File size: 24,166 Bytes
bd6e7b3 |
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 |
2023-10-18 22:35:32,803 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,803 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 128)
(position_embeddings): Embedding(512, 128)
(token_type_embeddings): Embedding(2, 128)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-1): 2 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=128, out_features=128, bias=True)
(key): Linear(in_features=128, out_features=128, bias=True)
(value): Linear(in_features=128, out_features=128, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=128, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=128, out_features=512, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=512, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=128, out_features=128, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=128, out_features=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-18 22:35:32,803 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,803 MultiCorpus: 5777 train + 722 dev + 723 test sentences
- NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
2023-10-18 22:35:32,803 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,803 Train: 5777 sentences
2023-10-18 22:35:32,803 (train_with_dev=False, train_with_test=False)
2023-10-18 22:35:32,803 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,803 Training Params:
2023-10-18 22:35:32,803 - learning_rate: "5e-05"
2023-10-18 22:35:32,803 - mini_batch_size: "4"
2023-10-18 22:35:32,804 - max_epochs: "10"
2023-10-18 22:35:32,804 - shuffle: "True"
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 Plugins:
2023-10-18 22:35:32,804 - TensorboardLogger
2023-10-18 22:35:32,804 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 22:35:32,804 - metric: "('micro avg', 'f1-score')"
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 Computation:
2023-10-18 22:35:32,804 - compute on device: cuda:0
2023-10-18 22:35:32,804 - embedding storage: none
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:32,804 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 22:35:35,293 epoch 1 - iter 144/1445 - loss 2.86625285 - time (sec): 2.49 - samples/sec: 7167.51 - lr: 0.000005 - momentum: 0.000000
2023-10-18 22:35:37,764 epoch 1 - iter 288/1445 - loss 2.39182936 - time (sec): 4.96 - samples/sec: 7294.65 - lr: 0.000010 - momentum: 0.000000
2023-10-18 22:35:40,191 epoch 1 - iter 432/1445 - loss 1.86271468 - time (sec): 7.39 - samples/sec: 7225.61 - lr: 0.000015 - momentum: 0.000000
2023-10-18 22:35:42,586 epoch 1 - iter 576/1445 - loss 1.48735779 - time (sec): 9.78 - samples/sec: 7273.86 - lr: 0.000020 - momentum: 0.000000
2023-10-18 22:35:44,941 epoch 1 - iter 720/1445 - loss 1.24724928 - time (sec): 12.14 - samples/sec: 7369.69 - lr: 0.000025 - momentum: 0.000000
2023-10-18 22:35:47,348 epoch 1 - iter 864/1445 - loss 1.09616008 - time (sec): 14.54 - samples/sec: 7359.26 - lr: 0.000030 - momentum: 0.000000
2023-10-18 22:35:49,769 epoch 1 - iter 1008/1445 - loss 0.97810336 - time (sec): 16.96 - samples/sec: 7381.19 - lr: 0.000035 - momentum: 0.000000
2023-10-18 22:35:52,205 epoch 1 - iter 1152/1445 - loss 0.89270314 - time (sec): 19.40 - samples/sec: 7340.76 - lr: 0.000040 - momentum: 0.000000
2023-10-18 22:35:54,547 epoch 1 - iter 1296/1445 - loss 0.82673392 - time (sec): 21.74 - samples/sec: 7317.91 - lr: 0.000045 - momentum: 0.000000
2023-10-18 22:35:56,894 epoch 1 - iter 1440/1445 - loss 0.77159928 - time (sec): 24.09 - samples/sec: 7297.89 - lr: 0.000050 - momentum: 0.000000
2023-10-18 22:35:56,976 ----------------------------------------------------------------------------------------------------
2023-10-18 22:35:56,976 EPOCH 1 done: loss 0.7706 - lr: 0.000050
2023-10-18 22:35:58,210 DEV : loss 0.2561441659927368 - f1-score (micro avg) 0.1895
2023-10-18 22:35:58,224 saving best model
2023-10-18 22:35:58,255 ----------------------------------------------------------------------------------------------------
2023-10-18 22:36:00,645 epoch 2 - iter 144/1445 - loss 0.20788149 - time (sec): 2.39 - samples/sec: 7083.52 - lr: 0.000049 - momentum: 0.000000
2023-10-18 22:36:03,009 epoch 2 - iter 288/1445 - loss 0.21650715 - time (sec): 4.75 - samples/sec: 7262.68 - lr: 0.000049 - momentum: 0.000000
2023-10-18 22:36:05,512 epoch 2 - iter 432/1445 - loss 0.20552295 - time (sec): 7.26 - samples/sec: 7238.70 - lr: 0.000048 - momentum: 0.000000
2023-10-18 22:36:07,838 epoch 2 - iter 576/1445 - loss 0.20926347 - time (sec): 9.58 - samples/sec: 7233.85 - lr: 0.000048 - momentum: 0.000000
2023-10-18 22:36:10,169 epoch 2 - iter 720/1445 - loss 0.20584467 - time (sec): 11.91 - samples/sec: 7258.79 - lr: 0.000047 - momentum: 0.000000
2023-10-18 22:36:12,625 epoch 2 - iter 864/1445 - loss 0.20048058 - time (sec): 14.37 - samples/sec: 7265.04 - lr: 0.000047 - momentum: 0.000000
2023-10-18 22:36:15,104 epoch 2 - iter 1008/1445 - loss 0.20118581 - time (sec): 16.85 - samples/sec: 7250.86 - lr: 0.000046 - momentum: 0.000000
2023-10-18 22:36:17,549 epoch 2 - iter 1152/1445 - loss 0.19964640 - time (sec): 19.29 - samples/sec: 7315.99 - lr: 0.000046 - momentum: 0.000000
2023-10-18 22:36:19,981 epoch 2 - iter 1296/1445 - loss 0.19527663 - time (sec): 21.73 - samples/sec: 7309.63 - lr: 0.000045 - momentum: 0.000000
2023-10-18 22:36:22,379 epoch 2 - iter 1440/1445 - loss 0.19935605 - time (sec): 24.12 - samples/sec: 7281.82 - lr: 0.000044 - momentum: 0.000000
2023-10-18 22:36:22,457 ----------------------------------------------------------------------------------------------------
2023-10-18 22:36:22,458 EPOCH 2 done: loss 0.1995 - lr: 0.000044
2023-10-18 22:36:24,553 DEV : loss 0.2152344286441803 - f1-score (micro avg) 0.3519
2023-10-18 22:36:24,567 saving best model
2023-10-18 22:36:24,602 ----------------------------------------------------------------------------------------------------
2023-10-18 22:36:26,941 epoch 3 - iter 144/1445 - loss 0.18735705 - time (sec): 2.34 - samples/sec: 7338.15 - lr: 0.000044 - momentum: 0.000000
2023-10-18 22:36:29,358 epoch 3 - iter 288/1445 - loss 0.16728570 - time (sec): 4.76 - samples/sec: 7410.31 - lr: 0.000043 - momentum: 0.000000
2023-10-18 22:36:31,777 epoch 3 - iter 432/1445 - loss 0.16394077 - time (sec): 7.17 - samples/sec: 7362.02 - lr: 0.000043 - momentum: 0.000000
2023-10-18 22:36:34,039 epoch 3 - iter 576/1445 - loss 0.16749371 - time (sec): 9.44 - samples/sec: 7493.93 - lr: 0.000042 - momentum: 0.000000
2023-10-18 22:36:36,322 epoch 3 - iter 720/1445 - loss 0.16886016 - time (sec): 11.72 - samples/sec: 7376.05 - lr: 0.000042 - momentum: 0.000000
2023-10-18 22:36:38,727 epoch 3 - iter 864/1445 - loss 0.16886698 - time (sec): 14.12 - samples/sec: 7388.63 - lr: 0.000041 - momentum: 0.000000
2023-10-18 22:36:41,158 epoch 3 - iter 1008/1445 - loss 0.16881585 - time (sec): 16.55 - samples/sec: 7410.17 - lr: 0.000041 - momentum: 0.000000
2023-10-18 22:36:43,478 epoch 3 - iter 1152/1445 - loss 0.16991782 - time (sec): 18.87 - samples/sec: 7372.83 - lr: 0.000040 - momentum: 0.000000
2023-10-18 22:36:45,934 epoch 3 - iter 1296/1445 - loss 0.17156863 - time (sec): 21.33 - samples/sec: 7402.98 - lr: 0.000039 - momentum: 0.000000
2023-10-18 22:36:48,481 epoch 3 - iter 1440/1445 - loss 0.16631620 - time (sec): 23.88 - samples/sec: 7358.61 - lr: 0.000039 - momentum: 0.000000
2023-10-18 22:36:48,556 ----------------------------------------------------------------------------------------------------
2023-10-18 22:36:48,557 EPOCH 3 done: loss 0.1663 - lr: 0.000039
2023-10-18 22:36:50,325 DEV : loss 0.2009856253862381 - f1-score (micro avg) 0.4532
2023-10-18 22:36:50,339 saving best model
2023-10-18 22:36:50,375 ----------------------------------------------------------------------------------------------------
2023-10-18 22:36:52,749 epoch 4 - iter 144/1445 - loss 0.15362789 - time (sec): 2.37 - samples/sec: 7481.75 - lr: 0.000038 - momentum: 0.000000
2023-10-18 22:36:55,135 epoch 4 - iter 288/1445 - loss 0.15463328 - time (sec): 4.76 - samples/sec: 7160.04 - lr: 0.000038 - momentum: 0.000000
2023-10-18 22:36:57,639 epoch 4 - iter 432/1445 - loss 0.15709099 - time (sec): 7.26 - samples/sec: 7172.16 - lr: 0.000037 - momentum: 0.000000
2023-10-18 22:37:00,051 epoch 4 - iter 576/1445 - loss 0.14884886 - time (sec): 9.68 - samples/sec: 7236.95 - lr: 0.000037 - momentum: 0.000000
2023-10-18 22:37:02,563 epoch 4 - iter 720/1445 - loss 0.14765128 - time (sec): 12.19 - samples/sec: 7264.09 - lr: 0.000036 - momentum: 0.000000
2023-10-18 22:37:04,985 epoch 4 - iter 864/1445 - loss 0.14686407 - time (sec): 14.61 - samples/sec: 7275.14 - lr: 0.000036 - momentum: 0.000000
2023-10-18 22:37:07,366 epoch 4 - iter 1008/1445 - loss 0.14711603 - time (sec): 16.99 - samples/sec: 7239.14 - lr: 0.000035 - momentum: 0.000000
2023-10-18 22:37:09,825 epoch 4 - iter 1152/1445 - loss 0.14929145 - time (sec): 19.45 - samples/sec: 7229.84 - lr: 0.000034 - momentum: 0.000000
2023-10-18 22:37:12,202 epoch 4 - iter 1296/1445 - loss 0.14891095 - time (sec): 21.83 - samples/sec: 7256.22 - lr: 0.000034 - momentum: 0.000000
2023-10-18 22:37:14,697 epoch 4 - iter 1440/1445 - loss 0.14884730 - time (sec): 24.32 - samples/sec: 7222.75 - lr: 0.000033 - momentum: 0.000000
2023-10-18 22:37:14,778 ----------------------------------------------------------------------------------------------------
2023-10-18 22:37:14,779 EPOCH 4 done: loss 0.1487 - lr: 0.000033
2023-10-18 22:37:16,559 DEV : loss 0.18706543743610382 - f1-score (micro avg) 0.5193
2023-10-18 22:37:16,573 saving best model
2023-10-18 22:37:16,608 ----------------------------------------------------------------------------------------------------
2023-10-18 22:37:18,997 epoch 5 - iter 144/1445 - loss 0.13686569 - time (sec): 2.39 - samples/sec: 7121.40 - lr: 0.000033 - momentum: 0.000000
2023-10-18 22:37:21,388 epoch 5 - iter 288/1445 - loss 0.12889149 - time (sec): 4.78 - samples/sec: 7193.65 - lr: 0.000032 - momentum: 0.000000
2023-10-18 22:37:23,809 epoch 5 - iter 432/1445 - loss 0.13048179 - time (sec): 7.20 - samples/sec: 7178.96 - lr: 0.000032 - momentum: 0.000000
2023-10-18 22:37:26,189 epoch 5 - iter 576/1445 - loss 0.13492520 - time (sec): 9.58 - samples/sec: 7161.88 - lr: 0.000031 - momentum: 0.000000
2023-10-18 22:37:28,631 epoch 5 - iter 720/1445 - loss 0.13512870 - time (sec): 12.02 - samples/sec: 7268.82 - lr: 0.000031 - momentum: 0.000000
2023-10-18 22:37:31,049 epoch 5 - iter 864/1445 - loss 0.13317304 - time (sec): 14.44 - samples/sec: 7327.92 - lr: 0.000030 - momentum: 0.000000
2023-10-18 22:37:33,468 epoch 5 - iter 1008/1445 - loss 0.13354051 - time (sec): 16.86 - samples/sec: 7313.61 - lr: 0.000029 - momentum: 0.000000
2023-10-18 22:37:35,963 epoch 5 - iter 1152/1445 - loss 0.13644795 - time (sec): 19.35 - samples/sec: 7314.08 - lr: 0.000029 - momentum: 0.000000
2023-10-18 22:37:38,334 epoch 5 - iter 1296/1445 - loss 0.13740177 - time (sec): 21.72 - samples/sec: 7269.49 - lr: 0.000028 - momentum: 0.000000
2023-10-18 22:37:40,700 epoch 5 - iter 1440/1445 - loss 0.13509823 - time (sec): 24.09 - samples/sec: 7284.09 - lr: 0.000028 - momentum: 0.000000
2023-10-18 22:37:40,787 ----------------------------------------------------------------------------------------------------
2023-10-18 22:37:40,788 EPOCH 5 done: loss 0.1353 - lr: 0.000028
2023-10-18 22:37:42,905 DEV : loss 0.19456517696380615 - f1-score (micro avg) 0.5458
2023-10-18 22:37:42,919 saving best model
2023-10-18 22:37:42,954 ----------------------------------------------------------------------------------------------------
2023-10-18 22:37:45,320 epoch 6 - iter 144/1445 - loss 0.11571536 - time (sec): 2.37 - samples/sec: 7102.98 - lr: 0.000027 - momentum: 0.000000
2023-10-18 22:37:47,734 epoch 6 - iter 288/1445 - loss 0.12384211 - time (sec): 4.78 - samples/sec: 7258.64 - lr: 0.000027 - momentum: 0.000000
2023-10-18 22:37:50,160 epoch 6 - iter 432/1445 - loss 0.13225920 - time (sec): 7.21 - samples/sec: 7253.70 - lr: 0.000026 - momentum: 0.000000
2023-10-18 22:37:52,606 epoch 6 - iter 576/1445 - loss 0.12932638 - time (sec): 9.65 - samples/sec: 7336.81 - lr: 0.000026 - momentum: 0.000000
2023-10-18 22:37:55,094 epoch 6 - iter 720/1445 - loss 0.13232474 - time (sec): 12.14 - samples/sec: 7421.31 - lr: 0.000025 - momentum: 0.000000
2023-10-18 22:37:57,438 epoch 6 - iter 864/1445 - loss 0.13260978 - time (sec): 14.48 - samples/sec: 7330.43 - lr: 0.000024 - momentum: 0.000000
2023-10-18 22:37:59,561 epoch 6 - iter 1008/1445 - loss 0.13037248 - time (sec): 16.61 - samples/sec: 7438.74 - lr: 0.000024 - momentum: 0.000000
2023-10-18 22:38:01,644 epoch 6 - iter 1152/1445 - loss 0.12744445 - time (sec): 18.69 - samples/sec: 7497.79 - lr: 0.000023 - momentum: 0.000000
2023-10-18 22:38:03,752 epoch 6 - iter 1296/1445 - loss 0.12733070 - time (sec): 20.80 - samples/sec: 7576.59 - lr: 0.000023 - momentum: 0.000000
2023-10-18 22:38:05,837 epoch 6 - iter 1440/1445 - loss 0.12752773 - time (sec): 22.88 - samples/sec: 7676.69 - lr: 0.000022 - momentum: 0.000000
2023-10-18 22:38:05,905 ----------------------------------------------------------------------------------------------------
2023-10-18 22:38:05,905 EPOCH 6 done: loss 0.1276 - lr: 0.000022
2023-10-18 22:38:07,688 DEV : loss 0.17982900142669678 - f1-score (micro avg) 0.5598
2023-10-18 22:38:07,703 saving best model
2023-10-18 22:38:07,740 ----------------------------------------------------------------------------------------------------
2023-10-18 22:38:09,970 epoch 7 - iter 144/1445 - loss 0.12277903 - time (sec): 2.23 - samples/sec: 8485.81 - lr: 0.000022 - momentum: 0.000000
2023-10-18 22:38:12,362 epoch 7 - iter 288/1445 - loss 0.12334114 - time (sec): 4.62 - samples/sec: 8187.85 - lr: 0.000021 - momentum: 0.000000
2023-10-18 22:38:14,733 epoch 7 - iter 432/1445 - loss 0.12246111 - time (sec): 6.99 - samples/sec: 7768.69 - lr: 0.000021 - momentum: 0.000000
2023-10-18 22:38:17,119 epoch 7 - iter 576/1445 - loss 0.11964029 - time (sec): 9.38 - samples/sec: 7702.34 - lr: 0.000020 - momentum: 0.000000
2023-10-18 22:38:19,570 epoch 7 - iter 720/1445 - loss 0.12254055 - time (sec): 11.83 - samples/sec: 7662.96 - lr: 0.000019 - momentum: 0.000000
2023-10-18 22:38:21,895 epoch 7 - iter 864/1445 - loss 0.12133982 - time (sec): 14.15 - samples/sec: 7530.25 - lr: 0.000019 - momentum: 0.000000
2023-10-18 22:38:24,278 epoch 7 - iter 1008/1445 - loss 0.12022597 - time (sec): 16.54 - samples/sec: 7530.13 - lr: 0.000018 - momentum: 0.000000
2023-10-18 22:38:26,625 epoch 7 - iter 1152/1445 - loss 0.11991213 - time (sec): 18.88 - samples/sec: 7461.88 - lr: 0.000018 - momentum: 0.000000
2023-10-18 22:38:29,015 epoch 7 - iter 1296/1445 - loss 0.12152671 - time (sec): 21.27 - samples/sec: 7436.68 - lr: 0.000017 - momentum: 0.000000
2023-10-18 22:38:31,393 epoch 7 - iter 1440/1445 - loss 0.11965156 - time (sec): 23.65 - samples/sec: 7414.95 - lr: 0.000017 - momentum: 0.000000
2023-10-18 22:38:31,479 ----------------------------------------------------------------------------------------------------
2023-10-18 22:38:31,479 EPOCH 7 done: loss 0.1195 - lr: 0.000017
2023-10-18 22:38:33,243 DEV : loss 0.17696666717529297 - f1-score (micro avg) 0.5872
2023-10-18 22:38:33,257 saving best model
2023-10-18 22:38:33,291 ----------------------------------------------------------------------------------------------------
2023-10-18 22:38:35,714 epoch 8 - iter 144/1445 - loss 0.11113135 - time (sec): 2.42 - samples/sec: 7759.48 - lr: 0.000016 - momentum: 0.000000
2023-10-18 22:38:38,069 epoch 8 - iter 288/1445 - loss 0.11518653 - time (sec): 4.78 - samples/sec: 7472.68 - lr: 0.000016 - momentum: 0.000000
2023-10-18 22:38:40,463 epoch 8 - iter 432/1445 - loss 0.11080588 - time (sec): 7.17 - samples/sec: 7551.22 - lr: 0.000015 - momentum: 0.000000
2023-10-18 22:38:42,881 epoch 8 - iter 576/1445 - loss 0.11458603 - time (sec): 9.59 - samples/sec: 7566.20 - lr: 0.000014 - momentum: 0.000000
2023-10-18 22:38:45,211 epoch 8 - iter 720/1445 - loss 0.11325887 - time (sec): 11.92 - samples/sec: 7521.84 - lr: 0.000014 - momentum: 0.000000
2023-10-18 22:38:47,586 epoch 8 - iter 864/1445 - loss 0.11535133 - time (sec): 14.29 - samples/sec: 7499.72 - lr: 0.000013 - momentum: 0.000000
2023-10-18 22:38:49,927 epoch 8 - iter 1008/1445 - loss 0.11466974 - time (sec): 16.64 - samples/sec: 7399.78 - lr: 0.000013 - momentum: 0.000000
2023-10-18 22:38:52,351 epoch 8 - iter 1152/1445 - loss 0.11643710 - time (sec): 19.06 - samples/sec: 7432.46 - lr: 0.000012 - momentum: 0.000000
2023-10-18 22:38:54,772 epoch 8 - iter 1296/1445 - loss 0.11547388 - time (sec): 21.48 - samples/sec: 7376.25 - lr: 0.000012 - momentum: 0.000000
2023-10-18 22:38:57,156 epoch 8 - iter 1440/1445 - loss 0.11315324 - time (sec): 23.86 - samples/sec: 7365.81 - lr: 0.000011 - momentum: 0.000000
2023-10-18 22:38:57,228 ----------------------------------------------------------------------------------------------------
2023-10-18 22:38:57,228 EPOCH 8 done: loss 0.1134 - lr: 0.000011
2023-10-18 22:38:59,325 DEV : loss 0.18520388007164001 - f1-score (micro avg) 0.5793
2023-10-18 22:38:59,341 ----------------------------------------------------------------------------------------------------
2023-10-18 22:39:01,877 epoch 9 - iter 144/1445 - loss 0.10887282 - time (sec): 2.54 - samples/sec: 7397.71 - lr: 0.000011 - momentum: 0.000000
2023-10-18 22:39:04,328 epoch 9 - iter 288/1445 - loss 0.11482268 - time (sec): 4.99 - samples/sec: 7375.84 - lr: 0.000010 - momentum: 0.000000
2023-10-18 22:39:06,789 epoch 9 - iter 432/1445 - loss 0.11164932 - time (sec): 7.45 - samples/sec: 7362.59 - lr: 0.000009 - momentum: 0.000000
2023-10-18 22:39:09,250 epoch 9 - iter 576/1445 - loss 0.11268148 - time (sec): 9.91 - samples/sec: 7377.27 - lr: 0.000009 - momentum: 0.000000
2023-10-18 22:39:11,620 epoch 9 - iter 720/1445 - loss 0.11314413 - time (sec): 12.28 - samples/sec: 7299.42 - lr: 0.000008 - momentum: 0.000000
2023-10-18 22:39:14,036 epoch 9 - iter 864/1445 - loss 0.11255961 - time (sec): 14.69 - samples/sec: 7329.47 - lr: 0.000008 - momentum: 0.000000
2023-10-18 22:39:16,437 epoch 9 - iter 1008/1445 - loss 0.11294305 - time (sec): 17.10 - samples/sec: 7310.68 - lr: 0.000007 - momentum: 0.000000
2023-10-18 22:39:18,815 epoch 9 - iter 1152/1445 - loss 0.11188029 - time (sec): 19.47 - samples/sec: 7268.82 - lr: 0.000007 - momentum: 0.000000
2023-10-18 22:39:21,293 epoch 9 - iter 1296/1445 - loss 0.10885370 - time (sec): 21.95 - samples/sec: 7270.80 - lr: 0.000006 - momentum: 0.000000
2023-10-18 22:39:23,515 epoch 9 - iter 1440/1445 - loss 0.10971729 - time (sec): 24.17 - samples/sec: 7267.20 - lr: 0.000006 - momentum: 0.000000
2023-10-18 22:39:23,585 ----------------------------------------------------------------------------------------------------
2023-10-18 22:39:23,586 EPOCH 9 done: loss 0.1097 - lr: 0.000006
2023-10-18 22:39:25,383 DEV : loss 0.1853523552417755 - f1-score (micro avg) 0.5984
2023-10-18 22:39:25,398 saving best model
2023-10-18 22:39:25,433 ----------------------------------------------------------------------------------------------------
2023-10-18 22:39:27,799 epoch 10 - iter 144/1445 - loss 0.09962782 - time (sec): 2.37 - samples/sec: 7376.05 - lr: 0.000005 - momentum: 0.000000
2023-10-18 22:39:30,273 epoch 10 - iter 288/1445 - loss 0.08889531 - time (sec): 4.84 - samples/sec: 7309.52 - lr: 0.000004 - momentum: 0.000000
2023-10-18 22:39:32,650 epoch 10 - iter 432/1445 - loss 0.09811058 - time (sec): 7.22 - samples/sec: 7371.91 - lr: 0.000004 - momentum: 0.000000
2023-10-18 22:39:35,027 epoch 10 - iter 576/1445 - loss 0.10124252 - time (sec): 9.59 - samples/sec: 7326.03 - lr: 0.000003 - momentum: 0.000000
2023-10-18 22:39:37,386 epoch 10 - iter 720/1445 - loss 0.10043443 - time (sec): 11.95 - samples/sec: 7433.53 - lr: 0.000003 - momentum: 0.000000
2023-10-18 22:39:39,866 epoch 10 - iter 864/1445 - loss 0.10093884 - time (sec): 14.43 - samples/sec: 7359.99 - lr: 0.000002 - momentum: 0.000000
2023-10-18 22:39:42,282 epoch 10 - iter 1008/1445 - loss 0.10082663 - time (sec): 16.85 - samples/sec: 7272.67 - lr: 0.000002 - momentum: 0.000000
2023-10-18 22:39:44,701 epoch 10 - iter 1152/1445 - loss 0.10177923 - time (sec): 19.27 - samples/sec: 7310.18 - lr: 0.000001 - momentum: 0.000000
2023-10-18 22:39:47,102 epoch 10 - iter 1296/1445 - loss 0.10379308 - time (sec): 21.67 - samples/sec: 7271.08 - lr: 0.000001 - momentum: 0.000000
2023-10-18 22:39:49,469 epoch 10 - iter 1440/1445 - loss 0.10584891 - time (sec): 24.04 - samples/sec: 7302.09 - lr: 0.000000 - momentum: 0.000000
2023-10-18 22:39:49,547 ----------------------------------------------------------------------------------------------------
2023-10-18 22:39:49,547 EPOCH 10 done: loss 0.1055 - lr: 0.000000
2023-10-18 22:39:51,338 DEV : loss 0.18715591728687286 - f1-score (micro avg) 0.5955
2023-10-18 22:39:51,383 ----------------------------------------------------------------------------------------------------
2023-10-18 22:39:51,383 Loading model from best epoch ...
2023-10-18 22:39:51,466 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-18 22:39:52,786
Results:
- F-score (micro) 0.6129
- F-score (macro) 0.4332
- Accuracy 0.4549
By class:
precision recall f1-score support
LOC 0.6827 0.7140 0.6980 458
PER 0.6284 0.5332 0.5769 482
ORG 0.0833 0.0145 0.0247 69
micro avg 0.6500 0.5798 0.6129 1009
macro avg 0.4648 0.4206 0.4332 1009
weighted avg 0.6157 0.5798 0.5941 1009
2023-10-18 22:39:52,786 ----------------------------------------------------------------------------------------------------
|