training.log

2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(31103, 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=17, bias=True)
  (loss_function): CrossEntropyLoss()
)"
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Corpus: 758 train + 94 dev + 96 test sentences
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Train:  758 sentences
2024-03-26 15:47:36,999         (train_with_dev=False, train_with_test=False)
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Training Params:
2024-03-26 15:47:36,999  - learning_rate: "3e-05" 
2024-03-26 15:47:36,999  - mini_batch_size: "16"
2024-03-26 15:47:36,999  - max_epochs: "10"
2024-03-26 15:47:36,999  - shuffle: "True"
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Plugins:
2024-03-26 15:47:36,999  - TensorboardLogger
2024-03-26 15:47:36,999  - LinearScheduler | warmup_fraction: '0.1'
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Final evaluation on model from best epoch (best-model.pt)
2024-03-26 15:47:36,999  - metric: "('micro avg', 'f1-score')"
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Computation:
2024-03-26 15:47:36,999  - compute on device: cuda:0
2024-03-26 15:47:36,999  - embedding storage: none
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs16-e10-lr3e-05-3"
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:36,999 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:37,000 Logging anything other than scalars to TensorBoard is currently not supported.
2024-03-26 15:47:38,243 epoch 1 - iter 4/48 - loss 3.37379841 - time (sec): 1.24 - samples/sec: 2215.07 - lr: 0.000002 - momentum: 0.000000
2024-03-26 15:47:40,206 epoch 1 - iter 8/48 - loss 3.38378942 - time (sec): 3.21 - samples/sec: 1816.61 - lr: 0.000004 - momentum: 0.000000
2024-03-26 15:47:41,730 epoch 1 - iter 12/48 - loss 3.35565868 - time (sec): 4.73 - samples/sec: 1770.37 - lr: 0.000007 - momentum: 0.000000
2024-03-26 15:47:44,610 epoch 1 - iter 16/48 - loss 3.28068558 - time (sec): 7.61 - samples/sec: 1524.04 - lr: 0.000009 - momentum: 0.000000
2024-03-26 15:47:46,256 epoch 1 - iter 20/48 - loss 3.13339846 - time (sec): 9.26 - samples/sec: 1556.12 - lr: 0.000012 - momentum: 0.000000
2024-03-26 15:47:47,687 epoch 1 - iter 24/48 - loss 2.99408989 - time (sec): 10.69 - samples/sec: 1606.41 - lr: 0.000014 - momentum: 0.000000
2024-03-26 15:47:49,001 epoch 1 - iter 28/48 - loss 2.84824149 - time (sec): 12.00 - samples/sec: 1627.05 - lr: 0.000017 - momentum: 0.000000
2024-03-26 15:47:51,083 epoch 1 - iter 32/48 - loss 2.70044326 - time (sec): 14.08 - samples/sec: 1613.86 - lr: 0.000019 - momentum: 0.000000
2024-03-26 15:47:52,621 epoch 1 - iter 36/48 - loss 2.57582595 - time (sec): 15.62 - samples/sec: 1633.62 - lr: 0.000022 - momentum: 0.000000
2024-03-26 15:47:54,837 epoch 1 - iter 40/48 - loss 2.44489920 - time (sec): 17.84 - samples/sec: 1624.49 - lr: 0.000024 - momentum: 0.000000
2024-03-26 15:47:56,731 epoch 1 - iter 44/48 - loss 2.33561949 - time (sec): 19.73 - samples/sec: 1625.16 - lr: 0.000027 - momentum: 0.000000
2024-03-26 15:47:58,339 epoch 1 - iter 48/48 - loss 2.24504382 - time (sec): 21.34 - samples/sec: 1615.44 - lr: 0.000029 - momentum: 0.000000
2024-03-26 15:47:58,339 ----------------------------------------------------------------------------------------------------
2024-03-26 15:47:58,339 EPOCH 1 done: loss 2.2450 - lr: 0.000029
2024-03-26 15:47:59,148 DEV : loss 0.8031646609306335 - f1-score (micro avg)  0.4656
2024-03-26 15:47:59,149 saving best model
2024-03-26 15:47:59,410 ----------------------------------------------------------------------------------------------------
2024-03-26 15:48:00,812 epoch 2 - iter 4/48 - loss 1.04326321 - time (sec): 1.40 - samples/sec: 1780.71 - lr: 0.000030 - momentum: 0.000000
2024-03-26 15:48:02,265 epoch 2 - iter 8/48 - loss 0.87730803 - time (sec): 2.85 - samples/sec: 1710.29 - lr: 0.000030 - momentum: 0.000000
2024-03-26 15:48:03,681 epoch 2 - iter 12/48 - loss 0.83901534 - time (sec): 4.27 - samples/sec: 1800.20 - lr: 0.000029 - momentum: 0.000000
2024-03-26 15:48:05,535 epoch 2 - iter 16/48 - loss 0.77100321 - time (sec): 6.12 - samples/sec: 1756.57 - lr: 0.000029 - momentum: 0.000000
2024-03-26 15:48:07,867 epoch 2 - iter 20/48 - loss 0.73954646 - time (sec): 8.46 - samples/sec: 1676.84 - lr: 0.000029 - momentum: 0.000000
2024-03-26 15:48:09,869 epoch 2 - iter 24/48 - loss 0.69136182 - time (sec): 10.46 - samples/sec: 1658.52 - lr: 0.000028 - momentum: 0.000000
2024-03-26 15:48:12,567 epoch 2 - iter 28/48 - loss 0.66596220 - time (sec): 13.16 - samples/sec: 1590.53 - lr: 0.000028 - momentum: 0.000000
2024-03-26 15:48:14,742 epoch 2 - iter 32/48 - loss 0.64037489 - time (sec): 15.33 - samples/sec: 1556.83 - lr: 0.000028 - momentum: 0.000000
2024-03-26 15:48:16,449 epoch 2 - iter 36/48 - loss 0.62884232 - time (sec): 17.04 - samples/sec: 1550.49 - lr: 0.000028 - momentum: 0.000000
2024-03-26 15:48:18,141 epoch 2 - iter 40/48 - loss 0.62020735 - time (sec): 18.73 - samples/sec: 1557.51 - lr: 0.000027 - momentum: 0.000000
2024-03-26 15:48:20,284 epoch 2 - iter 44/48 - loss 0.60189604 - time (sec): 20.87 - samples/sec: 1552.36 - lr: 0.000027 - momentum: 0.000000
2024-03-26 15:48:21,787 epoch 2 - iter 48/48 - loss 0.58624485 - time (sec): 22.38 - samples/sec: 1540.59 - lr: 0.000027 - momentum: 0.000000
2024-03-26 15:48:21,787 ----------------------------------------------------------------------------------------------------
2024-03-26 15:48:21,787 EPOCH 2 done: loss 0.5862 - lr: 0.000027
2024-03-26 15:48:22,767 DEV : loss 0.32458996772766113 - f1-score (micro avg)  0.7892
2024-03-26 15:48:22,768 saving best model
2024-03-26 15:48:23,190 ----------------------------------------------------------------------------------------------------
2024-03-26 15:48:24,682 epoch 3 - iter 4/48 - loss 0.35901192 - time (sec): 1.49 - samples/sec: 1643.98 - lr: 0.000026 - momentum: 0.000000
2024-03-26 15:48:27,381 epoch 3 - iter 8/48 - loss 0.31347438 - time (sec): 4.19 - samples/sec: 1367.54 - lr: 0.000026 - momentum: 0.000000
2024-03-26 15:48:28,614 epoch 3 - iter 12/48 - loss 0.32826115 - time (sec): 5.42 - samples/sec: 1502.29 - lr: 0.000026 - momentum: 0.000000
2024-03-26 15:48:29,957 epoch 3 - iter 16/48 - loss 0.30830080 - time (sec): 6.77 - samples/sec: 1631.60 - lr: 0.000026 - momentum: 0.000000
2024-03-26 15:48:31,394 epoch 3 - iter 20/48 - loss 0.31154007 - time (sec): 8.20 - samples/sec: 1647.17 - lr: 0.000025 - momentum: 0.000000
2024-03-26 15:48:34,065 epoch 3 - iter 24/48 - loss 0.30431891 - time (sec): 10.87 - samples/sec: 1536.24 - lr: 0.000025 - momentum: 0.000000
2024-03-26 15:48:35,947 epoch 3 - iter 28/48 - loss 0.30275570 - time (sec): 12.76 - samples/sec: 1553.88 - lr: 0.000025 - momentum: 0.000000
2024-03-26 15:48:38,432 epoch 3 - iter 32/48 - loss 0.29026230 - time (sec): 15.24 - samples/sec: 1496.08 - lr: 0.000025 - momentum: 0.000000
2024-03-26 15:48:40,337 epoch 3 - iter 36/48 - loss 0.29110826 - time (sec): 17.14 - samples/sec: 1491.88 - lr: 0.000024 - momentum: 0.000000
2024-03-26 15:48:42,660 epoch 3 - iter 40/48 - loss 0.28131814 - time (sec): 19.47 - samples/sec: 1467.23 - lr: 0.000024 - momentum: 0.000000
2024-03-26 15:48:45,068 epoch 3 - iter 44/48 - loss 0.28892993 - time (sec): 21.88 - samples/sec: 1454.64 - lr: 0.000024 - momentum: 0.000000
2024-03-26 15:48:47,362 epoch 3 - iter 48/48 - loss 0.28042318 - time (sec): 24.17 - samples/sec: 1426.23 - lr: 0.000023 - momentum: 0.000000
2024-03-26 15:48:47,362 ----------------------------------------------------------------------------------------------------
2024-03-26 15:48:47,362 EPOCH 3 done: loss 0.2804 - lr: 0.000023
2024-03-26 15:48:48,272 DEV : loss 0.23968861997127533 - f1-score (micro avg)  0.8524
2024-03-26 15:48:48,275 saving best model
2024-03-26 15:48:48,727 ----------------------------------------------------------------------------------------------------
2024-03-26 15:48:50,103 epoch 4 - iter 4/48 - loss 0.21412296 - time (sec): 1.37 - samples/sec: 1824.20 - lr: 0.000023 - momentum: 0.000000
2024-03-26 15:48:51,996 epoch 4 - iter 8/48 - loss 0.20087814 - time (sec): 3.27 - samples/sec: 1640.43 - lr: 0.000023 - momentum: 0.000000
2024-03-26 15:48:54,504 epoch 4 - iter 12/48 - loss 0.18530637 - time (sec): 5.77 - samples/sec: 1461.50 - lr: 0.000023 - momentum: 0.000000
2024-03-26 15:48:56,381 epoch 4 - iter 16/48 - loss 0.19056545 - time (sec): 7.65 - samples/sec: 1479.99 - lr: 0.000022 - momentum: 0.000000
2024-03-26 15:48:58,737 epoch 4 - iter 20/48 - loss 0.18109565 - time (sec): 10.01 - samples/sec: 1468.23 - lr: 0.000022 - momentum: 0.000000
2024-03-26 15:49:01,604 epoch 4 - iter 24/48 - loss 0.17043274 - time (sec): 12.87 - samples/sec: 1416.31 - lr: 0.000022 - momentum: 0.000000
2024-03-26 15:49:02,712 epoch 4 - iter 28/48 - loss 0.17008703 - time (sec): 13.98 - samples/sec: 1452.82 - lr: 0.000022 - momentum: 0.000000
2024-03-26 15:49:05,694 epoch 4 - iter 32/48 - loss 0.16578596 - time (sec): 16.96 - samples/sec: 1392.19 - lr: 0.000021 - momentum: 0.000000
2024-03-26 15:49:07,403 epoch 4 - iter 36/48 - loss 0.17310898 - time (sec): 18.67 - samples/sec: 1424.82 - lr: 0.000021 - momentum: 0.000000
2024-03-26 15:49:10,200 epoch 4 - iter 40/48 - loss 0.17983930 - time (sec): 21.47 - samples/sec: 1391.90 - lr: 0.000021 - momentum: 0.000000
2024-03-26 15:49:11,102 epoch 4 - iter 44/48 - loss 0.18378026 - time (sec): 22.37 - samples/sec: 1438.31 - lr: 0.000020 - momentum: 0.000000
2024-03-26 15:49:12,572 epoch 4 - iter 48/48 - loss 0.18337316 - time (sec): 23.84 - samples/sec: 1445.82 - lr: 0.000020 - momentum: 0.000000
2024-03-26 15:49:12,572 ----------------------------------------------------------------------------------------------------
2024-03-26 15:49:12,572 EPOCH 4 done: loss 0.1834 - lr: 0.000020
2024-03-26 15:49:13,476 DEV : loss 0.20375721156597137 - f1-score (micro avg)  0.8751
2024-03-26 15:49:13,477 saving best model
2024-03-26 15:49:13,891 ----------------------------------------------------------------------------------------------------
2024-03-26 15:49:16,313 epoch 5 - iter 4/48 - loss 0.11807576 - time (sec): 2.42 - samples/sec: 1313.26 - lr: 0.000020 - momentum: 0.000000
2024-03-26 15:49:17,731 epoch 5 - iter 8/48 - loss 0.14793918 - time (sec): 3.84 - samples/sec: 1483.23 - lr: 0.000020 - momentum: 0.000000
2024-03-26 15:49:19,178 epoch 5 - iter 12/48 - loss 0.14657960 - time (sec): 5.29 - samples/sec: 1559.11 - lr: 0.000019 - momentum: 0.000000
2024-03-26 15:49:21,349 epoch 5 - iter 16/48 - loss 0.14409177 - time (sec): 7.46 - samples/sec: 1475.54 - lr: 0.000019 - momentum: 0.000000
2024-03-26 15:49:23,405 epoch 5 - iter 20/48 - loss 0.15265255 - time (sec): 9.51 - samples/sec: 1480.21 - lr: 0.000019 - momentum: 0.000000
2024-03-26 15:49:25,879 epoch 5 - iter 24/48 - loss 0.14616029 - time (sec): 11.99 - samples/sec: 1468.65 - lr: 0.000018 - momentum: 0.000000
2024-03-26 15:49:28,433 epoch 5 - iter 28/48 - loss 0.13912038 - time (sec): 14.54 - samples/sec: 1447.64 - lr: 0.000018 - momentum: 0.000000
2024-03-26 15:49:30,299 epoch 5 - iter 32/48 - loss 0.13859993 - time (sec): 16.41 - samples/sec: 1451.45 - lr: 0.000018 - momentum: 0.000000
2024-03-26 15:49:32,115 epoch 5 - iter 36/48 - loss 0.13486299 - time (sec): 18.22 - samples/sec: 1451.25 - lr: 0.000018 - momentum: 0.000000
2024-03-26 15:49:34,416 epoch 5 - iter 40/48 - loss 0.13391851 - time (sec): 20.52 - samples/sec: 1439.04 - lr: 0.000017 - momentum: 0.000000
2024-03-26 15:49:36,365 epoch 5 - iter 44/48 - loss 0.13625635 - time (sec): 22.47 - samples/sec: 1437.33 - lr: 0.000017 - momentum: 0.000000
2024-03-26 15:49:37,417 epoch 5 - iter 48/48 - loss 0.13539195 - time (sec): 23.52 - samples/sec: 1465.38 - lr: 0.000017 - momentum: 0.000000
2024-03-26 15:49:37,417 ----------------------------------------------------------------------------------------------------
2024-03-26 15:49:37,417 EPOCH 5 done: loss 0.1354 - lr: 0.000017
2024-03-26 15:49:38,319 DEV : loss 0.19656339287757874 - f1-score (micro avg)  0.8769
2024-03-26 15:49:38,319 saving best model
2024-03-26 15:49:38,757 ----------------------------------------------------------------------------------------------------
2024-03-26 15:49:41,340 epoch 6 - iter 4/48 - loss 0.09964959 - time (sec): 2.58 - samples/sec: 1231.29 - lr: 0.000017 - momentum: 0.000000
2024-03-26 15:49:43,319 epoch 6 - iter 8/48 - loss 0.10546942 - time (sec): 4.56 - samples/sec: 1287.23 - lr: 0.000016 - momentum: 0.000000
2024-03-26 15:49:44,879 epoch 6 - iter 12/48 - loss 0.10479654 - time (sec): 6.12 - samples/sec: 1441.45 - lr: 0.000016 - momentum: 0.000000
2024-03-26 15:49:46,811 epoch 6 - iter 16/48 - loss 0.09781057 - time (sec): 8.05 - samples/sec: 1444.08 - lr: 0.000016 - momentum: 0.000000
2024-03-26 15:49:47,869 epoch 6 - iter 20/48 - loss 0.10170422 - time (sec): 9.11 - samples/sec: 1533.69 - lr: 0.000015 - momentum: 0.000000
2024-03-26 15:49:49,769 epoch 6 - iter 24/48 - loss 0.10095479 - time (sec): 11.01 - samples/sec: 1517.96 - lr: 0.000015 - momentum: 0.000000
2024-03-26 15:49:50,901 epoch 6 - iter 28/48 - loss 0.10031886 - time (sec): 12.14 - samples/sec: 1566.60 - lr: 0.000015 - momentum: 0.000000
2024-03-26 15:49:52,650 epoch 6 - iter 32/48 - loss 0.09608854 - time (sec): 13.89 - samples/sec: 1585.85 - lr: 0.000015 - momentum: 0.000000
2024-03-26 15:49:55,118 epoch 6 - iter 36/48 - loss 0.10539029 - time (sec): 16.36 - samples/sec: 1552.15 - lr: 0.000014 - momentum: 0.000000
2024-03-26 15:49:57,149 epoch 6 - iter 40/48 - loss 0.10342541 - time (sec): 18.39 - samples/sec: 1545.02 - lr: 0.000014 - momentum: 0.000000
2024-03-26 15:49:59,006 epoch 6 - iter 44/48 - loss 0.10552790 - time (sec): 20.25 - samples/sec: 1553.60 - lr: 0.000014 - momentum: 0.000000
2024-03-26 15:50:00,528 epoch 6 - iter 48/48 - loss 0.10513778 - time (sec): 21.77 - samples/sec: 1583.52 - lr: 0.000014 - momentum: 0.000000
2024-03-26 15:50:00,528 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:00,528 EPOCH 6 done: loss 0.1051 - lr: 0.000014
2024-03-26 15:50:01,423 DEV : loss 0.17874132096767426 - f1-score (micro avg)  0.8906
2024-03-26 15:50:01,424 saving best model
2024-03-26 15:50:01,864 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:03,950 epoch 7 - iter 4/48 - loss 0.10289225 - time (sec): 2.08 - samples/sec: 1326.42 - lr: 0.000013 - momentum: 0.000000
2024-03-26 15:50:05,640 epoch 7 - iter 8/48 - loss 0.09604354 - time (sec): 3.77 - samples/sec: 1522.30 - lr: 0.000013 - momentum: 0.000000
2024-03-26 15:50:07,700 epoch 7 - iter 12/48 - loss 0.08236734 - time (sec): 5.83 - samples/sec: 1468.53 - lr: 0.000013 - momentum: 0.000000
2024-03-26 15:50:10,260 epoch 7 - iter 16/48 - loss 0.07567250 - time (sec): 8.39 - samples/sec: 1407.95 - lr: 0.000012 - momentum: 0.000000
2024-03-26 15:50:12,931 epoch 7 - iter 20/48 - loss 0.07694176 - time (sec): 11.07 - samples/sec: 1412.55 - lr: 0.000012 - momentum: 0.000000
2024-03-26 15:50:14,448 epoch 7 - iter 24/48 - loss 0.07791950 - time (sec): 12.58 - samples/sec: 1432.47 - lr: 0.000012 - momentum: 0.000000
2024-03-26 15:50:16,533 epoch 7 - iter 28/48 - loss 0.07423173 - time (sec): 14.67 - samples/sec: 1450.44 - lr: 0.000012 - momentum: 0.000000
2024-03-26 15:50:18,667 epoch 7 - iter 32/48 - loss 0.07743964 - time (sec): 16.80 - samples/sec: 1455.12 - lr: 0.000011 - momentum: 0.000000
2024-03-26 15:50:20,872 epoch 7 - iter 36/48 - loss 0.08204888 - time (sec): 19.01 - samples/sec: 1440.31 - lr: 0.000011 - momentum: 0.000000
2024-03-26 15:50:22,443 epoch 7 - iter 40/48 - loss 0.07843893 - time (sec): 20.58 - samples/sec: 1448.97 - lr: 0.000011 - momentum: 0.000000
2024-03-26 15:50:24,087 epoch 7 - iter 44/48 - loss 0.08223725 - time (sec): 22.22 - samples/sec: 1467.91 - lr: 0.000010 - momentum: 0.000000
2024-03-26 15:50:25,403 epoch 7 - iter 48/48 - loss 0.08252587 - time (sec): 23.54 - samples/sec: 1464.57 - lr: 0.000010 - momentum: 0.000000
2024-03-26 15:50:25,403 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:25,403 EPOCH 7 done: loss 0.0825 - lr: 0.000010
2024-03-26 15:50:26,297 DEV : loss 0.17732246220111847 - f1-score (micro avg)  0.9049
2024-03-26 15:50:26,298 saving best model
2024-03-26 15:50:26,725 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:29,038 epoch 8 - iter 4/48 - loss 0.06075169 - time (sec): 2.31 - samples/sec: 1271.50 - lr: 0.000010 - momentum: 0.000000
2024-03-26 15:50:31,556 epoch 8 - iter 8/48 - loss 0.05551287 - time (sec): 4.83 - samples/sec: 1369.60 - lr: 0.000010 - momentum: 0.000000
2024-03-26 15:50:33,525 epoch 8 - iter 12/48 - loss 0.05367756 - time (sec): 6.80 - samples/sec: 1353.52 - lr: 0.000009 - momentum: 0.000000
2024-03-26 15:50:35,496 epoch 8 - iter 16/48 - loss 0.05290307 - time (sec): 8.77 - samples/sec: 1367.30 - lr: 0.000009 - momentum: 0.000000
2024-03-26 15:50:37,000 epoch 8 - iter 20/48 - loss 0.05432871 - time (sec): 10.27 - samples/sec: 1391.60 - lr: 0.000009 - momentum: 0.000000
2024-03-26 15:50:39,319 epoch 8 - iter 24/48 - loss 0.05341962 - time (sec): 12.59 - samples/sec: 1377.15 - lr: 0.000009 - momentum: 0.000000
2024-03-26 15:50:41,440 epoch 8 - iter 28/48 - loss 0.05337120 - time (sec): 14.71 - samples/sec: 1369.90 - lr: 0.000008 - momentum: 0.000000
2024-03-26 15:50:43,722 epoch 8 - iter 32/48 - loss 0.06255002 - time (sec): 17.00 - samples/sec: 1381.28 - lr: 0.000008 - momentum: 0.000000
2024-03-26 15:50:46,862 epoch 8 - iter 36/48 - loss 0.06460117 - time (sec): 20.14 - samples/sec: 1332.82 - lr: 0.000008 - momentum: 0.000000
2024-03-26 15:50:48,818 epoch 8 - iter 40/48 - loss 0.06712721 - time (sec): 22.09 - samples/sec: 1339.68 - lr: 0.000007 - momentum: 0.000000
2024-03-26 15:50:49,609 epoch 8 - iter 44/48 - loss 0.06594343 - time (sec): 22.88 - samples/sec: 1388.37 - lr: 0.000007 - momentum: 0.000000
2024-03-26 15:50:51,407 epoch 8 - iter 48/48 - loss 0.06743138 - time (sec): 24.68 - samples/sec: 1396.74 - lr: 0.000007 - momentum: 0.000000
2024-03-26 15:50:51,407 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:51,407 EPOCH 8 done: loss 0.0674 - lr: 0.000007
2024-03-26 15:50:52,311 DEV : loss 0.17159819602966309 - f1-score (micro avg)  0.9157
2024-03-26 15:50:52,312 saving best model
2024-03-26 15:50:52,740 ----------------------------------------------------------------------------------------------------
2024-03-26 15:50:55,418 epoch 9 - iter 4/48 - loss 0.03996473 - time (sec): 2.68 - samples/sec: 1232.16 - lr: 0.000007 - momentum: 0.000000
2024-03-26 15:50:57,081 epoch 9 - iter 8/48 - loss 0.04324845 - time (sec): 4.34 - samples/sec: 1322.13 - lr: 0.000006 - momentum: 0.000000
2024-03-26 15:50:59,184 epoch 9 - iter 12/48 - loss 0.05334992 - time (sec): 6.44 - samples/sec: 1393.21 - lr: 0.000006 - momentum: 0.000000
2024-03-26 15:51:01,255 epoch 9 - iter 16/48 - loss 0.05554006 - time (sec): 8.51 - samples/sec: 1422.38 - lr: 0.000006 - momentum: 0.000000
2024-03-26 15:51:03,568 epoch 9 - iter 20/48 - loss 0.04996482 - time (sec): 10.83 - samples/sec: 1397.40 - lr: 0.000006 - momentum: 0.000000
2024-03-26 15:51:05,474 epoch 9 - iter 24/48 - loss 0.05118172 - time (sec): 12.73 - samples/sec: 1390.82 - lr: 0.000005 - momentum: 0.000000
2024-03-26 15:51:08,665 epoch 9 - iter 28/48 - loss 0.05247513 - time (sec): 15.92 - samples/sec: 1341.59 - lr: 0.000005 - momentum: 0.000000
2024-03-26 15:51:10,022 epoch 9 - iter 32/48 - loss 0.05419220 - time (sec): 17.28 - samples/sec: 1382.48 - lr: 0.000005 - momentum: 0.000000
2024-03-26 15:51:12,370 epoch 9 - iter 36/48 - loss 0.05323258 - time (sec): 19.63 - samples/sec: 1372.98 - lr: 0.000004 - momentum: 0.000000
2024-03-26 15:51:13,823 epoch 9 - iter 40/48 - loss 0.05598120 - time (sec): 21.08 - samples/sec: 1390.82 - lr: 0.000004 - momentum: 0.000000
2024-03-26 15:51:15,323 epoch 9 - iter 44/48 - loss 0.06011503 - time (sec): 22.58 - samples/sec: 1408.71 - lr: 0.000004 - momentum: 0.000000
2024-03-26 15:51:16,718 epoch 9 - iter 48/48 - loss 0.05993914 - time (sec): 23.98 - samples/sec: 1437.74 - lr: 0.000004 - momentum: 0.000000
2024-03-26 15:51:16,718 ----------------------------------------------------------------------------------------------------
2024-03-26 15:51:16,718 EPOCH 9 done: loss 0.0599 - lr: 0.000004
2024-03-26 15:51:17,641 DEV : loss 0.17445135116577148 - f1-score (micro avg)  0.9153
2024-03-26 15:51:17,642 ----------------------------------------------------------------------------------------------------
2024-03-26 15:51:20,004 epoch 10 - iter 4/48 - loss 0.03793612 - time (sec): 2.36 - samples/sec: 1393.76 - lr: 0.000003 - momentum: 0.000000
2024-03-26 15:51:21,979 epoch 10 - iter 8/48 - loss 0.03970409 - time (sec): 4.34 - samples/sec: 1347.83 - lr: 0.000003 - momentum: 0.000000
2024-03-26 15:51:23,153 epoch 10 - iter 12/48 - loss 0.05682156 - time (sec): 5.51 - samples/sec: 1513.67 - lr: 0.000003 - momentum: 0.000000
2024-03-26 15:51:24,664 epoch 10 - iter 16/48 - loss 0.06071482 - time (sec): 7.02 - samples/sec: 1597.92 - lr: 0.000002 - momentum: 0.000000
2024-03-26 15:51:26,354 epoch 10 - iter 20/48 - loss 0.06010429 - time (sec): 8.71 - samples/sec: 1638.72 - lr: 0.000002 - momentum: 0.000000
2024-03-26 15:51:28,361 epoch 10 - iter 24/48 - loss 0.05659568 - time (sec): 10.72 - samples/sec: 1590.02 - lr: 0.000002 - momentum: 0.000000
2024-03-26 15:51:30,466 epoch 10 - iter 28/48 - loss 0.05309482 - time (sec): 12.82 - samples/sec: 1555.51 - lr: 0.000002 - momentum: 0.000000
2024-03-26 15:51:32,568 epoch 10 - iter 32/48 - loss 0.05297842 - time (sec): 14.93 - samples/sec: 1563.19 - lr: 0.000001 - momentum: 0.000000
2024-03-26 15:51:33,959 epoch 10 - iter 36/48 - loss 0.05326019 - time (sec): 16.32 - samples/sec: 1562.80 - lr: 0.000001 - momentum: 0.000000
2024-03-26 15:51:36,578 epoch 10 - iter 40/48 - loss 0.05017067 - time (sec): 18.94 - samples/sec: 1524.02 - lr: 0.000001 - momentum: 0.000000
2024-03-26 15:51:39,089 epoch 10 - iter 44/48 - loss 0.05227028 - time (sec): 21.45 - samples/sec: 1499.29 - lr: 0.000001 - momentum: 0.000000
2024-03-26 15:51:40,674 epoch 10 - iter 48/48 - loss 0.05245429 - time (sec): 23.03 - samples/sec: 1496.71 - lr: 0.000000 - momentum: 0.000000
2024-03-26 15:51:40,674 ----------------------------------------------------------------------------------------------------
2024-03-26 15:51:40,674 EPOCH 10 done: loss 0.0525 - lr: 0.000000
2024-03-26 15:51:41,572 DEV : loss 0.17229919135570526 - f1-score (micro avg)  0.9175
2024-03-26 15:51:41,573 saving best model
2024-03-26 15:51:42,279 ----------------------------------------------------------------------------------------------------
2024-03-26 15:51:42,280 Loading model from best epoch ...
2024-03-26 15:51:42,995 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software
2024-03-26 15:51:43,741 
Results:
- F-score (micro) 0.9033
- F-score (macro) 0.6868
- Accuracy 0.8259

By class:
              precision    recall  f1-score   support

 Unternehmen     0.8864    0.8797    0.8830       266
 Auslagerung     0.8697    0.9116    0.8902       249
         Ort     0.9635    0.9851    0.9742       134
    Software     0.0000    0.0000    0.0000         0

   micro avg     0.8931    0.9137    0.9033       649
   macro avg     0.6799    0.6941    0.6868       649
weighted avg     0.8959    0.9137    0.9046       649

2024-03-26 15:51:43,741 ----------------------------------------------------------------------------------------------------