2023-10-14 19:00:14,964 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 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=21, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
 - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Train:  3575 sentences
2023-10-14 19:00:14,966         (train_with_dev=False, train_with_test=False)
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Training Params:
2023-10-14 19:00:14,966  - learning_rate: "0.00016" 
2023-10-14 19:00:14,966  - mini_batch_size: "8"
2023-10-14 19:00:14,966  - max_epochs: "10"
2023-10-14 19:00:14,966  - shuffle: "True"
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Plugins:
2023-10-14 19:00:14,966  - TensorboardLogger
2023-10-14 19:00:14,966  - LinearScheduler | warmup_fraction: '0.1'
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Final evaluation on model from best epoch (best-model.pt)
2023-10-14 19:00:14,966  - metric: "('micro avg', 'f1-score')"
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Computation:
2023-10-14 19:00:14,966  - compute on device: cuda:0
2023-10-14 19:00:14,966  - embedding storage: none
2023-10-14 19:00:14,966 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,966 Model training base path: "hmbench-hipe2020/de-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1"
2023-10-14 19:00:14,967 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,967 ----------------------------------------------------------------------------------------------------
2023-10-14 19:00:14,967 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-14 19:00:30,898 epoch 1 - iter 44/447 - loss 3.04933307 - time (sec): 15.93 - samples/sec: 576.13 - lr: 0.000015 - momentum: 0.000000
2023-10-14 19:00:45,957 epoch 1 - iter 88/447 - loss 3.03049307 - time (sec): 30.99 - samples/sec: 557.03 - lr: 0.000031 - momentum: 0.000000
2023-10-14 19:01:01,268 epoch 1 - iter 132/447 - loss 2.97087840 - time (sec): 46.30 - samples/sec: 550.45 - lr: 0.000047 - momentum: 0.000000
2023-10-14 19:01:16,602 epoch 1 - iter 176/447 - loss 2.83649791 - time (sec): 61.63 - samples/sec: 550.28 - lr: 0.000063 - momentum: 0.000000
2023-10-14 19:01:31,333 epoch 1 - iter 220/447 - loss 2.68309761 - time (sec): 76.37 - samples/sec: 542.95 - lr: 0.000078 - momentum: 0.000000
2023-10-14 19:01:46,512 epoch 1 - iter 264/447 - loss 2.50013370 - time (sec): 91.54 - samples/sec: 540.63 - lr: 0.000094 - momentum: 0.000000
2023-10-14 19:02:02,652 epoch 1 - iter 308/447 - loss 2.28314799 - time (sec): 107.68 - samples/sec: 545.51 - lr: 0.000110 - momentum: 0.000000
2023-10-14 19:02:18,362 epoch 1 - iter 352/447 - loss 2.09975990 - time (sec): 123.39 - samples/sec: 544.15 - lr: 0.000126 - momentum: 0.000000
2023-10-14 19:02:36,146 epoch 1 - iter 396/447 - loss 1.89626135 - time (sec): 141.18 - samples/sec: 548.51 - lr: 0.000141 - momentum: 0.000000
2023-10-14 19:02:51,141 epoch 1 - iter 440/447 - loss 1.76849735 - time (sec): 156.17 - samples/sec: 545.52 - lr: 0.000157 - momentum: 0.000000
2023-10-14 19:02:53,538 ----------------------------------------------------------------------------------------------------
2023-10-14 19:02:53,538 EPOCH 1 done: loss 1.7498 - lr: 0.000157
2023-10-14 19:03:16,193 DEV : loss 0.46884480118751526 - f1-score (micro avg)  0.0
2023-10-14 19:03:16,219 ----------------------------------------------------------------------------------------------------
2023-10-14 19:03:31,567 epoch 2 - iter 44/447 - loss 0.50554270 - time (sec): 15.35 - samples/sec: 551.38 - lr: 0.000158 - momentum: 0.000000
2023-10-14 19:03:46,868 epoch 2 - iter 88/447 - loss 0.47764680 - time (sec): 30.65 - samples/sec: 549.37 - lr: 0.000157 - momentum: 0.000000
2023-10-14 19:04:02,679 epoch 2 - iter 132/447 - loss 0.43925964 - time (sec): 46.46 - samples/sec: 564.23 - lr: 0.000155 - momentum: 0.000000
2023-10-14 19:04:19,791 epoch 2 - iter 176/447 - loss 0.41230032 - time (sec): 63.57 - samples/sec: 560.04 - lr: 0.000153 - momentum: 0.000000
2023-10-14 19:04:35,331 epoch 2 - iter 220/447 - loss 0.39359034 - time (sec): 79.11 - samples/sec: 558.93 - lr: 0.000151 - momentum: 0.000000
2023-10-14 19:04:51,169 epoch 2 - iter 264/447 - loss 0.37438209 - time (sec): 94.95 - samples/sec: 558.11 - lr: 0.000150 - momentum: 0.000000
2023-10-14 19:05:06,366 epoch 2 - iter 308/447 - loss 0.37309143 - time (sec): 110.15 - samples/sec: 553.18 - lr: 0.000148 - momentum: 0.000000
2023-10-14 19:05:21,885 epoch 2 - iter 352/447 - loss 0.36297809 - time (sec): 125.66 - samples/sec: 552.95 - lr: 0.000146 - momentum: 0.000000
2023-10-14 19:05:37,947 epoch 2 - iter 396/447 - loss 0.35386572 - time (sec): 141.73 - samples/sec: 549.54 - lr: 0.000144 - momentum: 0.000000
2023-10-14 19:05:52,857 epoch 2 - iter 440/447 - loss 0.34628553 - time (sec): 156.64 - samples/sec: 545.93 - lr: 0.000143 - momentum: 0.000000
2023-10-14 19:05:55,141 ----------------------------------------------------------------------------------------------------
2023-10-14 19:05:55,142 EPOCH 2 done: loss 0.3467 - lr: 0.000143
2023-10-14 19:06:20,103 DEV : loss 0.24183328449726105 - f1-score (micro avg)  0.4694
2023-10-14 19:06:20,129 saving best model
2023-10-14 19:06:20,733 ----------------------------------------------------------------------------------------------------
2023-10-14 19:06:36,008 epoch 3 - iter 44/447 - loss 0.28141804 - time (sec): 15.27 - samples/sec: 538.43 - lr: 0.000141 - momentum: 0.000000
2023-10-14 19:06:51,185 epoch 3 - iter 88/447 - loss 0.24664339 - time (sec): 30.45 - samples/sec: 536.51 - lr: 0.000139 - momentum: 0.000000
2023-10-14 19:07:07,008 epoch 3 - iter 132/447 - loss 0.23953289 - time (sec): 46.27 - samples/sec: 538.68 - lr: 0.000137 - momentum: 0.000000
2023-10-14 19:07:22,222 epoch 3 - iter 176/447 - loss 0.23619688 - time (sec): 61.49 - samples/sec: 540.69 - lr: 0.000135 - momentum: 0.000000
2023-10-14 19:07:39,636 epoch 3 - iter 220/447 - loss 0.22688332 - time (sec): 78.90 - samples/sec: 549.23 - lr: 0.000134 - momentum: 0.000000
2023-10-14 19:07:54,915 epoch 3 - iter 264/447 - loss 0.22266002 - time (sec): 94.18 - samples/sec: 546.75 - lr: 0.000132 - momentum: 0.000000
2023-10-14 19:08:10,027 epoch 3 - iter 308/447 - loss 0.21742813 - time (sec): 109.29 - samples/sec: 546.15 - lr: 0.000130 - momentum: 0.000000
2023-10-14 19:08:24,715 epoch 3 - iter 352/447 - loss 0.21064762 - time (sec): 123.98 - samples/sec: 544.71 - lr: 0.000128 - momentum: 0.000000
2023-10-14 19:08:40,176 epoch 3 - iter 396/447 - loss 0.20461919 - time (sec): 139.44 - samples/sec: 547.69 - lr: 0.000127 - momentum: 0.000000
2023-10-14 19:08:55,401 epoch 3 - iter 440/447 - loss 0.19928171 - time (sec): 154.67 - samples/sec: 549.82 - lr: 0.000125 - momentum: 0.000000
2023-10-14 19:08:57,869 ----------------------------------------------------------------------------------------------------
2023-10-14 19:08:57,870 EPOCH 3 done: loss 0.1981 - lr: 0.000125
2023-10-14 19:09:22,759 DEV : loss 0.17111451923847198 - f1-score (micro avg)  0.6802
2023-10-14 19:09:22,785 saving best model
2023-10-14 19:09:26,745 ----------------------------------------------------------------------------------------------------
2023-10-14 19:09:41,997 epoch 4 - iter 44/447 - loss 0.14979506 - time (sec): 15.25 - samples/sec: 546.16 - lr: 0.000123 - momentum: 0.000000
2023-10-14 19:09:57,020 epoch 4 - iter 88/447 - loss 0.14345141 - time (sec): 30.27 - samples/sec: 530.81 - lr: 0.000121 - momentum: 0.000000
2023-10-14 19:10:12,122 epoch 4 - iter 132/447 - loss 0.13772700 - time (sec): 45.37 - samples/sec: 530.14 - lr: 0.000119 - momentum: 0.000000
2023-10-14 19:10:27,565 epoch 4 - iter 176/447 - loss 0.13768946 - time (sec): 60.82 - samples/sec: 529.88 - lr: 0.000118 - momentum: 0.000000
2023-10-14 19:10:42,615 epoch 4 - iter 220/447 - loss 0.13136140 - time (sec): 75.87 - samples/sec: 529.21 - lr: 0.000116 - momentum: 0.000000
2023-10-14 19:10:58,702 epoch 4 - iter 264/447 - loss 0.12547106 - time (sec): 91.95 - samples/sec: 534.89 - lr: 0.000114 - momentum: 0.000000
2023-10-14 19:11:13,915 epoch 4 - iter 308/447 - loss 0.11893535 - time (sec): 107.17 - samples/sec: 533.90 - lr: 0.000112 - momentum: 0.000000
2023-10-14 19:11:29,205 epoch 4 - iter 352/447 - loss 0.11655379 - time (sec): 122.46 - samples/sec: 533.75 - lr: 0.000111 - momentum: 0.000000
2023-10-14 19:11:46,858 epoch 4 - iter 396/447 - loss 0.11527255 - time (sec): 140.11 - samples/sec: 537.46 - lr: 0.000109 - momentum: 0.000000
2023-10-14 19:12:03,500 epoch 4 - iter 440/447 - loss 0.11047397 - time (sec): 156.75 - samples/sec: 541.22 - lr: 0.000107 - momentum: 0.000000
2023-10-14 19:12:06,159 ----------------------------------------------------------------------------------------------------
2023-10-14 19:12:06,159 EPOCH 4 done: loss 0.1091 - lr: 0.000107
2023-10-14 19:12:31,058 DEV : loss 0.15927954018115997 - f1-score (micro avg)  0.7318
2023-10-14 19:12:31,084 saving best model
2023-10-14 19:12:35,558 ----------------------------------------------------------------------------------------------------
2023-10-14 19:12:50,508 epoch 5 - iter 44/447 - loss 0.05896953 - time (sec): 14.95 - samples/sec: 512.04 - lr: 0.000105 - momentum: 0.000000
2023-10-14 19:13:05,907 epoch 5 - iter 88/447 - loss 0.05595016 - time (sec): 30.35 - samples/sec: 527.00 - lr: 0.000103 - momentum: 0.000000
2023-10-14 19:13:21,775 epoch 5 - iter 132/447 - loss 0.05463563 - time (sec): 46.22 - samples/sec: 538.24 - lr: 0.000102 - momentum: 0.000000
2023-10-14 19:13:37,097 epoch 5 - iter 176/447 - loss 0.06369098 - time (sec): 61.54 - samples/sec: 538.54 - lr: 0.000100 - momentum: 0.000000
2023-10-14 19:13:52,538 epoch 5 - iter 220/447 - loss 0.06209360 - time (sec): 76.98 - samples/sec: 539.52 - lr: 0.000098 - momentum: 0.000000
2023-10-14 19:14:10,442 epoch 5 - iter 264/447 - loss 0.06529404 - time (sec): 94.88 - samples/sec: 538.92 - lr: 0.000096 - momentum: 0.000000
2023-10-14 19:14:25,491 epoch 5 - iter 308/447 - loss 0.06511075 - time (sec): 109.93 - samples/sec: 537.52 - lr: 0.000095 - momentum: 0.000000
2023-10-14 19:14:40,822 epoch 5 - iter 352/447 - loss 0.06432897 - time (sec): 125.26 - samples/sec: 539.81 - lr: 0.000093 - momentum: 0.000000
2023-10-14 19:14:56,567 epoch 5 - iter 396/447 - loss 0.06384615 - time (sec): 141.01 - samples/sec: 543.02 - lr: 0.000091 - momentum: 0.000000
2023-10-14 19:15:12,216 epoch 5 - iter 440/447 - loss 0.06466372 - time (sec): 156.66 - samples/sec: 543.72 - lr: 0.000089 - momentum: 0.000000
2023-10-14 19:15:14,647 ----------------------------------------------------------------------------------------------------
2023-10-14 19:15:14,648 EPOCH 5 done: loss 0.0652 - lr: 0.000089
2023-10-14 19:15:39,413 DEV : loss 0.1628938466310501 - f1-score (micro avg)  0.7511
2023-10-14 19:15:39,439 saving best model
2023-10-14 19:15:43,868 ----------------------------------------------------------------------------------------------------
2023-10-14 19:15:59,093 epoch 6 - iter 44/447 - loss 0.03203516 - time (sec): 15.22 - samples/sec: 559.43 - lr: 0.000087 - momentum: 0.000000
2023-10-14 19:16:14,248 epoch 6 - iter 88/447 - loss 0.03647027 - time (sec): 30.38 - samples/sec: 553.80 - lr: 0.000086 - momentum: 0.000000
2023-10-14 19:16:29,750 epoch 6 - iter 132/447 - loss 0.04391932 - time (sec): 45.88 - samples/sec: 549.93 - lr: 0.000084 - momentum: 0.000000
2023-10-14 19:16:45,162 epoch 6 - iter 176/447 - loss 0.04250684 - time (sec): 61.29 - samples/sec: 550.85 - lr: 0.000082 - momentum: 0.000000
2023-10-14 19:17:00,391 epoch 6 - iter 220/447 - loss 0.04230744 - time (sec): 76.52 - samples/sec: 545.69 - lr: 0.000080 - momentum: 0.000000
2023-10-14 19:17:17,699 epoch 6 - iter 264/447 - loss 0.04276753 - time (sec): 93.83 - samples/sec: 546.15 - lr: 0.000079 - momentum: 0.000000
2023-10-14 19:17:33,820 epoch 6 - iter 308/447 - loss 0.04228643 - time (sec): 109.95 - samples/sec: 548.42 - lr: 0.000077 - momentum: 0.000000
2023-10-14 19:17:49,709 epoch 6 - iter 352/447 - loss 0.04210539 - time (sec): 125.84 - samples/sec: 545.91 - lr: 0.000075 - momentum: 0.000000
2023-10-14 19:18:04,818 epoch 6 - iter 396/447 - loss 0.04429856 - time (sec): 140.95 - samples/sec: 543.50 - lr: 0.000073 - momentum: 0.000000
2023-10-14 19:18:20,485 epoch 6 - iter 440/447 - loss 0.04396709 - time (sec): 156.61 - samples/sec: 543.95 - lr: 0.000072 - momentum: 0.000000
2023-10-14 19:18:22,901 ----------------------------------------------------------------------------------------------------
2023-10-14 19:18:22,901 EPOCH 6 done: loss 0.0437 - lr: 0.000072
2023-10-14 19:18:47,687 DEV : loss 0.20442622900009155 - f1-score (micro avg)  0.7406
2023-10-14 19:18:47,714 ----------------------------------------------------------------------------------------------------
2023-10-14 19:19:04,763 epoch 7 - iter 44/447 - loss 0.04203418 - time (sec): 17.05 - samples/sec: 567.45 - lr: 0.000070 - momentum: 0.000000
2023-10-14 19:19:20,038 epoch 7 - iter 88/447 - loss 0.03827106 - time (sec): 32.32 - samples/sec: 567.39 - lr: 0.000068 - momentum: 0.000000
2023-10-14 19:19:34,797 epoch 7 - iter 132/447 - loss 0.04291611 - time (sec): 47.08 - samples/sec: 555.88 - lr: 0.000066 - momentum: 0.000000
2023-10-14 19:19:49,756 epoch 7 - iter 176/447 - loss 0.04006105 - time (sec): 62.04 - samples/sec: 555.08 - lr: 0.000064 - momentum: 0.000000
2023-10-14 19:20:05,094 epoch 7 - iter 220/447 - loss 0.03598479 - time (sec): 77.38 - samples/sec: 557.10 - lr: 0.000063 - momentum: 0.000000
2023-10-14 19:20:21,135 epoch 7 - iter 264/447 - loss 0.03417475 - time (sec): 93.42 - samples/sec: 556.20 - lr: 0.000061 - momentum: 0.000000
2023-10-14 19:20:36,240 epoch 7 - iter 308/447 - loss 0.03436650 - time (sec): 108.53 - samples/sec: 555.56 - lr: 0.000059 - momentum: 0.000000
2023-10-14 19:20:51,080 epoch 7 - iter 352/447 - loss 0.03224839 - time (sec): 123.37 - samples/sec: 555.02 - lr: 0.000057 - momentum: 0.000000
2023-10-14 19:21:06,308 epoch 7 - iter 396/447 - loss 0.03196958 - time (sec): 138.59 - samples/sec: 556.57 - lr: 0.000056 - momentum: 0.000000
2023-10-14 19:21:21,295 epoch 7 - iter 440/447 - loss 0.03053808 - time (sec): 153.58 - samples/sec: 555.18 - lr: 0.000054 - momentum: 0.000000
2023-10-14 19:21:23,626 ----------------------------------------------------------------------------------------------------
2023-10-14 19:21:23,627 EPOCH 7 done: loss 0.0304 - lr: 0.000054
2023-10-14 19:21:48,360 DEV : loss 0.20464175939559937 - f1-score (micro avg)  0.7543
2023-10-14 19:21:48,387 saving best model
2023-10-14 19:21:52,937 ----------------------------------------------------------------------------------------------------
2023-10-14 19:22:08,136 epoch 8 - iter 44/447 - loss 0.02645942 - time (sec): 15.20 - samples/sec: 538.20 - lr: 0.000052 - momentum: 0.000000
2023-10-14 19:22:23,894 epoch 8 - iter 88/447 - loss 0.03397824 - time (sec): 30.96 - samples/sec: 543.04 - lr: 0.000050 - momentum: 0.000000
2023-10-14 19:22:38,936 epoch 8 - iter 132/447 - loss 0.02970954 - time (sec): 46.00 - samples/sec: 537.04 - lr: 0.000048 - momentum: 0.000000
2023-10-14 19:22:54,728 epoch 8 - iter 176/447 - loss 0.02736998 - time (sec): 61.79 - samples/sec: 549.83 - lr: 0.000047 - momentum: 0.000000
2023-10-14 19:23:10,849 epoch 8 - iter 220/447 - loss 0.02505732 - time (sec): 77.91 - samples/sec: 553.41 - lr: 0.000045 - momentum: 0.000000
2023-10-14 19:23:25,908 epoch 8 - iter 264/447 - loss 0.02422629 - time (sec): 92.97 - samples/sec: 548.88 - lr: 0.000043 - momentum: 0.000000
2023-10-14 19:23:42,873 epoch 8 - iter 308/447 - loss 0.02549261 - time (sec): 109.93 - samples/sec: 546.97 - lr: 0.000041 - momentum: 0.000000
2023-10-14 19:23:58,183 epoch 8 - iter 352/447 - loss 0.02414264 - time (sec): 125.24 - samples/sec: 545.13 - lr: 0.000040 - momentum: 0.000000
2023-10-14 19:24:13,650 epoch 8 - iter 396/447 - loss 0.02399407 - time (sec): 140.71 - samples/sec: 544.19 - lr: 0.000038 - momentum: 0.000000
2023-10-14 19:24:29,061 epoch 8 - iter 440/447 - loss 0.02256911 - time (sec): 156.12 - samples/sec: 545.74 - lr: 0.000036 - momentum: 0.000000
2023-10-14 19:24:31,511 ----------------------------------------------------------------------------------------------------
2023-10-14 19:24:31,511 EPOCH 8 done: loss 0.0224 - lr: 0.000036
2023-10-14 19:24:56,306 DEV : loss 0.21208828687667847 - f1-score (micro avg)  0.7607
2023-10-14 19:24:56,333 saving best model
2023-10-14 19:25:00,659 ----------------------------------------------------------------------------------------------------
2023-10-14 19:25:17,927 epoch 9 - iter 44/447 - loss 0.03408679 - time (sec): 17.27 - samples/sec: 563.02 - lr: 0.000034 - momentum: 0.000000
2023-10-14 19:25:34,781 epoch 9 - iter 88/447 - loss 0.02496360 - time (sec): 34.12 - samples/sec: 550.06 - lr: 0.000032 - momentum: 0.000000
2023-10-14 19:25:50,098 epoch 9 - iter 132/447 - loss 0.02108694 - time (sec): 49.44 - samples/sec: 553.76 - lr: 0.000031 - momentum: 0.000000
2023-10-14 19:26:05,436 epoch 9 - iter 176/447 - loss 0.01990705 - time (sec): 64.77 - samples/sec: 557.87 - lr: 0.000029 - momentum: 0.000000
2023-10-14 19:26:20,317 epoch 9 - iter 220/447 - loss 0.01878604 - time (sec): 79.66 - samples/sec: 550.37 - lr: 0.000027 - momentum: 0.000000
2023-10-14 19:26:35,552 epoch 9 - iter 264/447 - loss 0.02147376 - time (sec): 94.89 - samples/sec: 548.57 - lr: 0.000025 - momentum: 0.000000
2023-10-14 19:26:50,978 epoch 9 - iter 308/447 - loss 0.01958079 - time (sec): 110.32 - samples/sec: 542.18 - lr: 0.000024 - momentum: 0.000000
2023-10-14 19:27:06,264 epoch 9 - iter 352/447 - loss 0.01867083 - time (sec): 125.60 - samples/sec: 542.81 - lr: 0.000022 - momentum: 0.000000
2023-10-14 19:27:21,734 epoch 9 - iter 396/447 - loss 0.01771515 - time (sec): 141.07 - samples/sec: 544.03 - lr: 0.000020 - momentum: 0.000000
2023-10-14 19:27:37,248 epoch 9 - iter 440/447 - loss 0.01853660 - time (sec): 156.59 - samples/sec: 544.27 - lr: 0.000018 - momentum: 0.000000
2023-10-14 19:27:39,658 ----------------------------------------------------------------------------------------------------
2023-10-14 19:27:39,658 EPOCH 9 done: loss 0.0184 - lr: 0.000018
2023-10-14 19:28:04,802 DEV : loss 0.21300099790096283 - f1-score (micro avg)  0.7555
2023-10-14 19:28:04,828 ----------------------------------------------------------------------------------------------------
2023-10-14 19:28:20,506 epoch 10 - iter 44/447 - loss 0.01825573 - time (sec): 15.68 - samples/sec: 558.22 - lr: 0.000016 - momentum: 0.000000
2023-10-14 19:28:35,569 epoch 10 - iter 88/447 - loss 0.01697777 - time (sec): 30.74 - samples/sec: 534.17 - lr: 0.000015 - momentum: 0.000000
2023-10-14 19:28:50,986 epoch 10 - iter 132/447 - loss 0.01431545 - time (sec): 46.16 - samples/sec: 534.38 - lr: 0.000013 - momentum: 0.000000
2023-10-14 19:29:06,987 epoch 10 - iter 176/447 - loss 0.01363602 - time (sec): 62.16 - samples/sec: 540.38 - lr: 0.000011 - momentum: 0.000000
2023-10-14 19:29:24,791 epoch 10 - iter 220/447 - loss 0.01703956 - time (sec): 79.96 - samples/sec: 547.33 - lr: 0.000009 - momentum: 0.000000
2023-10-14 19:29:40,217 epoch 10 - iter 264/447 - loss 0.01589241 - time (sec): 95.39 - samples/sec: 546.05 - lr: 0.000008 - momentum: 0.000000
2023-10-14 19:29:55,393 epoch 10 - iter 308/447 - loss 0.01523190 - time (sec): 110.56 - samples/sec: 542.18 - lr: 0.000006 - momentum: 0.000000
2023-10-14 19:30:10,721 epoch 10 - iter 352/447 - loss 0.01453450 - time (sec): 125.89 - samples/sec: 536.79 - lr: 0.000004 - momentum: 0.000000
2023-10-14 19:30:26,320 epoch 10 - iter 396/447 - loss 0.01404711 - time (sec): 141.49 - samples/sec: 538.43 - lr: 0.000002 - momentum: 0.000000
2023-10-14 19:30:42,363 epoch 10 - iter 440/447 - loss 0.01559727 - time (sec): 157.53 - samples/sec: 540.67 - lr: 0.000001 - momentum: 0.000000
2023-10-14 19:30:44,798 ----------------------------------------------------------------------------------------------------
2023-10-14 19:30:44,798 EPOCH 10 done: loss 0.0161 - lr: 0.000001
2023-10-14 19:31:09,873 DEV : loss 0.2216092348098755 - f1-score (micro avg)  0.7554
2023-10-14 19:31:10,513 ----------------------------------------------------------------------------------------------------
2023-10-14 19:31:10,514 Loading model from best epoch ...
2023-10-14 19:31:12,868 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
2023-10-14 19:31:34,412 
Results:
- F-score (micro) 0.752
- F-score (macro) 0.6601
- Accuracy 0.6184

By class:
              precision    recall  f1-score   support

         loc     0.8473    0.8658    0.8564       596
        pers     0.6649    0.7508    0.7052       333
         org     0.5351    0.4621    0.4959       132
        prod     0.6182    0.5152    0.5620        66
        time     0.7111    0.6531    0.6809        49

   micro avg     0.7448    0.7594    0.7520      1176
   macro avg     0.6753    0.6494    0.6601      1176
weighted avg     0.7421    0.7594    0.7493      1176

2023-10-14 19:31:34,412 ----------------------------------------------------------------------------------------------------