File size: 25,374 Bytes
515f8ce |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 |
2023-10-19 00:16:41,198 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,199 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=81, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-19 00:16:41,199 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,199 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 00:16:41,199 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,199 Train: 6900 sentences
2023-10-19 00:16:41,200 (train_with_dev=False, train_with_test=False)
2023-10-19 00:16:41,200 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,200 Training Params:
2023-10-19 00:16:41,200 - learning_rate: "3e-05"
2023-10-19 00:16:41,200 - mini_batch_size: "16"
2023-10-19 00:16:41,200 - max_epochs: "10"
2023-10-19 00:16:41,200 - shuffle: "True"
2023-10-19 00:16:41,200 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,200 Plugins:
2023-10-19 00:16:41,200 - TensorboardLogger
2023-10-19 00:16:41,200 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 00:16:41,200 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,200 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 00:16:41,200 - metric: "('micro avg', 'f1-score')"
2023-10-19 00:16:41,200 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,200 Computation:
2023-10-19 00:16:41,200 - compute on device: cuda:0
2023-10-19 00:16:41,200 - embedding storage: none
2023-10-19 00:16:41,200 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,200 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-2"
2023-10-19 00:16:41,201 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,201 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:41,201 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 00:16:56,550 epoch 1 - iter 43/432 - loss 4.74339679 - time (sec): 15.35 - samples/sec: 393.65 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:17:10,707 epoch 1 - iter 86/432 - loss 3.69280224 - time (sec): 29.51 - samples/sec: 416.26 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:17:25,377 epoch 1 - iter 129/432 - loss 3.11907087 - time (sec): 44.18 - samples/sec: 412.84 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:17:39,369 epoch 1 - iter 172/432 - loss 2.79415985 - time (sec): 58.17 - samples/sec: 418.02 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:17:54,435 epoch 1 - iter 215/432 - loss 2.57050206 - time (sec): 73.23 - samples/sec: 411.49 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:18:09,813 epoch 1 - iter 258/432 - loss 2.33799933 - time (sec): 88.61 - samples/sec: 413.95 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:18:24,648 epoch 1 - iter 301/432 - loss 2.16172499 - time (sec): 103.45 - samples/sec: 414.53 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:18:39,760 epoch 1 - iter 344/432 - loss 2.01712724 - time (sec): 118.56 - samples/sec: 413.49 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:18:54,151 epoch 1 - iter 387/432 - loss 1.88891723 - time (sec): 132.95 - samples/sec: 413.69 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:19:09,750 epoch 1 - iter 430/432 - loss 1.76466676 - time (sec): 148.55 - samples/sec: 414.43 - lr: 0.000030 - momentum: 0.000000
2023-10-19 00:19:10,345 ----------------------------------------------------------------------------------------------------
2023-10-19 00:19:10,346 EPOCH 1 done: loss 1.7605 - lr: 0.000030
2023-10-19 00:19:23,881 DEV : loss 0.5642062425613403 - f1-score (micro avg) 0.6351
2023-10-19 00:19:23,905 saving best model
2023-10-19 00:19:24,363 ----------------------------------------------------------------------------------------------------
2023-10-19 00:19:38,473 epoch 2 - iter 43/432 - loss 0.63277954 - time (sec): 14.11 - samples/sec: 460.79 - lr: 0.000030 - momentum: 0.000000
2023-10-19 00:19:52,843 epoch 2 - iter 86/432 - loss 0.58715243 - time (sec): 28.48 - samples/sec: 447.57 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:20:08,079 epoch 2 - iter 129/432 - loss 0.57597451 - time (sec): 43.71 - samples/sec: 428.05 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:20:23,330 epoch 2 - iter 172/432 - loss 0.55894939 - time (sec): 58.97 - samples/sec: 424.51 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:20:38,457 epoch 2 - iter 215/432 - loss 0.54682286 - time (sec): 74.09 - samples/sec: 418.14 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:20:53,042 epoch 2 - iter 258/432 - loss 0.53151093 - time (sec): 88.68 - samples/sec: 418.66 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:21:07,908 epoch 2 - iter 301/432 - loss 0.51887975 - time (sec): 103.54 - samples/sec: 414.79 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:21:22,719 epoch 2 - iter 344/432 - loss 0.51217919 - time (sec): 118.35 - samples/sec: 414.72 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:21:37,756 epoch 2 - iter 387/432 - loss 0.49869397 - time (sec): 133.39 - samples/sec: 414.52 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:21:52,045 epoch 2 - iter 430/432 - loss 0.49068478 - time (sec): 147.68 - samples/sec: 417.04 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:21:52,617 ----------------------------------------------------------------------------------------------------
2023-10-19 00:21:52,617 EPOCH 2 done: loss 0.4907 - lr: 0.000027
2023-10-19 00:22:05,834 DEV : loss 0.346346378326416 - f1-score (micro avg) 0.7698
2023-10-19 00:22:05,858 saving best model
2023-10-19 00:22:07,095 ----------------------------------------------------------------------------------------------------
2023-10-19 00:22:21,551 epoch 3 - iter 43/432 - loss 0.34282667 - time (sec): 14.45 - samples/sec: 406.92 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:22:36,270 epoch 3 - iter 86/432 - loss 0.33200713 - time (sec): 29.17 - samples/sec: 403.75 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:22:52,022 epoch 3 - iter 129/432 - loss 0.32080282 - time (sec): 44.93 - samples/sec: 396.68 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:23:07,641 epoch 3 - iter 172/432 - loss 0.31771938 - time (sec): 60.54 - samples/sec: 393.81 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:23:22,177 epoch 3 - iter 215/432 - loss 0.31302256 - time (sec): 75.08 - samples/sec: 400.77 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:23:36,579 epoch 3 - iter 258/432 - loss 0.31007470 - time (sec): 89.48 - samples/sec: 407.35 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:23:50,695 epoch 3 - iter 301/432 - loss 0.30555352 - time (sec): 103.60 - samples/sec: 412.23 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:24:06,473 epoch 3 - iter 344/432 - loss 0.29928908 - time (sec): 119.38 - samples/sec: 411.36 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:24:20,745 epoch 3 - iter 387/432 - loss 0.29428176 - time (sec): 133.65 - samples/sec: 412.12 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:24:35,460 epoch 3 - iter 430/432 - loss 0.29672467 - time (sec): 148.36 - samples/sec: 415.78 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:24:35,971 ----------------------------------------------------------------------------------------------------
2023-10-19 00:24:35,971 EPOCH 3 done: loss 0.2967 - lr: 0.000023
2023-10-19 00:24:49,187 DEV : loss 0.31504037976264954 - f1-score (micro avg) 0.7963
2023-10-19 00:24:49,211 saving best model
2023-10-19 00:24:50,467 ----------------------------------------------------------------------------------------------------
2023-10-19 00:25:05,412 epoch 4 - iter 43/432 - loss 0.20335532 - time (sec): 14.94 - samples/sec: 420.97 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:25:20,061 epoch 4 - iter 86/432 - loss 0.22350075 - time (sec): 29.59 - samples/sec: 420.23 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:25:35,172 epoch 4 - iter 129/432 - loss 0.22388534 - time (sec): 44.70 - samples/sec: 421.31 - lr: 0.000022 - momentum: 0.000000
2023-10-19 00:25:49,750 epoch 4 - iter 172/432 - loss 0.22617688 - time (sec): 59.28 - samples/sec: 417.61 - lr: 0.000022 - momentum: 0.000000
2023-10-19 00:26:05,215 epoch 4 - iter 215/432 - loss 0.21971434 - time (sec): 74.75 - samples/sec: 414.52 - lr: 0.000022 - momentum: 0.000000
2023-10-19 00:26:20,389 epoch 4 - iter 258/432 - loss 0.22117839 - time (sec): 89.92 - samples/sec: 414.89 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:26:35,115 epoch 4 - iter 301/432 - loss 0.22265378 - time (sec): 104.65 - samples/sec: 416.69 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:26:49,810 epoch 4 - iter 344/432 - loss 0.22151182 - time (sec): 119.34 - samples/sec: 416.37 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:27:03,535 epoch 4 - iter 387/432 - loss 0.21789655 - time (sec): 133.07 - samples/sec: 419.09 - lr: 0.000020 - momentum: 0.000000
2023-10-19 00:27:18,579 epoch 4 - iter 430/432 - loss 0.21456196 - time (sec): 148.11 - samples/sec: 416.70 - lr: 0.000020 - momentum: 0.000000
2023-10-19 00:27:19,241 ----------------------------------------------------------------------------------------------------
2023-10-19 00:27:19,242 EPOCH 4 done: loss 0.2144 - lr: 0.000020
2023-10-19 00:27:32,562 DEV : loss 0.3091279864311218 - f1-score (micro avg) 0.8213
2023-10-19 00:27:32,590 saving best model
2023-10-19 00:27:34,992 ----------------------------------------------------------------------------------------------------
2023-10-19 00:27:49,017 epoch 5 - iter 43/432 - loss 0.17866192 - time (sec): 14.02 - samples/sec: 435.90 - lr: 0.000020 - momentum: 0.000000
2023-10-19 00:28:03,936 epoch 5 - iter 86/432 - loss 0.17512337 - time (sec): 28.94 - samples/sec: 420.14 - lr: 0.000019 - momentum: 0.000000
2023-10-19 00:28:19,866 epoch 5 - iter 129/432 - loss 0.16824137 - time (sec): 44.87 - samples/sec: 407.60 - lr: 0.000019 - momentum: 0.000000
2023-10-19 00:28:34,676 epoch 5 - iter 172/432 - loss 0.16860082 - time (sec): 59.68 - samples/sec: 411.83 - lr: 0.000019 - momentum: 0.000000
2023-10-19 00:28:49,495 epoch 5 - iter 215/432 - loss 0.16529930 - time (sec): 74.50 - samples/sec: 410.46 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:29:03,952 epoch 5 - iter 258/432 - loss 0.16770005 - time (sec): 88.96 - samples/sec: 417.59 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:29:18,790 epoch 5 - iter 301/432 - loss 0.16640170 - time (sec): 103.80 - samples/sec: 416.69 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:29:33,385 epoch 5 - iter 344/432 - loss 0.16427645 - time (sec): 118.39 - samples/sec: 418.21 - lr: 0.000017 - momentum: 0.000000
2023-10-19 00:29:48,488 epoch 5 - iter 387/432 - loss 0.16540814 - time (sec): 133.50 - samples/sec: 416.79 - lr: 0.000017 - momentum: 0.000000
2023-10-19 00:30:02,971 epoch 5 - iter 430/432 - loss 0.16431132 - time (sec): 147.98 - samples/sec: 416.45 - lr: 0.000017 - momentum: 0.000000
2023-10-19 00:30:03,520 ----------------------------------------------------------------------------------------------------
2023-10-19 00:30:03,521 EPOCH 5 done: loss 0.1640 - lr: 0.000017
2023-10-19 00:30:16,827 DEV : loss 0.3160895109176636 - f1-score (micro avg) 0.8377
2023-10-19 00:30:16,851 saving best model
2023-10-19 00:30:18,089 ----------------------------------------------------------------------------------------------------
2023-10-19 00:30:33,807 epoch 6 - iter 43/432 - loss 0.11962951 - time (sec): 15.72 - samples/sec: 392.96 - lr: 0.000016 - momentum: 0.000000
2023-10-19 00:30:48,631 epoch 6 - iter 86/432 - loss 0.11884539 - time (sec): 30.54 - samples/sec: 397.61 - lr: 0.000016 - momentum: 0.000000
2023-10-19 00:31:03,258 epoch 6 - iter 129/432 - loss 0.12228484 - time (sec): 45.17 - samples/sec: 400.22 - lr: 0.000016 - momentum: 0.000000
2023-10-19 00:31:17,032 epoch 6 - iter 172/432 - loss 0.12474293 - time (sec): 58.94 - samples/sec: 414.07 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:31:31,618 epoch 6 - iter 215/432 - loss 0.12867530 - time (sec): 73.53 - samples/sec: 415.73 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:31:46,035 epoch 6 - iter 258/432 - loss 0.12946820 - time (sec): 87.94 - samples/sec: 419.70 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:32:01,941 epoch 6 - iter 301/432 - loss 0.13096586 - time (sec): 103.85 - samples/sec: 416.74 - lr: 0.000014 - momentum: 0.000000
2023-10-19 00:32:16,804 epoch 6 - iter 344/432 - loss 0.12989295 - time (sec): 118.71 - samples/sec: 415.91 - lr: 0.000014 - momentum: 0.000000
2023-10-19 00:32:31,446 epoch 6 - iter 387/432 - loss 0.12982969 - time (sec): 133.35 - samples/sec: 414.74 - lr: 0.000014 - momentum: 0.000000
2023-10-19 00:32:46,889 epoch 6 - iter 430/432 - loss 0.12896680 - time (sec): 148.80 - samples/sec: 414.57 - lr: 0.000013 - momentum: 0.000000
2023-10-19 00:32:47,622 ----------------------------------------------------------------------------------------------------
2023-10-19 00:32:47,623 EPOCH 6 done: loss 0.1289 - lr: 0.000013
2023-10-19 00:33:00,960 DEV : loss 0.33405086398124695 - f1-score (micro avg) 0.8325
2023-10-19 00:33:00,984 ----------------------------------------------------------------------------------------------------
2023-10-19 00:33:14,708 epoch 7 - iter 43/432 - loss 0.09581046 - time (sec): 13.72 - samples/sec: 465.09 - lr: 0.000013 - momentum: 0.000000
2023-10-19 00:33:29,254 epoch 7 - iter 86/432 - loss 0.09800936 - time (sec): 28.27 - samples/sec: 441.95 - lr: 0.000013 - momentum: 0.000000
2023-10-19 00:33:44,617 epoch 7 - iter 129/432 - loss 0.09725239 - time (sec): 43.63 - samples/sec: 419.20 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:34:00,001 epoch 7 - iter 172/432 - loss 0.09688733 - time (sec): 59.02 - samples/sec: 416.05 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:34:14,468 epoch 7 - iter 215/432 - loss 0.10137512 - time (sec): 73.48 - samples/sec: 420.10 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:34:29,569 epoch 7 - iter 258/432 - loss 0.10565885 - time (sec): 88.58 - samples/sec: 418.11 - lr: 0.000011 - momentum: 0.000000
2023-10-19 00:34:44,754 epoch 7 - iter 301/432 - loss 0.10530649 - time (sec): 103.77 - samples/sec: 416.15 - lr: 0.000011 - momentum: 0.000000
2023-10-19 00:34:59,759 epoch 7 - iter 344/432 - loss 0.10536216 - time (sec): 118.77 - samples/sec: 414.76 - lr: 0.000011 - momentum: 0.000000
2023-10-19 00:35:15,545 epoch 7 - iter 387/432 - loss 0.10554671 - time (sec): 134.56 - samples/sec: 412.00 - lr: 0.000010 - momentum: 0.000000
2023-10-19 00:35:31,052 epoch 7 - iter 430/432 - loss 0.10598819 - time (sec): 150.07 - samples/sec: 411.01 - lr: 0.000010 - momentum: 0.000000
2023-10-19 00:35:31,863 ----------------------------------------------------------------------------------------------------
2023-10-19 00:35:31,863 EPOCH 7 done: loss 0.1058 - lr: 0.000010
2023-10-19 00:35:45,283 DEV : loss 0.351141095161438 - f1-score (micro avg) 0.831
2023-10-19 00:35:45,307 ----------------------------------------------------------------------------------------------------
2023-10-19 00:35:59,848 epoch 8 - iter 43/432 - loss 0.07709807 - time (sec): 14.54 - samples/sec: 410.88 - lr: 0.000010 - momentum: 0.000000
2023-10-19 00:36:14,941 epoch 8 - iter 86/432 - loss 0.08407471 - time (sec): 29.63 - samples/sec: 424.33 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:36:29,079 epoch 8 - iter 129/432 - loss 0.07999086 - time (sec): 43.77 - samples/sec: 416.05 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:36:42,973 epoch 8 - iter 172/432 - loss 0.08291254 - time (sec): 57.66 - samples/sec: 434.37 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:36:57,433 epoch 8 - iter 215/432 - loss 0.08343817 - time (sec): 72.12 - samples/sec: 436.23 - lr: 0.000008 - momentum: 0.000000
2023-10-19 00:37:12,605 epoch 8 - iter 258/432 - loss 0.08221956 - time (sec): 87.30 - samples/sec: 429.21 - lr: 0.000008 - momentum: 0.000000
2023-10-19 00:37:27,858 epoch 8 - iter 301/432 - loss 0.08082516 - time (sec): 102.55 - samples/sec: 426.54 - lr: 0.000008 - momentum: 0.000000
2023-10-19 00:37:42,508 epoch 8 - iter 344/432 - loss 0.08300870 - time (sec): 117.20 - samples/sec: 427.00 - lr: 0.000007 - momentum: 0.000000
2023-10-19 00:37:57,378 epoch 8 - iter 387/432 - loss 0.08417221 - time (sec): 132.07 - samples/sec: 422.73 - lr: 0.000007 - momentum: 0.000000
2023-10-19 00:38:12,945 epoch 8 - iter 430/432 - loss 0.08447959 - time (sec): 147.64 - samples/sec: 417.49 - lr: 0.000007 - momentum: 0.000000
2023-10-19 00:38:13,806 ----------------------------------------------------------------------------------------------------
2023-10-19 00:38:13,806 EPOCH 8 done: loss 0.0846 - lr: 0.000007
2023-10-19 00:38:27,128 DEV : loss 0.35482051968574524 - f1-score (micro avg) 0.8445
2023-10-19 00:38:27,153 saving best model
2023-10-19 00:38:28,401 ----------------------------------------------------------------------------------------------------
2023-10-19 00:38:42,957 epoch 9 - iter 43/432 - loss 0.07970238 - time (sec): 14.55 - samples/sec: 410.87 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:38:57,617 epoch 9 - iter 86/432 - loss 0.06637511 - time (sec): 29.21 - samples/sec: 426.50 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:39:13,050 epoch 9 - iter 129/432 - loss 0.06582245 - time (sec): 44.65 - samples/sec: 415.68 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:39:29,031 epoch 9 - iter 172/432 - loss 0.06680679 - time (sec): 60.63 - samples/sec: 400.85 - lr: 0.000005 - momentum: 0.000000
2023-10-19 00:39:43,689 epoch 9 - iter 215/432 - loss 0.06514411 - time (sec): 75.29 - samples/sec: 410.03 - lr: 0.000005 - momentum: 0.000000
2023-10-19 00:39:58,720 epoch 9 - iter 258/432 - loss 0.06484547 - time (sec): 90.32 - samples/sec: 409.12 - lr: 0.000005 - momentum: 0.000000
2023-10-19 00:40:13,802 epoch 9 - iter 301/432 - loss 0.06626985 - time (sec): 105.40 - samples/sec: 411.40 - lr: 0.000004 - momentum: 0.000000
2023-10-19 00:40:28,801 epoch 9 - iter 344/432 - loss 0.06745724 - time (sec): 120.40 - samples/sec: 409.92 - lr: 0.000004 - momentum: 0.000000
2023-10-19 00:40:43,958 epoch 9 - iter 387/432 - loss 0.06792850 - time (sec): 135.56 - samples/sec: 408.61 - lr: 0.000004 - momentum: 0.000000
2023-10-19 00:40:59,712 epoch 9 - iter 430/432 - loss 0.06892771 - time (sec): 151.31 - samples/sec: 407.87 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:41:00,072 ----------------------------------------------------------------------------------------------------
2023-10-19 00:41:00,072 EPOCH 9 done: loss 0.0689 - lr: 0.000003
2023-10-19 00:41:13,916 DEV : loss 0.3687077760696411 - f1-score (micro avg) 0.839
2023-10-19 00:41:13,941 ----------------------------------------------------------------------------------------------------
2023-10-19 00:41:27,952 epoch 10 - iter 43/432 - loss 0.06914216 - time (sec): 14.01 - samples/sec: 423.21 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:41:43,413 epoch 10 - iter 86/432 - loss 0.06348909 - time (sec): 29.47 - samples/sec: 402.17 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:41:58,231 epoch 10 - iter 129/432 - loss 0.06567792 - time (sec): 44.29 - samples/sec: 408.14 - lr: 0.000002 - momentum: 0.000000
2023-10-19 00:42:13,509 epoch 10 - iter 172/432 - loss 0.06502152 - time (sec): 59.57 - samples/sec: 413.44 - lr: 0.000002 - momentum: 0.000000
2023-10-19 00:42:28,837 epoch 10 - iter 215/432 - loss 0.06585712 - time (sec): 74.89 - samples/sec: 417.08 - lr: 0.000002 - momentum: 0.000000
2023-10-19 00:42:43,697 epoch 10 - iter 258/432 - loss 0.06365877 - time (sec): 89.75 - samples/sec: 417.12 - lr: 0.000001 - momentum: 0.000000
2023-10-19 00:42:58,257 epoch 10 - iter 301/432 - loss 0.06317799 - time (sec): 104.31 - samples/sec: 418.47 - lr: 0.000001 - momentum: 0.000000
2023-10-19 00:43:13,120 epoch 10 - iter 344/432 - loss 0.06253740 - time (sec): 119.18 - samples/sec: 418.00 - lr: 0.000001 - momentum: 0.000000
2023-10-19 00:43:26,660 epoch 10 - iter 387/432 - loss 0.06022767 - time (sec): 132.72 - samples/sec: 419.38 - lr: 0.000000 - momentum: 0.000000
2023-10-19 00:43:42,384 epoch 10 - iter 430/432 - loss 0.05945663 - time (sec): 148.44 - samples/sec: 415.36 - lr: 0.000000 - momentum: 0.000000
2023-10-19 00:43:43,064 ----------------------------------------------------------------------------------------------------
2023-10-19 00:43:43,064 EPOCH 10 done: loss 0.0593 - lr: 0.000000
2023-10-19 00:43:56,330 DEV : loss 0.37211665511131287 - f1-score (micro avg) 0.837
2023-10-19 00:43:56,780 ----------------------------------------------------------------------------------------------------
2023-10-19 00:43:56,781 Loading model from best epoch ...
2023-10-19 00:43:58,908 SequenceTagger predicts: Dictionary with 81 tags: O, S-location-route, B-location-route, E-location-route, I-location-route, S-location-stop, B-location-stop, E-location-stop, I-location-stop, S-trigger, B-trigger, E-trigger, I-trigger, S-organization-company, B-organization-company, E-organization-company, I-organization-company, S-location-city, B-location-city, E-location-city, I-location-city, S-location, B-location, E-location, I-location, S-event-cause, B-event-cause, E-event-cause, I-event-cause, S-location-street, B-location-street, E-location-street, I-location-street, S-time, B-time, E-time, I-time, S-date, B-date, E-date, I-date, S-number, B-number, E-number, I-number, S-duration, B-duration, E-duration, I-duration, S-organization
2023-10-19 00:44:16,847
Results:
- F-score (micro) 0.7524
- F-score (macro) 0.553
- Accuracy 0.6489
By class:
precision recall f1-score support
trigger 0.6983 0.6086 0.6504 833
location-stop 0.8598 0.7856 0.8210 765
location 0.8076 0.8331 0.8201 665
location-city 0.7705 0.8958 0.8284 566
date 0.8786 0.8452 0.8616 394
location-street 0.9137 0.8782 0.8956 386
time 0.7917 0.8906 0.8382 256
location-route 0.8138 0.7077 0.7571 284
organization-company 0.7578 0.6706 0.7116 252
number 0.6378 0.8389 0.7246 149
distance 1.0000 1.0000 1.0000 167
duration 0.3091 0.3129 0.3110 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.8333 0.1449 0.2469 69
organization 0.3750 0.5357 0.4412 28
person 0.4500 0.9000 0.6000 10
set 0.0000 0.0000 0.0000 0
org-position 0.0000 0.0000 0.0000 1
money 0.0000 0.0000 0.0000 0
micro avg 0.7403 0.7650 0.7524 4988
macro avg 0.5735 0.5709 0.5530 4988
weighted avg 0.7861 0.7650 0.7697 4988
2023-10-19 00:44:16,847 ----------------------------------------------------------------------------------------------------
|