File size: 24,095 Bytes
4ec514f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
2023-10-13 08:39:45,554 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,555 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 08:39:45,555 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,555 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 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Train: 1100 sentences
2023-10-13 08:39:45,556 (train_with_dev=False, train_with_test=False)
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Training Params:
2023-10-13 08:39:45,556 - learning_rate: "3e-05"
2023-10-13 08:39:45,556 - mini_batch_size: "4"
2023-10-13 08:39:45,556 - max_epochs: "10"
2023-10-13 08:39:45,556 - shuffle: "True"
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Plugins:
2023-10-13 08:39:45,556 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:39:45,556 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Computation:
2023-10-13 08:39:45,556 - compute on device: cuda:0
2023-10-13 08:39:45,556 - embedding storage: none
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:45,556 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:46,790 epoch 1 - iter 27/275 - loss 3.34492708 - time (sec): 1.23 - samples/sec: 1750.17 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:39:47,978 epoch 1 - iter 54/275 - loss 2.98549674 - time (sec): 2.42 - samples/sec: 1825.23 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:39:49,165 epoch 1 - iter 81/275 - loss 2.39560273 - time (sec): 3.61 - samples/sec: 1828.02 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:39:50,389 epoch 1 - iter 108/275 - loss 1.98325714 - time (sec): 4.83 - samples/sec: 1816.83 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:39:51,611 epoch 1 - iter 135/275 - loss 1.71558303 - time (sec): 6.05 - samples/sec: 1845.41 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:39:52,892 epoch 1 - iter 162/275 - loss 1.52471697 - time (sec): 7.33 - samples/sec: 1822.66 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:39:54,072 epoch 1 - iter 189/275 - loss 1.35824731 - time (sec): 8.51 - samples/sec: 1846.57 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:39:55,267 epoch 1 - iter 216/275 - loss 1.22688036 - time (sec): 9.71 - samples/sec: 1858.03 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:39:56,481 epoch 1 - iter 243/275 - loss 1.13136521 - time (sec): 10.92 - samples/sec: 1846.19 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:39:57,668 epoch 1 - iter 270/275 - loss 1.04758440 - time (sec): 12.11 - samples/sec: 1840.99 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:39:57,903 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:57,903 EPOCH 1 done: loss 1.0321 - lr: 0.000029
2023-10-13 08:39:58,431 DEV : loss 0.2740706205368042 - f1-score (micro avg) 0.5938
2023-10-13 08:39:58,436 saving best model
2023-10-13 08:39:58,817 ----------------------------------------------------------------------------------------------------
2023-10-13 08:39:59,987 epoch 2 - iter 27/275 - loss 0.28926253 - time (sec): 1.17 - samples/sec: 1781.92 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:40:01,165 epoch 2 - iter 54/275 - loss 0.23992950 - time (sec): 2.35 - samples/sec: 1866.76 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:40:02,369 epoch 2 - iter 81/275 - loss 0.22474376 - time (sec): 3.55 - samples/sec: 1828.65 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:40:03,619 epoch 2 - iter 108/275 - loss 0.21005906 - time (sec): 4.80 - samples/sec: 1842.77 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:40:04,881 epoch 2 - iter 135/275 - loss 0.20172376 - time (sec): 6.06 - samples/sec: 1825.64 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:40:06,115 epoch 2 - iter 162/275 - loss 0.20055598 - time (sec): 7.30 - samples/sec: 1850.68 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:40:07,349 epoch 2 - iter 189/275 - loss 0.18706140 - time (sec): 8.53 - samples/sec: 1832.71 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:40:08,561 epoch 2 - iter 216/275 - loss 0.18860587 - time (sec): 9.74 - samples/sec: 1851.88 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:40:09,744 epoch 2 - iter 243/275 - loss 0.18268234 - time (sec): 10.93 - samples/sec: 1855.54 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:40:10,926 epoch 2 - iter 270/275 - loss 0.17950041 - time (sec): 12.11 - samples/sec: 1840.47 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:40:11,158 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:11,158 EPOCH 2 done: loss 0.1813 - lr: 0.000027
2023-10-13 08:40:11,857 DEV : loss 0.13900607824325562 - f1-score (micro avg) 0.8047
2023-10-13 08:40:11,862 saving best model
2023-10-13 08:40:12,515 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:13,678 epoch 3 - iter 27/275 - loss 0.09446228 - time (sec): 1.16 - samples/sec: 1980.46 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:40:14,878 epoch 3 - iter 54/275 - loss 0.10509112 - time (sec): 2.36 - samples/sec: 1903.10 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:40:16,054 epoch 3 - iter 81/275 - loss 0.11020384 - time (sec): 3.53 - samples/sec: 1895.80 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:40:17,252 epoch 3 - iter 108/275 - loss 0.10919792 - time (sec): 4.73 - samples/sec: 1899.21 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:40:18,436 epoch 3 - iter 135/275 - loss 0.10692203 - time (sec): 5.91 - samples/sec: 1898.30 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:40:19,618 epoch 3 - iter 162/275 - loss 0.10449658 - time (sec): 7.10 - samples/sec: 1894.76 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:40:20,817 epoch 3 - iter 189/275 - loss 0.10461865 - time (sec): 8.29 - samples/sec: 1921.91 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:40:22,002 epoch 3 - iter 216/275 - loss 0.09838979 - time (sec): 9.48 - samples/sec: 1911.69 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:40:23,220 epoch 3 - iter 243/275 - loss 0.09432405 - time (sec): 10.70 - samples/sec: 1906.52 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:40:24,429 epoch 3 - iter 270/275 - loss 0.09763774 - time (sec): 11.91 - samples/sec: 1885.15 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:40:24,657 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:24,657 EPOCH 3 done: loss 0.0969 - lr: 0.000023
2023-10-13 08:40:25,296 DEV : loss 0.14131943881511688 - f1-score (micro avg) 0.8547
2023-10-13 08:40:25,300 saving best model
2023-10-13 08:40:25,754 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:26,928 epoch 4 - iter 27/275 - loss 0.04827930 - time (sec): 1.17 - samples/sec: 1870.32 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:40:28,133 epoch 4 - iter 54/275 - loss 0.06353083 - time (sec): 2.38 - samples/sec: 1813.08 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:40:29,327 epoch 4 - iter 81/275 - loss 0.07903506 - time (sec): 3.57 - samples/sec: 1779.84 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:40:30,548 epoch 4 - iter 108/275 - loss 0.07878090 - time (sec): 4.79 - samples/sec: 1769.53 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:40:31,755 epoch 4 - iter 135/275 - loss 0.07751083 - time (sec): 6.00 - samples/sec: 1783.48 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:40:32,968 epoch 4 - iter 162/275 - loss 0.07629198 - time (sec): 7.21 - samples/sec: 1796.70 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:40:34,202 epoch 4 - iter 189/275 - loss 0.07261307 - time (sec): 8.45 - samples/sec: 1766.74 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:40:35,369 epoch 4 - iter 216/275 - loss 0.07313839 - time (sec): 9.61 - samples/sec: 1785.81 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:40:36,561 epoch 4 - iter 243/275 - loss 0.07538749 - time (sec): 10.81 - samples/sec: 1825.46 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:40:37,776 epoch 4 - iter 270/275 - loss 0.07645860 - time (sec): 12.02 - samples/sec: 1856.66 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:40:37,995 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:37,995 EPOCH 4 done: loss 0.0761 - lr: 0.000020
2023-10-13 08:40:38,699 DEV : loss 0.14559561014175415 - f1-score (micro avg) 0.8656
2023-10-13 08:40:38,704 saving best model
2023-10-13 08:40:39,189 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:40,424 epoch 5 - iter 27/275 - loss 0.05390686 - time (sec): 1.22 - samples/sec: 1804.58 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:40:41,626 epoch 5 - iter 54/275 - loss 0.04559267 - time (sec): 2.43 - samples/sec: 1899.76 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:40:42,837 epoch 5 - iter 81/275 - loss 0.04680050 - time (sec): 3.64 - samples/sec: 1853.64 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:40:44,051 epoch 5 - iter 108/275 - loss 0.05446991 - time (sec): 4.85 - samples/sec: 1878.52 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:40:45,234 epoch 5 - iter 135/275 - loss 0.05015221 - time (sec): 6.03 - samples/sec: 1894.64 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:40:46,414 epoch 5 - iter 162/275 - loss 0.04864770 - time (sec): 7.21 - samples/sec: 1879.46 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:40:47,604 epoch 5 - iter 189/275 - loss 0.04806670 - time (sec): 8.41 - samples/sec: 1837.40 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:40:48,806 epoch 5 - iter 216/275 - loss 0.05702823 - time (sec): 9.61 - samples/sec: 1847.71 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:40:49,985 epoch 5 - iter 243/275 - loss 0.05475300 - time (sec): 10.79 - samples/sec: 1845.76 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:40:51,186 epoch 5 - iter 270/275 - loss 0.05316789 - time (sec): 11.99 - samples/sec: 1853.62 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:40:51,410 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:51,410 EPOCH 5 done: loss 0.0543 - lr: 0.000017
2023-10-13 08:40:52,122 DEV : loss 0.15457984805107117 - f1-score (micro avg) 0.8707
2023-10-13 08:40:52,127 saving best model
2023-10-13 08:40:52,597 ----------------------------------------------------------------------------------------------------
2023-10-13 08:40:53,788 epoch 6 - iter 27/275 - loss 0.00834565 - time (sec): 1.18 - samples/sec: 1908.10 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:40:55,006 epoch 6 - iter 54/275 - loss 0.02701269 - time (sec): 2.40 - samples/sec: 1919.62 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:40:56,211 epoch 6 - iter 81/275 - loss 0.03904077 - time (sec): 3.60 - samples/sec: 1911.62 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:40:57,411 epoch 6 - iter 108/275 - loss 0.03642560 - time (sec): 4.80 - samples/sec: 1858.63 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:40:58,631 epoch 6 - iter 135/275 - loss 0.03601588 - time (sec): 6.02 - samples/sec: 1882.34 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:40:59,814 epoch 6 - iter 162/275 - loss 0.03433120 - time (sec): 7.21 - samples/sec: 1879.51 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:41:01,007 epoch 6 - iter 189/275 - loss 0.03662864 - time (sec): 8.40 - samples/sec: 1886.94 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:41:02,182 epoch 6 - iter 216/275 - loss 0.03698452 - time (sec): 9.57 - samples/sec: 1874.16 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:41:03,366 epoch 6 - iter 243/275 - loss 0.03825393 - time (sec): 10.76 - samples/sec: 1882.59 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:41:04,534 epoch 6 - iter 270/275 - loss 0.03667517 - time (sec): 11.93 - samples/sec: 1882.16 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:41:04,754 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:04,755 EPOCH 6 done: loss 0.0375 - lr: 0.000013
2023-10-13 08:41:05,396 DEV : loss 0.1502944976091385 - f1-score (micro avg) 0.8729
2023-10-13 08:41:05,401 saving best model
2023-10-13 08:41:05,888 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:07,112 epoch 7 - iter 27/275 - loss 0.02041576 - time (sec): 1.22 - samples/sec: 1600.53 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:41:08,316 epoch 7 - iter 54/275 - loss 0.03416922 - time (sec): 2.42 - samples/sec: 1704.67 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:41:09,519 epoch 7 - iter 81/275 - loss 0.03933149 - time (sec): 3.63 - samples/sec: 1780.34 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:41:10,762 epoch 7 - iter 108/275 - loss 0.04294870 - time (sec): 4.87 - samples/sec: 1811.96 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:41:11,981 epoch 7 - iter 135/275 - loss 0.03624465 - time (sec): 6.09 - samples/sec: 1814.33 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:41:13,188 epoch 7 - iter 162/275 - loss 0.03659759 - time (sec): 7.29 - samples/sec: 1820.53 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:41:14,389 epoch 7 - iter 189/275 - loss 0.03260483 - time (sec): 8.49 - samples/sec: 1849.24 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:41:15,586 epoch 7 - iter 216/275 - loss 0.03719664 - time (sec): 9.69 - samples/sec: 1875.70 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:41:16,810 epoch 7 - iter 243/275 - loss 0.03579088 - time (sec): 10.92 - samples/sec: 1846.59 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:41:18,079 epoch 7 - iter 270/275 - loss 0.03303033 - time (sec): 12.18 - samples/sec: 1827.51 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:41:18,313 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:18,313 EPOCH 7 done: loss 0.0333 - lr: 0.000010
2023-10-13 08:41:18,948 DEV : loss 0.15816469490528107 - f1-score (micro avg) 0.8841
2023-10-13 08:41:18,953 saving best model
2023-10-13 08:41:19,419 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:20,613 epoch 8 - iter 27/275 - loss 0.01789827 - time (sec): 1.19 - samples/sec: 1820.05 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:41:21,843 epoch 8 - iter 54/275 - loss 0.02164511 - time (sec): 2.42 - samples/sec: 1751.53 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:41:23,007 epoch 8 - iter 81/275 - loss 0.01780909 - time (sec): 3.59 - samples/sec: 1791.00 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:41:24,190 epoch 8 - iter 108/275 - loss 0.02271763 - time (sec): 4.77 - samples/sec: 1836.00 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:41:25,365 epoch 8 - iter 135/275 - loss 0.02433439 - time (sec): 5.94 - samples/sec: 1839.26 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:41:26,546 epoch 8 - iter 162/275 - loss 0.02185385 - time (sec): 7.12 - samples/sec: 1825.82 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:41:27,723 epoch 8 - iter 189/275 - loss 0.02114702 - time (sec): 8.30 - samples/sec: 1841.08 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:41:28,924 epoch 8 - iter 216/275 - loss 0.02175805 - time (sec): 9.50 - samples/sec: 1867.75 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:41:30,118 epoch 8 - iter 243/275 - loss 0.02104962 - time (sec): 10.70 - samples/sec: 1880.63 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:41:31,309 epoch 8 - iter 270/275 - loss 0.02010803 - time (sec): 11.89 - samples/sec: 1873.25 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:41:31,547 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:31,547 EPOCH 8 done: loss 0.0222 - lr: 0.000007
2023-10-13 08:41:32,253 DEV : loss 0.1525907665491104 - f1-score (micro avg) 0.8868
2023-10-13 08:41:32,258 saving best model
2023-10-13 08:41:32,757 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:34,168 epoch 9 - iter 27/275 - loss 0.00228100 - time (sec): 1.41 - samples/sec: 1422.83 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:41:35,499 epoch 9 - iter 54/275 - loss 0.03448114 - time (sec): 2.74 - samples/sec: 1523.55 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:41:36,895 epoch 9 - iter 81/275 - loss 0.02760678 - time (sec): 4.14 - samples/sec: 1543.92 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:41:38,286 epoch 9 - iter 108/275 - loss 0.02505676 - time (sec): 5.53 - samples/sec: 1582.30 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:41:39,649 epoch 9 - iter 135/275 - loss 0.02264791 - time (sec): 6.89 - samples/sec: 1606.19 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:41:41,003 epoch 9 - iter 162/275 - loss 0.02014999 - time (sec): 8.24 - samples/sec: 1621.65 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:41:42,340 epoch 9 - iter 189/275 - loss 0.01792590 - time (sec): 9.58 - samples/sec: 1614.02 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:41:43,767 epoch 9 - iter 216/275 - loss 0.01783111 - time (sec): 11.01 - samples/sec: 1621.48 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:41:45,240 epoch 9 - iter 243/275 - loss 0.01810447 - time (sec): 12.48 - samples/sec: 1621.95 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:41:46,634 epoch 9 - iter 270/275 - loss 0.02018950 - time (sec): 13.87 - samples/sec: 1606.63 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:41:46,882 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:46,883 EPOCH 9 done: loss 0.0201 - lr: 0.000003
2023-10-13 08:41:47,566 DEV : loss 0.15038155019283295 - f1-score (micro avg) 0.8889
2023-10-13 08:41:47,571 saving best model
2023-10-13 08:41:48,024 ----------------------------------------------------------------------------------------------------
2023-10-13 08:41:49,299 epoch 10 - iter 27/275 - loss 0.00487508 - time (sec): 1.27 - samples/sec: 1597.62 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:41:50,558 epoch 10 - iter 54/275 - loss 0.01171812 - time (sec): 2.53 - samples/sec: 1731.39 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:41:51,839 epoch 10 - iter 81/275 - loss 0.00947176 - time (sec): 3.81 - samples/sec: 1707.63 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:41:53,089 epoch 10 - iter 108/275 - loss 0.01091956 - time (sec): 5.06 - samples/sec: 1724.90 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:41:54,287 epoch 10 - iter 135/275 - loss 0.01359143 - time (sec): 6.26 - samples/sec: 1808.40 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:41:55,487 epoch 10 - iter 162/275 - loss 0.01467793 - time (sec): 7.46 - samples/sec: 1772.72 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:41:56,784 epoch 10 - iter 189/275 - loss 0.01368588 - time (sec): 8.75 - samples/sec: 1785.40 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:41:57,986 epoch 10 - iter 216/275 - loss 0.01604266 - time (sec): 9.96 - samples/sec: 1799.19 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:41:59,170 epoch 10 - iter 243/275 - loss 0.01505167 - time (sec): 11.14 - samples/sec: 1789.24 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:42:00,378 epoch 10 - iter 270/275 - loss 0.01518889 - time (sec): 12.35 - samples/sec: 1808.44 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:42:00,598 ----------------------------------------------------------------------------------------------------
2023-10-13 08:42:00,598 EPOCH 10 done: loss 0.0156 - lr: 0.000000
2023-10-13 08:42:01,252 DEV : loss 0.1532716304063797 - f1-score (micro avg) 0.8793
2023-10-13 08:42:01,614 ----------------------------------------------------------------------------------------------------
2023-10-13 08:42:01,616 Loading model from best epoch ...
2023-10-13 08:42:03,286 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 08:42:04,059
Results:
- F-score (micro) 0.9147
- F-score (macro) 0.8082
- Accuracy 0.8551
By class:
precision recall f1-score support
scope 0.8852 0.9205 0.9025 176
pers 0.9839 0.9531 0.9683 128
work 0.8375 0.9054 0.8701 74
loc 0.6667 1.0000 0.8000 2
object 0.5000 0.5000 0.5000 2
micro avg 0.9031 0.9267 0.9147 382
macro avg 0.7747 0.8558 0.8082 382
weighted avg 0.9059 0.9267 0.9156 382
2023-10-13 08:42:04,059 ----------------------------------------------------------------------------------------------------
|