File size: 24,014 Bytes
68f63c0 |
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 |
2023-10-13 08:11:11,974 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,975 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 08:11:11,975 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 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 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Train: 1100 sentences
2023-10-13 08:11:11,976 (train_with_dev=False, train_with_test=False)
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Training Params:
2023-10-13 08:11:11,976 - learning_rate: "3e-05"
2023-10-13 08:11:11,976 - mini_batch_size: "4"
2023-10-13 08:11:11,976 - max_epochs: "10"
2023-10-13 08:11:11,976 - shuffle: "True"
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Plugins:
2023-10-13 08:11:11,976 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:11:11,976 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Computation:
2023-10-13 08:11:11,976 - compute on device: cuda:0
2023-10-13 08:11:11,976 - embedding storage: none
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:11,976 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:14,096 epoch 1 - iter 27/275 - loss 3.41344393 - time (sec): 2.12 - samples/sec: 948.02 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:11:15,305 epoch 1 - iter 54/275 - loss 3.04522400 - time (sec): 3.33 - samples/sec: 1292.44 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:11:16,450 epoch 1 - iter 81/275 - loss 2.43708544 - time (sec): 4.47 - samples/sec: 1474.71 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:11:17,588 epoch 1 - iter 108/275 - loss 2.03067121 - time (sec): 5.61 - samples/sec: 1548.78 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:11:18,736 epoch 1 - iter 135/275 - loss 1.74150180 - time (sec): 6.76 - samples/sec: 1625.01 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:11:19,897 epoch 1 - iter 162/275 - loss 1.52957870 - time (sec): 7.92 - samples/sec: 1667.91 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:11:21,094 epoch 1 - iter 189/275 - loss 1.37151362 - time (sec): 9.12 - samples/sec: 1704.72 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:11:22,275 epoch 1 - iter 216/275 - loss 1.25757942 - time (sec): 10.30 - samples/sec: 1714.05 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:11:23,488 epoch 1 - iter 243/275 - loss 1.16205347 - time (sec): 11.51 - samples/sec: 1734.45 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:11:24,675 epoch 1 - iter 270/275 - loss 1.07527020 - time (sec): 12.70 - samples/sec: 1761.36 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:11:24,901 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:24,901 EPOCH 1 done: loss 1.0626 - lr: 0.000029
2023-10-13 08:11:25,495 DEV : loss 0.26535165309906006 - f1-score (micro avg) 0.6651
2023-10-13 08:11:25,505 saving best model
2023-10-13 08:11:25,977 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:27,434 epoch 2 - iter 27/275 - loss 0.28291135 - time (sec): 1.46 - samples/sec: 1409.65 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:11:28,640 epoch 2 - iter 54/275 - loss 0.28411411 - time (sec): 2.66 - samples/sec: 1600.51 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:11:29,903 epoch 2 - iter 81/275 - loss 0.26595659 - time (sec): 3.92 - samples/sec: 1592.39 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:11:31,103 epoch 2 - iter 108/275 - loss 0.24583362 - time (sec): 5.12 - samples/sec: 1671.33 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:11:32,271 epoch 2 - iter 135/275 - loss 0.23033553 - time (sec): 6.29 - samples/sec: 1746.89 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:11:33,517 epoch 2 - iter 162/275 - loss 0.21824353 - time (sec): 7.54 - samples/sec: 1737.36 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:11:34,745 epoch 2 - iter 189/275 - loss 0.20901579 - time (sec): 8.77 - samples/sec: 1757.63 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:11:35,978 epoch 2 - iter 216/275 - loss 0.20381171 - time (sec): 10.00 - samples/sec: 1770.95 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:11:37,260 epoch 2 - iter 243/275 - loss 0.19606007 - time (sec): 11.28 - samples/sec: 1767.74 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:11:38,477 epoch 2 - iter 270/275 - loss 0.19753698 - time (sec): 12.50 - samples/sec: 1788.59 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:11:38,715 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:38,715 EPOCH 2 done: loss 0.1966 - lr: 0.000027
2023-10-13 08:11:39,429 DEV : loss 0.14341259002685547 - f1-score (micro avg) 0.8225
2023-10-13 08:11:39,433 saving best model
2023-10-13 08:11:40,074 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:41,246 epoch 3 - iter 27/275 - loss 0.14052391 - time (sec): 1.17 - samples/sec: 1804.82 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:11:42,416 epoch 3 - iter 54/275 - loss 0.11470335 - time (sec): 2.34 - samples/sec: 1907.08 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:11:43,589 epoch 3 - iter 81/275 - loss 0.11498850 - time (sec): 3.51 - samples/sec: 1916.97 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:11:44,783 epoch 3 - iter 108/275 - loss 0.12164868 - time (sec): 4.71 - samples/sec: 1940.40 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:11:45,992 epoch 3 - iter 135/275 - loss 0.11937486 - time (sec): 5.92 - samples/sec: 1907.64 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:11:47,232 epoch 3 - iter 162/275 - loss 0.11352774 - time (sec): 7.16 - samples/sec: 1877.03 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:11:48,465 epoch 3 - iter 189/275 - loss 0.10844061 - time (sec): 8.39 - samples/sec: 1882.81 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:11:49,656 epoch 3 - iter 216/275 - loss 0.11716378 - time (sec): 9.58 - samples/sec: 1890.06 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:11:50,825 epoch 3 - iter 243/275 - loss 0.11039802 - time (sec): 10.75 - samples/sec: 1867.89 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:11:52,038 epoch 3 - iter 270/275 - loss 0.11167883 - time (sec): 11.96 - samples/sec: 1867.36 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:11:52,258 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:52,258 EPOCH 3 done: loss 0.1124 - lr: 0.000023
2023-10-13 08:11:52,964 DEV : loss 0.1699625849723816 - f1-score (micro avg) 0.8219
2023-10-13 08:11:52,968 ----------------------------------------------------------------------------------------------------
2023-10-13 08:11:54,180 epoch 4 - iter 27/275 - loss 0.07822413 - time (sec): 1.21 - samples/sec: 1936.44 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:11:55,369 epoch 4 - iter 54/275 - loss 0.06541721 - time (sec): 2.40 - samples/sec: 1994.01 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:11:56,534 epoch 4 - iter 81/275 - loss 0.08294608 - time (sec): 3.56 - samples/sec: 1970.79 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:11:57,734 epoch 4 - iter 108/275 - loss 0.08110684 - time (sec): 4.77 - samples/sec: 1884.74 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:11:58,920 epoch 4 - iter 135/275 - loss 0.07760535 - time (sec): 5.95 - samples/sec: 1893.24 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:12:00,144 epoch 4 - iter 162/275 - loss 0.08207656 - time (sec): 7.17 - samples/sec: 1869.14 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:12:01,281 epoch 4 - iter 189/275 - loss 0.08297912 - time (sec): 8.31 - samples/sec: 1888.93 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:12:02,415 epoch 4 - iter 216/275 - loss 0.07657454 - time (sec): 9.45 - samples/sec: 1877.55 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:12:03,558 epoch 4 - iter 243/275 - loss 0.07536046 - time (sec): 10.59 - samples/sec: 1886.54 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:12:04,696 epoch 4 - iter 270/275 - loss 0.08231829 - time (sec): 11.73 - samples/sec: 1907.55 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:12:04,908 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:04,908 EPOCH 4 done: loss 0.0836 - lr: 0.000020
2023-10-13 08:12:05,597 DEV : loss 0.18230104446411133 - f1-score (micro avg) 0.837
2023-10-13 08:12:05,601 saving best model
2023-10-13 08:12:06,054 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:07,291 epoch 5 - iter 27/275 - loss 0.05892632 - time (sec): 1.24 - samples/sec: 1574.79 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:12:08,517 epoch 5 - iter 54/275 - loss 0.04236338 - time (sec): 2.46 - samples/sec: 1650.75 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:12:09,771 epoch 5 - iter 81/275 - loss 0.04541577 - time (sec): 3.72 - samples/sec: 1782.19 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:12:10,956 epoch 5 - iter 108/275 - loss 0.04872586 - time (sec): 4.90 - samples/sec: 1850.56 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:12:12,114 epoch 5 - iter 135/275 - loss 0.04698697 - time (sec): 6.06 - samples/sec: 1887.81 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:12:13,300 epoch 5 - iter 162/275 - loss 0.05183769 - time (sec): 7.24 - samples/sec: 1896.20 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:12:14,480 epoch 5 - iter 189/275 - loss 0.06089727 - time (sec): 8.42 - samples/sec: 1877.66 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:12:15,659 epoch 5 - iter 216/275 - loss 0.06591564 - time (sec): 9.60 - samples/sec: 1879.51 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:12:16,866 epoch 5 - iter 243/275 - loss 0.06742207 - time (sec): 10.81 - samples/sec: 1865.01 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:12:18,117 epoch 5 - iter 270/275 - loss 0.06374218 - time (sec): 12.06 - samples/sec: 1858.11 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:12:18,357 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:18,358 EPOCH 5 done: loss 0.0641 - lr: 0.000017
2023-10-13 08:12:19,077 DEV : loss 0.16086943447589874 - f1-score (micro avg) 0.8507
2023-10-13 08:12:19,082 saving best model
2023-10-13 08:12:19,703 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:20,959 epoch 6 - iter 27/275 - loss 0.06482260 - time (sec): 1.25 - samples/sec: 1651.89 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:12:22,261 epoch 6 - iter 54/275 - loss 0.05022329 - time (sec): 2.56 - samples/sec: 1712.96 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:12:23,586 epoch 6 - iter 81/275 - loss 0.04459889 - time (sec): 3.88 - samples/sec: 1681.97 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:12:24,931 epoch 6 - iter 108/275 - loss 0.05034734 - time (sec): 5.23 - samples/sec: 1691.27 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:12:26,185 epoch 6 - iter 135/275 - loss 0.04794843 - time (sec): 6.48 - samples/sec: 1702.29 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:12:27,457 epoch 6 - iter 162/275 - loss 0.04469048 - time (sec): 7.75 - samples/sec: 1711.83 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:12:28,720 epoch 6 - iter 189/275 - loss 0.03975858 - time (sec): 9.01 - samples/sec: 1731.47 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:12:29,929 epoch 6 - iter 216/275 - loss 0.03696781 - time (sec): 10.22 - samples/sec: 1733.47 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:12:31,186 epoch 6 - iter 243/275 - loss 0.03935542 - time (sec): 11.48 - samples/sec: 1740.67 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:12:32,458 epoch 6 - iter 270/275 - loss 0.04392720 - time (sec): 12.75 - samples/sec: 1756.94 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:12:32,682 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:32,682 EPOCH 6 done: loss 0.0434 - lr: 0.000013
2023-10-13 08:12:33,386 DEV : loss 0.15735526382923126 - f1-score (micro avg) 0.8684
2023-10-13 08:12:33,391 saving best model
2023-10-13 08:12:33,883 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:35,068 epoch 7 - iter 27/275 - loss 0.01718411 - time (sec): 1.18 - samples/sec: 2037.96 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:12:36,219 epoch 7 - iter 54/275 - loss 0.02632338 - time (sec): 2.33 - samples/sec: 1891.42 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:12:37,464 epoch 7 - iter 81/275 - loss 0.01990612 - time (sec): 3.58 - samples/sec: 1772.46 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:12:38,653 epoch 7 - iter 108/275 - loss 0.03743037 - time (sec): 4.77 - samples/sec: 1812.69 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:12:39,876 epoch 7 - iter 135/275 - loss 0.03668093 - time (sec): 5.99 - samples/sec: 1784.90 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:12:41,155 epoch 7 - iter 162/275 - loss 0.03138511 - time (sec): 7.27 - samples/sec: 1791.69 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:12:42,421 epoch 7 - iter 189/275 - loss 0.02939117 - time (sec): 8.54 - samples/sec: 1799.94 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:12:43,718 epoch 7 - iter 216/275 - loss 0.03085943 - time (sec): 9.83 - samples/sec: 1803.62 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:12:44,987 epoch 7 - iter 243/275 - loss 0.03208756 - time (sec): 11.10 - samples/sec: 1778.53 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:12:46,313 epoch 7 - iter 270/275 - loss 0.03284565 - time (sec): 12.43 - samples/sec: 1793.59 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:12:46,537 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:46,537 EPOCH 7 done: loss 0.0325 - lr: 0.000010
2023-10-13 08:12:47,234 DEV : loss 0.16358648240566254 - f1-score (micro avg) 0.8633
2023-10-13 08:12:47,239 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:48,482 epoch 8 - iter 27/275 - loss 0.02547032 - time (sec): 1.24 - samples/sec: 1880.06 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:12:49,720 epoch 8 - iter 54/275 - loss 0.02214925 - time (sec): 2.48 - samples/sec: 1855.71 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:12:50,960 epoch 8 - iter 81/275 - loss 0.03531222 - time (sec): 3.72 - samples/sec: 1818.99 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:12:52,130 epoch 8 - iter 108/275 - loss 0.02923483 - time (sec): 4.89 - samples/sec: 1832.89 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:12:53,363 epoch 8 - iter 135/275 - loss 0.03178601 - time (sec): 6.12 - samples/sec: 1831.24 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:12:54,617 epoch 8 - iter 162/275 - loss 0.03043106 - time (sec): 7.38 - samples/sec: 1811.28 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:12:55,797 epoch 8 - iter 189/275 - loss 0.02728853 - time (sec): 8.56 - samples/sec: 1810.65 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:12:57,030 epoch 8 - iter 216/275 - loss 0.02688451 - time (sec): 9.79 - samples/sec: 1807.76 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:12:58,291 epoch 8 - iter 243/275 - loss 0.02524643 - time (sec): 11.05 - samples/sec: 1809.57 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:12:59,521 epoch 8 - iter 270/275 - loss 0.02538893 - time (sec): 12.28 - samples/sec: 1824.14 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:12:59,737 ----------------------------------------------------------------------------------------------------
2023-10-13 08:12:59,738 EPOCH 8 done: loss 0.0250 - lr: 0.000007
2023-10-13 08:13:00,504 DEV : loss 0.16763055324554443 - f1-score (micro avg) 0.8729
2023-10-13 08:13:00,509 saving best model
2023-10-13 08:13:00,952 ----------------------------------------------------------------------------------------------------
2023-10-13 08:13:02,247 epoch 9 - iter 27/275 - loss 0.01042150 - time (sec): 1.29 - samples/sec: 1822.65 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:13:03,531 epoch 9 - iter 54/275 - loss 0.00705875 - time (sec): 2.57 - samples/sec: 1730.90 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:13:04,847 epoch 9 - iter 81/275 - loss 0.01890319 - time (sec): 3.89 - samples/sec: 1820.81 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:13:06,113 epoch 9 - iter 108/275 - loss 0.02308810 - time (sec): 5.15 - samples/sec: 1807.70 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:13:07,375 epoch 9 - iter 135/275 - loss 0.02162080 - time (sec): 6.41 - samples/sec: 1789.05 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:13:08,602 epoch 9 - iter 162/275 - loss 0.02289687 - time (sec): 7.64 - samples/sec: 1822.00 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:13:09,762 epoch 9 - iter 189/275 - loss 0.02061129 - time (sec): 8.80 - samples/sec: 1811.46 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:13:10,960 epoch 9 - iter 216/275 - loss 0.01818496 - time (sec): 10.00 - samples/sec: 1816.10 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:13:12,137 epoch 9 - iter 243/275 - loss 0.01863008 - time (sec): 11.18 - samples/sec: 1806.89 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:13:13,308 epoch 9 - iter 270/275 - loss 0.02041663 - time (sec): 12.35 - samples/sec: 1818.35 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:13:13,526 ----------------------------------------------------------------------------------------------------
2023-10-13 08:13:13,527 EPOCH 9 done: loss 0.0206 - lr: 0.000003
2023-10-13 08:13:14,226 DEV : loss 0.1689862459897995 - f1-score (micro avg) 0.8694
2023-10-13 08:13:14,230 ----------------------------------------------------------------------------------------------------
2023-10-13 08:13:15,404 epoch 10 - iter 27/275 - loss 0.00787064 - time (sec): 1.17 - samples/sec: 1973.41 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:13:16,591 epoch 10 - iter 54/275 - loss 0.01301629 - time (sec): 2.36 - samples/sec: 2044.00 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:13:17,826 epoch 10 - iter 81/275 - loss 0.00982255 - time (sec): 3.59 - samples/sec: 1971.45 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:13:19,103 epoch 10 - iter 108/275 - loss 0.01059154 - time (sec): 4.87 - samples/sec: 1900.79 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:13:20,337 epoch 10 - iter 135/275 - loss 0.01257537 - time (sec): 6.11 - samples/sec: 1903.15 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:13:21,583 epoch 10 - iter 162/275 - loss 0.01410965 - time (sec): 7.35 - samples/sec: 1858.97 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:13:22,791 epoch 10 - iter 189/275 - loss 0.01325312 - time (sec): 8.56 - samples/sec: 1849.43 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:13:24,014 epoch 10 - iter 216/275 - loss 0.01642775 - time (sec): 9.78 - samples/sec: 1838.64 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:13:25,279 epoch 10 - iter 243/275 - loss 0.01749416 - time (sec): 11.05 - samples/sec: 1833.44 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:13:26,539 epoch 10 - iter 270/275 - loss 0.01729275 - time (sec): 12.31 - samples/sec: 1819.59 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:13:26,757 ----------------------------------------------------------------------------------------------------
2023-10-13 08:13:26,757 EPOCH 10 done: loss 0.0171 - lr: 0.000000
2023-10-13 08:13:27,449 DEV : loss 0.17212548851966858 - f1-score (micro avg) 0.8738
2023-10-13 08:13:27,453 saving best model
2023-10-13 08:13:28,281 ----------------------------------------------------------------------------------------------------
2023-10-13 08:13:28,283 Loading model from best epoch ...
2023-10-13 08:13:30,102 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 08:13:30,894
Results:
- F-score (micro) 0.9043
- F-score (macro) 0.5419
- Accuracy 0.8394
By class:
precision recall f1-score support
scope 0.8883 0.9034 0.8958 176
pers 0.9683 0.9531 0.9606 128
work 0.8421 0.8649 0.8533 74
object 0.0000 0.0000 0.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.9055 0.9031 0.9043 382
macro avg 0.5397 0.5443 0.5419 382
weighted avg 0.8968 0.9031 0.8999 382
2023-10-13 08:13:30,894 ----------------------------------------------------------------------------------------------------
|