2023-10-13 08:19:08,899 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,902 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()
)"
2023-10-13 08:19:08,902 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,902 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
 - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
2023-10-13 08:19:08,902 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,902 Train:  6183 sentences
2023-10-13 08:19:08,902         (train_with_dev=False, train_with_test=False)
2023-10-13 08:19:08,902 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,902 Training Params:
2023-10-13 08:19:08,903  - learning_rate: "0.00016" 
2023-10-13 08:19:08,903  - mini_batch_size: "8"
2023-10-13 08:19:08,903  - max_epochs: "10"
2023-10-13 08:19:08,903  - shuffle: "True"
2023-10-13 08:19:08,903 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,903 Plugins:
2023-10-13 08:19:08,903  - TensorboardLogger
2023-10-13 08:19:08,903  - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:19:08,903 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,903 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:19:08,903  - metric: "('micro avg', 'f1-score')"
2023-10-13 08:19:08,903 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,904 Computation:
2023-10-13 08:19:08,904  - compute on device: cuda:0
2023-10-13 08:19:08,904  - embedding storage: none
2023-10-13 08:19:08,904 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,904 Model training base path: "hmbench-topres19th/en-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1"
2023-10-13 08:19:08,904 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,904 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:08,904 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-13 08:19:50,141 epoch 1 - iter 77/773 - loss 2.58730266 - time (sec): 41.23 - samples/sec: 301.42 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:20:30,710 epoch 1 - iter 154/773 - loss 2.55059890 - time (sec): 81.80 - samples/sec: 299.71 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:21:10,668 epoch 1 - iter 231/773 - loss 2.39904412 - time (sec): 121.76 - samples/sec: 297.29 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:21:51,323 epoch 1 - iter 308/773 - loss 2.15465609 - time (sec): 162.42 - samples/sec: 304.57 - lr: 0.000064 - momentum: 0.000000
2023-10-13 08:22:32,528 epoch 1 - iter 385/773 - loss 1.91746015 - time (sec): 203.62 - samples/sec: 302.07 - lr: 0.000079 - momentum: 0.000000
2023-10-13 08:23:13,165 epoch 1 - iter 462/773 - loss 1.68296157 - time (sec): 244.26 - samples/sec: 301.35 - lr: 0.000095 - momentum: 0.000000
2023-10-13 08:23:54,263 epoch 1 - iter 539/773 - loss 1.47564652 - time (sec): 285.36 - samples/sec: 302.30 - lr: 0.000111 - momentum: 0.000000
2023-10-13 08:24:33,555 epoch 1 - iter 616/773 - loss 1.33003809 - time (sec): 324.65 - samples/sec: 300.69 - lr: 0.000127 - momentum: 0.000000
2023-10-13 08:25:14,174 epoch 1 - iter 693/773 - loss 1.19198349 - time (sec): 365.27 - samples/sec: 304.37 - lr: 0.000143 - momentum: 0.000000
2023-10-13 08:25:54,562 epoch 1 - iter 770/773 - loss 1.08563981 - time (sec): 405.66 - samples/sec: 305.32 - lr: 0.000159 - momentum: 0.000000
2023-10-13 08:25:56,056 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:56,056 EPOCH 1 done: loss 1.0826 - lr: 0.000159
2023-10-13 08:26:13,153 DEV : loss 0.11099149286746979 - f1-score (micro avg)  0.1016
2023-10-13 08:26:13,184 saving best model
2023-10-13 08:26:14,082 ----------------------------------------------------------------------------------------------------
2023-10-13 08:26:54,066 epoch 2 - iter 77/773 - loss 0.14305981 - time (sec): 39.98 - samples/sec: 292.54 - lr: 0.000158 - momentum: 0.000000
2023-10-13 08:27:35,342 epoch 2 - iter 154/773 - loss 0.13795277 - time (sec): 81.26 - samples/sec: 290.12 - lr: 0.000156 - momentum: 0.000000
2023-10-13 08:28:17,325 epoch 2 - iter 231/773 - loss 0.13042122 - time (sec): 123.24 - samples/sec: 296.86 - lr: 0.000155 - momentum: 0.000000
2023-10-13 08:28:59,076 epoch 2 - iter 308/773 - loss 0.12544485 - time (sec): 164.99 - samples/sec: 299.44 - lr: 0.000153 - momentum: 0.000000
2023-10-13 08:29:40,403 epoch 2 - iter 385/773 - loss 0.11796362 - time (sec): 206.32 - samples/sec: 301.05 - lr: 0.000151 - momentum: 0.000000
2023-10-13 08:30:20,228 epoch 2 - iter 462/773 - loss 0.11608104 - time (sec): 246.14 - samples/sec: 298.83 - lr: 0.000149 - momentum: 0.000000
2023-10-13 08:31:00,760 epoch 2 - iter 539/773 - loss 0.11492213 - time (sec): 286.68 - samples/sec: 298.69 - lr: 0.000148 - momentum: 0.000000
2023-10-13 08:31:41,887 epoch 2 - iter 616/773 - loss 0.11409853 - time (sec): 327.80 - samples/sec: 298.31 - lr: 0.000146 - momentum: 0.000000
2023-10-13 08:32:24,110 epoch 2 - iter 693/773 - loss 0.10924535 - time (sec): 370.03 - samples/sec: 300.79 - lr: 0.000144 - momentum: 0.000000
2023-10-13 08:33:04,730 epoch 2 - iter 770/773 - loss 0.10522174 - time (sec): 410.65 - samples/sec: 301.53 - lr: 0.000142 - momentum: 0.000000
2023-10-13 08:33:06,213 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:06,214 EPOCH 2 done: loss 0.1051 - lr: 0.000142
2023-10-13 08:33:23,548 DEV : loss 0.05811596289277077 - f1-score (micro avg)  0.7475
2023-10-13 08:33:23,577 saving best model
2023-10-13 08:33:26,281 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:06,347 epoch 3 - iter 77/773 - loss 0.07785087 - time (sec): 40.06 - samples/sec: 304.00 - lr: 0.000140 - momentum: 0.000000
2023-10-13 08:34:47,144 epoch 3 - iter 154/773 - loss 0.07400192 - time (sec): 80.86 - samples/sec: 301.26 - lr: 0.000139 - momentum: 0.000000
2023-10-13 08:35:27,746 epoch 3 - iter 231/773 - loss 0.06533236 - time (sec): 121.46 - samples/sec: 307.32 - lr: 0.000137 - momentum: 0.000000
2023-10-13 08:36:06,754 epoch 3 - iter 308/773 - loss 0.06656562 - time (sec): 160.47 - samples/sec: 301.45 - lr: 0.000135 - momentum: 0.000000
2023-10-13 08:36:46,986 epoch 3 - iter 385/773 - loss 0.06409639 - time (sec): 200.70 - samples/sec: 303.24 - lr: 0.000133 - momentum: 0.000000
2023-10-13 08:37:28,249 epoch 3 - iter 462/773 - loss 0.06382119 - time (sec): 241.96 - samples/sec: 303.68 - lr: 0.000132 - momentum: 0.000000
2023-10-13 08:38:10,144 epoch 3 - iter 539/773 - loss 0.06259696 - time (sec): 283.86 - samples/sec: 303.91 - lr: 0.000130 - momentum: 0.000000
2023-10-13 08:38:52,032 epoch 3 - iter 616/773 - loss 0.06115232 - time (sec): 325.75 - samples/sec: 303.96 - lr: 0.000128 - momentum: 0.000000
2023-10-13 08:39:34,247 epoch 3 - iter 693/773 - loss 0.06103512 - time (sec): 367.96 - samples/sec: 304.31 - lr: 0.000126 - momentum: 0.000000
2023-10-13 08:40:14,706 epoch 3 - iter 770/773 - loss 0.06073176 - time (sec): 408.42 - samples/sec: 303.28 - lr: 0.000125 - momentum: 0.000000
2023-10-13 08:40:16,218 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:16,218 EPOCH 3 done: loss 0.0606 - lr: 0.000125
2023-10-13 08:40:33,594 DEV : loss 0.0552801787853241 - f1-score (micro avg)  0.7881
2023-10-13 08:40:33,623 saving best model
2023-10-13 08:40:36,276 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:18,425 epoch 4 - iter 77/773 - loss 0.04476949 - time (sec): 42.15 - samples/sec: 300.04 - lr: 0.000123 - momentum: 0.000000
2023-10-13 08:42:00,086 epoch 4 - iter 154/773 - loss 0.03746333 - time (sec): 83.81 - samples/sec: 295.93 - lr: 0.000121 - momentum: 0.000000
2023-10-13 08:42:42,080 epoch 4 - iter 231/773 - loss 0.03607636 - time (sec): 125.80 - samples/sec: 298.86 - lr: 0.000119 - momentum: 0.000000
2023-10-13 08:43:22,064 epoch 4 - iter 308/773 - loss 0.03867782 - time (sec): 165.78 - samples/sec: 293.02 - lr: 0.000117 - momentum: 0.000000
2023-10-13 08:44:02,559 epoch 4 - iter 385/773 - loss 0.03895762 - time (sec): 206.28 - samples/sec: 296.12 - lr: 0.000116 - momentum: 0.000000
2023-10-13 08:44:43,495 epoch 4 - iter 462/773 - loss 0.03983620 - time (sec): 247.22 - samples/sec: 298.78 - lr: 0.000114 - momentum: 0.000000
2023-10-13 08:45:25,523 epoch 4 - iter 539/773 - loss 0.03920856 - time (sec): 289.24 - samples/sec: 299.42 - lr: 0.000112 - momentum: 0.000000
2023-10-13 08:46:08,084 epoch 4 - iter 616/773 - loss 0.03888995 - time (sec): 331.80 - samples/sec: 298.84 - lr: 0.000110 - momentum: 0.000000
2023-10-13 08:46:50,278 epoch 4 - iter 693/773 - loss 0.03923841 - time (sec): 374.00 - samples/sec: 298.91 - lr: 0.000109 - momentum: 0.000000
2023-10-13 08:47:32,327 epoch 4 - iter 770/773 - loss 0.03856068 - time (sec): 416.05 - samples/sec: 297.69 - lr: 0.000107 - momentum: 0.000000
2023-10-13 08:47:33,887 ----------------------------------------------------------------------------------------------------
2023-10-13 08:47:33,887 EPOCH 4 done: loss 0.0385 - lr: 0.000107
2023-10-13 08:47:52,334 DEV : loss 0.06545507162809372 - f1-score (micro avg)  0.8016
2023-10-13 08:47:52,364 saving best model
2023-10-13 08:47:55,049 ----------------------------------------------------------------------------------------------------
2023-10-13 08:48:38,854 epoch 5 - iter 77/773 - loss 0.01846706 - time (sec): 43.80 - samples/sec: 288.79 - lr: 0.000105 - momentum: 0.000000
2023-10-13 08:49:21,723 epoch 5 - iter 154/773 - loss 0.02454332 - time (sec): 86.67 - samples/sec: 296.98 - lr: 0.000103 - momentum: 0.000000
2023-10-13 08:50:02,363 epoch 5 - iter 231/773 - loss 0.02461244 - time (sec): 127.31 - samples/sec: 293.55 - lr: 0.000101 - momentum: 0.000000
2023-10-13 08:50:44,834 epoch 5 - iter 308/773 - loss 0.02573056 - time (sec): 169.78 - samples/sec: 294.29 - lr: 0.000100 - momentum: 0.000000
2023-10-13 08:51:26,399 epoch 5 - iter 385/773 - loss 0.02503993 - time (sec): 211.34 - samples/sec: 293.14 - lr: 0.000098 - momentum: 0.000000
2023-10-13 08:52:08,335 epoch 5 - iter 462/773 - loss 0.02523957 - time (sec): 253.28 - samples/sec: 293.25 - lr: 0.000096 - momentum: 0.000000
2023-10-13 08:52:50,137 epoch 5 - iter 539/773 - loss 0.02476814 - time (sec): 295.08 - samples/sec: 292.50 - lr: 0.000094 - momentum: 0.000000
2023-10-13 08:53:32,478 epoch 5 - iter 616/773 - loss 0.02532580 - time (sec): 337.42 - samples/sec: 291.70 - lr: 0.000093 - momentum: 0.000000
2023-10-13 08:54:14,968 epoch 5 - iter 693/773 - loss 0.02453011 - time (sec): 379.91 - samples/sec: 292.62 - lr: 0.000091 - momentum: 0.000000
2023-10-13 08:54:57,343 epoch 5 - iter 770/773 - loss 0.02434157 - time (sec): 422.29 - samples/sec: 292.92 - lr: 0.000089 - momentum: 0.000000
2023-10-13 08:54:58,958 ----------------------------------------------------------------------------------------------------
2023-10-13 08:54:58,958 EPOCH 5 done: loss 0.0244 - lr: 0.000089
2023-10-13 08:55:16,703 DEV : loss 0.0751594752073288 - f1-score (micro avg)  0.8144
2023-10-13 08:55:16,734 saving best model
2023-10-13 08:55:19,789 ----------------------------------------------------------------------------------------------------
2023-10-13 08:56:01,233 epoch 6 - iter 77/773 - loss 0.01673791 - time (sec): 41.44 - samples/sec: 317.64 - lr: 0.000087 - momentum: 0.000000
2023-10-13 08:56:42,436 epoch 6 - iter 154/773 - loss 0.01680699 - time (sec): 82.64 - samples/sec: 312.25 - lr: 0.000085 - momentum: 0.000000
2023-10-13 08:57:23,912 epoch 6 - iter 231/773 - loss 0.01587428 - time (sec): 124.12 - samples/sec: 312.83 - lr: 0.000084 - momentum: 0.000000
2023-10-13 08:58:04,159 epoch 6 - iter 308/773 - loss 0.01703803 - time (sec): 164.37 - samples/sec: 309.35 - lr: 0.000082 - momentum: 0.000000
2023-10-13 08:58:45,074 epoch 6 - iter 385/773 - loss 0.01583363 - time (sec): 205.28 - samples/sec: 308.11 - lr: 0.000080 - momentum: 0.000000
2023-10-13 08:59:24,621 epoch 6 - iter 462/773 - loss 0.01716180 - time (sec): 244.83 - samples/sec: 302.92 - lr: 0.000078 - momentum: 0.000000
2023-10-13 09:00:06,607 epoch 6 - iter 539/773 - loss 0.01706255 - time (sec): 286.81 - samples/sec: 302.79 - lr: 0.000077 - momentum: 0.000000
2023-10-13 09:00:46,986 epoch 6 - iter 616/773 - loss 0.01715802 - time (sec): 327.19 - samples/sec: 302.13 - lr: 0.000075 - momentum: 0.000000
2023-10-13 09:01:27,957 epoch 6 - iter 693/773 - loss 0.01750027 - time (sec): 368.16 - samples/sec: 300.91 - lr: 0.000073 - momentum: 0.000000
2023-10-13 09:02:08,865 epoch 6 - iter 770/773 - loss 0.01766724 - time (sec): 409.07 - samples/sec: 302.36 - lr: 0.000071 - momentum: 0.000000
2023-10-13 09:02:10,479 ----------------------------------------------------------------------------------------------------
2023-10-13 09:02:10,479 EPOCH 6 done: loss 0.0176 - lr: 0.000071
2023-10-13 09:02:27,976 DEV : loss 0.08374767750501633 - f1-score (micro avg)  0.7984
2023-10-13 09:02:28,010 ----------------------------------------------------------------------------------------------------
2023-10-13 09:03:07,761 epoch 7 - iter 77/773 - loss 0.01033091 - time (sec): 39.75 - samples/sec: 295.81 - lr: 0.000069 - momentum: 0.000000
2023-10-13 09:03:48,071 epoch 7 - iter 154/773 - loss 0.01115286 - time (sec): 80.06 - samples/sec: 312.36 - lr: 0.000068 - momentum: 0.000000
2023-10-13 09:04:27,324 epoch 7 - iter 231/773 - loss 0.01249494 - time (sec): 119.31 - samples/sec: 308.50 - lr: 0.000066 - momentum: 0.000000
2023-10-13 09:05:07,581 epoch 7 - iter 308/773 - loss 0.01131802 - time (sec): 159.57 - samples/sec: 304.43 - lr: 0.000064 - momentum: 0.000000
2023-10-13 09:05:47,131 epoch 7 - iter 385/773 - loss 0.01181494 - time (sec): 199.12 - samples/sec: 300.09 - lr: 0.000062 - momentum: 0.000000
2023-10-13 09:06:28,020 epoch 7 - iter 462/773 - loss 0.01230035 - time (sec): 240.01 - samples/sec: 303.00 - lr: 0.000061 - momentum: 0.000000
2023-10-13 09:07:08,824 epoch 7 - iter 539/773 - loss 0.01249036 - time (sec): 280.81 - samples/sec: 306.60 - lr: 0.000059 - momentum: 0.000000
2023-10-13 09:07:49,019 epoch 7 - iter 616/773 - loss 0.01225369 - time (sec): 321.01 - samples/sec: 307.52 - lr: 0.000057 - momentum: 0.000000
2023-10-13 09:08:29,608 epoch 7 - iter 693/773 - loss 0.01221858 - time (sec): 361.60 - samples/sec: 311.11 - lr: 0.000055 - momentum: 0.000000
2023-10-13 09:09:08,846 epoch 7 - iter 770/773 - loss 0.01224012 - time (sec): 400.83 - samples/sec: 308.94 - lr: 0.000054 - momentum: 0.000000
2023-10-13 09:09:10,350 ----------------------------------------------------------------------------------------------------
2023-10-13 09:09:10,350 EPOCH 7 done: loss 0.0122 - lr: 0.000054
2023-10-13 09:09:27,602 DEV : loss 0.09720773994922638 - f1-score (micro avg)  0.7937
2023-10-13 09:09:27,634 ----------------------------------------------------------------------------------------------------
2023-10-13 09:10:07,791 epoch 8 - iter 77/773 - loss 0.01708732 - time (sec): 40.16 - samples/sec: 291.97 - lr: 0.000052 - momentum: 0.000000
2023-10-13 09:10:49,357 epoch 8 - iter 154/773 - loss 0.01343491 - time (sec): 81.72 - samples/sec: 296.01 - lr: 0.000050 - momentum: 0.000000
2023-10-13 09:11:30,343 epoch 8 - iter 231/773 - loss 0.01154821 - time (sec): 122.71 - samples/sec: 297.74 - lr: 0.000048 - momentum: 0.000000
2023-10-13 09:12:12,352 epoch 8 - iter 308/773 - loss 0.01089407 - time (sec): 164.72 - samples/sec: 295.88 - lr: 0.000046 - momentum: 0.000000
2023-10-13 09:12:53,254 epoch 8 - iter 385/773 - loss 0.01019327 - time (sec): 205.62 - samples/sec: 298.89 - lr: 0.000045 - momentum: 0.000000
2023-10-13 09:13:33,143 epoch 8 - iter 462/773 - loss 0.01018692 - time (sec): 245.51 - samples/sec: 299.10 - lr: 0.000043 - momentum: 0.000000
2023-10-13 09:14:13,585 epoch 8 - iter 539/773 - loss 0.00949815 - time (sec): 285.95 - samples/sec: 300.80 - lr: 0.000041 - momentum: 0.000000
2023-10-13 09:14:53,793 epoch 8 - iter 616/773 - loss 0.00908648 - time (sec): 326.16 - samples/sec: 302.26 - lr: 0.000039 - momentum: 0.000000
2023-10-13 09:15:35,446 epoch 8 - iter 693/773 - loss 0.00876514 - time (sec): 367.81 - samples/sec: 303.70 - lr: 0.000038 - momentum: 0.000000
2023-10-13 09:16:15,879 epoch 8 - iter 770/773 - loss 0.00886285 - time (sec): 408.24 - samples/sec: 303.07 - lr: 0.000036 - momentum: 0.000000
2023-10-13 09:16:17,537 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:17,538 EPOCH 8 done: loss 0.0088 - lr: 0.000036
2023-10-13 09:16:35,753 DEV : loss 0.09890314191579819 - f1-score (micro avg)  0.7911
2023-10-13 09:16:35,783 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:17,503 epoch 9 - iter 77/773 - loss 0.00646634 - time (sec): 41.72 - samples/sec: 304.55 - lr: 0.000034 - momentum: 0.000000
2023-10-13 09:17:58,563 epoch 9 - iter 154/773 - loss 0.00554555 - time (sec): 82.78 - samples/sec: 314.97 - lr: 0.000032 - momentum: 0.000000
2023-10-13 09:18:37,848 epoch 9 - iter 231/773 - loss 0.00533044 - time (sec): 122.06 - samples/sec: 310.68 - lr: 0.000030 - momentum: 0.000000
2023-10-13 09:19:18,324 epoch 9 - iter 308/773 - loss 0.00587687 - time (sec): 162.54 - samples/sec: 312.71 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:19:58,350 epoch 9 - iter 385/773 - loss 0.00628664 - time (sec): 202.56 - samples/sec: 306.65 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:20:38,748 epoch 9 - iter 462/773 - loss 0.00615498 - time (sec): 242.96 - samples/sec: 306.57 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:21:19,766 epoch 9 - iter 539/773 - loss 0.00604577 - time (sec): 283.98 - samples/sec: 305.10 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:22:01,519 epoch 9 - iter 616/773 - loss 0.00611423 - time (sec): 325.73 - samples/sec: 304.07 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:22:43,185 epoch 9 - iter 693/773 - loss 0.00630368 - time (sec): 367.40 - samples/sec: 303.01 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:23:23,592 epoch 9 - iter 770/773 - loss 0.00633550 - time (sec): 407.81 - samples/sec: 303.33 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:23:25,195 ----------------------------------------------------------------------------------------------------
2023-10-13 09:23:25,196 EPOCH 9 done: loss 0.0063 - lr: 0.000018
2023-10-13 09:23:42,559 DEV : loss 0.10465419292449951 - f1-score (micro avg)  0.804
2023-10-13 09:23:42,588 ----------------------------------------------------------------------------------------------------
2023-10-13 09:24:23,348 epoch 10 - iter 77/773 - loss 0.00813140 - time (sec): 40.76 - samples/sec: 294.03 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:25:03,909 epoch 10 - iter 154/773 - loss 0.00628416 - time (sec): 81.32 - samples/sec: 295.21 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:25:45,244 epoch 10 - iter 231/773 - loss 0.00587552 - time (sec): 122.65 - samples/sec: 307.28 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:26:24,689 epoch 10 - iter 308/773 - loss 0.00556725 - time (sec): 162.10 - samples/sec: 307.03 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:27:05,760 epoch 10 - iter 385/773 - loss 0.00507982 - time (sec): 203.17 - samples/sec: 311.80 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:27:45,942 epoch 10 - iter 462/773 - loss 0.00493721 - time (sec): 243.35 - samples/sec: 307.84 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:28:25,346 epoch 10 - iter 539/773 - loss 0.00467343 - time (sec): 282.76 - samples/sec: 306.12 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:29:05,476 epoch 10 - iter 616/773 - loss 0.00474369 - time (sec): 322.88 - samples/sec: 306.60 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:29:45,952 epoch 10 - iter 693/773 - loss 0.00460932 - time (sec): 363.36 - samples/sec: 307.07 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:30:25,663 epoch 10 - iter 770/773 - loss 0.00490796 - time (sec): 403.07 - samples/sec: 307.22 - lr: 0.000000 - momentum: 0.000000
2023-10-13 09:30:27,137 ----------------------------------------------------------------------------------------------------
2023-10-13 09:30:27,137 EPOCH 10 done: loss 0.0049 - lr: 0.000000
2023-10-13 09:30:44,002 DEV : loss 0.10406773537397385 - f1-score (micro avg)  0.7952
2023-10-13 09:30:44,940 ----------------------------------------------------------------------------------------------------
2023-10-13 09:30:44,942 Loading model from best epoch ...
2023-10-13 09:30:49,804 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
2023-10-13 09:31:46,437 
Results:
- F-score (micro) 0.7939
- F-score (macro) 0.7132
- Accuracy 0.6792

By class:
              precision    recall  f1-score   support

         LOC     0.8423    0.8467    0.8445       946
    BUILDING     0.5489    0.5459    0.5474       185
      STREET     0.7843    0.7143    0.7477        56

   micro avg     0.7943    0.7936    0.7939      1187
   macro avg     0.7252    0.7023    0.7132      1187
weighted avg     0.7938    0.7936    0.7936      1187

2023-10-13 09:31:46,437 ----------------------------------------------------------------------------------------------------