File size: 24,218 Bytes
ec91270 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
2023-10-23 15:49:02,712 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,713 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(64001, 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()
)"
2023-10-23 15:49:02,713 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,713 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
2023-10-23 15:49:02,713 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Train: 1100 sentences
2023-10-23 15:49:02,714 (train_with_dev=False, train_with_test=False)
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Training Params:
2023-10-23 15:49:02,714 - learning_rate: "3e-05"
2023-10-23 15:49:02,714 - mini_batch_size: "4"
2023-10-23 15:49:02,714 - max_epochs: "10"
2023-10-23 15:49:02,714 - shuffle: "True"
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Plugins:
2023-10-23 15:49:02,714 - TensorboardLogger
2023-10-23 15:49:02,714 - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 15:49:02,714 - metric: "('micro avg', 'f1-score')"
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Computation:
2023-10-23 15:49:02,714 - compute on device: cuda:0
2023-10-23 15:49:02,714 - embedding storage: none
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:02,714 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 15:49:04,134 epoch 1 - iter 27/275 - loss 2.83941383 - time (sec): 1.42 - samples/sec: 1260.09 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:49:05,543 epoch 1 - iter 54/275 - loss 2.14658630 - time (sec): 2.83 - samples/sec: 1439.75 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:49:06,964 epoch 1 - iter 81/275 - loss 1.72389593 - time (sec): 4.25 - samples/sec: 1523.60 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:49:08,373 epoch 1 - iter 108/275 - loss 1.46781181 - time (sec): 5.66 - samples/sec: 1569.08 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:49:09,768 epoch 1 - iter 135/275 - loss 1.28242063 - time (sec): 7.05 - samples/sec: 1581.18 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:49:11,165 epoch 1 - iter 162/275 - loss 1.12735272 - time (sec): 8.45 - samples/sec: 1591.46 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:49:12,563 epoch 1 - iter 189/275 - loss 1.02268702 - time (sec): 9.85 - samples/sec: 1582.62 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:49:13,960 epoch 1 - iter 216/275 - loss 0.91909206 - time (sec): 11.24 - samples/sec: 1607.03 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:49:15,355 epoch 1 - iter 243/275 - loss 0.84777616 - time (sec): 12.64 - samples/sec: 1606.88 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:49:16,737 epoch 1 - iter 270/275 - loss 0.78992865 - time (sec): 14.02 - samples/sec: 1597.84 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:49:16,993 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:16,994 EPOCH 1 done: loss 0.7815 - lr: 0.000029
2023-10-23 15:49:17,408 DEV : loss 0.17806066572666168 - f1-score (micro avg) 0.7256
2023-10-23 15:49:17,414 saving best model
2023-10-23 15:49:17,807 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:19,194 epoch 2 - iter 27/275 - loss 0.22098647 - time (sec): 1.39 - samples/sec: 1834.03 - lr: 0.000030 - momentum: 0.000000
2023-10-23 15:49:20,589 epoch 2 - iter 54/275 - loss 0.22583475 - time (sec): 2.78 - samples/sec: 1648.14 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:49:21,977 epoch 2 - iter 81/275 - loss 0.19163146 - time (sec): 4.17 - samples/sec: 1597.05 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:49:23,396 epoch 2 - iter 108/275 - loss 0.19026888 - time (sec): 5.59 - samples/sec: 1540.17 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:49:24,807 epoch 2 - iter 135/275 - loss 0.17483222 - time (sec): 7.00 - samples/sec: 1541.10 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:49:26,223 epoch 2 - iter 162/275 - loss 0.17437410 - time (sec): 8.41 - samples/sec: 1531.54 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:49:27,666 epoch 2 - iter 189/275 - loss 0.16454035 - time (sec): 9.86 - samples/sec: 1533.95 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:49:29,094 epoch 2 - iter 216/275 - loss 0.17001907 - time (sec): 11.29 - samples/sec: 1547.08 - lr: 0.000027 - momentum: 0.000000
2023-10-23 15:49:30,501 epoch 2 - iter 243/275 - loss 0.16952883 - time (sec): 12.69 - samples/sec: 1556.75 - lr: 0.000027 - momentum: 0.000000
2023-10-23 15:49:31,915 epoch 2 - iter 270/275 - loss 0.16760966 - time (sec): 14.11 - samples/sec: 1582.65 - lr: 0.000027 - momentum: 0.000000
2023-10-23 15:49:32,173 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:32,174 EPOCH 2 done: loss 0.1669 - lr: 0.000027
2023-10-23 15:49:32,710 DEV : loss 0.1282263696193695 - f1-score (micro avg) 0.823
2023-10-23 15:49:32,715 saving best model
2023-10-23 15:49:33,267 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:34,603 epoch 3 - iter 27/275 - loss 0.11417363 - time (sec): 1.33 - samples/sec: 1752.69 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:49:35,971 epoch 3 - iter 54/275 - loss 0.10292930 - time (sec): 2.70 - samples/sec: 1682.84 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:49:37,343 epoch 3 - iter 81/275 - loss 0.11259165 - time (sec): 4.07 - samples/sec: 1658.61 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:49:38,693 epoch 3 - iter 108/275 - loss 0.11306199 - time (sec): 5.42 - samples/sec: 1673.09 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:49:39,998 epoch 3 - iter 135/275 - loss 0.10315859 - time (sec): 6.73 - samples/sec: 1691.92 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:49:41,256 epoch 3 - iter 162/275 - loss 0.09810185 - time (sec): 7.98 - samples/sec: 1703.55 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:49:42,535 epoch 3 - iter 189/275 - loss 0.09949418 - time (sec): 9.26 - samples/sec: 1708.34 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:49:43,884 epoch 3 - iter 216/275 - loss 0.09940572 - time (sec): 10.61 - samples/sec: 1692.65 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:49:45,221 epoch 3 - iter 243/275 - loss 0.09918018 - time (sec): 11.95 - samples/sec: 1700.14 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:49:46,548 epoch 3 - iter 270/275 - loss 0.09785407 - time (sec): 13.28 - samples/sec: 1677.37 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:49:46,810 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:46,810 EPOCH 3 done: loss 0.0986 - lr: 0.000023
2023-10-23 15:49:47,349 DEV : loss 0.1556384116411209 - f1-score (micro avg) 0.8397
2023-10-23 15:49:47,354 saving best model
2023-10-23 15:49:47,902 ----------------------------------------------------------------------------------------------------
2023-10-23 15:49:49,268 epoch 4 - iter 27/275 - loss 0.10635465 - time (sec): 1.36 - samples/sec: 1699.34 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:49:50,661 epoch 4 - iter 54/275 - loss 0.07787905 - time (sec): 2.76 - samples/sec: 1710.12 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:49:52,050 epoch 4 - iter 81/275 - loss 0.07086144 - time (sec): 4.15 - samples/sec: 1619.19 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:49:53,470 epoch 4 - iter 108/275 - loss 0.06660226 - time (sec): 5.57 - samples/sec: 1579.83 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:49:55,026 epoch 4 - iter 135/275 - loss 0.06133614 - time (sec): 7.12 - samples/sec: 1579.05 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:49:56,436 epoch 4 - iter 162/275 - loss 0.07371892 - time (sec): 8.53 - samples/sec: 1600.96 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:49:57,837 epoch 4 - iter 189/275 - loss 0.06854694 - time (sec): 9.93 - samples/sec: 1601.60 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:49:59,240 epoch 4 - iter 216/275 - loss 0.07000006 - time (sec): 11.34 - samples/sec: 1590.97 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:50:00,651 epoch 4 - iter 243/275 - loss 0.06874057 - time (sec): 12.75 - samples/sec: 1562.29 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:50:02,081 epoch 4 - iter 270/275 - loss 0.06913971 - time (sec): 14.18 - samples/sec: 1577.52 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:50:02,344 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:02,344 EPOCH 4 done: loss 0.0702 - lr: 0.000020
2023-10-23 15:50:02,885 DEV : loss 0.1502317488193512 - f1-score (micro avg) 0.8561
2023-10-23 15:50:02,890 saving best model
2023-10-23 15:50:03,412 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:04,753 epoch 5 - iter 27/275 - loss 0.05181714 - time (sec): 1.34 - samples/sec: 1740.38 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:50:06,005 epoch 5 - iter 54/275 - loss 0.07653701 - time (sec): 2.59 - samples/sec: 1739.60 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:50:07,269 epoch 5 - iter 81/275 - loss 0.06745093 - time (sec): 3.86 - samples/sec: 1753.54 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:50:08,532 epoch 5 - iter 108/275 - loss 0.05451561 - time (sec): 5.12 - samples/sec: 1742.89 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:50:09,799 epoch 5 - iter 135/275 - loss 0.05158637 - time (sec): 6.39 - samples/sec: 1769.32 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:50:11,070 epoch 5 - iter 162/275 - loss 0.05025736 - time (sec): 7.66 - samples/sec: 1749.73 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:50:12,346 epoch 5 - iter 189/275 - loss 0.04870088 - time (sec): 8.93 - samples/sec: 1752.00 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:50:13,649 epoch 5 - iter 216/275 - loss 0.04861125 - time (sec): 10.24 - samples/sec: 1747.96 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:50:14,972 epoch 5 - iter 243/275 - loss 0.05333777 - time (sec): 11.56 - samples/sec: 1721.85 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:50:16,328 epoch 5 - iter 270/275 - loss 0.05110952 - time (sec): 12.92 - samples/sec: 1723.24 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:50:16,568 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:16,568 EPOCH 5 done: loss 0.0516 - lr: 0.000017
2023-10-23 15:50:17,100 DEV : loss 0.14082755148410797 - f1-score (micro avg) 0.891
2023-10-23 15:50:17,105 saving best model
2023-10-23 15:50:17,625 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:19,040 epoch 6 - iter 27/275 - loss 0.00386518 - time (sec): 1.41 - samples/sec: 1784.05 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:50:20,440 epoch 6 - iter 54/275 - loss 0.02921163 - time (sec): 2.81 - samples/sec: 1583.87 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:50:21,835 epoch 6 - iter 81/275 - loss 0.02939935 - time (sec): 4.21 - samples/sec: 1575.72 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:50:23,184 epoch 6 - iter 108/275 - loss 0.02973268 - time (sec): 5.56 - samples/sec: 1623.15 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:50:24,544 epoch 6 - iter 135/275 - loss 0.02759517 - time (sec): 6.92 - samples/sec: 1619.60 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:50:25,902 epoch 6 - iter 162/275 - loss 0.03106721 - time (sec): 8.27 - samples/sec: 1602.30 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:50:27,254 epoch 6 - iter 189/275 - loss 0.03200975 - time (sec): 9.63 - samples/sec: 1600.57 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:50:28,594 epoch 6 - iter 216/275 - loss 0.03413447 - time (sec): 10.97 - samples/sec: 1606.80 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:50:29,960 epoch 6 - iter 243/275 - loss 0.03567708 - time (sec): 12.33 - samples/sec: 1618.86 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:50:31,317 epoch 6 - iter 270/275 - loss 0.03741332 - time (sec): 13.69 - samples/sec: 1631.75 - lr: 0.000013 - momentum: 0.000000
2023-10-23 15:50:31,570 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:31,571 EPOCH 6 done: loss 0.0385 - lr: 0.000013
2023-10-23 15:50:32,119 DEV : loss 0.16913354396820068 - f1-score (micro avg) 0.8636
2023-10-23 15:50:32,125 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:33,534 epoch 7 - iter 27/275 - loss 0.04239827 - time (sec): 1.41 - samples/sec: 1661.75 - lr: 0.000013 - momentum: 0.000000
2023-10-23 15:50:34,955 epoch 7 - iter 54/275 - loss 0.03679797 - time (sec): 2.83 - samples/sec: 1551.80 - lr: 0.000013 - momentum: 0.000000
2023-10-23 15:50:36,351 epoch 7 - iter 81/275 - loss 0.03544132 - time (sec): 4.23 - samples/sec: 1533.62 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:50:37,751 epoch 7 - iter 108/275 - loss 0.03506543 - time (sec): 5.63 - samples/sec: 1577.68 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:50:39,184 epoch 7 - iter 135/275 - loss 0.03111449 - time (sec): 7.06 - samples/sec: 1574.98 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:50:40,590 epoch 7 - iter 162/275 - loss 0.02965772 - time (sec): 8.46 - samples/sec: 1558.89 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:50:42,017 epoch 7 - iter 189/275 - loss 0.02765179 - time (sec): 9.89 - samples/sec: 1570.22 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:50:43,434 epoch 7 - iter 216/275 - loss 0.02591692 - time (sec): 11.31 - samples/sec: 1581.26 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:50:44,860 epoch 7 - iter 243/275 - loss 0.02934153 - time (sec): 12.73 - samples/sec: 1586.85 - lr: 0.000010 - momentum: 0.000000
2023-10-23 15:50:46,288 epoch 7 - iter 270/275 - loss 0.02777065 - time (sec): 14.16 - samples/sec: 1576.34 - lr: 0.000010 - momentum: 0.000000
2023-10-23 15:50:46,565 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:46,566 EPOCH 7 done: loss 0.0278 - lr: 0.000010
2023-10-23 15:50:47,104 DEV : loss 0.16255125403404236 - f1-score (micro avg) 0.8921
2023-10-23 15:50:47,109 saving best model
2023-10-23 15:50:47,650 ----------------------------------------------------------------------------------------------------
2023-10-23 15:50:49,094 epoch 8 - iter 27/275 - loss 0.04335307 - time (sec): 1.44 - samples/sec: 1509.48 - lr: 0.000010 - momentum: 0.000000
2023-10-23 15:50:50,577 epoch 8 - iter 54/275 - loss 0.02995593 - time (sec): 2.92 - samples/sec: 1564.81 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:50:52,039 epoch 8 - iter 81/275 - loss 0.03529654 - time (sec): 4.39 - samples/sec: 1527.29 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:50:53,509 epoch 8 - iter 108/275 - loss 0.02984522 - time (sec): 5.86 - samples/sec: 1565.65 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:50:54,955 epoch 8 - iter 135/275 - loss 0.02572520 - time (sec): 7.30 - samples/sec: 1575.37 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:50:56,432 epoch 8 - iter 162/275 - loss 0.02300740 - time (sec): 8.78 - samples/sec: 1591.54 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:50:57,902 epoch 8 - iter 189/275 - loss 0.02124124 - time (sec): 10.25 - samples/sec: 1563.76 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:50:59,316 epoch 8 - iter 216/275 - loss 0.01934416 - time (sec): 11.66 - samples/sec: 1547.46 - lr: 0.000007 - momentum: 0.000000
2023-10-23 15:51:00,830 epoch 8 - iter 243/275 - loss 0.02046265 - time (sec): 13.18 - samples/sec: 1530.95 - lr: 0.000007 - momentum: 0.000000
2023-10-23 15:51:02,342 epoch 8 - iter 270/275 - loss 0.02074013 - time (sec): 14.69 - samples/sec: 1518.47 - lr: 0.000007 - momentum: 0.000000
2023-10-23 15:51:02,628 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:02,628 EPOCH 8 done: loss 0.0226 - lr: 0.000007
2023-10-23 15:51:03,168 DEV : loss 0.15772368013858795 - f1-score (micro avg) 0.8953
2023-10-23 15:51:03,174 saving best model
2023-10-23 15:51:03,723 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:05,148 epoch 9 - iter 27/275 - loss 0.01504040 - time (sec): 1.42 - samples/sec: 1600.13 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:51:06,569 epoch 9 - iter 54/275 - loss 0.01703108 - time (sec): 2.84 - samples/sec: 1611.83 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:51:07,979 epoch 9 - iter 81/275 - loss 0.02222312 - time (sec): 4.25 - samples/sec: 1597.43 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:51:09,366 epoch 9 - iter 108/275 - loss 0.02072152 - time (sec): 5.64 - samples/sec: 1592.87 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:51:10,792 epoch 9 - iter 135/275 - loss 0.01794282 - time (sec): 7.06 - samples/sec: 1600.44 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:51:12,232 epoch 9 - iter 162/275 - loss 0.01549132 - time (sec): 8.50 - samples/sec: 1609.76 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:51:13,672 epoch 9 - iter 189/275 - loss 0.01519766 - time (sec): 9.95 - samples/sec: 1589.81 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:51:15,129 epoch 9 - iter 216/275 - loss 0.01494770 - time (sec): 11.40 - samples/sec: 1587.79 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:51:16,584 epoch 9 - iter 243/275 - loss 0.01368241 - time (sec): 12.86 - samples/sec: 1576.48 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:51:18,013 epoch 9 - iter 270/275 - loss 0.01433322 - time (sec): 14.29 - samples/sec: 1572.91 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:51:18,281 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:18,281 EPOCH 9 done: loss 0.0141 - lr: 0.000003
2023-10-23 15:51:18,817 DEV : loss 0.16109435260295868 - f1-score (micro avg) 0.8953
2023-10-23 15:51:18,822 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:20,254 epoch 10 - iter 27/275 - loss 0.01426170 - time (sec): 1.43 - samples/sec: 1472.72 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:51:21,704 epoch 10 - iter 54/275 - loss 0.00849233 - time (sec): 2.88 - samples/sec: 1510.58 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:51:23,155 epoch 10 - iter 81/275 - loss 0.00932013 - time (sec): 4.33 - samples/sec: 1551.58 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:51:24,587 epoch 10 - iter 108/275 - loss 0.00701482 - time (sec): 5.76 - samples/sec: 1570.09 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:51:26,045 epoch 10 - iter 135/275 - loss 0.00720699 - time (sec): 7.22 - samples/sec: 1540.00 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:51:27,472 epoch 10 - iter 162/275 - loss 0.00872732 - time (sec): 8.65 - samples/sec: 1518.11 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:51:28,940 epoch 10 - iter 189/275 - loss 0.00824989 - time (sec): 10.12 - samples/sec: 1509.48 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:51:30,385 epoch 10 - iter 216/275 - loss 0.01055276 - time (sec): 11.56 - samples/sec: 1525.31 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:51:31,861 epoch 10 - iter 243/275 - loss 0.01278568 - time (sec): 13.04 - samples/sec: 1530.53 - lr: 0.000000 - momentum: 0.000000
2023-10-23 15:51:33,313 epoch 10 - iter 270/275 - loss 0.01209491 - time (sec): 14.49 - samples/sec: 1541.25 - lr: 0.000000 - momentum: 0.000000
2023-10-23 15:51:33,576 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:33,577 EPOCH 10 done: loss 0.0119 - lr: 0.000000
2023-10-23 15:51:34,109 DEV : loss 0.16141371428966522 - f1-score (micro avg) 0.8994
2023-10-23 15:51:34,114 saving best model
2023-10-23 15:51:35,051 ----------------------------------------------------------------------------------------------------
2023-10-23 15:51:35,052 Loading model from best epoch ...
2023-10-23 15:51:36,783 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
2023-10-23 15:51:37,444
Results:
- F-score (micro) 0.9041
- F-score (macro) 0.7376
- Accuracy 0.8411
By class:
precision recall f1-score support
scope 0.8883 0.9034 0.8958 176
pers 0.9685 0.9609 0.9647 128
work 0.8451 0.8108 0.8276 74
object 1.0000 1.0000 1.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.9077 0.9005 0.9041 382
macro avg 0.7404 0.7350 0.7376 382
weighted avg 0.9027 0.9005 0.9015 382
2023-10-23 15:51:37,444 ----------------------------------------------------------------------------------------------------
|