25 - lr: 0.000092 - momentum: 0.000000
2023-10-12 08:34:00,064 epoch 5 - iter 432/723 - loss 0.03360565 - time (sec): 238.48 - samples/sec: 444.15 - lr: 0.000090 - momentum: 0.000000
2023-10-12 08:34:39,275 epoch 5 - iter 504/723 - loss 0.03312167 - time (sec): 277.69 - samples/sec: 441.48 - lr: 0.000088 - momentum: 0.000000
2023-10-12 08:35:18,887 epoch 5 - iter 576/723 - loss 0.03433857 - time (sec): 317.30 - samples/sec: 441.66 - lr: 0.000087 - momentum: 0.000000
2023-10-12 08:35:58,667 epoch 5 - iter 648/723 - loss 0.03418627 - time (sec): 357.08 - samples/sec: 439.78 - lr: 0.000085 - momentum: 0.000000
2023-10-12 08:36:40,918 epoch 5 - iter 720/723 - loss 0.03402481 - time (sec): 399.33 - samples/sec: 439.89 - lr: 0.000083 - momentum: 0.000000
2023-10-12 08:36:42,163 ----------------------------------------------------------------------------------------------------
2023-10-12 08:36:42,163 EPOCH 5 done: loss 0.0341 - lr: 0.000083
2023-10-12 08:37:03,913 DEV : loss 0.07782100886106491 - f1-score (micro avg)  0.8638
2023-10-12 08:37:03,946 ----------------------------------------------------------------------------------------------------
2023-10-12 08:37:43,843 epoch 6 - iter 72/723 - loss 0.01464938 - time (sec): 39.89 - samples/sec: 452.14 - lr: 0.000082 - momentum: 0.000000
2023-10-12 08:38:22,116 epoch 6 - iter 144/723 - loss 0.01875237 - time (sec): 78.17 - samples/sec: 435.06 - lr: 0.000080 - momentum: 0.000000
2023-10-12 08:39:02,232 epoch 6 - iter 216/723 - loss 0.02077035 - time (sec): 118.28 - samples/sec: 433.66 - lr: 0.000078 - momentum: 0.000000
2023-10-12 08:39:41,484 epoch 6 - iter 288/723 - loss 0.02049800 - time (sec): 157.54 - samples/sec: 430.16 - lr: 0.000077 - momentum: 0.000000
2023-10-12 08:40:23,494 epoch 6 - iter 360/723 - loss 0.02030551 - time (sec): 199.55 - samples/sec: 431.18 - lr: 0.000075 - momentum: 0.000000
2023-10-12 08:41:04,121 epoch 6 - iter 432/723 - loss 0.02215626 - time (sec): 240.17 - samples/sec: 430.60 - lr: 0.000073 - momentum: 0.000000
2023-10-12 08:41:44,167 epoch 6 - iter 504/723 - loss 0.02096728 - time (sec): 280.22 - samples/sec: 431.63 - lr: 0.000072 - momentum: 0.000000
2023-10-12 08:42:23,101 epoch 6 - iter 576/723 - loss 0.02191746 - time (sec): 319.15 - samples/sec: 434.46 - lr: 0.000070 - momentum: 0.000000
2023-10-12 08:43:02,162 epoch 6 - iter 648/723 - loss 0.02354005 - time (sec): 358.21 - samples/sec: 438.29 - lr: 0.000068 - momentum: 0.000000
2023-10-12 08:43:40,781 epoch 6 - iter 720/723 - loss 0.02607016 - time (sec): 396.83 - samples/sec: 442.42 - lr: 0.000067 - momentum: 0.000000
2023-10-12 08:43:42,005 ----------------------------------------------------------------------------------------------------
2023-10-12 08:43:42,006 EPOCH 6 done: loss 0.0265 - lr: 0.000067
2023-10-12 08:44:02,246 DEV : loss 0.08978129923343658 - f1-score (micro avg)  0.854
2023-10-12 08:44:02,275 ----------------------------------------------------------------------------------------------------
2023-10-12 08:44:40,574 epoch 7 - iter 72/723 - loss 0.01729660 - time (sec): 38.30 - samples/sec: 487.34 - lr: 0.000065 - momentum: 0.000000
2023-10-12 08:45:18,498 epoch 7 - iter 144/723 - loss 0.01451077 - time (sec): 76.22 - samples/sec: 457.95 - lr: 0.000063 - momentum: 0.000000
2023-10-12 08:45:57,439 epoch 7 - iter 216/723 - loss 0.01907941 - time (sec): 115.16 - samples/sec: 460.81 - lr: 0.000062 - momentum: 0.000000
2023-10-12 08:46:35,776 epoch 7 - iter 288/723 - loss 0.01940333 - time (sec): 153.50 - samples/sec: 466.12 - lr: 0.000060 - momentum: 0.000000
2023-10-12 08:47:15,269 epoch 7 - iter 360/723 - loss 0.02120133 - time (sec): 192.99 - samples/sec: 462.97 - lr: 0.000058 - momentum: 0.000000
2023-10-12 08:47:55,556 epoch 7 - iter 432/723 - loss 0.01988510 - time (sec): 233.28 - samples/sec: 453.47 - lr: 0.000057 - momentum: 0.000000
2023-10-12 08:48:35,033 epoch 7 - iter 504/723 - loss 0.02053563 - time (sec): 272.76 - samples/sec: 452.06 - lr: 0.000055 - momentum: 0.000000
2023-10-12 08:49:13,606 epoch 7 - iter 576/723 - loss 0.02179287 - time (sec): 311.33 - samples/sec: 452.47 - lr: 0.000053 - momentum: 0.000000
2023-10-12 08:49:54,431 epoch 7 - iter 648/723 - loss 0.02091802 - time (sec): 352.15 - samples/sec: 448.33 - lr: 0.000052 - momentum: 0.000000
2023-10-12 08:50:35,056 epoch 7 - iter 720/723 - loss 0.02017315 - time (sec): 392.78 - samples/sec: 447.22 - lr: 0.000050 - momentum: 0.000000
2023-10-12 08:50:36,310 ----------------------------------------------------------------------------------------------------
2023-10-12 08:50:36,310 EPOCH 7 done: loss 0.0201 - lr: 0.000050
2023-10-12 08:50:58,422 DEV : loss 0.11653382331132889 - f1-score (micro avg)  0.8511
2023-10-12 08:50:58,458 ----------------------------------------------------------------------------------------------------
2023-10-12 08:51:40,177 epoch 8 - iter 72/723 - loss 0.01619778 - time (sec): 41.72 - samples/sec: 399.14 - lr: 0.000048 - momentum: 0.000000
2023-10-12 08:52:21,636 epoch 8 - iter 144/723 - loss 0.01782970 - time (sec): 83.18 - samples/sec: 414.15 - lr: 0.000047 - momentum: 0.000000
2023-10-12 08:53:02,713 epoch 8 - iter 216/723 - loss 0.01611145 - time (sec): 124.25 - samples/sec: 416.95 - lr: 0.000045 - momentum: 0.000000
2023-10-12 08:53:45,293 epoch 8 - iter 288/723 - loss 0.01547392 - time (sec): 166.83 - samples/sec: 418.76 - lr: 0.000043 - momentum: 0.000000
2023-10-12 08:54:27,936 epoch 8 - iter 360/723 - loss 0.01534668 - time (sec): 209.48 - samples/sec: 420.64 - lr: 0.000042 - momentum: 0.000000
2023-10-12 08:55:07,886 epoch 8 - iter 432/723 - loss 0.01896167 - time (sec): 249.43 - samples/sec: 423.89 - lr: 0.000040 - momentum: 0.000000
2023-10-12 08:55:45,574 epoch 8 - iter 504/723 - loss 0.01782626 - time (sec): 287.11 - samples/sec: 432.18 - lr: 0.000038 - momentum: 0.000000
2023-10-12 08:56:22,951 epoch 8 - iter 576/723 - loss 0.01762016 - time (sec): 324.49 - samples/sec: 438.31 - lr: 0.000037 - momentum: 0.000000
2023-10-12 08:56:59,857 epoch 8 - iter 648/723 - loss 0.01764830 - time (sec): 361.40 - samples/sec: 441.20 - lr: 0.000035 - momentum: 0.000000
2023-10-12 08:57:36,207 epoch 8 - iter 720/723 - loss 0.01780592 - time (sec): 397.75 - samples/sec: 441.77 - lr: 0.000033 - momentum: 0.000000
2023-10-12 08:57:37,268 ----------------------------------------------------------------------------------------------------
2023-10-12 08:57:37,268 EPOCH 8 done: loss 0.0178 - lr: 0.000033
2023-10-12 08:57:57,134 DEV : loss 0.10788174718618393 - f1-score (micro avg)  0.8644
2023-10-12 08:57:57,165 ----------------------------------------------------------------------------------------------------
2023-10-12 08:58:34,389 epoch 9 - iter 72/723 - loss 0.01835794 - time (sec): 37.22 - samples/sec: 462.34 - lr: 0.000032 - momentum: 0.000000
2023-10-12 08:59:12,112 epoch 9 - iter 144/723 - loss 0.01698658 - time (sec): 74.95 - samples/sec: 449.81 - lr: 0.000030 - momentum: 0.000000
2023-10-12 08:59:51,780 epoch 9 - iter 216/723 - loss 0.01309983 - time (sec): 114.61 - samples/sec: 459.12 - lr: 0.000028 - momentum: 0.000000
2023-10-12 09:00:29,513 epoch 9 - iter 288/723 - loss 0.01229615 - time (sec): 152.35 - samples/sec: 459.60 - lr: 0.000027 - momentum: 0.000000
2023-10-12 09:01:06,464 epoch 9 - iter 360/723 - loss 0.01261841 - time (sec): 189.30 - samples/sec: 461.10 - lr: 0.000025 - momentum: 0.000000
2023-10-12 09:01:44,103 epoch 9 - iter 432/723 - loss 0.01234066 - time (sec): 226.94 - samples/sec: 461.97 - lr: 0.000023 - momentum: 0.000000
2023-10-12 09:02:21,553 epoch 9 - iter 504/723 - loss 0.01224423 - time (sec): 264.39 - samples/sec: 463.87 - lr: 0.000022 - momentum: 0.000000
2023-10-12 09:02:58,848 epoch 9 - iter 576/723 - loss 0.01176578 - time (sec): 301.68 - samples/sec: 463.07 - lr: 0.000020 - momentum: 0.000000
2023-10-12 09:03:36,647 epoch 9 - iter 648/723 - loss 0.01323611 - time (sec): 339.48 - samples/sec: 464.50 - lr: 0.000018 - momentum: 0.000000
2023-10-12 09:04:14,638 epoch 9 - iter 720/723 - loss 0.01378374 - time (sec): 377.47 - samples/sec: 464.75 - lr: 0.000017 - momentum: 0.000000
2023-10-12 09:04:15,962 ----------------------------------------------------------------------------------------------------
2023-10-12 09:04:15,962 EPOCH 9 done: loss 0.0137 - lr: 0.000017
2023-10-12 09:04:36,857 DEV : loss 0.11403186619281769 - f1-score (micro avg)  0.8648
2023-10-12 09:04:36,886 ----------------------------------------------------------------------------------------------------
2023-10-12 09:05:15,113 epoch 10 - iter 72/723 - loss 0.00964273 - time (sec): 38.22 - samples/sec: 459.50 - lr: 0.000015 - momentum: 0.000000
2023-10-12 09:05:52,189 epoch 10 - iter 144/723 - loss 0.00804987 - time (sec): 75.30 - samples/sec: 462.18 - lr: 0.000013 - momentum: 0.000000
2023-10-12 09:06:30,158 epoch 10 - iter 216/723 - loss 0.00815867 - time (sec): 113.27 - samples/sec: 467.77 - lr: 0.000012 - momentum: 0.000000
2023-10-12 09:07:07,264 epoch 10 - iter 288/723 - loss 0.00943711 - time (sec): 150.38 - samples/sec: 463.33 - lr: 0.000010 - momentum: 0.000000
2023-10-12 09:07:44,150 epoch 10 - iter 360/723 - loss 0.00912893 - time (sec): 187.26 - samples/sec: 459.36 - lr: 0.000008 - momentum: 0.000000
2023-10-12 09:08:22,630 epoch 10 - iter 432/723 - loss 0.00970888 - time (sec): 225.74 - samples/sec: 461.10 - lr: 0.000007 - momentum: 0.000000
2023-10-12 09:09:02,323 epoch 10 - iter 504/723 - loss 0.00930103 - time (sec): 265.43 - samples/sec: 461.35 - lr: 0.000005 - momentum: 0.000000
2023-10-12 09:09:40,627 epoch 10 - iter 576/723 - loss 0.00981756 - time (sec): 303.74 - samples/sec: 459.74 - lr: 0.000003 - momentum: 0.000000
2023-10-12 09:10:20,091 epoch 10 - iter 648/723 - loss 0.01037803 - time (sec): 343.20 - samples/sec: 458.44 - lr: 0.000002 - momentum: 0.000000
2023-10-12 09:10:59,941 epoch 10 - iter 720/723 - loss 0.01182190 - time (sec): 383.05 - samples/sec: 459.01 - lr: 0.000000 - momentum: 0.000000
2023-10-12 09:11:01,081 ----------------------------------------------------------------------------------------------------
2023-10-12 09:11:01,081 EPOCH 10 done: loss 0.0118 - lr: 0.000000
2023-10-12 09:11:22,387 DEV : loss 0.12052779644727707 - f1-score (micro avg)  0.8641
2023-10-12 09:11:25,037 ----------------------------------------------------------------------------------------------------
2023-10-12 09:11:25,041 Loading model from best epoch ...
2023-10-12 09:11:30,263 SequenceTagger predicts: Dictionary with 13 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
2023-10-12 09:11:51,517 
Results:
- F-score (micro) 0.8569
- F-score (macro) 0.6861
- Accuracy 0.7587

By class:
              precision    recall  f1-score   support

         PER     0.8466    0.8817    0.8638       482
         LOC     0.8827    0.9367    0.9089       458
         ORG     0.4828    0.2029    0.2857        69

   micro avg     0.8535    0.8603    0.8569      1009
   macro avg     0.7374    0.6738    0.6861      1009
weighted avg     0.8381    0.8603    0.8447      1009

2023-10-12 09:11:51,518 ----------------------------------------------------------------------------------------------------