File size: 25,379 Bytes
1ef10b2 |
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 01:39:56,601 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,602 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 01:39:56,602 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,602 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 01:39:56,602 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,602 Train: 6900 sentences
2023-10-19 01:39:56,602 (train_with_dev=False, train_with_test=False)
2023-10-19 01:39:56,602 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,602 Training Params:
2023-10-19 01:39:56,603 - learning_rate: "5e-05"
2023-10-19 01:39:56,603 - mini_batch_size: "16"
2023-10-19 01:39:56,603 - max_epochs: "10"
2023-10-19 01:39:56,603 - shuffle: "True"
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,603 Plugins:
2023-10-19 01:39:56,603 - TensorboardLogger
2023-10-19 01:39:56,603 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,603 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 01:39:56,603 - metric: "('micro avg', 'f1-score')"
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,603 Computation:
2023-10-19 01:39:56,603 - compute on device: cuda:0
2023-10-19 01:39:56,603 - embedding storage: none
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,603 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-3"
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,603 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:56,604 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 01:40:11,037 epoch 1 - iter 43/432 - loss 4.25713314 - time (sec): 14.43 - samples/sec: 430.01 - lr: 0.000005 - momentum: 0.000000
2023-10-19 01:40:25,630 epoch 1 - iter 86/432 - loss 3.24789196 - time (sec): 29.03 - samples/sec: 420.70 - lr: 0.000010 - momentum: 0.000000
2023-10-19 01:40:40,727 epoch 1 - iter 129/432 - loss 2.71426774 - time (sec): 44.12 - samples/sec: 420.26 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:40:55,443 epoch 1 - iter 172/432 - loss 2.40284727 - time (sec): 58.84 - samples/sec: 419.42 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:41:10,081 epoch 1 - iter 215/432 - loss 2.15479567 - time (sec): 73.48 - samples/sec: 420.02 - lr: 0.000025 - momentum: 0.000000
2023-10-19 01:41:25,394 epoch 1 - iter 258/432 - loss 1.94996109 - time (sec): 88.79 - samples/sec: 417.19 - lr: 0.000030 - momentum: 0.000000
2023-10-19 01:41:40,178 epoch 1 - iter 301/432 - loss 1.78391625 - time (sec): 103.57 - samples/sec: 418.57 - lr: 0.000035 - momentum: 0.000000
2023-10-19 01:41:55,533 epoch 1 - iter 344/432 - loss 1.65459407 - time (sec): 118.93 - samples/sec: 414.58 - lr: 0.000040 - momentum: 0.000000
2023-10-19 01:42:10,188 epoch 1 - iter 387/432 - loss 1.54328420 - time (sec): 133.58 - samples/sec: 415.90 - lr: 0.000045 - momentum: 0.000000
2023-10-19 01:42:24,418 epoch 1 - iter 430/432 - loss 1.44458615 - time (sec): 147.81 - samples/sec: 417.31 - lr: 0.000050 - momentum: 0.000000
2023-10-19 01:42:25,052 ----------------------------------------------------------------------------------------------------
2023-10-19 01:42:25,052 EPOCH 1 done: loss 1.4425 - lr: 0.000050
2023-10-19 01:42:38,766 DEV : loss 0.45496100187301636 - f1-score (micro avg) 0.7175
2023-10-19 01:42:38,790 saving best model
2023-10-19 01:42:39,214 ----------------------------------------------------------------------------------------------------
2023-10-19 01:42:54,241 epoch 2 - iter 43/432 - loss 0.45728563 - time (sec): 15.03 - samples/sec: 415.63 - lr: 0.000049 - momentum: 0.000000
2023-10-19 01:43:08,781 epoch 2 - iter 86/432 - loss 0.45661912 - time (sec): 29.57 - samples/sec: 414.74 - lr: 0.000049 - momentum: 0.000000
2023-10-19 01:43:23,811 epoch 2 - iter 129/432 - loss 0.44475303 - time (sec): 44.60 - samples/sec: 414.57 - lr: 0.000048 - momentum: 0.000000
2023-10-19 01:43:38,997 epoch 2 - iter 172/432 - loss 0.43971531 - time (sec): 59.78 - samples/sec: 418.02 - lr: 0.000048 - momentum: 0.000000
2023-10-19 01:43:54,683 epoch 2 - iter 215/432 - loss 0.43320350 - time (sec): 75.47 - samples/sec: 412.79 - lr: 0.000047 - momentum: 0.000000
2023-10-19 01:44:10,487 epoch 2 - iter 258/432 - loss 0.42523129 - time (sec): 91.27 - samples/sec: 411.43 - lr: 0.000047 - momentum: 0.000000
2023-10-19 01:44:24,503 epoch 2 - iter 301/432 - loss 0.41730337 - time (sec): 105.29 - samples/sec: 413.24 - lr: 0.000046 - momentum: 0.000000
2023-10-19 01:44:39,860 epoch 2 - iter 344/432 - loss 0.40943162 - time (sec): 120.64 - samples/sec: 412.31 - lr: 0.000046 - momentum: 0.000000
2023-10-19 01:44:55,802 epoch 2 - iter 387/432 - loss 0.40131277 - time (sec): 136.59 - samples/sec: 407.01 - lr: 0.000045 - momentum: 0.000000
2023-10-19 01:45:11,079 epoch 2 - iter 430/432 - loss 0.39353999 - time (sec): 151.86 - samples/sec: 406.04 - lr: 0.000044 - momentum: 0.000000
2023-10-19 01:45:11,757 ----------------------------------------------------------------------------------------------------
2023-10-19 01:45:11,758 EPOCH 2 done: loss 0.3936 - lr: 0.000044
2023-10-19 01:45:25,074 DEV : loss 0.34911495447158813 - f1-score (micro avg) 0.7839
2023-10-19 01:45:25,098 saving best model
2023-10-19 01:45:26,362 ----------------------------------------------------------------------------------------------------
2023-10-19 01:45:42,225 epoch 3 - iter 43/432 - loss 0.23809661 - time (sec): 15.86 - samples/sec: 384.64 - lr: 0.000044 - momentum: 0.000000
2023-10-19 01:45:56,725 epoch 3 - iter 86/432 - loss 0.25537867 - time (sec): 30.36 - samples/sec: 400.60 - lr: 0.000043 - momentum: 0.000000
2023-10-19 01:46:12,566 epoch 3 - iter 129/432 - loss 0.25249369 - time (sec): 46.20 - samples/sec: 397.89 - lr: 0.000043 - momentum: 0.000000
2023-10-19 01:46:28,424 epoch 3 - iter 172/432 - loss 0.24958478 - time (sec): 62.06 - samples/sec: 390.97 - lr: 0.000042 - momentum: 0.000000
2023-10-19 01:46:43,338 epoch 3 - iter 215/432 - loss 0.24589922 - time (sec): 76.98 - samples/sec: 394.71 - lr: 0.000042 - momentum: 0.000000
2023-10-19 01:46:57,935 epoch 3 - iter 258/432 - loss 0.24803978 - time (sec): 91.57 - samples/sec: 401.48 - lr: 0.000041 - momentum: 0.000000
2023-10-19 01:47:13,333 epoch 3 - iter 301/432 - loss 0.25300654 - time (sec): 106.97 - samples/sec: 400.09 - lr: 0.000041 - momentum: 0.000000
2023-10-19 01:47:27,657 epoch 3 - iter 344/432 - loss 0.25326885 - time (sec): 121.29 - samples/sec: 404.99 - lr: 0.000040 - momentum: 0.000000
2023-10-19 01:47:42,549 epoch 3 - iter 387/432 - loss 0.25155598 - time (sec): 136.19 - samples/sec: 405.65 - lr: 0.000039 - momentum: 0.000000
2023-10-19 01:47:58,354 epoch 3 - iter 430/432 - loss 0.24897874 - time (sec): 151.99 - samples/sec: 405.38 - lr: 0.000039 - momentum: 0.000000
2023-10-19 01:47:58,869 ----------------------------------------------------------------------------------------------------
2023-10-19 01:47:58,869 EPOCH 3 done: loss 0.2490 - lr: 0.000039
2023-10-19 01:48:12,087 DEV : loss 0.3246375322341919 - f1-score (micro avg) 0.8108
2023-10-19 01:48:12,111 saving best model
2023-10-19 01:48:13,359 ----------------------------------------------------------------------------------------------------
2023-10-19 01:48:27,749 epoch 4 - iter 43/432 - loss 0.15451661 - time (sec): 14.39 - samples/sec: 429.09 - lr: 0.000038 - momentum: 0.000000
2023-10-19 01:48:42,381 epoch 4 - iter 86/432 - loss 0.15328832 - time (sec): 29.02 - samples/sec: 427.64 - lr: 0.000038 - momentum: 0.000000
2023-10-19 01:48:57,422 epoch 4 - iter 129/432 - loss 0.16923728 - time (sec): 44.06 - samples/sec: 422.89 - lr: 0.000037 - momentum: 0.000000
2023-10-19 01:49:12,798 epoch 4 - iter 172/432 - loss 0.17532061 - time (sec): 59.44 - samples/sec: 418.25 - lr: 0.000037 - momentum: 0.000000
2023-10-19 01:49:27,957 epoch 4 - iter 215/432 - loss 0.18129161 - time (sec): 74.60 - samples/sec: 411.85 - lr: 0.000036 - momentum: 0.000000
2023-10-19 01:49:42,076 epoch 4 - iter 258/432 - loss 0.18102947 - time (sec): 88.71 - samples/sec: 414.35 - lr: 0.000036 - momentum: 0.000000
2023-10-19 01:49:56,693 epoch 4 - iter 301/432 - loss 0.17706809 - time (sec): 103.33 - samples/sec: 414.23 - lr: 0.000035 - momentum: 0.000000
2023-10-19 01:50:10,961 epoch 4 - iter 344/432 - loss 0.17600081 - time (sec): 117.60 - samples/sec: 420.72 - lr: 0.000034 - momentum: 0.000000
2023-10-19 01:50:26,404 epoch 4 - iter 387/432 - loss 0.17705983 - time (sec): 133.04 - samples/sec: 415.10 - lr: 0.000034 - momentum: 0.000000
2023-10-19 01:50:41,675 epoch 4 - iter 430/432 - loss 0.17678007 - time (sec): 148.31 - samples/sec: 415.08 - lr: 0.000033 - momentum: 0.000000
2023-10-19 01:50:42,245 ----------------------------------------------------------------------------------------------------
2023-10-19 01:50:42,245 EPOCH 4 done: loss 0.1773 - lr: 0.000033
2023-10-19 01:50:55,364 DEV : loss 0.29224464297294617 - f1-score (micro avg) 0.8349
2023-10-19 01:50:55,388 saving best model
2023-10-19 01:50:56,635 ----------------------------------------------------------------------------------------------------
2023-10-19 01:51:11,222 epoch 5 - iter 43/432 - loss 0.12751561 - time (sec): 14.59 - samples/sec: 398.73 - lr: 0.000033 - momentum: 0.000000
2023-10-19 01:51:25,804 epoch 5 - iter 86/432 - loss 0.12363292 - time (sec): 29.17 - samples/sec: 408.91 - lr: 0.000032 - momentum: 0.000000
2023-10-19 01:51:40,313 epoch 5 - iter 129/432 - loss 0.12950420 - time (sec): 43.68 - samples/sec: 420.14 - lr: 0.000032 - momentum: 0.000000
2023-10-19 01:51:54,408 epoch 5 - iter 172/432 - loss 0.12809390 - time (sec): 57.77 - samples/sec: 427.66 - lr: 0.000031 - momentum: 0.000000
2023-10-19 01:52:09,245 epoch 5 - iter 215/432 - loss 0.13394395 - time (sec): 72.61 - samples/sec: 424.89 - lr: 0.000031 - momentum: 0.000000
2023-10-19 01:52:25,088 epoch 5 - iter 258/432 - loss 0.13182392 - time (sec): 88.45 - samples/sec: 417.72 - lr: 0.000030 - momentum: 0.000000
2023-10-19 01:52:40,113 epoch 5 - iter 301/432 - loss 0.13212724 - time (sec): 103.48 - samples/sec: 416.20 - lr: 0.000029 - momentum: 0.000000
2023-10-19 01:52:55,382 epoch 5 - iter 344/432 - loss 0.13098423 - time (sec): 118.75 - samples/sec: 414.14 - lr: 0.000029 - momentum: 0.000000
2023-10-19 01:53:09,958 epoch 5 - iter 387/432 - loss 0.13216788 - time (sec): 133.32 - samples/sec: 416.82 - lr: 0.000028 - momentum: 0.000000
2023-10-19 01:53:25,239 epoch 5 - iter 430/432 - loss 0.13046149 - time (sec): 148.60 - samples/sec: 415.11 - lr: 0.000028 - momentum: 0.000000
2023-10-19 01:53:25,712 ----------------------------------------------------------------------------------------------------
2023-10-19 01:53:25,713 EPOCH 5 done: loss 0.1305 - lr: 0.000028
2023-10-19 01:53:39,313 DEV : loss 0.32371342182159424 - f1-score (micro avg) 0.8266
2023-10-19 01:53:39,360 ----------------------------------------------------------------------------------------------------
2023-10-19 01:53:55,116 epoch 6 - iter 43/432 - loss 0.08270545 - time (sec): 15.75 - samples/sec: 388.28 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:54:10,124 epoch 6 - iter 86/432 - loss 0.08062138 - time (sec): 30.76 - samples/sec: 396.33 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:54:25,180 epoch 6 - iter 129/432 - loss 0.08479993 - time (sec): 45.82 - samples/sec: 408.11 - lr: 0.000026 - momentum: 0.000000
2023-10-19 01:54:39,491 epoch 6 - iter 172/432 - loss 0.09233340 - time (sec): 60.13 - samples/sec: 414.18 - lr: 0.000026 - momentum: 0.000000
2023-10-19 01:54:54,018 epoch 6 - iter 215/432 - loss 0.09404072 - time (sec): 74.66 - samples/sec: 415.41 - lr: 0.000025 - momentum: 0.000000
2023-10-19 01:55:09,360 epoch 6 - iter 258/432 - loss 0.09241168 - time (sec): 90.00 - samples/sec: 412.03 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:55:24,823 epoch 6 - iter 301/432 - loss 0.09115702 - time (sec): 105.46 - samples/sec: 408.85 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:55:40,215 epoch 6 - iter 344/432 - loss 0.09173961 - time (sec): 120.85 - samples/sec: 410.46 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:55:55,726 epoch 6 - iter 387/432 - loss 0.09239848 - time (sec): 136.36 - samples/sec: 408.04 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:56:10,691 epoch 6 - iter 430/432 - loss 0.09560995 - time (sec): 151.33 - samples/sec: 407.44 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:56:11,371 ----------------------------------------------------------------------------------------------------
2023-10-19 01:56:11,371 EPOCH 6 done: loss 0.0956 - lr: 0.000022
2023-10-19 01:56:24,571 DEV : loss 0.33836397528648376 - f1-score (micro avg) 0.8366
2023-10-19 01:56:24,595 saving best model
2023-10-19 01:56:25,847 ----------------------------------------------------------------------------------------------------
2023-10-19 01:56:41,610 epoch 7 - iter 43/432 - loss 0.07430404 - time (sec): 15.76 - samples/sec: 395.59 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:56:56,421 epoch 7 - iter 86/432 - loss 0.07375232 - time (sec): 30.57 - samples/sec: 420.31 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:57:10,786 epoch 7 - iter 129/432 - loss 0.07598234 - time (sec): 44.94 - samples/sec: 416.57 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:57:26,303 epoch 7 - iter 172/432 - loss 0.07509303 - time (sec): 60.45 - samples/sec: 410.82 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:57:42,174 epoch 7 - iter 215/432 - loss 0.07645940 - time (sec): 76.33 - samples/sec: 406.76 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:57:57,853 epoch 7 - iter 258/432 - loss 0.07560066 - time (sec): 92.00 - samples/sec: 401.87 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:58:12,315 epoch 7 - iter 301/432 - loss 0.07564389 - time (sec): 106.47 - samples/sec: 404.02 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:58:26,427 epoch 7 - iter 344/432 - loss 0.07480741 - time (sec): 120.58 - samples/sec: 407.24 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:58:41,447 epoch 7 - iter 387/432 - loss 0.07468539 - time (sec): 135.60 - samples/sec: 408.08 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:58:57,103 epoch 7 - iter 430/432 - loss 0.07527820 - time (sec): 151.25 - samples/sec: 407.55 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:58:57,823 ----------------------------------------------------------------------------------------------------
2023-10-19 01:58:57,823 EPOCH 7 done: loss 0.0752 - lr: 0.000017
2023-10-19 01:59:11,170 DEV : loss 0.366791695356369 - f1-score (micro avg) 0.835
2023-10-19 01:59:11,195 ----------------------------------------------------------------------------------------------------
2023-10-19 01:59:26,059 epoch 8 - iter 43/432 - loss 0.05625100 - time (sec): 14.86 - samples/sec: 391.47 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:59:41,193 epoch 8 - iter 86/432 - loss 0.05428466 - time (sec): 30.00 - samples/sec: 402.91 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:59:56,249 epoch 8 - iter 129/432 - loss 0.05442877 - time (sec): 45.05 - samples/sec: 416.65 - lr: 0.000015 - momentum: 0.000000
2023-10-19 02:00:10,299 epoch 8 - iter 172/432 - loss 0.05554676 - time (sec): 59.10 - samples/sec: 418.21 - lr: 0.000014 - momentum: 0.000000
2023-10-19 02:00:26,123 epoch 8 - iter 215/432 - loss 0.05670463 - time (sec): 74.93 - samples/sec: 412.94 - lr: 0.000014 - momentum: 0.000000
2023-10-19 02:00:42,124 epoch 8 - iter 258/432 - loss 0.05639046 - time (sec): 90.93 - samples/sec: 412.58 - lr: 0.000013 - momentum: 0.000000
2023-10-19 02:00:58,560 epoch 8 - iter 301/432 - loss 0.05698070 - time (sec): 107.36 - samples/sec: 408.39 - lr: 0.000013 - momentum: 0.000000
2023-10-19 02:01:12,870 epoch 8 - iter 344/432 - loss 0.05669179 - time (sec): 121.67 - samples/sec: 410.66 - lr: 0.000012 - momentum: 0.000000
2023-10-19 02:01:27,187 epoch 8 - iter 387/432 - loss 0.05647273 - time (sec): 135.99 - samples/sec: 410.80 - lr: 0.000012 - momentum: 0.000000
2023-10-19 02:01:42,211 epoch 8 - iter 430/432 - loss 0.05599076 - time (sec): 151.01 - samples/sec: 408.03 - lr: 0.000011 - momentum: 0.000000
2023-10-19 02:01:42,730 ----------------------------------------------------------------------------------------------------
2023-10-19 02:01:42,730 EPOCH 8 done: loss 0.0559 - lr: 0.000011
2023-10-19 02:01:56,092 DEV : loss 0.3890858292579651 - f1-score (micro avg) 0.8455
2023-10-19 02:01:56,117 saving best model
2023-10-19 02:01:57,379 ----------------------------------------------------------------------------------------------------
2023-10-19 02:02:11,342 epoch 9 - iter 43/432 - loss 0.03669925 - time (sec): 13.96 - samples/sec: 437.43 - lr: 0.000011 - momentum: 0.000000
2023-10-19 02:02:25,561 epoch 9 - iter 86/432 - loss 0.03253165 - time (sec): 28.18 - samples/sec: 443.85 - lr: 0.000010 - momentum: 0.000000
2023-10-19 02:02:39,678 epoch 9 - iter 129/432 - loss 0.03230387 - time (sec): 42.30 - samples/sec: 436.34 - lr: 0.000009 - momentum: 0.000000
2023-10-19 02:02:54,485 epoch 9 - iter 172/432 - loss 0.03547786 - time (sec): 57.10 - samples/sec: 434.76 - lr: 0.000009 - momentum: 0.000000
2023-10-19 02:03:09,360 epoch 9 - iter 215/432 - loss 0.03554073 - time (sec): 71.98 - samples/sec: 431.86 - lr: 0.000008 - momentum: 0.000000
2023-10-19 02:03:24,437 epoch 9 - iter 258/432 - loss 0.03645877 - time (sec): 87.06 - samples/sec: 428.05 - lr: 0.000008 - momentum: 0.000000
2023-10-19 02:03:40,009 epoch 9 - iter 301/432 - loss 0.03894331 - time (sec): 102.63 - samples/sec: 422.18 - lr: 0.000007 - momentum: 0.000000
2023-10-19 02:03:54,976 epoch 9 - iter 344/432 - loss 0.04040420 - time (sec): 117.60 - samples/sec: 419.48 - lr: 0.000007 - momentum: 0.000000
2023-10-19 02:04:10,792 epoch 9 - iter 387/432 - loss 0.04188062 - time (sec): 133.41 - samples/sec: 414.28 - lr: 0.000006 - momentum: 0.000000
2023-10-19 02:04:25,690 epoch 9 - iter 430/432 - loss 0.04223260 - time (sec): 148.31 - samples/sec: 416.20 - lr: 0.000006 - momentum: 0.000000
2023-10-19 02:04:26,228 ----------------------------------------------------------------------------------------------------
2023-10-19 02:04:26,228 EPOCH 9 done: loss 0.0423 - lr: 0.000006
2023-10-19 02:04:39,946 DEV : loss 0.42729729413986206 - f1-score (micro avg) 0.8371
2023-10-19 02:04:39,970 ----------------------------------------------------------------------------------------------------
2023-10-19 02:04:55,624 epoch 10 - iter 43/432 - loss 0.02081255 - time (sec): 15.65 - samples/sec: 405.15 - lr: 0.000005 - momentum: 0.000000
2023-10-19 02:05:10,511 epoch 10 - iter 86/432 - loss 0.02735695 - time (sec): 30.54 - samples/sec: 415.62 - lr: 0.000004 - momentum: 0.000000
2023-10-19 02:05:24,272 epoch 10 - iter 129/432 - loss 0.03060242 - time (sec): 44.30 - samples/sec: 419.49 - lr: 0.000004 - momentum: 0.000000
2023-10-19 02:05:39,137 epoch 10 - iter 172/432 - loss 0.02883699 - time (sec): 59.17 - samples/sec: 420.60 - lr: 0.000003 - momentum: 0.000000
2023-10-19 02:05:53,697 epoch 10 - iter 215/432 - loss 0.03080710 - time (sec): 73.73 - samples/sec: 418.95 - lr: 0.000003 - momentum: 0.000000
2023-10-19 02:06:08,310 epoch 10 - iter 258/432 - loss 0.03245300 - time (sec): 88.34 - samples/sec: 417.77 - lr: 0.000002 - momentum: 0.000000
2023-10-19 02:06:23,371 epoch 10 - iter 301/432 - loss 0.03296380 - time (sec): 103.40 - samples/sec: 418.36 - lr: 0.000002 - momentum: 0.000000
2023-10-19 02:06:39,073 epoch 10 - iter 344/432 - loss 0.03338415 - time (sec): 119.10 - samples/sec: 414.26 - lr: 0.000001 - momentum: 0.000000
2023-10-19 02:06:53,055 epoch 10 - iter 387/432 - loss 0.03464620 - time (sec): 133.08 - samples/sec: 418.93 - lr: 0.000001 - momentum: 0.000000
2023-10-19 02:07:08,821 epoch 10 - iter 430/432 - loss 0.03437346 - time (sec): 148.85 - samples/sec: 413.85 - lr: 0.000000 - momentum: 0.000000
2023-10-19 02:07:09,419 ----------------------------------------------------------------------------------------------------
2023-10-19 02:07:09,420 EPOCH 10 done: loss 0.0344 - lr: 0.000000
2023-10-19 02:07:22,605 DEV : loss 0.4345364570617676 - f1-score (micro avg) 0.8397
2023-10-19 02:07:23,067 ----------------------------------------------------------------------------------------------------
2023-10-19 02:07:23,068 Loading model from best epoch ...
2023-10-19 02:07:25,281 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 02:07:43,100
Results:
- F-score (micro) 0.752
- F-score (macro) 0.5641
- Accuracy 0.6451
By class:
precision recall f1-score support
location-stop 0.8407 0.8484 0.8445 765
trigger 0.6564 0.5138 0.5764 833
location 0.7890 0.8376 0.8125 665
location-city 0.8415 0.8534 0.8474 566
date 0.9040 0.8604 0.8817 394
location-street 0.9471 0.8808 0.9128 386
time 0.7862 0.8906 0.8352 256
location-route 0.7375 0.6725 0.7035 284
organization-company 0.8309 0.6825 0.7495 252
distance 0.9881 0.9940 0.9910 167
number 0.7135 0.8188 0.7625 149
duration 0.3185 0.3067 0.3125 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.9500 0.2754 0.4270 69
organization 0.5200 0.4643 0.4906 28
person 0.4444 0.8000 0.5714 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 0.7493 0.7548 0.7520 4988
macro avg 0.5930 0.5631 0.5641 4988
weighted avg 0.7900 0.7548 0.7673 4988
2023-10-19 02:07:43,100 ----------------------------------------------------------------------------------------------------
|