File size: 24,150 Bytes
cdb5e9d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
2023-10-18 16:10:45,266 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,266 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-18 16:10:45,266 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,266 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-18 16:10:45,266 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,266 Train: 1214 sentences
2023-10-18 16:10:45,266 (train_with_dev=False, train_with_test=False)
2023-10-18 16:10:45,266 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Training Params:
2023-10-18 16:10:45,267 - learning_rate: "3e-05"
2023-10-18 16:10:45,267 - mini_batch_size: "8"
2023-10-18 16:10:45,267 - max_epochs: "10"
2023-10-18 16:10:45,267 - shuffle: "True"
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Plugins:
2023-10-18 16:10:45,267 - TensorboardLogger
2023-10-18 16:10:45,267 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 16:10:45,267 - metric: "('micro avg', 'f1-score')"
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Computation:
2023-10-18 16:10:45,267 - compute on device: cuda:0
2023-10-18 16:10:45,267 - embedding storage: none
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Model training base path: "hmbench-ajmc/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:45,267 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 16:10:45,643 epoch 1 - iter 15/152 - loss 4.00194862 - time (sec): 0.38 - samples/sec: 8872.39 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:10:46,007 epoch 1 - iter 30/152 - loss 3.93032449 - time (sec): 0.74 - samples/sec: 8857.31 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:10:46,391 epoch 1 - iter 45/152 - loss 3.90027579 - time (sec): 1.12 - samples/sec: 8845.87 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:10:46,761 epoch 1 - iter 60/152 - loss 3.82549513 - time (sec): 1.49 - samples/sec: 8629.62 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:10:47,105 epoch 1 - iter 75/152 - loss 3.71965164 - time (sec): 1.84 - samples/sec: 8711.14 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:10:47,450 epoch 1 - iter 90/152 - loss 3.58454282 - time (sec): 2.18 - samples/sec: 8739.34 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:10:47,795 epoch 1 - iter 105/152 - loss 3.43789527 - time (sec): 2.53 - samples/sec: 8731.14 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:10:48,129 epoch 1 - iter 120/152 - loss 3.30319039 - time (sec): 2.86 - samples/sec: 8678.74 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:10:48,470 epoch 1 - iter 135/152 - loss 3.11978823 - time (sec): 3.20 - samples/sec: 8750.76 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:10:48,824 epoch 1 - iter 150/152 - loss 2.97198898 - time (sec): 3.56 - samples/sec: 8635.08 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:10:48,872 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:48,873 EPOCH 1 done: loss 2.9587 - lr: 0.000029
2023-10-18 16:10:49,350 DEV : loss 0.8460401296615601 - f1-score (micro avg) 0.0
2023-10-18 16:10:49,356 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:49,733 epoch 2 - iter 15/152 - loss 0.99039188 - time (sec): 0.38 - samples/sec: 8243.63 - lr: 0.000030 - momentum: 0.000000
2023-10-18 16:10:50,111 epoch 2 - iter 30/152 - loss 0.89924649 - time (sec): 0.75 - samples/sec: 8463.66 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:10:50,447 epoch 2 - iter 45/152 - loss 0.89484187 - time (sec): 1.09 - samples/sec: 8546.18 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:10:50,772 epoch 2 - iter 60/152 - loss 0.90047475 - time (sec): 1.42 - samples/sec: 8772.68 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:10:51,082 epoch 2 - iter 75/152 - loss 0.85006453 - time (sec): 1.73 - samples/sec: 8869.57 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:10:51,408 epoch 2 - iter 90/152 - loss 0.85261376 - time (sec): 2.05 - samples/sec: 8921.11 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:10:51,737 epoch 2 - iter 105/152 - loss 0.84452527 - time (sec): 2.38 - samples/sec: 9077.56 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:10:52,067 epoch 2 - iter 120/152 - loss 0.84136420 - time (sec): 2.71 - samples/sec: 9127.68 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:10:52,389 epoch 2 - iter 135/152 - loss 0.82452902 - time (sec): 3.03 - samples/sec: 9111.12 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:10:52,713 epoch 2 - iter 150/152 - loss 0.82874038 - time (sec): 3.36 - samples/sec: 9147.55 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:10:52,755 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:52,755 EPOCH 2 done: loss 0.8277 - lr: 0.000027
2023-10-18 16:10:53,250 DEV : loss 0.6869751214981079 - f1-score (micro avg) 0.0
2023-10-18 16:10:53,256 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:53,594 epoch 3 - iter 15/152 - loss 0.71007861 - time (sec): 0.34 - samples/sec: 8663.36 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:10:53,915 epoch 3 - iter 30/152 - loss 0.72173453 - time (sec): 0.66 - samples/sec: 9286.33 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:10:54,243 epoch 3 - iter 45/152 - loss 0.71552143 - time (sec): 0.99 - samples/sec: 9286.50 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:10:54,580 epoch 3 - iter 60/152 - loss 0.69879105 - time (sec): 1.32 - samples/sec: 9501.57 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:10:54,910 epoch 3 - iter 75/152 - loss 0.66378317 - time (sec): 1.65 - samples/sec: 9334.83 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:10:55,239 epoch 3 - iter 90/152 - loss 0.64699215 - time (sec): 1.98 - samples/sec: 9166.23 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:10:55,579 epoch 3 - iter 105/152 - loss 0.63360388 - time (sec): 2.32 - samples/sec: 9073.35 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:10:55,926 epoch 3 - iter 120/152 - loss 0.63428746 - time (sec): 2.67 - samples/sec: 9078.16 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:10:56,278 epoch 3 - iter 135/152 - loss 0.63744324 - time (sec): 3.02 - samples/sec: 9102.45 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:10:56,627 epoch 3 - iter 150/152 - loss 0.62855569 - time (sec): 3.37 - samples/sec: 9084.64 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:10:56,672 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:56,672 EPOCH 3 done: loss 0.6253 - lr: 0.000023
2023-10-18 16:10:57,159 DEV : loss 0.5135114789009094 - f1-score (micro avg) 0.0181
2023-10-18 16:10:57,164 saving best model
2023-10-18 16:10:57,197 ----------------------------------------------------------------------------------------------------
2023-10-18 16:10:57,464 epoch 4 - iter 15/152 - loss 0.59486776 - time (sec): 0.27 - samples/sec: 10646.48 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:10:57,733 epoch 4 - iter 30/152 - loss 0.62103914 - time (sec): 0.54 - samples/sec: 11352.89 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:10:57,992 epoch 4 - iter 45/152 - loss 0.59834986 - time (sec): 0.79 - samples/sec: 11531.11 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:10:58,252 epoch 4 - iter 60/152 - loss 0.58045269 - time (sec): 1.05 - samples/sec: 11638.12 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:10:58,513 epoch 4 - iter 75/152 - loss 0.57649671 - time (sec): 1.32 - samples/sec: 11623.58 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:10:58,774 epoch 4 - iter 90/152 - loss 0.56525450 - time (sec): 1.58 - samples/sec: 11620.33 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:10:59,055 epoch 4 - iter 105/152 - loss 0.55064825 - time (sec): 1.86 - samples/sec: 11574.46 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:10:59,336 epoch 4 - iter 120/152 - loss 0.53920561 - time (sec): 2.14 - samples/sec: 11569.34 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:10:59,655 epoch 4 - iter 135/152 - loss 0.53041123 - time (sec): 2.46 - samples/sec: 11269.83 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:10:59,990 epoch 4 - iter 150/152 - loss 0.52477527 - time (sec): 2.79 - samples/sec: 10967.30 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:11:00,034 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:00,034 EPOCH 4 done: loss 0.5230 - lr: 0.000020
2023-10-18 16:11:00,549 DEV : loss 0.42890670895576477 - f1-score (micro avg) 0.2158
2023-10-18 16:11:00,554 saving best model
2023-10-18 16:11:00,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:00,913 epoch 5 - iter 15/152 - loss 0.42012484 - time (sec): 0.33 - samples/sec: 9828.59 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:11:01,250 epoch 5 - iter 30/152 - loss 0.45240271 - time (sec): 0.66 - samples/sec: 9358.30 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:11:01,575 epoch 5 - iter 45/152 - loss 0.44060881 - time (sec): 0.99 - samples/sec: 9068.59 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:11:01,913 epoch 5 - iter 60/152 - loss 0.48649653 - time (sec): 1.33 - samples/sec: 8980.75 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:11:02,245 epoch 5 - iter 75/152 - loss 0.48018059 - time (sec): 1.66 - samples/sec: 9075.73 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:11:02,572 epoch 5 - iter 90/152 - loss 0.47988015 - time (sec): 1.98 - samples/sec: 9281.66 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:11:02,886 epoch 5 - iter 105/152 - loss 0.47894319 - time (sec): 2.30 - samples/sec: 9371.53 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:11:03,203 epoch 5 - iter 120/152 - loss 0.47141827 - time (sec): 2.62 - samples/sec: 9356.51 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:11:03,541 epoch 5 - iter 135/152 - loss 0.46962915 - time (sec): 2.95 - samples/sec: 9355.58 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:11:03,858 epoch 5 - iter 150/152 - loss 0.45784441 - time (sec): 3.27 - samples/sec: 9367.37 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:11:03,896 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:03,897 EPOCH 5 done: loss 0.4599 - lr: 0.000017
2023-10-18 16:11:04,412 DEV : loss 0.38793084025382996 - f1-score (micro avg) 0.2661
2023-10-18 16:11:04,417 saving best model
2023-10-18 16:11:04,449 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:04,780 epoch 6 - iter 15/152 - loss 0.38728378 - time (sec): 0.33 - samples/sec: 8716.49 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:11:05,103 epoch 6 - iter 30/152 - loss 0.43917481 - time (sec): 0.65 - samples/sec: 9334.42 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:11:05,419 epoch 6 - iter 45/152 - loss 0.42210125 - time (sec): 0.97 - samples/sec: 9261.61 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:11:05,739 epoch 6 - iter 60/152 - loss 0.43358170 - time (sec): 1.29 - samples/sec: 9215.79 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:11:06,062 epoch 6 - iter 75/152 - loss 0.43677357 - time (sec): 1.61 - samples/sec: 9142.77 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:11:06,400 epoch 6 - iter 90/152 - loss 0.43060696 - time (sec): 1.95 - samples/sec: 9191.67 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:11:06,719 epoch 6 - iter 105/152 - loss 0.42919675 - time (sec): 2.27 - samples/sec: 9261.38 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:11:07,046 epoch 6 - iter 120/152 - loss 0.41978387 - time (sec): 2.60 - samples/sec: 9343.64 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:11:07,399 epoch 6 - iter 135/152 - loss 0.42473343 - time (sec): 2.95 - samples/sec: 9277.22 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:11:07,750 epoch 6 - iter 150/152 - loss 0.42455247 - time (sec): 3.30 - samples/sec: 9270.99 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:11:07,792 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:07,792 EPOCH 6 done: loss 0.4240 - lr: 0.000013
2023-10-18 16:11:08,294 DEV : loss 0.36627092957496643 - f1-score (micro avg) 0.3059
2023-10-18 16:11:08,299 saving best model
2023-10-18 16:11:08,332 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:08,684 epoch 7 - iter 15/152 - loss 0.42443388 - time (sec): 0.35 - samples/sec: 9353.96 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:11:09,013 epoch 7 - iter 30/152 - loss 0.43107976 - time (sec): 0.68 - samples/sec: 9315.62 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:11:09,355 epoch 7 - iter 45/152 - loss 0.43213838 - time (sec): 1.02 - samples/sec: 9195.84 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:11:09,677 epoch 7 - iter 60/152 - loss 0.43004851 - time (sec): 1.34 - samples/sec: 9259.06 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:11:10,021 epoch 7 - iter 75/152 - loss 0.43143165 - time (sec): 1.69 - samples/sec: 9178.06 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:11:10,343 epoch 7 - iter 90/152 - loss 0.42030296 - time (sec): 2.01 - samples/sec: 9080.88 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:11:10,670 epoch 7 - iter 105/152 - loss 0.41714489 - time (sec): 2.34 - samples/sec: 9168.85 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:11:10,989 epoch 7 - iter 120/152 - loss 0.41080530 - time (sec): 2.66 - samples/sec: 9172.11 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:11:11,304 epoch 7 - iter 135/152 - loss 0.40597047 - time (sec): 2.97 - samples/sec: 9266.47 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:11:11,630 epoch 7 - iter 150/152 - loss 0.40237893 - time (sec): 3.30 - samples/sec: 9282.50 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:11:11,674 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:11,674 EPOCH 7 done: loss 0.3989 - lr: 0.000010
2023-10-18 16:11:12,189 DEV : loss 0.34827205538749695 - f1-score (micro avg) 0.3443
2023-10-18 16:11:12,195 saving best model
2023-10-18 16:11:12,228 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:12,561 epoch 8 - iter 15/152 - loss 0.39763025 - time (sec): 0.33 - samples/sec: 9434.85 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:11:12,887 epoch 8 - iter 30/152 - loss 0.39423381 - time (sec): 0.66 - samples/sec: 9268.55 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:11:13,213 epoch 8 - iter 45/152 - loss 0.40063428 - time (sec): 0.98 - samples/sec: 9205.29 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:11:13,548 epoch 8 - iter 60/152 - loss 0.39201927 - time (sec): 1.32 - samples/sec: 9205.39 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:11:13,904 epoch 8 - iter 75/152 - loss 0.39276233 - time (sec): 1.67 - samples/sec: 9062.29 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:11:14,257 epoch 8 - iter 90/152 - loss 0.39413049 - time (sec): 2.03 - samples/sec: 8991.94 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:11:14,598 epoch 8 - iter 105/152 - loss 0.39315056 - time (sec): 2.37 - samples/sec: 9030.40 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:11:14,938 epoch 8 - iter 120/152 - loss 0.39718127 - time (sec): 2.71 - samples/sec: 9105.15 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:11:15,275 epoch 8 - iter 135/152 - loss 0.39900868 - time (sec): 3.05 - samples/sec: 9122.55 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:11:15,604 epoch 8 - iter 150/152 - loss 0.38543416 - time (sec): 3.37 - samples/sec: 9100.19 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:11:15,642 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:15,643 EPOCH 8 done: loss 0.3853 - lr: 0.000007
2023-10-18 16:11:16,160 DEV : loss 0.3415715992450714 - f1-score (micro avg) 0.3607
2023-10-18 16:11:16,166 saving best model
2023-10-18 16:11:16,198 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:16,550 epoch 9 - iter 15/152 - loss 0.37449454 - time (sec): 0.35 - samples/sec: 9501.05 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:11:16,873 epoch 9 - iter 30/152 - loss 0.35152597 - time (sec): 0.67 - samples/sec: 9574.63 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:11:17,192 epoch 9 - iter 45/152 - loss 0.36547659 - time (sec): 0.99 - samples/sec: 9754.90 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:11:17,530 epoch 9 - iter 60/152 - loss 0.35377707 - time (sec): 1.33 - samples/sec: 9596.35 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:11:17,857 epoch 9 - iter 75/152 - loss 0.37707230 - time (sec): 1.66 - samples/sec: 9577.50 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:11:18,184 epoch 9 - iter 90/152 - loss 0.38457408 - time (sec): 1.98 - samples/sec: 9608.64 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:11:18,499 epoch 9 - iter 105/152 - loss 0.38246205 - time (sec): 2.30 - samples/sec: 9499.41 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:11:18,821 epoch 9 - iter 120/152 - loss 0.37841646 - time (sec): 2.62 - samples/sec: 9440.01 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:11:19,157 epoch 9 - iter 135/152 - loss 0.38219358 - time (sec): 2.96 - samples/sec: 9318.53 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:11:19,474 epoch 9 - iter 150/152 - loss 0.37840206 - time (sec): 3.27 - samples/sec: 9363.98 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:11:19,513 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:19,513 EPOCH 9 done: loss 0.3758 - lr: 0.000004
2023-10-18 16:11:20,019 DEV : loss 0.33774086833000183 - f1-score (micro avg) 0.3705
2023-10-18 16:11:20,025 saving best model
2023-10-18 16:11:20,058 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:20,382 epoch 10 - iter 15/152 - loss 0.29312128 - time (sec): 0.32 - samples/sec: 9094.57 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:11:20,702 epoch 10 - iter 30/152 - loss 0.34740243 - time (sec): 0.64 - samples/sec: 9449.94 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:11:21,037 epoch 10 - iter 45/152 - loss 0.33882855 - time (sec): 0.98 - samples/sec: 9418.48 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:11:21,363 epoch 10 - iter 60/152 - loss 0.34352526 - time (sec): 1.30 - samples/sec: 9374.66 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:11:21,701 epoch 10 - iter 75/152 - loss 0.34753687 - time (sec): 1.64 - samples/sec: 9215.78 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:11:22,038 epoch 10 - iter 90/152 - loss 0.35076983 - time (sec): 1.98 - samples/sec: 9267.92 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:11:22,380 epoch 10 - iter 105/152 - loss 0.35893496 - time (sec): 2.32 - samples/sec: 9208.24 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:11:22,721 epoch 10 - iter 120/152 - loss 0.35889586 - time (sec): 2.66 - samples/sec: 9224.37 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:11:23,061 epoch 10 - iter 135/152 - loss 0.35917971 - time (sec): 3.00 - samples/sec: 9205.51 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:11:23,397 epoch 10 - iter 150/152 - loss 0.36218218 - time (sec): 3.34 - samples/sec: 9180.46 - lr: 0.000000 - momentum: 0.000000
2023-10-18 16:11:23,438 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:23,438 EPOCH 10 done: loss 0.3616 - lr: 0.000000
2023-10-18 16:11:23,957 DEV : loss 0.33346304297447205 - f1-score (micro avg) 0.3808
2023-10-18 16:11:23,963 saving best model
2023-10-18 16:11:24,024 ----------------------------------------------------------------------------------------------------
2023-10-18 16:11:24,025 Loading model from best epoch ...
2023-10-18 16:11:24,104 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
2023-10-18 16:11:24,588
Results:
- F-score (micro) 0.3636
- F-score (macro) 0.2306
- Accuracy 0.2285
By class:
precision recall f1-score support
scope 0.3536 0.4238 0.3855 151
work 0.1533 0.2421 0.1878 95
pers 0.6375 0.5312 0.5795 96
loc 0.0000 0.0000 0.0000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.3358 0.3966 0.3636 348
macro avg 0.2289 0.2394 0.2306 348
weighted avg 0.3711 0.3966 0.3784 348
2023-10-18 16:11:24,589 ----------------------------------------------------------------------------------------------------
|