File size: 23,981 Bytes
96bd014 |
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 |
2023-10-19 23:51:49,700 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 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=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 MultiCorpus: 1166 train + 165 dev + 415 test sentences
- NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 Train: 1166 sentences
2023-10-19 23:51:49,701 (train_with_dev=False, train_with_test=False)
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 Training Params:
2023-10-19 23:51:49,701 - learning_rate: "3e-05"
2023-10-19 23:51:49,701 - mini_batch_size: "8"
2023-10-19 23:51:49,701 - max_epochs: "10"
2023-10-19 23:51:49,701 - shuffle: "True"
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 Plugins:
2023-10-19 23:51:49,701 - TensorboardLogger
2023-10-19 23:51:49,701 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 23:51:49,701 - metric: "('micro avg', 'f1-score')"
2023-10-19 23:51:49,701 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,701 Computation:
2023-10-19 23:51:49,701 - compute on device: cuda:0
2023-10-19 23:51:49,701 - embedding storage: none
2023-10-19 23:51:49,702 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,702 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-19 23:51:49,702 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,702 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:49,702 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 23:51:50,088 epoch 1 - iter 14/146 - loss 3.34803276 - time (sec): 0.39 - samples/sec: 11886.51 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:51:50,441 epoch 1 - iter 28/146 - loss 3.24426997 - time (sec): 0.74 - samples/sec: 11746.87 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:51:50,828 epoch 1 - iter 42/146 - loss 3.17722726 - time (sec): 1.13 - samples/sec: 11334.14 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:51:51,227 epoch 1 - iter 56/146 - loss 3.06383245 - time (sec): 1.52 - samples/sec: 11127.79 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:51:51,611 epoch 1 - iter 70/146 - loss 2.97900869 - time (sec): 1.91 - samples/sec: 11251.57 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:51:51,985 epoch 1 - iter 84/146 - loss 2.86475164 - time (sec): 2.28 - samples/sec: 11411.19 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:51:52,374 epoch 1 - iter 98/146 - loss 2.76952224 - time (sec): 2.67 - samples/sec: 11378.82 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:51:52,748 epoch 1 - iter 112/146 - loss 2.62555563 - time (sec): 3.05 - samples/sec: 11482.65 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:51:53,129 epoch 1 - iter 126/146 - loss 2.50608976 - time (sec): 3.43 - samples/sec: 11324.46 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:51:53,511 epoch 1 - iter 140/146 - loss 2.38598195 - time (sec): 3.81 - samples/sec: 11288.10 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:51:53,672 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:53,672 EPOCH 1 done: loss 2.3402 - lr: 0.000029
2023-10-19 23:51:53,941 DEV : loss 0.4833422005176544 - f1-score (micro avg) 0.0
2023-10-19 23:51:53,945 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:54,358 epoch 2 - iter 14/146 - loss 1.00186629 - time (sec): 0.41 - samples/sec: 12089.20 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:51:54,720 epoch 2 - iter 28/146 - loss 0.89014949 - time (sec): 0.78 - samples/sec: 11314.02 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:51:55,079 epoch 2 - iter 42/146 - loss 0.85331323 - time (sec): 1.13 - samples/sec: 11572.81 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:51:55,473 epoch 2 - iter 56/146 - loss 0.82062153 - time (sec): 1.53 - samples/sec: 11530.13 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:51:55,826 epoch 2 - iter 70/146 - loss 0.80036944 - time (sec): 1.88 - samples/sec: 11591.03 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:51:56,200 epoch 2 - iter 84/146 - loss 0.78167558 - time (sec): 2.25 - samples/sec: 11607.64 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:51:56,541 epoch 2 - iter 98/146 - loss 0.73470966 - time (sec): 2.60 - samples/sec: 11570.72 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:51:56,922 epoch 2 - iter 112/146 - loss 0.71674782 - time (sec): 2.98 - samples/sec: 11688.35 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:51:57,290 epoch 2 - iter 126/146 - loss 0.70473681 - time (sec): 3.35 - samples/sec: 11606.83 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:51:57,656 epoch 2 - iter 140/146 - loss 0.70770530 - time (sec): 3.71 - samples/sec: 11598.03 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:51:57,796 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:57,796 EPOCH 2 done: loss 0.7028 - lr: 0.000027
2023-10-19 23:51:58,422 DEV : loss 0.44611138105392456 - f1-score (micro avg) 0.0
2023-10-19 23:51:58,426 ----------------------------------------------------------------------------------------------------
2023-10-19 23:51:58,949 epoch 3 - iter 14/146 - loss 0.56843240 - time (sec): 0.52 - samples/sec: 7685.20 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:51:59,330 epoch 3 - iter 28/146 - loss 0.55665083 - time (sec): 0.90 - samples/sec: 9273.02 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:51:59,705 epoch 3 - iter 42/146 - loss 0.56927226 - time (sec): 1.28 - samples/sec: 10481.34 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:52:00,049 epoch 3 - iter 56/146 - loss 0.56146026 - time (sec): 1.62 - samples/sec: 10990.27 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:52:00,407 epoch 3 - iter 70/146 - loss 0.56962488 - time (sec): 1.98 - samples/sec: 11026.51 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:52:00,760 epoch 3 - iter 84/146 - loss 0.55978929 - time (sec): 2.33 - samples/sec: 11177.29 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:52:01,117 epoch 3 - iter 98/146 - loss 0.55736095 - time (sec): 2.69 - samples/sec: 11279.49 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:52:01,491 epoch 3 - iter 112/146 - loss 0.57916592 - time (sec): 3.06 - samples/sec: 11199.25 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:52:01,868 epoch 3 - iter 126/146 - loss 0.60494417 - time (sec): 3.44 - samples/sec: 11332.47 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:52:02,213 epoch 3 - iter 140/146 - loss 0.59677716 - time (sec): 3.79 - samples/sec: 11354.76 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:52:02,351 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:02,351 EPOCH 3 done: loss 0.5947 - lr: 0.000024
2023-10-19 23:52:02,980 DEV : loss 0.3864370584487915 - f1-score (micro avg) 0.0
2023-10-19 23:52:02,984 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:03,349 epoch 4 - iter 14/146 - loss 0.51833400 - time (sec): 0.36 - samples/sec: 11745.60 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:52:03,714 epoch 4 - iter 28/146 - loss 0.54395629 - time (sec): 0.73 - samples/sec: 11621.06 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:52:04,082 epoch 4 - iter 42/146 - loss 0.56680138 - time (sec): 1.10 - samples/sec: 10967.22 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:52:04,447 epoch 4 - iter 56/146 - loss 0.57277620 - time (sec): 1.46 - samples/sec: 11339.24 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:52:04,825 epoch 4 - iter 70/146 - loss 0.63447119 - time (sec): 1.84 - samples/sec: 11379.23 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:52:05,194 epoch 4 - iter 84/146 - loss 0.61181656 - time (sec): 2.21 - samples/sec: 11408.00 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:52:05,552 epoch 4 - iter 98/146 - loss 0.58758215 - time (sec): 2.57 - samples/sec: 11328.25 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:52:05,957 epoch 4 - iter 112/146 - loss 0.57376561 - time (sec): 2.97 - samples/sec: 11463.68 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:52:06,331 epoch 4 - iter 126/146 - loss 0.57197538 - time (sec): 3.35 - samples/sec: 11366.94 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:52:06,689 epoch 4 - iter 140/146 - loss 0.57285088 - time (sec): 3.70 - samples/sec: 11470.39 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:52:06,850 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:06,850 EPOCH 4 done: loss 0.5641 - lr: 0.000020
2023-10-19 23:52:07,480 DEV : loss 0.35983359813690186 - f1-score (micro avg) 0.0
2023-10-19 23:52:07,485 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:07,886 epoch 5 - iter 14/146 - loss 0.72697613 - time (sec): 0.40 - samples/sec: 11787.78 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:52:08,229 epoch 5 - iter 28/146 - loss 0.67048227 - time (sec): 0.74 - samples/sec: 11342.21 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:52:08,606 epoch 5 - iter 42/146 - loss 0.60440180 - time (sec): 1.12 - samples/sec: 11690.40 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:52:08,982 epoch 5 - iter 56/146 - loss 0.56150800 - time (sec): 1.50 - samples/sec: 11649.36 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:52:09,373 epoch 5 - iter 70/146 - loss 0.52666893 - time (sec): 1.89 - samples/sec: 11755.06 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:52:09,725 epoch 5 - iter 84/146 - loss 0.51426781 - time (sec): 2.24 - samples/sec: 11594.14 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:52:10,084 epoch 5 - iter 98/146 - loss 0.50838649 - time (sec): 2.60 - samples/sec: 11665.32 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:52:10,429 epoch 5 - iter 112/146 - loss 0.50712580 - time (sec): 2.94 - samples/sec: 11427.86 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:52:10,808 epoch 5 - iter 126/146 - loss 0.52046347 - time (sec): 3.32 - samples/sec: 11439.33 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:52:11,153 epoch 5 - iter 140/146 - loss 0.51748259 - time (sec): 3.67 - samples/sec: 11606.10 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:52:11,300 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:11,300 EPOCH 5 done: loss 0.5165 - lr: 0.000017
2023-10-19 23:52:11,942 DEV : loss 0.3400147259235382 - f1-score (micro avg) 0.0239
2023-10-19 23:52:11,946 saving best model
2023-10-19 23:52:11,974 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:12,348 epoch 6 - iter 14/146 - loss 0.71859012 - time (sec): 0.37 - samples/sec: 11707.07 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:52:12,718 epoch 6 - iter 28/146 - loss 0.56899183 - time (sec): 0.74 - samples/sec: 11591.23 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:52:13,066 epoch 6 - iter 42/146 - loss 0.51990607 - time (sec): 1.09 - samples/sec: 11725.64 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:52:13,421 epoch 6 - iter 56/146 - loss 0.53360635 - time (sec): 1.45 - samples/sec: 11407.04 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:52:13,794 epoch 6 - iter 70/146 - loss 0.51135818 - time (sec): 1.82 - samples/sec: 11590.61 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:52:14,173 epoch 6 - iter 84/146 - loss 0.52944252 - time (sec): 2.20 - samples/sec: 11857.16 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:52:14,529 epoch 6 - iter 98/146 - loss 0.51191496 - time (sec): 2.55 - samples/sec: 11896.68 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:52:14,897 epoch 6 - iter 112/146 - loss 0.50006322 - time (sec): 2.92 - samples/sec: 11820.64 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:52:15,263 epoch 6 - iter 126/146 - loss 0.49173276 - time (sec): 3.29 - samples/sec: 11820.55 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:52:15,633 epoch 6 - iter 140/146 - loss 0.48245262 - time (sec): 3.66 - samples/sec: 11790.09 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:52:15,786 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:15,786 EPOCH 6 done: loss 0.4839 - lr: 0.000014
2023-10-19 23:52:16,429 DEV : loss 0.330739289522171 - f1-score (micro avg) 0.0578
2023-10-19 23:52:16,433 saving best model
2023-10-19 23:52:16,467 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:16,808 epoch 7 - iter 14/146 - loss 0.39481050 - time (sec): 0.34 - samples/sec: 10822.62 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:52:17,182 epoch 7 - iter 28/146 - loss 0.37652749 - time (sec): 0.71 - samples/sec: 10971.66 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:52:17,551 epoch 7 - iter 42/146 - loss 0.41835909 - time (sec): 1.08 - samples/sec: 11195.45 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:52:17,895 epoch 7 - iter 56/146 - loss 0.42637595 - time (sec): 1.43 - samples/sec: 10986.57 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:52:18,285 epoch 7 - iter 70/146 - loss 0.46759904 - time (sec): 1.82 - samples/sec: 11177.84 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:52:18,641 epoch 7 - iter 84/146 - loss 0.47208007 - time (sec): 2.17 - samples/sec: 11097.59 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:52:19,156 epoch 7 - iter 98/146 - loss 0.46177264 - time (sec): 2.69 - samples/sec: 10435.71 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:52:19,543 epoch 7 - iter 112/146 - loss 0.47139861 - time (sec): 3.07 - samples/sec: 10770.10 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:52:19,935 epoch 7 - iter 126/146 - loss 0.47595257 - time (sec): 3.47 - samples/sec: 10955.23 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:52:20,297 epoch 7 - iter 140/146 - loss 0.46725905 - time (sec): 3.83 - samples/sec: 11088.10 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:52:20,466 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:20,466 EPOCH 7 done: loss 0.4635 - lr: 0.000010
2023-10-19 23:52:21,114 DEV : loss 0.32605770230293274 - f1-score (micro avg) 0.0972
2023-10-19 23:52:21,118 saving best model
2023-10-19 23:52:21,151 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:21,533 epoch 8 - iter 14/146 - loss 0.39063923 - time (sec): 0.38 - samples/sec: 11350.79 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:52:21,890 epoch 8 - iter 28/146 - loss 0.52358403 - time (sec): 0.74 - samples/sec: 11999.88 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:52:22,256 epoch 8 - iter 42/146 - loss 0.47448311 - time (sec): 1.10 - samples/sec: 11965.72 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:52:22,629 epoch 8 - iter 56/146 - loss 0.44651128 - time (sec): 1.48 - samples/sec: 11768.99 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:52:23,000 epoch 8 - iter 70/146 - loss 0.43905400 - time (sec): 1.85 - samples/sec: 11734.69 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:52:23,336 epoch 8 - iter 84/146 - loss 0.43488104 - time (sec): 2.18 - samples/sec: 11814.12 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:52:23,679 epoch 8 - iter 98/146 - loss 0.44948982 - time (sec): 2.53 - samples/sec: 11595.87 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:52:24,064 epoch 8 - iter 112/146 - loss 0.45606613 - time (sec): 2.91 - samples/sec: 11562.77 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:52:24,437 epoch 8 - iter 126/146 - loss 0.44624813 - time (sec): 3.28 - samples/sec: 11655.29 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:52:24,792 epoch 8 - iter 140/146 - loss 0.44820969 - time (sec): 3.64 - samples/sec: 11694.03 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:52:24,948 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:24,948 EPOCH 8 done: loss 0.4477 - lr: 0.000007
2023-10-19 23:52:25,586 DEV : loss 0.3263406455516815 - f1-score (micro avg) 0.1153
2023-10-19 23:52:25,590 saving best model
2023-10-19 23:52:25,622 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:25,985 epoch 9 - iter 14/146 - loss 0.37820188 - time (sec): 0.36 - samples/sec: 10688.65 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:52:26,348 epoch 9 - iter 28/146 - loss 0.43671802 - time (sec): 0.73 - samples/sec: 10798.78 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:52:26,711 epoch 9 - iter 42/146 - loss 0.41517691 - time (sec): 1.09 - samples/sec: 11087.48 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:52:27,068 epoch 9 - iter 56/146 - loss 0.41215518 - time (sec): 1.44 - samples/sec: 11017.47 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:52:27,440 epoch 9 - iter 70/146 - loss 0.41827437 - time (sec): 1.82 - samples/sec: 11438.00 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:52:27,791 epoch 9 - iter 84/146 - loss 0.42593948 - time (sec): 2.17 - samples/sec: 11533.40 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:52:28,171 epoch 9 - iter 98/146 - loss 0.44034346 - time (sec): 2.55 - samples/sec: 11779.63 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:52:28,533 epoch 9 - iter 112/146 - loss 0.44311122 - time (sec): 2.91 - samples/sec: 11922.65 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:52:28,895 epoch 9 - iter 126/146 - loss 0.44155197 - time (sec): 3.27 - samples/sec: 12014.38 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:52:29,249 epoch 9 - iter 140/146 - loss 0.44005196 - time (sec): 3.63 - samples/sec: 11838.33 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:52:29,394 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:29,394 EPOCH 9 done: loss 0.4382 - lr: 0.000004
2023-10-19 23:52:30,032 DEV : loss 0.3212380111217499 - f1-score (micro avg) 0.1858
2023-10-19 23:52:30,036 saving best model
2023-10-19 23:52:30,068 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:30,452 epoch 10 - iter 14/146 - loss 0.32923291 - time (sec): 0.38 - samples/sec: 13011.39 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:52:30,810 epoch 10 - iter 28/146 - loss 0.38363662 - time (sec): 0.74 - samples/sec: 12147.27 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:52:31,181 epoch 10 - iter 42/146 - loss 0.38745870 - time (sec): 1.11 - samples/sec: 11796.33 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:52:31,543 epoch 10 - iter 56/146 - loss 0.37499813 - time (sec): 1.47 - samples/sec: 11874.41 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:52:31,922 epoch 10 - iter 70/146 - loss 0.39212077 - time (sec): 1.85 - samples/sec: 11639.66 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:52:32,302 epoch 10 - iter 84/146 - loss 0.41564761 - time (sec): 2.23 - samples/sec: 11571.15 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:52:32,647 epoch 10 - iter 98/146 - loss 0.42084198 - time (sec): 2.58 - samples/sec: 11389.64 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:52:33,018 epoch 10 - iter 112/146 - loss 0.42000229 - time (sec): 2.95 - samples/sec: 11351.89 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:52:33,380 epoch 10 - iter 126/146 - loss 0.43344724 - time (sec): 3.31 - samples/sec: 11581.27 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:52:33,752 epoch 10 - iter 140/146 - loss 0.43011787 - time (sec): 3.68 - samples/sec: 11638.03 - lr: 0.000000 - momentum: 0.000000
2023-10-19 23:52:33,905 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:33,906 EPOCH 10 done: loss 0.4317 - lr: 0.000000
2023-10-19 23:52:34,546 DEV : loss 0.32181745767593384 - f1-score (micro avg) 0.1801
2023-10-19 23:52:34,578 ----------------------------------------------------------------------------------------------------
2023-10-19 23:52:34,579 Loading model from best epoch ...
2023-10-19 23:52:34,653 SequenceTagger predicts: Dictionary with 17 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, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-19 23:52:35,708
Results:
- F-score (micro) 0.1645
- F-score (macro) 0.0772
- Accuracy 0.0923
By class:
precision recall f1-score support
PER 0.2151 0.2126 0.2139 348
LOC 0.2727 0.0575 0.0949 261
ORG 0.0000 0.0000 0.0000 52
HumanProd 0.0000 0.0000 0.0000 22
micro avg 0.2231 0.1303 0.1645 683
macro avg 0.1220 0.0675 0.0772 683
weighted avg 0.2138 0.1303 0.1453 683
2023-10-19 23:52:35,708 ----------------------------------------------------------------------------------------------------
|