File size: 23,968 Bytes
e006c16 |
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 08:23:28,457 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,458 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 08:23:28,458 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,458 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 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Train: 1100 sentences
2023-10-13 08:23:28,459 (train_with_dev=False, train_with_test=False)
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Training Params:
2023-10-13 08:23:28,459 - learning_rate: "5e-05"
2023-10-13 08:23:28,459 - mini_batch_size: "4"
2023-10-13 08:23:28,459 - max_epochs: "10"
2023-10-13 08:23:28,459 - shuffle: "True"
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Plugins:
2023-10-13 08:23:28,459 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:23:28,459 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Computation:
2023-10-13 08:23:28,459 - compute on device: cuda:0
2023-10-13 08:23:28,459 - embedding storage: none
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:28,459 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:29,713 epoch 1 - iter 27/275 - loss 3.39902518 - time (sec): 1.25 - samples/sec: 1969.29 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:23:30,927 epoch 1 - iter 54/275 - loss 2.87294952 - time (sec): 2.47 - samples/sec: 1848.98 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:23:32,220 epoch 1 - iter 81/275 - loss 2.22493882 - time (sec): 3.76 - samples/sec: 1786.06 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:23:33,660 epoch 1 - iter 108/275 - loss 1.83215945 - time (sec): 5.20 - samples/sec: 1792.67 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:23:35,031 epoch 1 - iter 135/275 - loss 1.64868900 - time (sec): 6.57 - samples/sec: 1720.13 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:23:36,334 epoch 1 - iter 162/275 - loss 1.49452799 - time (sec): 7.87 - samples/sec: 1699.63 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:23:37,694 epoch 1 - iter 189/275 - loss 1.36894456 - time (sec): 9.23 - samples/sec: 1700.21 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:23:39,006 epoch 1 - iter 216/275 - loss 1.22942202 - time (sec): 10.55 - samples/sec: 1725.70 - lr: 0.000039 - momentum: 0.000000
2023-10-13 08:23:40,220 epoch 1 - iter 243/275 - loss 1.13670758 - time (sec): 11.76 - samples/sec: 1724.96 - lr: 0.000044 - momentum: 0.000000
2023-10-13 08:23:41,359 epoch 1 - iter 270/275 - loss 1.06530735 - time (sec): 12.90 - samples/sec: 1733.69 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:23:41,573 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:41,573 EPOCH 1 done: loss 1.0497 - lr: 0.000049
2023-10-13 08:23:42,353 DEV : loss 0.23358413577079773 - f1-score (micro avg) 0.712
2023-10-13 08:23:42,359 saving best model
2023-10-13 08:23:42,664 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:43,803 epoch 2 - iter 27/275 - loss 0.22629551 - time (sec): 1.14 - samples/sec: 2200.36 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:23:44,988 epoch 2 - iter 54/275 - loss 0.22270726 - time (sec): 2.32 - samples/sec: 1883.93 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:23:46,161 epoch 2 - iter 81/275 - loss 0.20667117 - time (sec): 3.50 - samples/sec: 1907.77 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:23:47,326 epoch 2 - iter 108/275 - loss 0.20192750 - time (sec): 4.66 - samples/sec: 1895.84 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:23:48,510 epoch 2 - iter 135/275 - loss 0.18672772 - time (sec): 5.85 - samples/sec: 1907.29 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:23:49,706 epoch 2 - iter 162/275 - loss 0.18416707 - time (sec): 7.04 - samples/sec: 1891.22 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:23:50,882 epoch 2 - iter 189/275 - loss 0.17608829 - time (sec): 8.22 - samples/sec: 1881.81 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:23:52,157 epoch 2 - iter 216/275 - loss 0.18436043 - time (sec): 9.49 - samples/sec: 1882.30 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:23:53,374 epoch 2 - iter 243/275 - loss 0.18599630 - time (sec): 10.71 - samples/sec: 1873.54 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:23:54,579 epoch 2 - iter 270/275 - loss 0.18136454 - time (sec): 11.91 - samples/sec: 1878.19 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:23:54,796 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:54,796 EPOCH 2 done: loss 0.1794 - lr: 0.000045
2023-10-13 08:23:55,430 DEV : loss 0.1404486447572708 - f1-score (micro avg) 0.8351
2023-10-13 08:23:55,435 saving best model
2023-10-13 08:23:55,832 ----------------------------------------------------------------------------------------------------
2023-10-13 08:23:57,062 epoch 3 - iter 27/275 - loss 0.13376844 - time (sec): 1.23 - samples/sec: 1664.30 - lr: 0.000044 - momentum: 0.000000
2023-10-13 08:23:58,325 epoch 3 - iter 54/275 - loss 0.12447582 - time (sec): 2.49 - samples/sec: 1721.00 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:23:59,513 epoch 3 - iter 81/275 - loss 0.12212165 - time (sec): 3.68 - samples/sec: 1816.92 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:24:00,638 epoch 3 - iter 108/275 - loss 0.12004262 - time (sec): 4.80 - samples/sec: 1865.63 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:24:01,789 epoch 3 - iter 135/275 - loss 0.11280775 - time (sec): 5.95 - samples/sec: 1881.82 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:24:02,919 epoch 3 - iter 162/275 - loss 0.11290164 - time (sec): 7.08 - samples/sec: 1872.88 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:24:04,064 epoch 3 - iter 189/275 - loss 0.10849768 - time (sec): 8.23 - samples/sec: 1893.46 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:24:05,201 epoch 3 - iter 216/275 - loss 0.10865497 - time (sec): 9.37 - samples/sec: 1876.12 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:24:06,339 epoch 3 - iter 243/275 - loss 0.11196281 - time (sec): 10.50 - samples/sec: 1901.51 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:24:07,481 epoch 3 - iter 270/275 - loss 0.11441067 - time (sec): 11.65 - samples/sec: 1920.62 - lr: 0.000039 - momentum: 0.000000
2023-10-13 08:24:07,696 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:07,696 EPOCH 3 done: loss 0.1137 - lr: 0.000039
2023-10-13 08:24:08,424 DEV : loss 0.15840192139148712 - f1-score (micro avg) 0.8302
2023-10-13 08:24:08,429 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:09,612 epoch 4 - iter 27/275 - loss 0.04289286 - time (sec): 1.18 - samples/sec: 1851.60 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:24:10,803 epoch 4 - iter 54/275 - loss 0.06359151 - time (sec): 2.37 - samples/sec: 1929.20 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:24:12,019 epoch 4 - iter 81/275 - loss 0.07865884 - time (sec): 3.59 - samples/sec: 1878.36 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:24:13,185 epoch 4 - iter 108/275 - loss 0.07465091 - time (sec): 4.75 - samples/sec: 1881.82 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:24:14,321 epoch 4 - iter 135/275 - loss 0.07631322 - time (sec): 5.89 - samples/sec: 1899.14 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:24:15,447 epoch 4 - iter 162/275 - loss 0.07773191 - time (sec): 7.02 - samples/sec: 1902.07 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:24:16,633 epoch 4 - iter 189/275 - loss 0.08141307 - time (sec): 8.20 - samples/sec: 1881.63 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:24:17,925 epoch 4 - iter 216/275 - loss 0.08450300 - time (sec): 9.50 - samples/sec: 1845.11 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:24:19,163 epoch 4 - iter 243/275 - loss 0.08201415 - time (sec): 10.73 - samples/sec: 1882.05 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:24:20,306 epoch 4 - iter 270/275 - loss 0.08401559 - time (sec): 11.88 - samples/sec: 1886.45 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:24:20,525 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:20,525 EPOCH 4 done: loss 0.0837 - lr: 0.000034
2023-10-13 08:24:21,177 DEV : loss 0.14714744687080383 - f1-score (micro avg) 0.8547
2023-10-13 08:24:21,182 saving best model
2023-10-13 08:24:21,610 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:22,819 epoch 5 - iter 27/275 - loss 0.05779460 - time (sec): 1.21 - samples/sec: 1938.10 - lr: 0.000033 - momentum: 0.000000
2023-10-13 08:24:24,023 epoch 5 - iter 54/275 - loss 0.05731164 - time (sec): 2.41 - samples/sec: 1900.43 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:24:25,225 epoch 5 - iter 81/275 - loss 0.08359211 - time (sec): 3.61 - samples/sec: 1842.00 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:24:26,431 epoch 5 - iter 108/275 - loss 0.07736091 - time (sec): 4.82 - samples/sec: 1829.20 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:24:27,694 epoch 5 - iter 135/275 - loss 0.07574006 - time (sec): 6.08 - samples/sec: 1834.90 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:24:29,106 epoch 5 - iter 162/275 - loss 0.06984948 - time (sec): 7.49 - samples/sec: 1784.72 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:24:30,362 epoch 5 - iter 189/275 - loss 0.06945974 - time (sec): 8.75 - samples/sec: 1786.23 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:24:31,586 epoch 5 - iter 216/275 - loss 0.06498528 - time (sec): 9.97 - samples/sec: 1764.83 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:24:32,793 epoch 5 - iter 243/275 - loss 0.06206434 - time (sec): 11.18 - samples/sec: 1778.79 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:24:34,068 epoch 5 - iter 270/275 - loss 0.05930514 - time (sec): 12.46 - samples/sec: 1784.40 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:24:34,302 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:34,303 EPOCH 5 done: loss 0.0589 - lr: 0.000028
2023-10-13 08:24:34,992 DEV : loss 0.1557360142469406 - f1-score (micro avg) 0.8764
2023-10-13 08:24:34,997 saving best model
2023-10-13 08:24:35,442 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:36,671 epoch 6 - iter 27/275 - loss 0.04213156 - time (sec): 1.23 - samples/sec: 1852.26 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:24:37,953 epoch 6 - iter 54/275 - loss 0.03746027 - time (sec): 2.51 - samples/sec: 1816.43 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:24:39,206 epoch 6 - iter 81/275 - loss 0.04423429 - time (sec): 3.76 - samples/sec: 1804.54 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:24:40,446 epoch 6 - iter 108/275 - loss 0.04302431 - time (sec): 5.00 - samples/sec: 1789.35 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:24:41,727 epoch 6 - iter 135/275 - loss 0.05133329 - time (sec): 6.28 - samples/sec: 1757.54 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:24:42,990 epoch 6 - iter 162/275 - loss 0.05113197 - time (sec): 7.55 - samples/sec: 1765.51 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:24:44,219 epoch 6 - iter 189/275 - loss 0.04766058 - time (sec): 8.78 - samples/sec: 1768.40 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:24:45,401 epoch 6 - iter 216/275 - loss 0.04578779 - time (sec): 9.96 - samples/sec: 1786.38 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:24:46,595 epoch 6 - iter 243/275 - loss 0.04590030 - time (sec): 11.15 - samples/sec: 1802.26 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:24:47,779 epoch 6 - iter 270/275 - loss 0.04431936 - time (sec): 12.34 - samples/sec: 1811.08 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:24:48,013 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:48,014 EPOCH 6 done: loss 0.0439 - lr: 0.000022
2023-10-13 08:24:48,683 DEV : loss 0.1554672122001648 - f1-score (micro avg) 0.8743
2023-10-13 08:24:48,688 ----------------------------------------------------------------------------------------------------
2023-10-13 08:24:49,910 epoch 7 - iter 27/275 - loss 0.00825223 - time (sec): 1.22 - samples/sec: 1803.21 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:24:51,120 epoch 7 - iter 54/275 - loss 0.01703077 - time (sec): 2.43 - samples/sec: 1833.99 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:24:52,305 epoch 7 - iter 81/275 - loss 0.01503006 - time (sec): 3.62 - samples/sec: 1784.71 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:24:53,481 epoch 7 - iter 108/275 - loss 0.01992351 - time (sec): 4.79 - samples/sec: 1859.00 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:24:54,668 epoch 7 - iter 135/275 - loss 0.02086434 - time (sec): 5.98 - samples/sec: 1889.01 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:24:55,847 epoch 7 - iter 162/275 - loss 0.02398405 - time (sec): 7.16 - samples/sec: 1861.64 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:24:57,072 epoch 7 - iter 189/275 - loss 0.02918174 - time (sec): 8.38 - samples/sec: 1867.97 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:24:58,265 epoch 7 - iter 216/275 - loss 0.03306324 - time (sec): 9.58 - samples/sec: 1879.74 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:24:59,466 epoch 7 - iter 243/275 - loss 0.03076299 - time (sec): 10.78 - samples/sec: 1864.56 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:25:00,706 epoch 7 - iter 270/275 - loss 0.02969565 - time (sec): 12.02 - samples/sec: 1859.25 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:25:00,936 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:00,936 EPOCH 7 done: loss 0.0296 - lr: 0.000017
2023-10-13 08:25:01,676 DEV : loss 0.16044297814369202 - f1-score (micro avg) 0.8674
2023-10-13 08:25:01,681 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:02,895 epoch 8 - iter 27/275 - loss 0.01298090 - time (sec): 1.21 - samples/sec: 1819.31 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:25:04,040 epoch 8 - iter 54/275 - loss 0.01025808 - time (sec): 2.36 - samples/sec: 1864.63 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:25:05,158 epoch 8 - iter 81/275 - loss 0.02586707 - time (sec): 3.48 - samples/sec: 1922.68 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:25:06,302 epoch 8 - iter 108/275 - loss 0.02302143 - time (sec): 4.62 - samples/sec: 1893.34 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:25:07,452 epoch 8 - iter 135/275 - loss 0.02504169 - time (sec): 5.77 - samples/sec: 1924.32 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:25:08,584 epoch 8 - iter 162/275 - loss 0.02809093 - time (sec): 6.90 - samples/sec: 1929.19 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:25:09,738 epoch 8 - iter 189/275 - loss 0.02567335 - time (sec): 8.06 - samples/sec: 1969.05 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:25:10,876 epoch 8 - iter 216/275 - loss 0.02470403 - time (sec): 9.19 - samples/sec: 1955.90 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:25:12,026 epoch 8 - iter 243/275 - loss 0.02352710 - time (sec): 10.34 - samples/sec: 1958.69 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:25:13,220 epoch 8 - iter 270/275 - loss 0.02178292 - time (sec): 11.54 - samples/sec: 1936.47 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:25:13,440 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:13,441 EPOCH 8 done: loss 0.0223 - lr: 0.000011
2023-10-13 08:25:14,105 DEV : loss 0.1707383543252945 - f1-score (micro avg) 0.8756
2023-10-13 08:25:14,110 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:15,267 epoch 9 - iter 27/275 - loss 0.00650434 - time (sec): 1.16 - samples/sec: 1932.08 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:25:16,425 epoch 9 - iter 54/275 - loss 0.01111044 - time (sec): 2.31 - samples/sec: 1917.46 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:25:17,602 epoch 9 - iter 81/275 - loss 0.01080575 - time (sec): 3.49 - samples/sec: 1910.45 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:25:18,771 epoch 9 - iter 108/275 - loss 0.01282098 - time (sec): 4.66 - samples/sec: 1925.84 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:25:19,914 epoch 9 - iter 135/275 - loss 0.01581696 - time (sec): 5.80 - samples/sec: 1961.44 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:25:21,172 epoch 9 - iter 162/275 - loss 0.01560980 - time (sec): 7.06 - samples/sec: 1918.53 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:25:22,356 epoch 9 - iter 189/275 - loss 0.01591003 - time (sec): 8.24 - samples/sec: 1898.82 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:25:23,524 epoch 9 - iter 216/275 - loss 0.01508954 - time (sec): 9.41 - samples/sec: 1920.66 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:25:24,711 epoch 9 - iter 243/275 - loss 0.01646518 - time (sec): 10.60 - samples/sec: 1908.94 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:25:25,918 epoch 9 - iter 270/275 - loss 0.01574494 - time (sec): 11.81 - samples/sec: 1893.24 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:25:26,130 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:26,131 EPOCH 9 done: loss 0.0155 - lr: 0.000006
2023-10-13 08:25:26,778 DEV : loss 0.16440145671367645 - f1-score (micro avg) 0.8822
2023-10-13 08:25:26,783 saving best model
2023-10-13 08:25:27,228 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:28,414 epoch 10 - iter 27/275 - loss 0.01136074 - time (sec): 1.18 - samples/sec: 2111.51 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:25:29,580 epoch 10 - iter 54/275 - loss 0.00715528 - time (sec): 2.35 - samples/sec: 1898.66 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:25:30,739 epoch 10 - iter 81/275 - loss 0.01069227 - time (sec): 3.51 - samples/sec: 1922.98 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:25:31,958 epoch 10 - iter 108/275 - loss 0.00857349 - time (sec): 4.73 - samples/sec: 1884.88 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:25:33,136 epoch 10 - iter 135/275 - loss 0.00833031 - time (sec): 5.91 - samples/sec: 1841.81 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:25:34,329 epoch 10 - iter 162/275 - loss 0.00906827 - time (sec): 7.10 - samples/sec: 1870.17 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:25:35,521 epoch 10 - iter 189/275 - loss 0.00820492 - time (sec): 8.29 - samples/sec: 1910.26 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:25:36,693 epoch 10 - iter 216/275 - loss 0.00800912 - time (sec): 9.46 - samples/sec: 1893.25 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:25:37,866 epoch 10 - iter 243/275 - loss 0.01035358 - time (sec): 10.64 - samples/sec: 1892.33 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:25:39,051 epoch 10 - iter 270/275 - loss 0.01116386 - time (sec): 11.82 - samples/sec: 1882.19 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:25:39,268 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:39,268 EPOCH 10 done: loss 0.0111 - lr: 0.000000
2023-10-13 08:25:39,961 DEV : loss 0.16304759681224823 - f1-score (micro avg) 0.8849
2023-10-13 08:25:39,966 saving best model
2023-10-13 08:25:40,728 ----------------------------------------------------------------------------------------------------
2023-10-13 08:25:40,729 Loading model from best epoch ...
2023-10-13 08:25:42,242 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 08:25:42,961
Results:
- F-score (micro) 0.9041
- F-score (macro) 0.8083
- Accuracy 0.8411
By class:
precision recall f1-score support
scope 0.8876 0.8977 0.8927 176
pers 0.9524 0.9375 0.9449 128
work 0.8767 0.8649 0.8707 74
object 1.0000 0.5000 0.6667 2
loc 1.0000 0.5000 0.6667 2
micro avg 0.9077 0.9005 0.9041 382
macro avg 0.9433 0.7400 0.8083 382
weighted avg 0.9084 0.9005 0.9035 382
2023-10-13 08:25:42,961 ----------------------------------------------------------------------------------------------------
|