File size: 23,977 Bytes
0e1a960 |
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 |
2023-10-13 08:32:58,176 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,176 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 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 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 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Train: 1100 sentences
2023-10-13 08:32:58,177 (train_with_dev=False, train_with_test=False)
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Training Params:
2023-10-13 08:32:58,177 - learning_rate: "5e-05"
2023-10-13 08:32:58,177 - mini_batch_size: "4"
2023-10-13 08:32:58,177 - max_epochs: "10"
2023-10-13 08:32:58,177 - shuffle: "True"
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Plugins:
2023-10-13 08:32:58,177 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:32:58,177 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Computation:
2023-10-13 08:32:58,177 - compute on device: cuda:0
2023-10-13 08:32:58,177 - embedding storage: none
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:58,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:32:59,590 epoch 1 - iter 27/275 - loss 3.04714313 - time (sec): 1.41 - samples/sec: 1715.29 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:33:00,991 epoch 1 - iter 54/275 - loss 2.39413413 - time (sec): 2.81 - samples/sec: 1613.81 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:33:02,339 epoch 1 - iter 81/275 - loss 1.84617130 - time (sec): 4.16 - samples/sec: 1644.84 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:33:03,683 epoch 1 - iter 108/275 - loss 1.54588332 - time (sec): 5.50 - samples/sec: 1641.17 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:33:05,047 epoch 1 - iter 135/275 - loss 1.36800336 - time (sec): 6.87 - samples/sec: 1643.09 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:33:06,382 epoch 1 - iter 162/275 - loss 1.24026566 - time (sec): 8.20 - samples/sec: 1617.43 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:33:07,765 epoch 1 - iter 189/275 - loss 1.10610285 - time (sec): 9.59 - samples/sec: 1637.41 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:33:09,127 epoch 1 - iter 216/275 - loss 1.00254786 - time (sec): 10.95 - samples/sec: 1630.58 - lr: 0.000039 - momentum: 0.000000
2023-10-13 08:33:10,472 epoch 1 - iter 243/275 - loss 0.93102179 - time (sec): 12.29 - samples/sec: 1634.52 - lr: 0.000044 - momentum: 0.000000
2023-10-13 08:33:11,832 epoch 1 - iter 270/275 - loss 0.86490296 - time (sec): 13.65 - samples/sec: 1631.39 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:33:12,079 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:12,079 EPOCH 1 done: loss 0.8551 - lr: 0.000049
2023-10-13 08:33:12,632 DEV : loss 0.19248613715171814 - f1-score (micro avg) 0.6941
2023-10-13 08:33:12,637 saving best model
2023-10-13 08:33:13,091 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:14,445 epoch 2 - iter 27/275 - loss 0.16238864 - time (sec): 1.35 - samples/sec: 1532.54 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:33:15,900 epoch 2 - iter 54/275 - loss 0.18066758 - time (sec): 2.81 - samples/sec: 1584.43 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:33:17,453 epoch 2 - iter 81/275 - loss 0.18789539 - time (sec): 4.36 - samples/sec: 1551.04 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:33:18,974 epoch 2 - iter 108/275 - loss 0.18090485 - time (sec): 5.88 - samples/sec: 1580.07 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:33:20,428 epoch 2 - iter 135/275 - loss 0.18258663 - time (sec): 7.34 - samples/sec: 1593.69 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:33:21,915 epoch 2 - iter 162/275 - loss 0.17760713 - time (sec): 8.82 - samples/sec: 1571.78 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:33:23,388 epoch 2 - iter 189/275 - loss 0.17570702 - time (sec): 10.30 - samples/sec: 1553.06 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:33:24,843 epoch 2 - iter 216/275 - loss 0.17496155 - time (sec): 11.75 - samples/sec: 1554.44 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:33:26,285 epoch 2 - iter 243/275 - loss 0.16582306 - time (sec): 13.19 - samples/sec: 1548.36 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:33:27,687 epoch 2 - iter 270/275 - loss 0.16263694 - time (sec): 14.60 - samples/sec: 1531.95 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:33:27,950 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:27,950 EPOCH 2 done: loss 0.1656 - lr: 0.000045
2023-10-13 08:33:28,614 DEV : loss 0.14798402786254883 - f1-score (micro avg) 0.8053
2023-10-13 08:33:28,620 saving best model
2023-10-13 08:33:29,177 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:30,521 epoch 3 - iter 27/275 - loss 0.11126465 - time (sec): 1.34 - samples/sec: 1708.17 - lr: 0.000044 - momentum: 0.000000
2023-10-13 08:33:31,839 epoch 3 - iter 54/275 - loss 0.13183460 - time (sec): 2.66 - samples/sec: 1745.63 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:33:33,210 epoch 3 - iter 81/275 - loss 0.12195720 - time (sec): 4.03 - samples/sec: 1712.27 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:33:34,559 epoch 3 - iter 108/275 - loss 0.10632686 - time (sec): 5.38 - samples/sec: 1687.34 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:33:36,112 epoch 3 - iter 135/275 - loss 0.12078275 - time (sec): 6.93 - samples/sec: 1658.65 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:33:37,472 epoch 3 - iter 162/275 - loss 0.12131658 - time (sec): 8.29 - samples/sec: 1634.39 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:33:38,827 epoch 3 - iter 189/275 - loss 0.11383941 - time (sec): 9.65 - samples/sec: 1638.61 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:33:40,153 epoch 3 - iter 216/275 - loss 0.11546269 - time (sec): 10.97 - samples/sec: 1636.87 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:33:41,437 epoch 3 - iter 243/275 - loss 0.11394532 - time (sec): 12.26 - samples/sec: 1654.98 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:33:42,750 epoch 3 - iter 270/275 - loss 0.11132217 - time (sec): 13.57 - samples/sec: 1650.18 - lr: 0.000039 - momentum: 0.000000
2023-10-13 08:33:42,992 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:42,992 EPOCH 3 done: loss 0.1098 - lr: 0.000039
2023-10-13 08:33:43,651 DEV : loss 0.15066391229629517 - f1-score (micro avg) 0.8683
2023-10-13 08:33:43,655 saving best model
2023-10-13 08:33:44,168 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:45,527 epoch 4 - iter 27/275 - loss 0.07288362 - time (sec): 1.36 - samples/sec: 1647.79 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:33:46,866 epoch 4 - iter 54/275 - loss 0.08201905 - time (sec): 2.69 - samples/sec: 1633.87 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:33:48,227 epoch 4 - iter 81/275 - loss 0.06593952 - time (sec): 4.06 - samples/sec: 1673.94 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:33:49,487 epoch 4 - iter 108/275 - loss 0.07562373 - time (sec): 5.31 - samples/sec: 1664.35 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:33:50,855 epoch 4 - iter 135/275 - loss 0.08332220 - time (sec): 6.68 - samples/sec: 1668.38 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:33:52,160 epoch 4 - iter 162/275 - loss 0.08850509 - time (sec): 7.99 - samples/sec: 1682.81 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:33:53,511 epoch 4 - iter 189/275 - loss 0.08602280 - time (sec): 9.34 - samples/sec: 1681.52 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:33:54,809 epoch 4 - iter 216/275 - loss 0.08576882 - time (sec): 10.64 - samples/sec: 1672.65 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:33:56,046 epoch 4 - iter 243/275 - loss 0.08711784 - time (sec): 11.87 - samples/sec: 1668.91 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:33:57,413 epoch 4 - iter 270/275 - loss 0.08385358 - time (sec): 13.24 - samples/sec: 1688.44 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:33:57,672 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:57,672 EPOCH 4 done: loss 0.0823 - lr: 0.000034
2023-10-13 08:33:58,348 DEV : loss 0.16972072422504425 - f1-score (micro avg) 0.862
2023-10-13 08:33:58,353 ----------------------------------------------------------------------------------------------------
2023-10-13 08:33:59,758 epoch 5 - iter 27/275 - loss 0.07002550 - time (sec): 1.40 - samples/sec: 1740.87 - lr: 0.000033 - momentum: 0.000000
2023-10-13 08:34:01,112 epoch 5 - iter 54/275 - loss 0.06055068 - time (sec): 2.76 - samples/sec: 1732.26 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:34:02,400 epoch 5 - iter 81/275 - loss 0.06519177 - time (sec): 4.05 - samples/sec: 1706.49 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:34:03,705 epoch 5 - iter 108/275 - loss 0.06009494 - time (sec): 5.35 - samples/sec: 1700.34 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:34:05,015 epoch 5 - iter 135/275 - loss 0.06524965 - time (sec): 6.66 - samples/sec: 1694.87 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:34:06,339 epoch 5 - iter 162/275 - loss 0.05954754 - time (sec): 7.98 - samples/sec: 1666.38 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:34:07,788 epoch 5 - iter 189/275 - loss 0.05966031 - time (sec): 9.43 - samples/sec: 1652.36 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:34:09,041 epoch 5 - iter 216/275 - loss 0.06153642 - time (sec): 10.69 - samples/sec: 1656.70 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:34:10,238 epoch 5 - iter 243/275 - loss 0.05870686 - time (sec): 11.88 - samples/sec: 1696.66 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:34:11,375 epoch 5 - iter 270/275 - loss 0.05725721 - time (sec): 13.02 - samples/sec: 1716.58 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:34:11,615 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:11,615 EPOCH 5 done: loss 0.0598 - lr: 0.000028
2023-10-13 08:34:12,370 DEV : loss 0.13807880878448486 - f1-score (micro avg) 0.8786
2023-10-13 08:34:12,375 saving best model
2023-10-13 08:34:12,930 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:14,288 epoch 6 - iter 27/275 - loss 0.05119173 - time (sec): 1.36 - samples/sec: 1736.70 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:34:15,602 epoch 6 - iter 54/275 - loss 0.04997304 - time (sec): 2.67 - samples/sec: 1775.66 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:34:16,926 epoch 6 - iter 81/275 - loss 0.04700888 - time (sec): 3.99 - samples/sec: 1682.59 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:34:18,154 epoch 6 - iter 108/275 - loss 0.04478485 - time (sec): 5.22 - samples/sec: 1696.14 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:34:19,394 epoch 6 - iter 135/275 - loss 0.04564487 - time (sec): 6.46 - samples/sec: 1723.93 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:34:20,689 epoch 6 - iter 162/275 - loss 0.04178622 - time (sec): 7.76 - samples/sec: 1718.19 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:34:21,994 epoch 6 - iter 189/275 - loss 0.04548401 - time (sec): 9.06 - samples/sec: 1701.43 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:34:23,397 epoch 6 - iter 216/275 - loss 0.04335930 - time (sec): 10.47 - samples/sec: 1692.68 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:34:24,713 epoch 6 - iter 243/275 - loss 0.04768471 - time (sec): 11.78 - samples/sec: 1713.43 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:34:25,961 epoch 6 - iter 270/275 - loss 0.04520765 - time (sec): 13.03 - samples/sec: 1722.15 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:34:26,192 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:26,192 EPOCH 6 done: loss 0.0459 - lr: 0.000022
2023-10-13 08:34:26,895 DEV : loss 0.13942967355251312 - f1-score (micro avg) 0.8851
2023-10-13 08:34:26,901 saving best model
2023-10-13 08:34:27,430 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:28,683 epoch 7 - iter 27/275 - loss 0.03084838 - time (sec): 1.25 - samples/sec: 1815.41 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:34:29,955 epoch 7 - iter 54/275 - loss 0.02247843 - time (sec): 2.52 - samples/sec: 1693.69 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:34:31,233 epoch 7 - iter 81/275 - loss 0.03578498 - time (sec): 3.80 - samples/sec: 1744.88 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:34:32,512 epoch 7 - iter 108/275 - loss 0.02970659 - time (sec): 5.08 - samples/sec: 1755.06 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:34:33,722 epoch 7 - iter 135/275 - loss 0.03215910 - time (sec): 6.29 - samples/sec: 1780.84 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:34:34,977 epoch 7 - iter 162/275 - loss 0.03234887 - time (sec): 7.55 - samples/sec: 1779.39 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:34:36,309 epoch 7 - iter 189/275 - loss 0.03111690 - time (sec): 8.88 - samples/sec: 1782.54 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:34:37,608 epoch 7 - iter 216/275 - loss 0.03139334 - time (sec): 10.18 - samples/sec: 1757.77 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:34:38,916 epoch 7 - iter 243/275 - loss 0.02834597 - time (sec): 11.48 - samples/sec: 1758.49 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:34:40,177 epoch 7 - iter 270/275 - loss 0.03079822 - time (sec): 12.75 - samples/sec: 1754.29 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:34:40,411 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:40,411 EPOCH 7 done: loss 0.0308 - lr: 0.000017
2023-10-13 08:34:41,083 DEV : loss 0.15453596413135529 - f1-score (micro avg) 0.868
2023-10-13 08:34:41,088 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:42,342 epoch 8 - iter 27/275 - loss 0.02109382 - time (sec): 1.25 - samples/sec: 1829.33 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:34:43,603 epoch 8 - iter 54/275 - loss 0.02025858 - time (sec): 2.51 - samples/sec: 1758.34 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:34:44,808 epoch 8 - iter 81/275 - loss 0.01822485 - time (sec): 3.72 - samples/sec: 1807.99 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:34:45,995 epoch 8 - iter 108/275 - loss 0.02322727 - time (sec): 4.90 - samples/sec: 1864.65 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:34:47,265 epoch 8 - iter 135/275 - loss 0.02349216 - time (sec): 6.18 - samples/sec: 1838.39 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:34:48,489 epoch 8 - iter 162/275 - loss 0.02354132 - time (sec): 7.40 - samples/sec: 1839.28 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:34:49,672 epoch 8 - iter 189/275 - loss 0.02656606 - time (sec): 8.58 - samples/sec: 1843.38 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:34:50,879 epoch 8 - iter 216/275 - loss 0.02469785 - time (sec): 9.79 - samples/sec: 1814.71 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:34:52,072 epoch 8 - iter 243/275 - loss 0.02272723 - time (sec): 10.98 - samples/sec: 1825.49 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:34:53,263 epoch 8 - iter 270/275 - loss 0.02072684 - time (sec): 12.17 - samples/sec: 1831.08 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:34:53,482 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:53,482 EPOCH 8 done: loss 0.0220 - lr: 0.000011
2023-10-13 08:34:54,207 DEV : loss 0.1433096081018448 - f1-score (micro avg) 0.8977
2023-10-13 08:34:54,212 saving best model
2023-10-13 08:34:54,706 ----------------------------------------------------------------------------------------------------
2023-10-13 08:34:55,954 epoch 9 - iter 27/275 - loss 0.02665393 - time (sec): 1.25 - samples/sec: 1821.64 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:34:57,125 epoch 9 - iter 54/275 - loss 0.01402467 - time (sec): 2.42 - samples/sec: 1798.96 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:34:58,276 epoch 9 - iter 81/275 - loss 0.01312050 - time (sec): 3.57 - samples/sec: 1846.45 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:34:59,425 epoch 9 - iter 108/275 - loss 0.01317766 - time (sec): 4.72 - samples/sec: 1811.17 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:35:00,589 epoch 9 - iter 135/275 - loss 0.01744292 - time (sec): 5.88 - samples/sec: 1893.37 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:35:01,743 epoch 9 - iter 162/275 - loss 0.01660356 - time (sec): 7.03 - samples/sec: 1934.90 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:35:02,999 epoch 9 - iter 189/275 - loss 0.01454803 - time (sec): 8.29 - samples/sec: 1909.02 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:35:04,237 epoch 9 - iter 216/275 - loss 0.01546288 - time (sec): 9.53 - samples/sec: 1892.29 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:35:05,448 epoch 9 - iter 243/275 - loss 0.01444547 - time (sec): 10.74 - samples/sec: 1874.69 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:35:06,649 epoch 9 - iter 270/275 - loss 0.01579205 - time (sec): 11.94 - samples/sec: 1869.33 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:35:06,875 ----------------------------------------------------------------------------------------------------
2023-10-13 08:35:06,875 EPOCH 9 done: loss 0.0162 - lr: 0.000006
2023-10-13 08:35:07,535 DEV : loss 0.14539609849452972 - f1-score (micro avg) 0.8889
2023-10-13 08:35:07,539 ----------------------------------------------------------------------------------------------------
2023-10-13 08:35:08,782 epoch 10 - iter 27/275 - loss 0.03744018 - time (sec): 1.24 - samples/sec: 1843.69 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:35:10,005 epoch 10 - iter 54/275 - loss 0.04391229 - time (sec): 2.46 - samples/sec: 1855.68 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:35:11,278 epoch 10 - iter 81/275 - loss 0.02903518 - time (sec): 3.74 - samples/sec: 1869.23 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:35:12,519 epoch 10 - iter 108/275 - loss 0.02592698 - time (sec): 4.98 - samples/sec: 1831.08 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:35:13,713 epoch 10 - iter 135/275 - loss 0.02103490 - time (sec): 6.17 - samples/sec: 1824.56 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:35:14,892 epoch 10 - iter 162/275 - loss 0.01951085 - time (sec): 7.35 - samples/sec: 1875.40 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:35:16,076 epoch 10 - iter 189/275 - loss 0.01714763 - time (sec): 8.54 - samples/sec: 1859.96 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:35:17,272 epoch 10 - iter 216/275 - loss 0.01515363 - time (sec): 9.73 - samples/sec: 1849.93 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:35:18,480 epoch 10 - iter 243/275 - loss 0.01499240 - time (sec): 10.94 - samples/sec: 1835.33 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:35:19,746 epoch 10 - iter 270/275 - loss 0.01408694 - time (sec): 12.21 - samples/sec: 1824.85 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:35:19,970 ----------------------------------------------------------------------------------------------------
2023-10-13 08:35:19,971 EPOCH 10 done: loss 0.0138 - lr: 0.000000
2023-10-13 08:35:20,618 DEV : loss 0.14501692354679108 - f1-score (micro avg) 0.8921
2023-10-13 08:35:20,989 ----------------------------------------------------------------------------------------------------
2023-10-13 08:35:20,991 Loading model from best epoch ...
2023-10-13 08:35:22,653 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 08:35:23,442
Results:
- F-score (micro) 0.9062
- F-score (macro) 0.8756
- Accuracy 0.8366
By class:
precision recall f1-score support
scope 0.8851 0.8750 0.8800 176
pers 0.9919 0.9531 0.9721 128
work 0.8533 0.8649 0.8591 74
object 1.0000 1.0000 1.0000 2
loc 1.0000 0.5000 0.6667 2
micro avg 0.9147 0.8979 0.9062 382
macro avg 0.9461 0.8386 0.8756 382
weighted avg 0.9159 0.8979 0.9063 382
2023-10-13 08:35:23,443 ----------------------------------------------------------------------------------------------------
|