File size: 23,827 Bytes
1cd0638 |
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 |
2024-03-26 16:13:04,091 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(31103, 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=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Corpus: 758 train + 94 dev + 96 test sentences
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Train: 758 sentences
2024-03-26 16:13:04,092 (train_with_dev=False, train_with_test=False)
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Training Params:
2024-03-26 16:13:04,092 - learning_rate: "3e-05"
2024-03-26 16:13:04,092 - mini_batch_size: "8"
2024-03-26 16:13:04,092 - max_epochs: "10"
2024-03-26 16:13:04,092 - shuffle: "True"
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Plugins:
2024-03-26 16:13:04,092 - TensorboardLogger
2024-03-26 16:13:04,092 - LinearScheduler | warmup_fraction: '0.1'
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Final evaluation on model from best epoch (best-model.pt)
2024-03-26 16:13:04,092 - metric: "('micro avg', 'f1-score')"
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Computation:
2024-03-26 16:13:04,092 - compute on device: cuda:0
2024-03-26 16:13:04,092 - embedding storage: none
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr3e-05-4"
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:04,092 Logging anything other than scalars to TensorBoard is currently not supported.
2024-03-26 16:13:05,441 epoch 1 - iter 9/95 - loss 3.01892317 - time (sec): 1.35 - samples/sec: 2152.42 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:13:06,820 epoch 1 - iter 18/95 - loss 2.94981305 - time (sec): 2.73 - samples/sec: 2022.04 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:13:08,432 epoch 1 - iter 27/95 - loss 2.78986887 - time (sec): 4.34 - samples/sec: 1976.26 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:13:10,392 epoch 1 - iter 36/95 - loss 2.58386486 - time (sec): 6.30 - samples/sec: 1895.02 - lr: 0.000011 - momentum: 0.000000
2024-03-26 16:13:12,239 epoch 1 - iter 45/95 - loss 2.39924465 - time (sec): 8.15 - samples/sec: 1914.24 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:13:14,452 epoch 1 - iter 54/95 - loss 2.24473941 - time (sec): 10.36 - samples/sec: 1848.24 - lr: 0.000017 - momentum: 0.000000
2024-03-26 16:13:16,455 epoch 1 - iter 63/95 - loss 2.10652823 - time (sec): 12.36 - samples/sec: 1828.33 - lr: 0.000020 - momentum: 0.000000
2024-03-26 16:13:17,425 epoch 1 - iter 72/95 - loss 2.02587073 - time (sec): 13.33 - samples/sec: 1873.71 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:13:19,697 epoch 1 - iter 81/95 - loss 1.88802215 - time (sec): 15.60 - samples/sec: 1820.33 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:13:21,027 epoch 1 - iter 90/95 - loss 1.75243499 - time (sec): 16.93 - samples/sec: 1887.35 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:13:22,289 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:22,290 EPOCH 1 done: loss 1.6837 - lr: 0.000028
2024-03-26 16:13:23,178 DEV : loss 0.5122107267379761 - f1-score (micro avg) 0.6199
2024-03-26 16:13:23,180 saving best model
2024-03-26 16:13:23,441 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:25,018 epoch 2 - iter 9/95 - loss 0.64396303 - time (sec): 1.58 - samples/sec: 1827.81 - lr: 0.000030 - momentum: 0.000000
2024-03-26 16:13:26,643 epoch 2 - iter 18/95 - loss 0.55024335 - time (sec): 3.20 - samples/sec: 1930.56 - lr: 0.000029 - momentum: 0.000000
2024-03-26 16:13:28,415 epoch 2 - iter 27/95 - loss 0.49926632 - time (sec): 4.97 - samples/sec: 1901.22 - lr: 0.000029 - momentum: 0.000000
2024-03-26 16:13:30,773 epoch 2 - iter 36/95 - loss 0.43995028 - time (sec): 7.33 - samples/sec: 1779.64 - lr: 0.000029 - momentum: 0.000000
2024-03-26 16:13:32,718 epoch 2 - iter 45/95 - loss 0.42382182 - time (sec): 9.28 - samples/sec: 1778.63 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:13:34,462 epoch 2 - iter 54/95 - loss 0.43455854 - time (sec): 11.02 - samples/sec: 1799.70 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:13:36,855 epoch 2 - iter 63/95 - loss 0.41135255 - time (sec): 13.41 - samples/sec: 1782.58 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:13:38,662 epoch 2 - iter 72/95 - loss 0.41076175 - time (sec): 15.22 - samples/sec: 1776.73 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:13:40,826 epoch 2 - iter 81/95 - loss 0.40019733 - time (sec): 17.38 - samples/sec: 1759.78 - lr: 0.000027 - momentum: 0.000000
2024-03-26 16:13:42,109 epoch 2 - iter 90/95 - loss 0.39608461 - time (sec): 18.67 - samples/sec: 1784.75 - lr: 0.000027 - momentum: 0.000000
2024-03-26 16:13:42,557 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:42,557 EPOCH 2 done: loss 0.3914 - lr: 0.000027
2024-03-26 16:13:43,466 DEV : loss 0.3047449290752411 - f1-score (micro avg) 0.8109
2024-03-26 16:13:43,467 saving best model
2024-03-26 16:13:43,903 ----------------------------------------------------------------------------------------------------
2024-03-26 16:13:45,404 epoch 3 - iter 9/95 - loss 0.23934414 - time (sec): 1.50 - samples/sec: 1767.18 - lr: 0.000026 - momentum: 0.000000
2024-03-26 16:13:47,113 epoch 3 - iter 18/95 - loss 0.21659015 - time (sec): 3.21 - samples/sec: 1742.16 - lr: 0.000026 - momentum: 0.000000
2024-03-26 16:13:48,946 epoch 3 - iter 27/95 - loss 0.21961110 - time (sec): 5.04 - samples/sec: 1766.65 - lr: 0.000026 - momentum: 0.000000
2024-03-26 16:13:50,724 epoch 3 - iter 36/95 - loss 0.22376893 - time (sec): 6.82 - samples/sec: 1770.25 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:13:52,726 epoch 3 - iter 45/95 - loss 0.22130363 - time (sec): 8.82 - samples/sec: 1789.86 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:13:54,955 epoch 3 - iter 54/95 - loss 0.21592911 - time (sec): 11.05 - samples/sec: 1752.80 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:13:56,657 epoch 3 - iter 63/95 - loss 0.20957384 - time (sec): 12.75 - samples/sec: 1754.24 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:13:58,612 epoch 3 - iter 72/95 - loss 0.20499047 - time (sec): 14.71 - samples/sec: 1760.18 - lr: 0.000024 - momentum: 0.000000
2024-03-26 16:14:00,581 epoch 3 - iter 81/95 - loss 0.21084290 - time (sec): 16.68 - samples/sec: 1775.97 - lr: 0.000024 - momentum: 0.000000
2024-03-26 16:14:02,808 epoch 3 - iter 90/95 - loss 0.20345167 - time (sec): 18.90 - samples/sec: 1754.34 - lr: 0.000024 - momentum: 0.000000
2024-03-26 16:14:03,421 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:03,421 EPOCH 3 done: loss 0.2055 - lr: 0.000024
2024-03-26 16:14:04,337 DEV : loss 0.21783055365085602 - f1-score (micro avg) 0.8673
2024-03-26 16:14:04,339 saving best model
2024-03-26 16:14:04,801 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:07,176 epoch 4 - iter 9/95 - loss 0.07517827 - time (sec): 2.38 - samples/sec: 1665.20 - lr: 0.000023 - momentum: 0.000000
2024-03-26 16:14:08,341 epoch 4 - iter 18/95 - loss 0.10000483 - time (sec): 3.54 - samples/sec: 1807.80 - lr: 0.000023 - momentum: 0.000000
2024-03-26 16:14:10,456 epoch 4 - iter 27/95 - loss 0.12477688 - time (sec): 5.66 - samples/sec: 1838.82 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:14:11,938 epoch 4 - iter 36/95 - loss 0.12845343 - time (sec): 7.14 - samples/sec: 1869.30 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:14:13,235 epoch 4 - iter 45/95 - loss 0.12810894 - time (sec): 8.43 - samples/sec: 1902.63 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:14:15,282 epoch 4 - iter 54/95 - loss 0.12646511 - time (sec): 10.48 - samples/sec: 1846.77 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:14:17,528 epoch 4 - iter 63/95 - loss 0.13973987 - time (sec): 12.73 - samples/sec: 1819.20 - lr: 0.000021 - momentum: 0.000000
2024-03-26 16:14:18,968 epoch 4 - iter 72/95 - loss 0.13882561 - time (sec): 14.17 - samples/sec: 1854.83 - lr: 0.000021 - momentum: 0.000000
2024-03-26 16:14:20,553 epoch 4 - iter 81/95 - loss 0.13686782 - time (sec): 15.75 - samples/sec: 1885.58 - lr: 0.000021 - momentum: 0.000000
2024-03-26 16:14:22,160 epoch 4 - iter 90/95 - loss 0.13516261 - time (sec): 17.36 - samples/sec: 1912.90 - lr: 0.000020 - momentum: 0.000000
2024-03-26 16:14:22,783 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:22,783 EPOCH 4 done: loss 0.1357 - lr: 0.000020
2024-03-26 16:14:23,693 DEV : loss 0.19859355688095093 - f1-score (micro avg) 0.9001
2024-03-26 16:14:23,694 saving best model
2024-03-26 16:14:24,137 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:25,337 epoch 5 - iter 9/95 - loss 0.15499173 - time (sec): 1.20 - samples/sec: 2465.78 - lr: 0.000020 - momentum: 0.000000
2024-03-26 16:14:26,763 epoch 5 - iter 18/95 - loss 0.12626124 - time (sec): 2.63 - samples/sec: 2220.05 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:14:28,731 epoch 5 - iter 27/95 - loss 0.11156913 - time (sec): 4.59 - samples/sec: 2001.98 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:14:31,129 epoch 5 - iter 36/95 - loss 0.10681209 - time (sec): 6.99 - samples/sec: 1816.67 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:14:32,338 epoch 5 - iter 45/95 - loss 0.11337595 - time (sec): 8.20 - samples/sec: 1862.46 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:14:34,180 epoch 5 - iter 54/95 - loss 0.10710186 - time (sec): 10.04 - samples/sec: 1906.04 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:14:36,215 epoch 5 - iter 63/95 - loss 0.10095178 - time (sec): 12.08 - samples/sec: 1892.23 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:14:37,462 epoch 5 - iter 72/95 - loss 0.09984606 - time (sec): 13.32 - samples/sec: 1921.32 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:14:39,985 epoch 5 - iter 81/95 - loss 0.09463996 - time (sec): 15.85 - samples/sec: 1853.36 - lr: 0.000017 - momentum: 0.000000
2024-03-26 16:14:42,006 epoch 5 - iter 90/95 - loss 0.09475277 - time (sec): 17.87 - samples/sec: 1832.33 - lr: 0.000017 - momentum: 0.000000
2024-03-26 16:14:42,871 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:42,871 EPOCH 5 done: loss 0.0957 - lr: 0.000017
2024-03-26 16:14:43,890 DEV : loss 0.17372848093509674 - f1-score (micro avg) 0.8924
2024-03-26 16:14:43,891 ----------------------------------------------------------------------------------------------------
2024-03-26 16:14:45,553 epoch 6 - iter 9/95 - loss 0.11813969 - time (sec): 1.66 - samples/sec: 1996.15 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:14:47,611 epoch 6 - iter 18/95 - loss 0.08450061 - time (sec): 3.72 - samples/sec: 1821.92 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:14:49,052 epoch 6 - iter 27/95 - loss 0.08305533 - time (sec): 5.16 - samples/sec: 1851.53 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:14:51,388 epoch 6 - iter 36/95 - loss 0.06803915 - time (sec): 7.50 - samples/sec: 1713.00 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:14:53,168 epoch 6 - iter 45/95 - loss 0.06604557 - time (sec): 9.28 - samples/sec: 1734.19 - lr: 0.000015 - momentum: 0.000000
2024-03-26 16:14:55,645 epoch 6 - iter 54/95 - loss 0.07294541 - time (sec): 11.75 - samples/sec: 1712.88 - lr: 0.000015 - momentum: 0.000000
2024-03-26 16:14:57,157 epoch 6 - iter 63/95 - loss 0.07352466 - time (sec): 13.27 - samples/sec: 1730.50 - lr: 0.000015 - momentum: 0.000000
2024-03-26 16:14:58,699 epoch 6 - iter 72/95 - loss 0.07270595 - time (sec): 14.81 - samples/sec: 1751.86 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:15:00,785 epoch 6 - iter 81/95 - loss 0.07352203 - time (sec): 16.89 - samples/sec: 1745.08 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:15:01,968 epoch 6 - iter 90/95 - loss 0.07693810 - time (sec): 18.08 - samples/sec: 1789.28 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:15:03,303 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:03,303 EPOCH 6 done: loss 0.0749 - lr: 0.000014
2024-03-26 16:15:04,234 DEV : loss 0.17936821281909943 - f1-score (micro avg) 0.9228
2024-03-26 16:15:04,236 saving best model
2024-03-26 16:15:04,682 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:06,057 epoch 7 - iter 9/95 - loss 0.06958458 - time (sec): 1.37 - samples/sec: 2311.25 - lr: 0.000013 - momentum: 0.000000
2024-03-26 16:15:08,176 epoch 7 - iter 18/95 - loss 0.05784086 - time (sec): 3.49 - samples/sec: 1931.12 - lr: 0.000013 - momentum: 0.000000
2024-03-26 16:15:10,073 epoch 7 - iter 27/95 - loss 0.06236455 - time (sec): 5.39 - samples/sec: 1813.90 - lr: 0.000013 - momentum: 0.000000
2024-03-26 16:15:11,375 epoch 7 - iter 36/95 - loss 0.06012303 - time (sec): 6.69 - samples/sec: 1869.77 - lr: 0.000012 - momentum: 0.000000
2024-03-26 16:15:13,075 epoch 7 - iter 45/95 - loss 0.05742602 - time (sec): 8.39 - samples/sec: 1875.36 - lr: 0.000012 - momentum: 0.000000
2024-03-26 16:15:15,276 epoch 7 - iter 54/95 - loss 0.05375127 - time (sec): 10.59 - samples/sec: 1849.97 - lr: 0.000012 - momentum: 0.000000
2024-03-26 16:15:17,316 epoch 7 - iter 63/95 - loss 0.05596495 - time (sec): 12.63 - samples/sec: 1802.49 - lr: 0.000011 - momentum: 0.000000
2024-03-26 16:15:19,447 epoch 7 - iter 72/95 - loss 0.05433191 - time (sec): 14.76 - samples/sec: 1777.64 - lr: 0.000011 - momentum: 0.000000
2024-03-26 16:15:20,963 epoch 7 - iter 81/95 - loss 0.05821444 - time (sec): 16.28 - samples/sec: 1784.00 - lr: 0.000011 - momentum: 0.000000
2024-03-26 16:15:22,840 epoch 7 - iter 90/95 - loss 0.06164903 - time (sec): 18.15 - samples/sec: 1811.68 - lr: 0.000010 - momentum: 0.000000
2024-03-26 16:15:23,531 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:23,531 EPOCH 7 done: loss 0.0607 - lr: 0.000010
2024-03-26 16:15:24,452 DEV : loss 0.17456422746181488 - f1-score (micro avg) 0.931
2024-03-26 16:15:24,455 saving best model
2024-03-26 16:15:24,925 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:26,576 epoch 8 - iter 9/95 - loss 0.03164527 - time (sec): 1.65 - samples/sec: 1783.01 - lr: 0.000010 - momentum: 0.000000
2024-03-26 16:15:28,709 epoch 8 - iter 18/95 - loss 0.03273288 - time (sec): 3.78 - samples/sec: 1752.09 - lr: 0.000010 - momentum: 0.000000
2024-03-26 16:15:30,558 epoch 8 - iter 27/95 - loss 0.04257132 - time (sec): 5.63 - samples/sec: 1723.16 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:15:32,534 epoch 8 - iter 36/95 - loss 0.04208931 - time (sec): 7.61 - samples/sec: 1731.08 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:15:33,565 epoch 8 - iter 45/95 - loss 0.05163225 - time (sec): 8.64 - samples/sec: 1815.79 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:15:35,509 epoch 8 - iter 54/95 - loss 0.05431701 - time (sec): 10.58 - samples/sec: 1804.85 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:15:37,748 epoch 8 - iter 63/95 - loss 0.05448027 - time (sec): 12.82 - samples/sec: 1787.38 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:15:39,958 epoch 8 - iter 72/95 - loss 0.05350915 - time (sec): 15.03 - samples/sec: 1778.34 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:15:41,669 epoch 8 - iter 81/95 - loss 0.05217506 - time (sec): 16.74 - samples/sec: 1782.50 - lr: 0.000007 - momentum: 0.000000
2024-03-26 16:15:43,594 epoch 8 - iter 90/95 - loss 0.04976103 - time (sec): 18.67 - samples/sec: 1778.45 - lr: 0.000007 - momentum: 0.000000
2024-03-26 16:15:44,189 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:44,190 EPOCH 8 done: loss 0.0505 - lr: 0.000007
2024-03-26 16:15:45,127 DEV : loss 0.18435950577259064 - f1-score (micro avg) 0.9326
2024-03-26 16:15:45,128 saving best model
2024-03-26 16:15:45,601 ----------------------------------------------------------------------------------------------------
2024-03-26 16:15:47,129 epoch 9 - iter 9/95 - loss 0.04389027 - time (sec): 1.53 - samples/sec: 2082.70 - lr: 0.000007 - momentum: 0.000000
2024-03-26 16:15:49,410 epoch 9 - iter 18/95 - loss 0.03620731 - time (sec): 3.81 - samples/sec: 1788.41 - lr: 0.000006 - momentum: 0.000000
2024-03-26 16:15:50,997 epoch 9 - iter 27/95 - loss 0.02956550 - time (sec): 5.40 - samples/sec: 1806.40 - lr: 0.000006 - momentum: 0.000000
2024-03-26 16:15:53,280 epoch 9 - iter 36/95 - loss 0.03571516 - time (sec): 7.68 - samples/sec: 1766.87 - lr: 0.000006 - momentum: 0.000000
2024-03-26 16:15:55,165 epoch 9 - iter 45/95 - loss 0.03668108 - time (sec): 9.56 - samples/sec: 1739.74 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:15:56,535 epoch 9 - iter 54/95 - loss 0.03858777 - time (sec): 10.93 - samples/sec: 1784.77 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:15:58,590 epoch 9 - iter 63/95 - loss 0.03601310 - time (sec): 12.99 - samples/sec: 1765.15 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:15:59,803 epoch 9 - iter 72/95 - loss 0.04076328 - time (sec): 14.20 - samples/sec: 1800.00 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:16:02,536 epoch 9 - iter 81/95 - loss 0.03883671 - time (sec): 16.93 - samples/sec: 1753.65 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:16:04,161 epoch 9 - iter 90/95 - loss 0.03642009 - time (sec): 18.56 - samples/sec: 1775.06 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:16:04,819 ----------------------------------------------------------------------------------------------------
2024-03-26 16:16:04,820 EPOCH 9 done: loss 0.0392 - lr: 0.000004
2024-03-26 16:16:05,747 DEV : loss 0.18579983711242676 - f1-score (micro avg) 0.9379
2024-03-26 16:16:05,749 saving best model
2024-03-26 16:16:06,220 ----------------------------------------------------------------------------------------------------
2024-03-26 16:16:08,063 epoch 10 - iter 9/95 - loss 0.03895271 - time (sec): 1.84 - samples/sec: 1684.25 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:16:10,318 epoch 10 - iter 18/95 - loss 0.03731677 - time (sec): 4.10 - samples/sec: 1627.21 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:16:11,737 epoch 10 - iter 27/95 - loss 0.03325541 - time (sec): 5.51 - samples/sec: 1778.77 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:16:13,455 epoch 10 - iter 36/95 - loss 0.03072498 - time (sec): 7.23 - samples/sec: 1824.40 - lr: 0.000002 - momentum: 0.000000
2024-03-26 16:16:14,871 epoch 10 - iter 45/95 - loss 0.03067039 - time (sec): 8.65 - samples/sec: 1856.85 - lr: 0.000002 - momentum: 0.000000
2024-03-26 16:16:15,893 epoch 10 - iter 54/95 - loss 0.02972160 - time (sec): 9.67 - samples/sec: 1929.57 - lr: 0.000002 - momentum: 0.000000
2024-03-26 16:16:17,698 epoch 10 - iter 63/95 - loss 0.02849617 - time (sec): 11.48 - samples/sec: 1904.78 - lr: 0.000001 - momentum: 0.000000
2024-03-26 16:16:19,950 epoch 10 - iter 72/95 - loss 0.03464330 - time (sec): 13.73 - samples/sec: 1857.14 - lr: 0.000001 - momentum: 0.000000
2024-03-26 16:16:21,578 epoch 10 - iter 81/95 - loss 0.03819664 - time (sec): 15.36 - samples/sec: 1850.26 - lr: 0.000001 - momentum: 0.000000
2024-03-26 16:16:23,897 epoch 10 - iter 90/95 - loss 0.03582206 - time (sec): 17.68 - samples/sec: 1838.69 - lr: 0.000000 - momentum: 0.000000
2024-03-26 16:16:25,150 ----------------------------------------------------------------------------------------------------
2024-03-26 16:16:25,150 EPOCH 10 done: loss 0.0380 - lr: 0.000000
2024-03-26 16:16:26,095 DEV : loss 0.19086487591266632 - f1-score (micro avg) 0.9417
2024-03-26 16:16:26,097 saving best model
2024-03-26 16:16:26,869 ----------------------------------------------------------------------------------------------------
2024-03-26 16:16:26,869 Loading model from best epoch ...
2024-03-26 16:16:27,761 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software
2024-03-26 16:16:28,529
Results:
- F-score (micro) 0.9067
- F-score (macro) 0.6885
- Accuracy 0.8329
By class:
precision recall f1-score support
Unternehmen 0.8931 0.8797 0.8864 266
Auslagerung 0.8833 0.9116 0.8972 249
Ort 0.9565 0.9851 0.9706 134
Software 0.0000 0.0000 0.0000 0
micro avg 0.8998 0.9137 0.9067 649
macro avg 0.6832 0.6941 0.6885 649
weighted avg 0.9024 0.9137 0.9079 649
2024-03-26 16:16:28,529 ----------------------------------------------------------------------------------------------------
|