File size: 23,930 Bytes
fc094bc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | 2023-10-13 08:49:59,758 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,759 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-13 08:49:59,759 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,759 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-13 08:49:59,759 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,759 Train: 1100 sentences
2023-10-13 08:49:59,759 (train_with_dev=False, train_with_test=False)
2023-10-13 08:49:59,759 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,759 Training Params:
2023-10-13 08:49:59,760 - learning_rate: "3e-05"
2023-10-13 08:49:59,760 - mini_batch_size: "4"
2023-10-13 08:49:59,760 - max_epochs: "10"
2023-10-13 08:49:59,760 - shuffle: "True"
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,760 Plugins:
2023-10-13 08:49:59,760 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,760 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:49:59,760 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,760 Computation:
2023-10-13 08:49:59,760 - compute on device: cuda:0
2023-10-13 08:49:59,760 - embedding storage: none
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,760 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:49:59,760 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:01,127 epoch 1 - iter 27/275 - loss 3.18511496 - time (sec): 1.37 - samples/sec: 1543.30 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:50:02,538 epoch 1 - iter 54/275 - loss 2.81783400 - time (sec): 2.78 - samples/sec: 1472.59 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:50:04,007 epoch 1 - iter 81/275 - loss 2.24004312 - time (sec): 4.25 - samples/sec: 1466.57 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:50:05,345 epoch 1 - iter 108/275 - loss 1.85643127 - time (sec): 5.58 - samples/sec: 1552.80 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:50:06,626 epoch 1 - iter 135/275 - loss 1.59454014 - time (sec): 6.87 - samples/sec: 1599.77 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:50:07,837 epoch 1 - iter 162/275 - loss 1.42708412 - time (sec): 8.08 - samples/sec: 1637.63 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:50:09,006 epoch 1 - iter 189/275 - loss 1.27632203 - time (sec): 9.25 - samples/sec: 1691.77 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:50:10,173 epoch 1 - iter 216/275 - loss 1.17092393 - time (sec): 10.41 - samples/sec: 1711.69 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:50:11,346 epoch 1 - iter 243/275 - loss 1.07418944 - time (sec): 11.59 - samples/sec: 1735.60 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:50:12,564 epoch 1 - iter 270/275 - loss 1.00087942 - time (sec): 12.80 - samples/sec: 1746.13 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:50:12,786 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:12,787 EPOCH 1 done: loss 0.9886 - lr: 0.000029
2023-10-13 08:50:13,394 DEV : loss 0.21467053890228271 - f1-score (micro avg) 0.7057
2023-10-13 08:50:13,399 saving best model
2023-10-13 08:50:13,826 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:15,065 epoch 2 - iter 27/275 - loss 0.27193987 - time (sec): 1.24 - samples/sec: 1819.61 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:50:16,282 epoch 2 - iter 54/275 - loss 0.21355875 - time (sec): 2.45 - samples/sec: 1813.82 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:50:17,494 epoch 2 - iter 81/275 - loss 0.19361040 - time (sec): 3.67 - samples/sec: 1870.35 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:50:18,729 epoch 2 - iter 108/275 - loss 0.19697749 - time (sec): 4.90 - samples/sec: 1916.06 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:50:19,914 epoch 2 - iter 135/275 - loss 0.19480719 - time (sec): 6.09 - samples/sec: 1925.14 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:50:21,167 epoch 2 - iter 162/275 - loss 0.19036163 - time (sec): 7.34 - samples/sec: 1875.08 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:50:22,536 epoch 2 - iter 189/275 - loss 0.18915738 - time (sec): 8.71 - samples/sec: 1807.53 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:50:23,861 epoch 2 - iter 216/275 - loss 0.18240104 - time (sec): 10.03 - samples/sec: 1803.76 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:50:25,223 epoch 2 - iter 243/275 - loss 0.17734318 - time (sec): 11.40 - samples/sec: 1784.59 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:50:26,645 epoch 2 - iter 270/275 - loss 0.17468446 - time (sec): 12.82 - samples/sec: 1746.37 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:50:26,888 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:26,889 EPOCH 2 done: loss 0.1748 - lr: 0.000027
2023-10-13 08:50:27,579 DEV : loss 0.1474207043647766 - f1-score (micro avg) 0.8391
2023-10-13 08:50:27,590 saving best model
2023-10-13 08:50:28,107 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:29,336 epoch 3 - iter 27/275 - loss 0.08983742 - time (sec): 1.22 - samples/sec: 1806.13 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:50:30,584 epoch 3 - iter 54/275 - loss 0.08149810 - time (sec): 2.47 - samples/sec: 1848.52 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:50:31,790 epoch 3 - iter 81/275 - loss 0.09230059 - time (sec): 3.68 - samples/sec: 1816.70 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:50:32,999 epoch 3 - iter 108/275 - loss 0.09328727 - time (sec): 4.88 - samples/sec: 1796.11 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:50:34,547 epoch 3 - iter 135/275 - loss 0.09080755 - time (sec): 6.43 - samples/sec: 1724.53 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:50:35,986 epoch 3 - iter 162/275 - loss 0.09660612 - time (sec): 7.87 - samples/sec: 1684.26 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:50:37,446 epoch 3 - iter 189/275 - loss 0.09770689 - time (sec): 9.33 - samples/sec: 1685.88 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:50:38,923 epoch 3 - iter 216/275 - loss 0.09415039 - time (sec): 10.81 - samples/sec: 1676.24 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:50:40,394 epoch 3 - iter 243/275 - loss 0.09545758 - time (sec): 12.28 - samples/sec: 1646.69 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:50:41,859 epoch 3 - iter 270/275 - loss 0.09920655 - time (sec): 13.74 - samples/sec: 1628.69 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:50:42,134 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:42,135 EPOCH 3 done: loss 0.0982 - lr: 0.000023
2023-10-13 08:50:42,865 DEV : loss 0.16546553373336792 - f1-score (micro avg) 0.845
2023-10-13 08:50:42,871 saving best model
2023-10-13 08:50:43,384 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:44,768 epoch 4 - iter 27/275 - loss 0.04689526 - time (sec): 1.38 - samples/sec: 1725.94 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:50:46,183 epoch 4 - iter 54/275 - loss 0.06555587 - time (sec): 2.80 - samples/sec: 1710.68 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:50:47,607 epoch 4 - iter 81/275 - loss 0.05828751 - time (sec): 4.22 - samples/sec: 1642.25 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:50:48,987 epoch 4 - iter 108/275 - loss 0.06656748 - time (sec): 5.60 - samples/sec: 1588.98 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:50:50,314 epoch 4 - iter 135/275 - loss 0.07012843 - time (sec): 6.93 - samples/sec: 1583.06 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:50:51,524 epoch 4 - iter 162/275 - loss 0.06218253 - time (sec): 8.14 - samples/sec: 1629.60 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:50:52,693 epoch 4 - iter 189/275 - loss 0.07424359 - time (sec): 9.31 - samples/sec: 1652.20 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:50:53,958 epoch 4 - iter 216/275 - loss 0.07690610 - time (sec): 10.57 - samples/sec: 1686.64 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:50:55,225 epoch 4 - iter 243/275 - loss 0.07530572 - time (sec): 11.84 - samples/sec: 1684.34 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:50:56,482 epoch 4 - iter 270/275 - loss 0.07860860 - time (sec): 13.09 - samples/sec: 1702.90 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:50:56,725 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:56,725 EPOCH 4 done: loss 0.0777 - lr: 0.000020
2023-10-13 08:50:57,403 DEV : loss 0.1455877721309662 - f1-score (micro avg) 0.8412
2023-10-13 08:50:57,408 ----------------------------------------------------------------------------------------------------
2023-10-13 08:50:58,637 epoch 5 - iter 27/275 - loss 0.03583915 - time (sec): 1.23 - samples/sec: 1934.21 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:50:59,864 epoch 5 - iter 54/275 - loss 0.05038324 - time (sec): 2.46 - samples/sec: 1863.62 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:51:01,072 epoch 5 - iter 81/275 - loss 0.06314964 - time (sec): 3.66 - samples/sec: 1809.70 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:51:02,316 epoch 5 - iter 108/275 - loss 0.06525363 - time (sec): 4.91 - samples/sec: 1847.91 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:51:03,592 epoch 5 - iter 135/275 - loss 0.05861941 - time (sec): 6.18 - samples/sec: 1848.08 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:51:04,844 epoch 5 - iter 162/275 - loss 0.05839377 - time (sec): 7.43 - samples/sec: 1805.68 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:51:06,076 epoch 5 - iter 189/275 - loss 0.05582493 - time (sec): 8.67 - samples/sec: 1817.74 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:51:07,365 epoch 5 - iter 216/275 - loss 0.06190340 - time (sec): 9.96 - samples/sec: 1804.07 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:51:08,651 epoch 5 - iter 243/275 - loss 0.06255433 - time (sec): 11.24 - samples/sec: 1804.27 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:51:09,868 epoch 5 - iter 270/275 - loss 0.05876610 - time (sec): 12.46 - samples/sec: 1798.45 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:51:10,093 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:10,093 EPOCH 5 done: loss 0.0580 - lr: 0.000017
2023-10-13 08:51:10,766 DEV : loss 0.17545810341835022 - f1-score (micro avg) 0.8642
2023-10-13 08:51:10,770 saving best model
2023-10-13 08:51:11,298 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:12,492 epoch 6 - iter 27/275 - loss 0.05239298 - time (sec): 1.18 - samples/sec: 1904.41 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:51:13,699 epoch 6 - iter 54/275 - loss 0.05168950 - time (sec): 2.39 - samples/sec: 1782.35 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:51:14,902 epoch 6 - iter 81/275 - loss 0.06269989 - time (sec): 3.59 - samples/sec: 1766.63 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:51:16,121 epoch 6 - iter 108/275 - loss 0.05317394 - time (sec): 4.81 - samples/sec: 1798.04 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:51:17,315 epoch 6 - iter 135/275 - loss 0.05372513 - time (sec): 6.01 - samples/sec: 1786.78 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:51:18,506 epoch 6 - iter 162/275 - loss 0.05411059 - time (sec): 7.20 - samples/sec: 1781.64 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:51:19,732 epoch 6 - iter 189/275 - loss 0.05236838 - time (sec): 8.42 - samples/sec: 1801.09 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:51:20,898 epoch 6 - iter 216/275 - loss 0.05119018 - time (sec): 9.59 - samples/sec: 1827.68 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:51:22,082 epoch 6 - iter 243/275 - loss 0.04738262 - time (sec): 10.77 - samples/sec: 1859.14 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:51:23,273 epoch 6 - iter 270/275 - loss 0.04608281 - time (sec): 11.97 - samples/sec: 1878.38 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:51:23,483 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:23,483 EPOCH 6 done: loss 0.0463 - lr: 0.000013
2023-10-13 08:51:24,131 DEV : loss 0.17988666892051697 - f1-score (micro avg) 0.864
2023-10-13 08:51:24,136 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:25,333 epoch 7 - iter 27/275 - loss 0.02589880 - time (sec): 1.20 - samples/sec: 1865.96 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:51:26,516 epoch 7 - iter 54/275 - loss 0.03031099 - time (sec): 2.38 - samples/sec: 1929.73 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:51:27,690 epoch 7 - iter 81/275 - loss 0.03342662 - time (sec): 3.55 - samples/sec: 1846.57 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:51:28,873 epoch 7 - iter 108/275 - loss 0.03723331 - time (sec): 4.74 - samples/sec: 1908.80 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:51:30,058 epoch 7 - iter 135/275 - loss 0.03485540 - time (sec): 5.92 - samples/sec: 1871.16 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:51:31,247 epoch 7 - iter 162/275 - loss 0.03562915 - time (sec): 7.11 - samples/sec: 1849.76 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:51:32,433 epoch 7 - iter 189/275 - loss 0.03341349 - time (sec): 8.30 - samples/sec: 1853.46 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:51:33,607 epoch 7 - iter 216/275 - loss 0.03492135 - time (sec): 9.47 - samples/sec: 1834.75 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:51:34,799 epoch 7 - iter 243/275 - loss 0.03638176 - time (sec): 10.66 - samples/sec: 1860.31 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:51:35,984 epoch 7 - iter 270/275 - loss 0.03517408 - time (sec): 11.85 - samples/sec: 1878.78 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:51:36,220 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:36,220 EPOCH 7 done: loss 0.0353 - lr: 0.000010
2023-10-13 08:51:36,891 DEV : loss 0.16233113408088684 - f1-score (micro avg) 0.8772
2023-10-13 08:51:36,895 saving best model
2023-10-13 08:51:37,357 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:38,552 epoch 8 - iter 27/275 - loss 0.04415221 - time (sec): 1.19 - samples/sec: 1885.22 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:51:39,939 epoch 8 - iter 54/275 - loss 0.03910510 - time (sec): 2.58 - samples/sec: 1807.48 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:51:41,321 epoch 8 - iter 81/275 - loss 0.03450106 - time (sec): 3.96 - samples/sec: 1763.73 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:51:42,682 epoch 8 - iter 108/275 - loss 0.03322144 - time (sec): 5.32 - samples/sec: 1711.64 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:51:43,883 epoch 8 - iter 135/275 - loss 0.03863140 - time (sec): 6.52 - samples/sec: 1706.65 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:51:45,051 epoch 8 - iter 162/275 - loss 0.03522197 - time (sec): 7.69 - samples/sec: 1732.02 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:51:46,264 epoch 8 - iter 189/275 - loss 0.03190950 - time (sec): 8.91 - samples/sec: 1713.96 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:51:47,536 epoch 8 - iter 216/275 - loss 0.03309587 - time (sec): 10.18 - samples/sec: 1733.68 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:51:48,783 epoch 8 - iter 243/275 - loss 0.03109874 - time (sec): 11.42 - samples/sec: 1748.54 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:51:50,021 epoch 8 - iter 270/275 - loss 0.02852667 - time (sec): 12.66 - samples/sec: 1763.71 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:51:50,253 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:50,253 EPOCH 8 done: loss 0.0287 - lr: 0.000007
2023-10-13 08:51:50,944 DEV : loss 0.1571986824274063 - f1-score (micro avg) 0.8717
2023-10-13 08:51:50,949 ----------------------------------------------------------------------------------------------------
2023-10-13 08:51:52,202 epoch 9 - iter 27/275 - loss 0.00898256 - time (sec): 1.25 - samples/sec: 1911.20 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:51:53,512 epoch 9 - iter 54/275 - loss 0.01148626 - time (sec): 2.56 - samples/sec: 1804.78 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:51:54,729 epoch 9 - iter 81/275 - loss 0.01045942 - time (sec): 3.78 - samples/sec: 1802.75 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:51:55,911 epoch 9 - iter 108/275 - loss 0.02500147 - time (sec): 4.96 - samples/sec: 1866.79 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:51:57,227 epoch 9 - iter 135/275 - loss 0.02624988 - time (sec): 6.28 - samples/sec: 1820.88 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:51:58,610 epoch 9 - iter 162/275 - loss 0.02513813 - time (sec): 7.66 - samples/sec: 1793.48 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:51:59,992 epoch 9 - iter 189/275 - loss 0.02662093 - time (sec): 9.04 - samples/sec: 1760.08 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:52:01,384 epoch 9 - iter 216/275 - loss 0.02526243 - time (sec): 10.43 - samples/sec: 1735.36 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:52:02,777 epoch 9 - iter 243/275 - loss 0.02403872 - time (sec): 11.83 - samples/sec: 1723.98 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:52:04,099 epoch 9 - iter 270/275 - loss 0.02364584 - time (sec): 13.15 - samples/sec: 1698.66 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:52:04,342 ----------------------------------------------------------------------------------------------------
2023-10-13 08:52:04,342 EPOCH 9 done: loss 0.0245 - lr: 0.000003
2023-10-13 08:52:05,007 DEV : loss 0.1661010980606079 - f1-score (micro avg) 0.8759
2023-10-13 08:52:05,012 ----------------------------------------------------------------------------------------------------
2023-10-13 08:52:06,284 epoch 10 - iter 27/275 - loss 0.04455625 - time (sec): 1.27 - samples/sec: 1725.22 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:52:07,467 epoch 10 - iter 54/275 - loss 0.04334836 - time (sec): 2.45 - samples/sec: 1846.71 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:52:08,648 epoch 10 - iter 81/275 - loss 0.03198027 - time (sec): 3.64 - samples/sec: 1869.62 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:52:09,837 epoch 10 - iter 108/275 - loss 0.02643589 - time (sec): 4.82 - samples/sec: 1886.01 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:52:11,031 epoch 10 - iter 135/275 - loss 0.02498862 - time (sec): 6.02 - samples/sec: 1889.90 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:52:12,224 epoch 10 - iter 162/275 - loss 0.02255539 - time (sec): 7.21 - samples/sec: 1901.99 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:52:13,464 epoch 10 - iter 189/275 - loss 0.02401308 - time (sec): 8.45 - samples/sec: 1878.69 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:52:14,648 epoch 10 - iter 216/275 - loss 0.02170947 - time (sec): 9.63 - samples/sec: 1886.06 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:52:15,829 epoch 10 - iter 243/275 - loss 0.02142910 - time (sec): 10.82 - samples/sec: 1889.66 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:52:16,995 epoch 10 - iter 270/275 - loss 0.02083004 - time (sec): 11.98 - samples/sec: 1865.83 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:52:17,210 ----------------------------------------------------------------------------------------------------
2023-10-13 08:52:17,210 EPOCH 10 done: loss 0.0205 - lr: 0.000000
2023-10-13 08:52:17,860 DEV : loss 0.16067276895046234 - f1-score (micro avg) 0.8732
2023-10-13 08:52:18,259 ----------------------------------------------------------------------------------------------------
2023-10-13 08:52:18,261 Loading model from best epoch ...
2023-10-13 08:52:19,947 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-13 08:52:20,758
Results:
- F-score (micro) 0.9105
- F-score (macro) 0.6799
- Accuracy 0.8439
By class:
precision recall f1-score support
scope 0.8977 0.8977 0.8977 176
pers 0.9606 0.9531 0.9569 128
work 0.8784 0.8784 0.8784 74
loc 1.0000 0.5000 0.6667 2
object 0.0000 0.0000 0.0000 2
micro avg 0.9153 0.9058 0.9105 382
macro avg 0.7473 0.6458 0.6799 382
weighted avg 0.9109 0.9058 0.9079 382
2023-10-13 08:52:20,758 ----------------------------------------------------------------------------------------------------
|