File size: 25,503 Bytes
b428604 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 |
2023-10-18 23:22:09,534 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,535 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()
)"
2023-10-18 23:22:09,535 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,536 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-18 23:22:09,536 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,536 Train: 6900 sentences
2023-10-18 23:22:09,536 (train_with_dev=False, train_with_test=False)
2023-10-18 23:22:09,536 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,536 Training Params:
2023-10-18 23:22:09,536 - learning_rate: "3e-05"
2023-10-18 23:22:09,536 - mini_batch_size: "16"
2023-10-18 23:22:09,536 - max_epochs: "10"
2023-10-18 23:22:09,536 - shuffle: "True"
2023-10-18 23:22:09,536 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,536 Plugins:
2023-10-18 23:22:09,536 - TensorboardLogger
2023-10-18 23:22:09,536 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 23:22:09,536 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,537 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 23:22:09,537 - metric: "('micro avg', 'f1-score')"
2023-10-18 23:22:09,537 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,537 Computation:
2023-10-18 23:22:09,537 - compute on device: cuda:0
2023-10-18 23:22:09,537 - embedding storage: none
2023-10-18 23:22:09,537 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,537 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-1"
2023-10-18 23:22:09,537 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,537 ----------------------------------------------------------------------------------------------------
2023-10-18 23:22:09,537 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 23:22:23,535 epoch 1 - iter 43/432 - loss 4.75760576 - time (sec): 14.00 - samples/sec: 432.61 - lr: 0.000003 - momentum: 0.000000
2023-10-18 23:22:37,284 epoch 1 - iter 86/432 - loss 3.79168637 - time (sec): 27.75 - samples/sec: 437.08 - lr: 0.000006 - momentum: 0.000000
2023-10-18 23:22:51,418 epoch 1 - iter 129/432 - loss 3.15291761 - time (sec): 41.88 - samples/sec: 438.07 - lr: 0.000009 - momentum: 0.000000
2023-10-18 23:23:04,784 epoch 1 - iter 172/432 - loss 2.77724614 - time (sec): 55.25 - samples/sec: 443.10 - lr: 0.000012 - momentum: 0.000000
2023-10-18 23:23:19,237 epoch 1 - iter 215/432 - loss 2.50566279 - time (sec): 69.70 - samples/sec: 436.43 - lr: 0.000015 - momentum: 0.000000
2023-10-18 23:23:32,744 epoch 1 - iter 258/432 - loss 2.27969539 - time (sec): 83.20 - samples/sec: 440.95 - lr: 0.000018 - momentum: 0.000000
2023-10-18 23:23:46,386 epoch 1 - iter 301/432 - loss 2.08743805 - time (sec): 96.85 - samples/sec: 445.69 - lr: 0.000021 - momentum: 0.000000
2023-10-18 23:24:00,733 epoch 1 - iter 344/432 - loss 1.94157999 - time (sec): 111.19 - samples/sec: 442.51 - lr: 0.000024 - momentum: 0.000000
2023-10-18 23:24:14,915 epoch 1 - iter 387/432 - loss 1.81951311 - time (sec): 125.38 - samples/sec: 439.73 - lr: 0.000027 - momentum: 0.000000
2023-10-18 23:24:29,890 epoch 1 - iter 430/432 - loss 1.70026851 - time (sec): 140.35 - samples/sec: 439.60 - lr: 0.000030 - momentum: 0.000000
2023-10-18 23:24:30,425 ----------------------------------------------------------------------------------------------------
2023-10-18 23:24:30,425 EPOCH 1 done: loss 1.6981 - lr: 0.000030
2023-10-18 23:24:43,545 DEV : loss 0.5471832156181335 - f1-score (micro avg) 0.667
2023-10-18 23:24:43,569 saving best model
2023-10-18 23:24:44,053 ----------------------------------------------------------------------------------------------------
2023-10-18 23:24:58,280 epoch 2 - iter 43/432 - loss 0.61594785 - time (sec): 14.23 - samples/sec: 447.65 - lr: 0.000030 - momentum: 0.000000
2023-10-18 23:25:11,929 epoch 2 - iter 86/432 - loss 0.58438105 - time (sec): 27.87 - samples/sec: 445.89 - lr: 0.000029 - momentum: 0.000000
2023-10-18 23:25:25,850 epoch 2 - iter 129/432 - loss 0.57439156 - time (sec): 41.80 - samples/sec: 439.74 - lr: 0.000029 - momentum: 0.000000
2023-10-18 23:25:40,059 epoch 2 - iter 172/432 - loss 0.54614426 - time (sec): 56.00 - samples/sec: 441.70 - lr: 0.000029 - momentum: 0.000000
2023-10-18 23:25:55,802 epoch 2 - iter 215/432 - loss 0.52793380 - time (sec): 71.75 - samples/sec: 432.46 - lr: 0.000028 - momentum: 0.000000
2023-10-18 23:26:10,341 epoch 2 - iter 258/432 - loss 0.51499945 - time (sec): 86.29 - samples/sec: 434.31 - lr: 0.000028 - momentum: 0.000000
2023-10-18 23:26:25,316 epoch 2 - iter 301/432 - loss 0.49807920 - time (sec): 101.26 - samples/sec: 432.03 - lr: 0.000028 - momentum: 0.000000
2023-10-18 23:26:40,222 epoch 2 - iter 344/432 - loss 0.48644736 - time (sec): 116.17 - samples/sec: 427.66 - lr: 0.000027 - momentum: 0.000000
2023-10-18 23:26:55,249 epoch 2 - iter 387/432 - loss 0.47199609 - time (sec): 131.19 - samples/sec: 424.24 - lr: 0.000027 - momentum: 0.000000
2023-10-18 23:27:11,118 epoch 2 - iter 430/432 - loss 0.46618631 - time (sec): 147.06 - samples/sec: 419.72 - lr: 0.000027 - momentum: 0.000000
2023-10-18 23:27:11,659 ----------------------------------------------------------------------------------------------------
2023-10-18 23:27:11,660 EPOCH 2 done: loss 0.4659 - lr: 0.000027
2023-10-18 23:27:24,698 DEV : loss 0.3461967706680298 - f1-score (micro avg) 0.7729
2023-10-18 23:27:24,722 saving best model
2023-10-18 23:27:26,021 ----------------------------------------------------------------------------------------------------
2023-10-18 23:27:40,354 epoch 3 - iter 43/432 - loss 0.31214822 - time (sec): 14.33 - samples/sec: 426.90 - lr: 0.000026 - momentum: 0.000000
2023-10-18 23:27:54,896 epoch 3 - iter 86/432 - loss 0.31299760 - time (sec): 28.87 - samples/sec: 421.26 - lr: 0.000026 - momentum: 0.000000
2023-10-18 23:28:09,898 epoch 3 - iter 129/432 - loss 0.30484547 - time (sec): 43.87 - samples/sec: 413.81 - lr: 0.000026 - momentum: 0.000000
2023-10-18 23:28:24,971 epoch 3 - iter 172/432 - loss 0.29888479 - time (sec): 58.95 - samples/sec: 412.70 - lr: 0.000025 - momentum: 0.000000
2023-10-18 23:28:40,149 epoch 3 - iter 215/432 - loss 0.30051912 - time (sec): 74.13 - samples/sec: 411.07 - lr: 0.000025 - momentum: 0.000000
2023-10-18 23:28:54,889 epoch 3 - iter 258/432 - loss 0.30047825 - time (sec): 88.87 - samples/sec: 416.03 - lr: 0.000025 - momentum: 0.000000
2023-10-18 23:29:09,664 epoch 3 - iter 301/432 - loss 0.29923078 - time (sec): 103.64 - samples/sec: 415.85 - lr: 0.000024 - momentum: 0.000000
2023-10-18 23:29:23,721 epoch 3 - iter 344/432 - loss 0.29751234 - time (sec): 117.70 - samples/sec: 420.53 - lr: 0.000024 - momentum: 0.000000
2023-10-18 23:29:38,262 epoch 3 - iter 387/432 - loss 0.29353934 - time (sec): 132.24 - samples/sec: 421.84 - lr: 0.000024 - momentum: 0.000000
2023-10-18 23:29:52,819 epoch 3 - iter 430/432 - loss 0.29071211 - time (sec): 146.80 - samples/sec: 420.39 - lr: 0.000023 - momentum: 0.000000
2023-10-18 23:29:53,454 ----------------------------------------------------------------------------------------------------
2023-10-18 23:29:53,455 EPOCH 3 done: loss 0.2903 - lr: 0.000023
2023-10-18 23:30:06,931 DEV : loss 0.30047762393951416 - f1-score (micro avg) 0.8112
2023-10-18 23:30:06,955 saving best model
2023-10-18 23:30:08,235 ----------------------------------------------------------------------------------------------------
2023-10-18 23:30:21,918 epoch 4 - iter 43/432 - loss 0.21553125 - time (sec): 13.68 - samples/sec: 480.79 - lr: 0.000023 - momentum: 0.000000
2023-10-18 23:30:37,085 epoch 4 - iter 86/432 - loss 0.22053010 - time (sec): 28.85 - samples/sec: 442.52 - lr: 0.000023 - momentum: 0.000000
2023-10-18 23:30:51,506 epoch 4 - iter 129/432 - loss 0.21910439 - time (sec): 43.27 - samples/sec: 440.91 - lr: 0.000022 - momentum: 0.000000
2023-10-18 23:31:05,246 epoch 4 - iter 172/432 - loss 0.21474027 - time (sec): 57.01 - samples/sec: 440.47 - lr: 0.000022 - momentum: 0.000000
2023-10-18 23:31:20,509 epoch 4 - iter 215/432 - loss 0.21802691 - time (sec): 72.27 - samples/sec: 437.99 - lr: 0.000022 - momentum: 0.000000
2023-10-18 23:31:35,462 epoch 4 - iter 258/432 - loss 0.21679757 - time (sec): 87.23 - samples/sec: 436.00 - lr: 0.000021 - momentum: 0.000000
2023-10-18 23:31:50,145 epoch 4 - iter 301/432 - loss 0.21374962 - time (sec): 101.91 - samples/sec: 432.60 - lr: 0.000021 - momentum: 0.000000
2023-10-18 23:32:04,748 epoch 4 - iter 344/432 - loss 0.20945206 - time (sec): 116.51 - samples/sec: 425.91 - lr: 0.000021 - momentum: 0.000000
2023-10-18 23:32:19,960 epoch 4 - iter 387/432 - loss 0.20989087 - time (sec): 131.72 - samples/sec: 423.09 - lr: 0.000020 - momentum: 0.000000
2023-10-18 23:32:35,115 epoch 4 - iter 430/432 - loss 0.20942007 - time (sec): 146.88 - samples/sec: 419.77 - lr: 0.000020 - momentum: 0.000000
2023-10-18 23:32:35,716 ----------------------------------------------------------------------------------------------------
2023-10-18 23:32:35,717 EPOCH 4 done: loss 0.2089 - lr: 0.000020
2023-10-18 23:32:48,612 DEV : loss 0.305877149105072 - f1-score (micro avg) 0.8234
2023-10-18 23:32:48,636 saving best model
2023-10-18 23:32:49,920 ----------------------------------------------------------------------------------------------------
2023-10-18 23:33:03,649 epoch 5 - iter 43/432 - loss 0.16781001 - time (sec): 13.73 - samples/sec: 423.90 - lr: 0.000020 - momentum: 0.000000
2023-10-18 23:33:18,972 epoch 5 - iter 86/432 - loss 0.16626377 - time (sec): 29.05 - samples/sec: 408.16 - lr: 0.000019 - momentum: 0.000000
2023-10-18 23:33:34,071 epoch 5 - iter 129/432 - loss 0.16260592 - time (sec): 44.15 - samples/sec: 402.67 - lr: 0.000019 - momentum: 0.000000
2023-10-18 23:33:48,740 epoch 5 - iter 172/432 - loss 0.15898066 - time (sec): 58.82 - samples/sec: 408.49 - lr: 0.000019 - momentum: 0.000000
2023-10-18 23:34:02,726 epoch 5 - iter 215/432 - loss 0.16434122 - time (sec): 72.80 - samples/sec: 411.18 - lr: 0.000018 - momentum: 0.000000
2023-10-18 23:34:17,574 epoch 5 - iter 258/432 - loss 0.16206014 - time (sec): 87.65 - samples/sec: 411.29 - lr: 0.000018 - momentum: 0.000000
2023-10-18 23:34:32,583 epoch 5 - iter 301/432 - loss 0.16111024 - time (sec): 102.66 - samples/sec: 415.20 - lr: 0.000018 - momentum: 0.000000
2023-10-18 23:34:45,435 epoch 5 - iter 344/432 - loss 0.15932449 - time (sec): 115.51 - samples/sec: 425.07 - lr: 0.000017 - momentum: 0.000000
2023-10-18 23:35:00,356 epoch 5 - iter 387/432 - loss 0.15868495 - time (sec): 130.44 - samples/sec: 424.17 - lr: 0.000017 - momentum: 0.000000
2023-10-18 23:35:15,913 epoch 5 - iter 430/432 - loss 0.16100694 - time (sec): 145.99 - samples/sec: 422.70 - lr: 0.000017 - momentum: 0.000000
2023-10-18 23:35:16,398 ----------------------------------------------------------------------------------------------------
2023-10-18 23:35:16,398 EPOCH 5 done: loss 0.1609 - lr: 0.000017
2023-10-18 23:35:29,484 DEV : loss 0.3180467188358307 - f1-score (micro avg) 0.8266
2023-10-18 23:35:29,508 saving best model
2023-10-18 23:35:31,528 ----------------------------------------------------------------------------------------------------
2023-10-18 23:35:46,762 epoch 6 - iter 43/432 - loss 0.12139549 - time (sec): 15.23 - samples/sec: 407.36 - lr: 0.000016 - momentum: 0.000000
2023-10-18 23:36:00,910 epoch 6 - iter 86/432 - loss 0.11575687 - time (sec): 29.38 - samples/sec: 437.71 - lr: 0.000016 - momentum: 0.000000
2023-10-18 23:36:15,240 epoch 6 - iter 129/432 - loss 0.12824583 - time (sec): 43.71 - samples/sec: 430.95 - lr: 0.000016 - momentum: 0.000000
2023-10-18 23:36:30,980 epoch 6 - iter 172/432 - loss 0.12638379 - time (sec): 59.45 - samples/sec: 423.77 - lr: 0.000015 - momentum: 0.000000
2023-10-18 23:36:45,226 epoch 6 - iter 215/432 - loss 0.12726516 - time (sec): 73.70 - samples/sec: 418.04 - lr: 0.000015 - momentum: 0.000000
2023-10-18 23:36:59,489 epoch 6 - iter 258/432 - loss 0.12675820 - time (sec): 87.96 - samples/sec: 420.41 - lr: 0.000015 - momentum: 0.000000
2023-10-18 23:37:13,934 epoch 6 - iter 301/432 - loss 0.12721952 - time (sec): 102.40 - samples/sec: 422.27 - lr: 0.000014 - momentum: 0.000000
2023-10-18 23:37:28,404 epoch 6 - iter 344/432 - loss 0.12580091 - time (sec): 116.87 - samples/sec: 423.39 - lr: 0.000014 - momentum: 0.000000
2023-10-18 23:37:43,360 epoch 6 - iter 387/432 - loss 0.12657720 - time (sec): 131.83 - samples/sec: 420.95 - lr: 0.000014 - momentum: 0.000000
2023-10-18 23:37:59,227 epoch 6 - iter 430/432 - loss 0.12513388 - time (sec): 147.70 - samples/sec: 417.76 - lr: 0.000013 - momentum: 0.000000
2023-10-18 23:37:59,751 ----------------------------------------------------------------------------------------------------
2023-10-18 23:37:59,752 EPOCH 6 done: loss 0.1251 - lr: 0.000013
2023-10-18 23:38:12,663 DEV : loss 0.3315909206867218 - f1-score (micro avg) 0.8341
2023-10-18 23:38:12,687 saving best model
2023-10-18 23:38:14,325 ----------------------------------------------------------------------------------------------------
2023-10-18 23:38:29,359 epoch 7 - iter 43/432 - loss 0.10710781 - time (sec): 15.03 - samples/sec: 394.00 - lr: 0.000013 - momentum: 0.000000
2023-10-18 23:38:44,447 epoch 7 - iter 86/432 - loss 0.10505496 - time (sec): 30.12 - samples/sec: 392.29 - lr: 0.000013 - momentum: 0.000000
2023-10-18 23:38:58,461 epoch 7 - iter 129/432 - loss 0.10484843 - time (sec): 44.14 - samples/sec: 414.75 - lr: 0.000012 - momentum: 0.000000
2023-10-18 23:39:12,787 epoch 7 - iter 172/432 - loss 0.10096346 - time (sec): 58.46 - samples/sec: 427.77 - lr: 0.000012 - momentum: 0.000000
2023-10-18 23:39:27,646 epoch 7 - iter 215/432 - loss 0.10332899 - time (sec): 73.32 - samples/sec: 422.47 - lr: 0.000012 - momentum: 0.000000
2023-10-18 23:39:41,653 epoch 7 - iter 258/432 - loss 0.10374389 - time (sec): 87.33 - samples/sec: 426.79 - lr: 0.000011 - momentum: 0.000000
2023-10-18 23:39:56,082 epoch 7 - iter 301/432 - loss 0.10457902 - time (sec): 101.76 - samples/sec: 427.53 - lr: 0.000011 - momentum: 0.000000
2023-10-18 23:40:10,410 epoch 7 - iter 344/432 - loss 0.10312114 - time (sec): 116.08 - samples/sec: 427.08 - lr: 0.000011 - momentum: 0.000000
2023-10-18 23:40:24,795 epoch 7 - iter 387/432 - loss 0.10178810 - time (sec): 130.47 - samples/sec: 424.05 - lr: 0.000010 - momentum: 0.000000
2023-10-18 23:40:38,988 epoch 7 - iter 430/432 - loss 0.10028660 - time (sec): 144.66 - samples/sec: 425.77 - lr: 0.000010 - momentum: 0.000000
2023-10-18 23:40:39,561 ----------------------------------------------------------------------------------------------------
2023-10-18 23:40:39,561 EPOCH 7 done: loss 0.1006 - lr: 0.000010
2023-10-18 23:40:52,891 DEV : loss 0.3369572162628174 - f1-score (micro avg) 0.8346
2023-10-18 23:40:52,915 saving best model
2023-10-18 23:40:54,216 ----------------------------------------------------------------------------------------------------
2023-10-18 23:41:08,861 epoch 8 - iter 43/432 - loss 0.07187557 - time (sec): 14.64 - samples/sec: 425.38 - lr: 0.000010 - momentum: 0.000000
2023-10-18 23:41:22,173 epoch 8 - iter 86/432 - loss 0.07672505 - time (sec): 27.96 - samples/sec: 444.34 - lr: 0.000009 - momentum: 0.000000
2023-10-18 23:41:37,793 epoch 8 - iter 129/432 - loss 0.07576497 - time (sec): 43.58 - samples/sec: 422.76 - lr: 0.000009 - momentum: 0.000000
2023-10-18 23:41:52,650 epoch 8 - iter 172/432 - loss 0.07916836 - time (sec): 58.43 - samples/sec: 415.35 - lr: 0.000009 - momentum: 0.000000
2023-10-18 23:42:06,898 epoch 8 - iter 215/432 - loss 0.08050354 - time (sec): 72.68 - samples/sec: 417.26 - lr: 0.000008 - momentum: 0.000000
2023-10-18 23:42:21,388 epoch 8 - iter 258/432 - loss 0.07912664 - time (sec): 87.17 - samples/sec: 419.35 - lr: 0.000008 - momentum: 0.000000
2023-10-18 23:42:36,467 epoch 8 - iter 301/432 - loss 0.07933223 - time (sec): 102.25 - samples/sec: 417.28 - lr: 0.000008 - momentum: 0.000000
2023-10-18 23:42:51,389 epoch 8 - iter 344/432 - loss 0.08115197 - time (sec): 117.17 - samples/sec: 415.73 - lr: 0.000007 - momentum: 0.000000
2023-10-18 23:43:07,766 epoch 8 - iter 387/432 - loss 0.08121199 - time (sec): 133.55 - samples/sec: 411.15 - lr: 0.000007 - momentum: 0.000000
2023-10-18 23:43:22,779 epoch 8 - iter 430/432 - loss 0.08078528 - time (sec): 148.56 - samples/sec: 415.04 - lr: 0.000007 - momentum: 0.000000
2023-10-18 23:43:23,350 ----------------------------------------------------------------------------------------------------
2023-10-18 23:43:23,351 EPOCH 8 done: loss 0.0807 - lr: 0.000007
2023-10-18 23:43:36,626 DEV : loss 0.36578330397605896 - f1-score (micro avg) 0.8352
2023-10-18 23:43:36,651 saving best model
2023-10-18 23:43:37,939 ----------------------------------------------------------------------------------------------------
2023-10-18 23:43:51,874 epoch 9 - iter 43/432 - loss 0.06019569 - time (sec): 13.93 - samples/sec: 459.92 - lr: 0.000006 - momentum: 0.000000
2023-10-18 23:44:05,890 epoch 9 - iter 86/432 - loss 0.05939192 - time (sec): 27.95 - samples/sec: 441.92 - lr: 0.000006 - momentum: 0.000000
2023-10-18 23:44:21,211 epoch 9 - iter 129/432 - loss 0.06399840 - time (sec): 43.27 - samples/sec: 426.90 - lr: 0.000006 - momentum: 0.000000
2023-10-18 23:44:36,731 epoch 9 - iter 172/432 - loss 0.06426966 - time (sec): 58.79 - samples/sec: 421.31 - lr: 0.000005 - momentum: 0.000000
2023-10-18 23:44:51,226 epoch 9 - iter 215/432 - loss 0.06330203 - time (sec): 73.29 - samples/sec: 424.79 - lr: 0.000005 - momentum: 0.000000
2023-10-18 23:45:06,543 epoch 9 - iter 258/432 - loss 0.06371165 - time (sec): 88.60 - samples/sec: 420.93 - lr: 0.000005 - momentum: 0.000000
2023-10-18 23:45:21,139 epoch 9 - iter 301/432 - loss 0.06531644 - time (sec): 103.20 - samples/sec: 422.93 - lr: 0.000004 - momentum: 0.000000
2023-10-18 23:45:36,684 epoch 9 - iter 344/432 - loss 0.06594531 - time (sec): 118.74 - samples/sec: 416.32 - lr: 0.000004 - momentum: 0.000000
2023-10-18 23:45:51,785 epoch 9 - iter 387/432 - loss 0.06530243 - time (sec): 133.84 - samples/sec: 414.80 - lr: 0.000004 - momentum: 0.000000
2023-10-18 23:46:06,616 epoch 9 - iter 430/432 - loss 0.06528131 - time (sec): 148.67 - samples/sec: 414.55 - lr: 0.000003 - momentum: 0.000000
2023-10-18 23:46:07,145 ----------------------------------------------------------------------------------------------------
2023-10-18 23:46:07,145 EPOCH 9 done: loss 0.0652 - lr: 0.000003
2023-10-18 23:46:20,567 DEV : loss 0.36841511726379395 - f1-score (micro avg) 0.8392
2023-10-18 23:46:20,592 saving best model
2023-10-18 23:46:21,872 ----------------------------------------------------------------------------------------------------
2023-10-18 23:46:36,539 epoch 10 - iter 43/432 - loss 0.06456485 - time (sec): 14.67 - samples/sec: 408.84 - lr: 0.000003 - momentum: 0.000000
2023-10-18 23:46:50,973 epoch 10 - iter 86/432 - loss 0.05967601 - time (sec): 29.10 - samples/sec: 408.80 - lr: 0.000003 - momentum: 0.000000
2023-10-18 23:47:04,800 epoch 10 - iter 129/432 - loss 0.06175374 - time (sec): 42.93 - samples/sec: 426.06 - lr: 0.000002 - momentum: 0.000000
2023-10-18 23:47:19,977 epoch 10 - iter 172/432 - loss 0.06001026 - time (sec): 58.10 - samples/sec: 423.29 - lr: 0.000002 - momentum: 0.000000
2023-10-18 23:47:34,542 epoch 10 - iter 215/432 - loss 0.05644803 - time (sec): 72.67 - samples/sec: 424.43 - lr: 0.000002 - momentum: 0.000000
2023-10-18 23:47:50,093 epoch 10 - iter 258/432 - loss 0.05666523 - time (sec): 88.22 - samples/sec: 419.44 - lr: 0.000001 - momentum: 0.000000
2023-10-18 23:48:04,554 epoch 10 - iter 301/432 - loss 0.05586013 - time (sec): 102.68 - samples/sec: 418.50 - lr: 0.000001 - momentum: 0.000000
2023-10-18 23:48:20,545 epoch 10 - iter 344/432 - loss 0.05609200 - time (sec): 118.67 - samples/sec: 414.11 - lr: 0.000001 - momentum: 0.000000
2023-10-18 23:48:36,202 epoch 10 - iter 387/432 - loss 0.05754005 - time (sec): 134.33 - samples/sec: 412.96 - lr: 0.000000 - momentum: 0.000000
2023-10-18 23:48:51,086 epoch 10 - iter 430/432 - loss 0.05860056 - time (sec): 149.21 - samples/sec: 413.03 - lr: 0.000000 - momentum: 0.000000
2023-10-18 23:48:51,652 ----------------------------------------------------------------------------------------------------
2023-10-18 23:48:51,652 EPOCH 10 done: loss 0.0585 - lr: 0.000000
2023-10-18 23:49:05,067 DEV : loss 0.37858790159225464 - f1-score (micro avg) 0.8379
2023-10-18 23:49:05,601 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:05,602 Loading model from best epoch ...
2023-10-18 23:49:07,975 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
2023-10-18 23:49:26,029
Results:
- F-score (micro) 0.7661
- F-score (macro) 0.5763
- Accuracy 0.6675
By class:
precision recall f1-score support
trigger 0.7225 0.6218 0.6684 833
location-stop 0.8467 0.8301 0.8383 765
location 0.8017 0.8451 0.8228 665
location-city 0.8006 0.8728 0.8352 566
date 0.8836 0.8477 0.8653 394
location-street 0.9465 0.8705 0.9069 386
time 0.7759 0.8789 0.8242 256
location-route 0.8653 0.7465 0.8015 284
organization-company 0.7600 0.6786 0.7170 252
distance 0.9940 1.0000 0.9970 167
number 0.6868 0.8389 0.7553 149
duration 0.3377 0.3190 0.3281 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.9259 0.3623 0.5208 69
organization 0.5000 0.5357 0.5172 28
person 0.4211 0.8000 0.5517 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 0.7550 0.7777 0.7661 4988
macro avg 0.5931 0.5815 0.5763 4988
weighted avg 0.8001 0.7777 0.7852 4988
2023-10-18 23:49:26,029 ----------------------------------------------------------------------------------------------------
|