training.log

2024-03-26 10:03:59,849 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 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 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Corpus: 758 train + 94 dev + 96 test sentences
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Train:  758 sentences
2024-03-26 10:03:59,850         (train_with_dev=False, train_with_test=False)
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Training Params:
2024-03-26 10:03:59,850  - learning_rate: "5e-05" 
2024-03-26 10:03:59,850  - mini_batch_size: "16"
2024-03-26 10:03:59,850  - max_epochs: "10"
2024-03-26 10:03:59,850  - shuffle: "True"
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Plugins:
2024-03-26 10:03:59,850  - TensorboardLogger
2024-03-26 10:03:59,850  - LinearScheduler | warmup_fraction: '0.1'
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Final evaluation on model from best epoch (best-model.pt)
2024-03-26 10:03:59,850  - metric: "('micro avg', 'f1-score')"
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Computation:
2024-03-26 10:03:59,850  - compute on device: cuda:0
2024-03-26 10:03:59,850  - embedding storage: none
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Model training base path: "flair-co-funer-gbert_base-bs16-e10-lr5e-05-3"
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 ----------------------------------------------------------------------------------------------------
2024-03-26 10:03:59,850 Logging anything other than scalars to TensorBoard is currently not supported.
2024-03-26 10:04:01,094 epoch 1 - iter 4/48 - loss 3.42847207 - time (sec): 1.24 - samples/sec: 2213.10 - lr: 0.000003 - momentum: 0.000000
2024-03-26 10:04:03,051 epoch 1 - iter 8/48 - loss 3.32248082 - time (sec): 3.20 - samples/sec: 1819.69 - lr: 0.000007 - momentum: 0.000000
2024-03-26 10:04:04,566 epoch 1 - iter 12/48 - loss 3.17815477 - time (sec): 4.72 - samples/sec: 1775.93 - lr: 0.000011 - momentum: 0.000000
2024-03-26 10:04:07,434 epoch 1 - iter 16/48 - loss 2.96264845 - time (sec): 7.58 - samples/sec: 1529.34 - lr: 0.000016 - momentum: 0.000000
2024-03-26 10:04:09,078 epoch 1 - iter 20/48 - loss 2.79126105 - time (sec): 9.23 - samples/sec: 1560.92 - lr: 0.000020 - momentum: 0.000000
2024-03-26 10:04:10,501 epoch 1 - iter 24/48 - loss 2.66809628 - time (sec): 10.65 - samples/sec: 1611.84 - lr: 0.000024 - momentum: 0.000000
2024-03-26 10:04:11,808 epoch 1 - iter 28/48 - loss 2.54471273 - time (sec): 11.96 - samples/sec: 1633.05 - lr: 0.000028 - momentum: 0.000000
2024-03-26 10:04:13,881 epoch 1 - iter 32/48 - loss 2.40956988 - time (sec): 14.03 - samples/sec: 1619.87 - lr: 0.000032 - momentum: 0.000000
2024-03-26 10:04:15,418 epoch 1 - iter 36/48 - loss 2.28409769 - time (sec): 15.57 - samples/sec: 1639.18 - lr: 0.000036 - momentum: 0.000000
2024-03-26 10:04:17,635 epoch 1 - iter 40/48 - loss 2.14660908 - time (sec): 17.78 - samples/sec: 1629.26 - lr: 0.000041 - momentum: 0.000000
2024-03-26 10:04:19,542 epoch 1 - iter 44/48 - loss 2.02954310 - time (sec): 19.69 - samples/sec: 1628.38 - lr: 0.000045 - momentum: 0.000000
2024-03-26 10:04:21,152 epoch 1 - iter 48/48 - loss 1.93848867 - time (sec): 21.30 - samples/sec: 1618.28 - lr: 0.000049 - momentum: 0.000000
2024-03-26 10:04:21,152 ----------------------------------------------------------------------------------------------------
2024-03-26 10:04:21,152 EPOCH 1 done: loss 1.9385 - lr: 0.000049
2024-03-26 10:04:21,961 DEV : loss 0.5561796426773071 - f1-score (micro avg)  0.6403
2024-03-26 10:04:21,962 saving best model
2024-03-26 10:04:22,243 ----------------------------------------------------------------------------------------------------
2024-03-26 10:04:23,645 epoch 2 - iter 4/48 - loss 0.68169693 - time (sec): 1.40 - samples/sec: 1780.37 - lr: 0.000050 - momentum: 0.000000
2024-03-26 10:04:25,098 epoch 2 - iter 8/48 - loss 0.58987382 - time (sec): 2.85 - samples/sec: 1709.75 - lr: 0.000049 - momentum: 0.000000
2024-03-26 10:04:26,501 epoch 2 - iter 12/48 - loss 0.57924523 - time (sec): 4.26 - samples/sec: 1805.47 - lr: 0.000049 - momentum: 0.000000
2024-03-26 10:04:28,350 epoch 2 - iter 16/48 - loss 0.53887829 - time (sec): 6.11 - samples/sec: 1761.61 - lr: 0.000048 - momentum: 0.000000
2024-03-26 10:04:30,676 epoch 2 - iter 20/48 - loss 0.52146094 - time (sec): 8.43 - samples/sec: 1681.60 - lr: 0.000048 - momentum: 0.000000
2024-03-26 10:04:32,671 epoch 2 - iter 24/48 - loss 0.48389242 - time (sec): 10.43 - samples/sec: 1663.33 - lr: 0.000047 - momentum: 0.000000
2024-03-26 10:04:35,363 epoch 2 - iter 28/48 - loss 0.46805210 - time (sec): 13.12 - samples/sec: 1594.97 - lr: 0.000047 - momentum: 0.000000
2024-03-26 10:04:37,528 epoch 2 - iter 32/48 - loss 0.45046616 - time (sec): 15.28 - samples/sec: 1561.55 - lr: 0.000046 - momentum: 0.000000
2024-03-26 10:04:39,221 epoch 2 - iter 36/48 - loss 0.44202409 - time (sec): 16.98 - samples/sec: 1555.99 - lr: 0.000046 - momentum: 0.000000
2024-03-26 10:04:40,911 epoch 2 - iter 40/48 - loss 0.44187690 - time (sec): 18.67 - samples/sec: 1562.70 - lr: 0.000046 - momentum: 0.000000
2024-03-26 10:04:43,039 epoch 2 - iter 44/48 - loss 0.43102293 - time (sec): 20.80 - samples/sec: 1558.14 - lr: 0.000045 - momentum: 0.000000
2024-03-26 10:04:44,533 epoch 2 - iter 48/48 - loss 0.41948321 - time (sec): 22.29 - samples/sec: 1546.53 - lr: 0.000045 - momentum: 0.000000
2024-03-26 10:04:44,533 ----------------------------------------------------------------------------------------------------
2024-03-26 10:04:44,533 EPOCH 2 done: loss 0.4195 - lr: 0.000045
2024-03-26 10:04:45,419 DEV : loss 0.2610315978527069 - f1-score (micro avg)  0.8488
2024-03-26 10:04:45,420 saving best model
2024-03-26 10:04:45,900 ----------------------------------------------------------------------------------------------------
2024-03-26 10:04:47,380 epoch 3 - iter 4/48 - loss 0.27115186 - time (sec): 1.48 - samples/sec: 1657.88 - lr: 0.000044 - momentum: 0.000000
2024-03-26 10:04:50,063 epoch 3 - iter 8/48 - loss 0.21895063 - time (sec): 4.16 - samples/sec: 1376.71 - lr: 0.000044 - momentum: 0.000000
2024-03-26 10:04:51,291 epoch 3 - iter 12/48 - loss 0.23419962 - time (sec): 5.39 - samples/sec: 1511.42 - lr: 0.000043 - momentum: 0.000000
2024-03-26 10:04:52,627 epoch 3 - iter 16/48 - loss 0.21189624 - time (sec): 6.73 - samples/sec: 1641.16 - lr: 0.000043 - momentum: 0.000000
2024-03-26 10:04:54,054 epoch 3 - iter 20/48 - loss 0.21487538 - time (sec): 8.15 - samples/sec: 1657.27 - lr: 0.000042 - momentum: 0.000000
2024-03-26 10:04:56,719 epoch 3 - iter 24/48 - loss 0.20856793 - time (sec): 10.82 - samples/sec: 1544.04 - lr: 0.000042 - momentum: 0.000000
2024-03-26 10:04:58,592 epoch 3 - iter 28/48 - loss 0.21250090 - time (sec): 12.69 - samples/sec: 1561.83 - lr: 0.000041 - momentum: 0.000000
2024-03-26 10:05:01,073 epoch 3 - iter 32/48 - loss 0.20205428 - time (sec): 15.17 - samples/sec: 1502.91 - lr: 0.000041 - momentum: 0.000000
2024-03-26 10:05:02,973 epoch 3 - iter 36/48 - loss 0.20232438 - time (sec): 17.07 - samples/sec: 1498.34 - lr: 0.000040 - momentum: 0.000000
2024-03-26 10:05:05,288 epoch 3 - iter 40/48 - loss 0.19607315 - time (sec): 19.39 - samples/sec: 1473.45 - lr: 0.000040 - momentum: 0.000000
2024-03-26 10:05:07,686 epoch 3 - iter 44/48 - loss 0.20415740 - time (sec): 21.78 - samples/sec: 1460.81 - lr: 0.000040 - momentum: 0.000000
2024-03-26 10:05:09,974 epoch 3 - iter 48/48 - loss 0.19702094 - time (sec): 24.07 - samples/sec: 1432.03 - lr: 0.000039 - momentum: 0.000000
2024-03-26 10:05:09,974 ----------------------------------------------------------------------------------------------------
2024-03-26 10:05:09,974 EPOCH 3 done: loss 0.1970 - lr: 0.000039
2024-03-26 10:05:10,863 DEV : loss 0.20633003115653992 - f1-score (micro avg)  0.8791
2024-03-26 10:05:10,864 saving best model
2024-03-26 10:05:11,310 ----------------------------------------------------------------------------------------------------
2024-03-26 10:05:12,768 epoch 4 - iter 4/48 - loss 0.15569544 - time (sec): 1.46 - samples/sec: 1719.96 - lr: 0.000039 - momentum: 0.000000
2024-03-26 10:05:14,663 epoch 4 - iter 8/48 - loss 0.13810570 - time (sec): 3.35 - samples/sec: 1599.03 - lr: 0.000038 - momentum: 0.000000
2024-03-26 10:05:17,174 epoch 4 - iter 12/48 - loss 0.12486450 - time (sec): 5.86 - samples/sec: 1439.69 - lr: 0.000038 - momentum: 0.000000
2024-03-26 10:05:19,053 epoch 4 - iter 16/48 - loss 0.12364042 - time (sec): 7.74 - samples/sec: 1462.77 - lr: 0.000037 - momentum: 0.000000
2024-03-26 10:05:21,409 epoch 4 - iter 20/48 - loss 0.11913852 - time (sec): 10.10 - samples/sec: 1455.15 - lr: 0.000037 - momentum: 0.000000
2024-03-26 10:05:24,284 epoch 4 - iter 24/48 - loss 0.11463006 - time (sec): 12.97 - samples/sec: 1405.63 - lr: 0.000036 - momentum: 0.000000
2024-03-26 10:05:25,402 epoch 4 - iter 28/48 - loss 0.11545901 - time (sec): 14.09 - samples/sec: 1441.74 - lr: 0.000036 - momentum: 0.000000
2024-03-26 10:05:28,399 epoch 4 - iter 32/48 - loss 0.11436647 - time (sec): 17.09 - samples/sec: 1382.25 - lr: 0.000035 - momentum: 0.000000
2024-03-26 10:05:30,117 epoch 4 - iter 36/48 - loss 0.12044215 - time (sec): 18.81 - samples/sec: 1414.80 - lr: 0.000035 - momentum: 0.000000
2024-03-26 10:05:32,925 epoch 4 - iter 40/48 - loss 0.12453469 - time (sec): 21.61 - samples/sec: 1382.74 - lr: 0.000034 - momentum: 0.000000
2024-03-26 10:05:33,832 epoch 4 - iter 44/48 - loss 0.12667938 - time (sec): 22.52 - samples/sec: 1428.87 - lr: 0.000034 - momentum: 0.000000
2024-03-26 10:05:35,307 epoch 4 - iter 48/48 - loss 0.12821766 - time (sec): 24.00 - samples/sec: 1436.61 - lr: 0.000034 - momentum: 0.000000
2024-03-26 10:05:35,308 ----------------------------------------------------------------------------------------------------
2024-03-26 10:05:35,308 EPOCH 4 done: loss 0.1282 - lr: 0.000034
2024-03-26 10:05:36,195 DEV : loss 0.1677311509847641 - f1-score (micro avg)  0.9039
2024-03-26 10:05:36,196 saving best model
2024-03-26 10:05:36,667 ----------------------------------------------------------------------------------------------------
2024-03-26 10:05:39,099 epoch 5 - iter 4/48 - loss 0.07272465 - time (sec): 2.43 - samples/sec: 1307.92 - lr: 0.000033 - momentum: 0.000000
2024-03-26 10:05:40,508 epoch 5 - iter 8/48 - loss 0.08934142 - time (sec): 3.84 - samples/sec: 1482.60 - lr: 0.000033 - momentum: 0.000000
2024-03-26 10:05:41,952 epoch 5 - iter 12/48 - loss 0.08879200 - time (sec): 5.28 - samples/sec: 1559.78 - lr: 0.000032 - momentum: 0.000000
2024-03-26 10:05:44,122 epoch 5 - iter 16/48 - loss 0.08576217 - time (sec): 7.45 - samples/sec: 1476.19 - lr: 0.000032 - momentum: 0.000000
2024-03-26 10:05:46,174 epoch 5 - iter 20/48 - loss 0.09482743 - time (sec): 9.51 - samples/sec: 1481.30 - lr: 0.000031 - momentum: 0.000000
2024-03-26 10:05:48,645 epoch 5 - iter 24/48 - loss 0.09094812 - time (sec): 11.98 - samples/sec: 1469.90 - lr: 0.000031 - momentum: 0.000000
2024-03-26 10:05:51,186 epoch 5 - iter 28/48 - loss 0.08571930 - time (sec): 14.52 - samples/sec: 1449.92 - lr: 0.000030 - momentum: 0.000000
2024-03-26 10:05:53,044 epoch 5 - iter 32/48 - loss 0.08483497 - time (sec): 16.38 - samples/sec: 1454.13 - lr: 0.000030 - momentum: 0.000000
2024-03-26 10:05:54,846 epoch 5 - iter 36/48 - loss 0.08308133 - time (sec): 18.18 - samples/sec: 1454.89 - lr: 0.000029 - momentum: 0.000000
2024-03-26 10:05:57,131 epoch 5 - iter 40/48 - loss 0.08378739 - time (sec): 20.46 - samples/sec: 1443.31 - lr: 0.000029 - momentum: 0.000000
2024-03-26 10:05:59,072 epoch 5 - iter 44/48 - loss 0.08769191 - time (sec): 22.40 - samples/sec: 1441.80 - lr: 0.000029 - momentum: 0.000000
2024-03-26 10:06:00,117 epoch 5 - iter 48/48 - loss 0.08679457 - time (sec): 23.45 - samples/sec: 1470.09 - lr: 0.000028 - momentum: 0.000000
2024-03-26 10:06:00,117 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:00,117 EPOCH 5 done: loss 0.0868 - lr: 0.000028
2024-03-26 10:06:01,011 DEV : loss 0.1546858549118042 - f1-score (micro avg)  0.9175
2024-03-26 10:06:01,012 saving best model
2024-03-26 10:06:01,464 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:04,054 epoch 6 - iter 4/48 - loss 0.06321178 - time (sec): 2.59 - samples/sec: 1228.55 - lr: 0.000028 - momentum: 0.000000
2024-03-26 10:06:06,037 epoch 6 - iter 8/48 - loss 0.06414214 - time (sec): 4.57 - samples/sec: 1284.40 - lr: 0.000027 - momentum: 0.000000
2024-03-26 10:06:07,599 epoch 6 - iter 12/48 - loss 0.06581955 - time (sec): 6.13 - samples/sec: 1438.56 - lr: 0.000027 - momentum: 0.000000
2024-03-26 10:06:09,552 epoch 6 - iter 16/48 - loss 0.06180199 - time (sec): 8.09 - samples/sec: 1438.19 - lr: 0.000026 - momentum: 0.000000
2024-03-26 10:06:10,624 epoch 6 - iter 20/48 - loss 0.06294844 - time (sec): 9.16 - samples/sec: 1525.74 - lr: 0.000026 - momentum: 0.000000
2024-03-26 10:06:12,543 epoch 6 - iter 24/48 - loss 0.06365673 - time (sec): 11.08 - samples/sec: 1508.95 - lr: 0.000025 - momentum: 0.000000
2024-03-26 10:06:13,683 epoch 6 - iter 28/48 - loss 0.06347676 - time (sec): 12.22 - samples/sec: 1556.99 - lr: 0.000025 - momentum: 0.000000
2024-03-26 10:06:15,443 epoch 6 - iter 32/48 - loss 0.06064851 - time (sec): 13.98 - samples/sec: 1576.17 - lr: 0.000024 - momentum: 0.000000
2024-03-26 10:06:17,849 epoch 6 - iter 36/48 - loss 0.07068180 - time (sec): 16.38 - samples/sec: 1549.98 - lr: 0.000024 - momentum: 0.000000
2024-03-26 10:06:19,898 epoch 6 - iter 40/48 - loss 0.06791519 - time (sec): 18.43 - samples/sec: 1541.53 - lr: 0.000023 - momentum: 0.000000
2024-03-26 10:06:21,769 epoch 6 - iter 44/48 - loss 0.06892305 - time (sec): 20.30 - samples/sec: 1549.34 - lr: 0.000023 - momentum: 0.000000
2024-03-26 10:06:23,311 epoch 6 - iter 48/48 - loss 0.06987396 - time (sec): 21.85 - samples/sec: 1577.99 - lr: 0.000023 - momentum: 0.000000
2024-03-26 10:06:23,312 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:23,312 EPOCH 6 done: loss 0.0699 - lr: 0.000023
2024-03-26 10:06:24,215 DEV : loss 0.15499736368656158 - f1-score (micro avg)  0.9189
2024-03-26 10:06:24,216 saving best model
2024-03-26 10:06:24,665 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:26,755 epoch 7 - iter 4/48 - loss 0.05729350 - time (sec): 2.09 - samples/sec: 1324.11 - lr: 0.000022 - momentum: 0.000000
2024-03-26 10:06:28,456 epoch 7 - iter 8/48 - loss 0.04997245 - time (sec): 3.79 - samples/sec: 1516.79 - lr: 0.000022 - momentum: 0.000000
2024-03-26 10:06:30,515 epoch 7 - iter 12/48 - loss 0.04178798 - time (sec): 5.85 - samples/sec: 1465.31 - lr: 0.000021 - momentum: 0.000000
2024-03-26 10:06:33,077 epoch 7 - iter 16/48 - loss 0.04138225 - time (sec): 8.41 - samples/sec: 1405.52 - lr: 0.000021 - momentum: 0.000000
2024-03-26 10:06:35,748 epoch 7 - iter 20/48 - loss 0.04467645 - time (sec): 11.08 - samples/sec: 1410.66 - lr: 0.000020 - momentum: 0.000000
2024-03-26 10:06:37,266 epoch 7 - iter 24/48 - loss 0.04533926 - time (sec): 12.60 - samples/sec: 1430.71 - lr: 0.000020 - momentum: 0.000000
2024-03-26 10:06:39,346 epoch 7 - iter 28/48 - loss 0.04288749 - time (sec): 14.68 - samples/sec: 1449.37 - lr: 0.000019 - momentum: 0.000000
2024-03-26 10:06:41,482 epoch 7 - iter 32/48 - loss 0.04691273 - time (sec): 16.81 - samples/sec: 1454.03 - lr: 0.000019 - momentum: 0.000000
2024-03-26 10:06:43,694 epoch 7 - iter 36/48 - loss 0.05060029 - time (sec): 19.03 - samples/sec: 1438.82 - lr: 0.000018 - momentum: 0.000000
2024-03-26 10:06:45,277 epoch 7 - iter 40/48 - loss 0.04841109 - time (sec): 20.61 - samples/sec: 1446.69 - lr: 0.000018 - momentum: 0.000000
2024-03-26 10:06:46,932 epoch 7 - iter 44/48 - loss 0.05180454 - time (sec): 22.26 - samples/sec: 1465.06 - lr: 0.000017 - momentum: 0.000000
2024-03-26 10:06:48,258 epoch 7 - iter 48/48 - loss 0.05225955 - time (sec): 23.59 - samples/sec: 1461.28 - lr: 0.000017 - momentum: 0.000000
2024-03-26 10:06:48,258 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:48,258 EPOCH 7 done: loss 0.0523 - lr: 0.000017
2024-03-26 10:06:49,158 DEV : loss 0.14614951610565186 - f1-score (micro avg)  0.9302
2024-03-26 10:06:49,159 saving best model
2024-03-26 10:06:49,691 ----------------------------------------------------------------------------------------------------
2024-03-26 10:06:52,031 epoch 8 - iter 4/48 - loss 0.03268631 - time (sec): 2.34 - samples/sec: 1257.01 - lr: 0.000017 - momentum: 0.000000
2024-03-26 10:06:54,563 epoch 8 - iter 8/48 - loss 0.03038363 - time (sec): 4.87 - samples/sec: 1358.16 - lr: 0.000016 - momentum: 0.000000
2024-03-26 10:06:56,543 epoch 8 - iter 12/48 - loss 0.03050544 - time (sec): 6.85 - samples/sec: 1343.37 - lr: 0.000016 - momentum: 0.000000
2024-03-26 10:06:58,522 epoch 8 - iter 16/48 - loss 0.03045574 - time (sec): 8.83 - samples/sec: 1358.09 - lr: 0.000015 - momentum: 0.000000
2024-03-26 10:07:00,040 epoch 8 - iter 20/48 - loss 0.03185719 - time (sec): 10.35 - samples/sec: 1381.75 - lr: 0.000015 - momentum: 0.000000
2024-03-26 10:07:02,371 epoch 8 - iter 24/48 - loss 0.03213468 - time (sec): 12.68 - samples/sec: 1367.90 - lr: 0.000014 - momentum: 0.000000
2024-03-26 10:07:04,500 epoch 8 - iter 28/48 - loss 0.03166780 - time (sec): 14.81 - samples/sec: 1361.22 - lr: 0.000014 - momentum: 0.000000
2024-03-26 10:07:06,790 epoch 8 - iter 32/48 - loss 0.03896785 - time (sec): 17.10 - samples/sec: 1373.13 - lr: 0.000013 - momentum: 0.000000
2024-03-26 10:07:09,945 epoch 8 - iter 36/48 - loss 0.04158676 - time (sec): 20.25 - samples/sec: 1325.12 - lr: 0.000013 - momentum: 0.000000
2024-03-26 10:07:11,914 epoch 8 - iter 40/48 - loss 0.04704426 - time (sec): 22.22 - samples/sec: 1331.89 - lr: 0.000012 - momentum: 0.000000
2024-03-26 10:07:12,710 epoch 8 - iter 44/48 - loss 0.04633177 - time (sec): 23.02 - samples/sec: 1380.29 - lr: 0.000012 - momentum: 0.000000
2024-03-26 10:07:14,516 epoch 8 - iter 48/48 - loss 0.04472291 - time (sec): 24.82 - samples/sec: 1388.72 - lr: 0.000011 - momentum: 0.000000
2024-03-26 10:07:14,516 ----------------------------------------------------------------------------------------------------
2024-03-26 10:07:14,516 EPOCH 8 done: loss 0.0447 - lr: 0.000011
2024-03-26 10:07:15,418 DEV : loss 0.1479821503162384 - f1-score (micro avg)  0.9288
2024-03-26 10:07:15,419 ----------------------------------------------------------------------------------------------------
2024-03-26 10:07:18,093 epoch 9 - iter 4/48 - loss 0.01932148 - time (sec): 2.67 - samples/sec: 1233.74 - lr: 0.000011 - momentum: 0.000000
2024-03-26 10:07:19,745 epoch 9 - iter 8/48 - loss 0.02825076 - time (sec): 4.32 - samples/sec: 1326.82 - lr: 0.000011 - momentum: 0.000000
2024-03-26 10:07:21,833 epoch 9 - iter 12/48 - loss 0.03408380 - time (sec): 6.41 - samples/sec: 1399.55 - lr: 0.000010 - momentum: 0.000000
2024-03-26 10:07:23,896 epoch 9 - iter 16/48 - loss 0.03627351 - time (sec): 8.48 - samples/sec: 1428.64 - lr: 0.000010 - momentum: 0.000000
2024-03-26 10:07:26,193 epoch 9 - iter 20/48 - loss 0.03172262 - time (sec): 10.77 - samples/sec: 1404.36 - lr: 0.000009 - momentum: 0.000000
2024-03-26 10:07:28,092 epoch 9 - iter 24/48 - loss 0.03134365 - time (sec): 12.67 - samples/sec: 1397.35 - lr: 0.000009 - momentum: 0.000000
2024-03-26 10:07:31,265 epoch 9 - iter 28/48 - loss 0.03364734 - time (sec): 15.84 - samples/sec: 1348.27 - lr: 0.000008 - momentum: 0.000000
2024-03-26 10:07:32,622 epoch 9 - iter 32/48 - loss 0.03433911 - time (sec): 17.20 - samples/sec: 1388.75 - lr: 0.000008 - momentum: 0.000000
2024-03-26 10:07:34,972 epoch 9 - iter 36/48 - loss 0.03454591 - time (sec): 19.55 - samples/sec: 1378.29 - lr: 0.000007 - momentum: 0.000000
2024-03-26 10:07:36,421 epoch 9 - iter 40/48 - loss 0.03528763 - time (sec): 21.00 - samples/sec: 1396.11 - lr: 0.000007 - momentum: 0.000000
2024-03-26 10:07:37,918 epoch 9 - iter 44/48 - loss 0.03734495 - time (sec): 22.50 - samples/sec: 1413.93 - lr: 0.000006 - momentum: 0.000000
2024-03-26 10:07:39,311 epoch 9 - iter 48/48 - loss 0.03725859 - time (sec): 23.89 - samples/sec: 1442.89 - lr: 0.000006 - momentum: 0.000000
2024-03-26 10:07:39,311 ----------------------------------------------------------------------------------------------------
2024-03-26 10:07:39,311 EPOCH 9 done: loss 0.0373 - lr: 0.000006
2024-03-26 10:07:40,211 DEV : loss 0.14975792169570923 - f1-score (micro avg)  0.9318
2024-03-26 10:07:40,212 saving best model
2024-03-26 10:07:40,684 ----------------------------------------------------------------------------------------------------
2024-03-26 10:07:43,043 epoch 10 - iter 4/48 - loss 0.01926073 - time (sec): 2.36 - samples/sec: 1396.63 - lr: 0.000006 - momentum: 0.000000
2024-03-26 10:07:44,946 epoch 10 - iter 8/48 - loss 0.01598110 - time (sec): 4.26 - samples/sec: 1372.00 - lr: 0.000005 - momentum: 0.000000
2024-03-26 10:07:46,127 epoch 10 - iter 12/48 - loss 0.02607911 - time (sec): 5.44 - samples/sec: 1533.24 - lr: 0.000005 - momentum: 0.000000
2024-03-26 10:07:47,639 epoch 10 - iter 16/48 - loss 0.03016914 - time (sec): 6.95 - samples/sec: 1613.71 - lr: 0.000004 - momentum: 0.000000
2024-03-26 10:07:49,327 epoch 10 - iter 20/48 - loss 0.03002684 - time (sec): 8.64 - samples/sec: 1652.04 - lr: 0.000004 - momentum: 0.000000
2024-03-26 10:07:51,329 epoch 10 - iter 24/48 - loss 0.02958951 - time (sec): 10.64 - samples/sec: 1601.27 - lr: 0.000003 - momentum: 0.000000
2024-03-26 10:07:53,434 epoch 10 - iter 28/48 - loss 0.02712996 - time (sec): 12.75 - samples/sec: 1564.85 - lr: 0.000003 - momentum: 0.000000
2024-03-26 10:07:55,523 epoch 10 - iter 32/48 - loss 0.02875308 - time (sec): 14.84 - samples/sec: 1572.48 - lr: 0.000002 - momentum: 0.000000
2024-03-26 10:07:56,902 epoch 10 - iter 36/48 - loss 0.02840770 - time (sec): 16.22 - samples/sec: 1572.50 - lr: 0.000002 - momentum: 0.000000
2024-03-26 10:07:59,501 epoch 10 - iter 40/48 - loss 0.02707974 - time (sec): 18.82 - samples/sec: 1533.75 - lr: 0.000001 - momentum: 0.000000
2024-03-26 10:08:01,999 epoch 10 - iter 44/48 - loss 0.03012453 - time (sec): 21.31 - samples/sec: 1508.73 - lr: 0.000001 - momentum: 0.000000
2024-03-26 10:08:03,574 epoch 10 - iter 48/48 - loss 0.03064875 - time (sec): 22.89 - samples/sec: 1506.14 - lr: 0.000000 - momentum: 0.000000
2024-03-26 10:08:03,574 ----------------------------------------------------------------------------------------------------
2024-03-26 10:08:03,574 EPOCH 10 done: loss 0.0306 - lr: 0.000000
2024-03-26 10:08:04,469 DEV : loss 0.14895965158939362 - f1-score (micro avg)  0.9334
2024-03-26 10:08:04,470 saving best model
2024-03-26 10:08:05,226 ----------------------------------------------------------------------------------------------------
2024-03-26 10:08:05,226 Loading model from best epoch ...
2024-03-26 10:08:06,139 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 10:08:06,969 
Results:
- F-score (micro) 0.9119
- F-score (macro) 0.6922
- Accuracy 0.8428

By class:
              precision    recall  f1-score   support

 Unternehmen     0.9183    0.8872    0.9025       266
 Auslagerung     0.8731    0.9116    0.8919       249
         Ort     0.9635    0.9851    0.9742       134
    Software     0.0000    0.0000    0.0000         0

   micro avg     0.9070    0.9168    0.9119       649
   macro avg     0.6887    0.6960    0.6922       649
weighted avg     0.9103    0.9168    0.9132       649

2024-03-26 10:08:06,969 ----------------------------------------------------------------------------------------------------