File size: 25,457 Bytes
5d1f60b |
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 |
2023-10-19 01:11:50,079 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,080 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 01:11:50,080 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,080 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 01:11:50,080 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,081 Train: 6900 sentences
2023-10-19 01:11:50,081 (train_with_dev=False, train_with_test=False)
2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,081 Training Params:
2023-10-19 01:11:50,081 - learning_rate: "3e-05"
2023-10-19 01:11:50,081 - mini_batch_size: "16"
2023-10-19 01:11:50,081 - max_epochs: "10"
2023-10-19 01:11:50,081 - shuffle: "True"
2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,081 Plugins:
2023-10-19 01:11:50,081 - TensorboardLogger
2023-10-19 01:11:50,081 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,081 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 01:11:50,081 - metric: "('micro avg', 'f1-score')"
2023-10-19 01:11:50,081 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,081 Computation:
2023-10-19 01:11:50,081 - compute on device: cuda:0
2023-10-19 01:11:50,082 - embedding storage: none
2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,082 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-3"
2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,082 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:50,082 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 01:12:04,567 epoch 1 - iter 43/432 - loss 4.48039409 - time (sec): 14.48 - samples/sec: 428.48 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:12:19,172 epoch 1 - iter 86/432 - loss 3.60384065 - time (sec): 29.09 - samples/sec: 419.78 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:12:34,227 epoch 1 - iter 129/432 - loss 3.00100989 - time (sec): 44.14 - samples/sec: 420.06 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:12:48,856 epoch 1 - iter 172/432 - loss 2.67529242 - time (sec): 58.77 - samples/sec: 419.88 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:13:03,508 epoch 1 - iter 215/432 - loss 2.41800710 - time (sec): 73.43 - samples/sec: 420.32 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:13:18,780 epoch 1 - iter 258/432 - loss 2.20845718 - time (sec): 88.70 - samples/sec: 417.62 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:13:33,474 epoch 1 - iter 301/432 - loss 2.03382086 - time (sec): 103.39 - samples/sec: 419.31 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:13:48,681 epoch 1 - iter 344/432 - loss 1.89777717 - time (sec): 118.60 - samples/sec: 415.73 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:14:03,153 epoch 1 - iter 387/432 - loss 1.77824460 - time (sec): 133.07 - samples/sec: 417.50 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:14:17,180 epoch 1 - iter 430/432 - loss 1.66845790 - time (sec): 147.10 - samples/sec: 419.34 - lr: 0.000030 - momentum: 0.000000
2023-10-19 01:14:17,812 ----------------------------------------------------------------------------------------------------
2023-10-19 01:14:17,813 EPOCH 1 done: loss 1.6662 - lr: 0.000030
2023-10-19 01:14:31,290 DEV : loss 0.5518006086349487 - f1-score (micro avg) 0.633
2023-10-19 01:14:31,318 saving best model
2023-10-19 01:14:31,797 ----------------------------------------------------------------------------------------------------
2023-10-19 01:14:46,715 epoch 2 - iter 43/432 - loss 0.58848912 - time (sec): 14.92 - samples/sec: 418.67 - lr: 0.000030 - momentum: 0.000000
2023-10-19 01:15:01,216 epoch 2 - iter 86/432 - loss 0.57906599 - time (sec): 29.42 - samples/sec: 416.84 - lr: 0.000029 - momentum: 0.000000
2023-10-19 01:15:16,263 epoch 2 - iter 129/432 - loss 0.55687926 - time (sec): 44.46 - samples/sec: 415.80 - lr: 0.000029 - momentum: 0.000000
2023-10-19 01:15:31,483 epoch 2 - iter 172/432 - loss 0.54911765 - time (sec): 59.68 - samples/sec: 418.70 - lr: 0.000029 - momentum: 0.000000
2023-10-19 01:15:47,092 epoch 2 - iter 215/432 - loss 0.53928280 - time (sec): 75.29 - samples/sec: 413.74 - lr: 0.000028 - momentum: 0.000000
2023-10-19 01:16:02,710 epoch 2 - iter 258/432 - loss 0.52556553 - time (sec): 90.91 - samples/sec: 413.06 - lr: 0.000028 - momentum: 0.000000
2023-10-19 01:16:16,574 epoch 2 - iter 301/432 - loss 0.51270046 - time (sec): 104.77 - samples/sec: 415.26 - lr: 0.000028 - momentum: 0.000000
2023-10-19 01:16:31,736 epoch 2 - iter 344/432 - loss 0.49960162 - time (sec): 119.94 - samples/sec: 414.74 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:16:47,479 epoch 2 - iter 387/432 - loss 0.48792945 - time (sec): 135.68 - samples/sec: 409.73 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:17:02,658 epoch 2 - iter 430/432 - loss 0.47759296 - time (sec): 150.86 - samples/sec: 408.74 - lr: 0.000027 - momentum: 0.000000
2023-10-19 01:17:03,329 ----------------------------------------------------------------------------------------------------
2023-10-19 01:17:03,329 EPOCH 2 done: loss 0.4774 - lr: 0.000027
2023-10-19 01:17:16,639 DEV : loss 0.3671756088733673 - f1-score (micro avg) 0.7689
2023-10-19 01:17:16,662 saving best model
2023-10-19 01:17:17,961 ----------------------------------------------------------------------------------------------------
2023-10-19 01:17:33,883 epoch 3 - iter 43/432 - loss 0.30082443 - time (sec): 15.92 - samples/sec: 383.21 - lr: 0.000026 - momentum: 0.000000
2023-10-19 01:17:48,498 epoch 3 - iter 86/432 - loss 0.31439609 - time (sec): 30.54 - samples/sec: 398.31 - lr: 0.000026 - momentum: 0.000000
2023-10-19 01:18:04,454 epoch 3 - iter 129/432 - loss 0.30878822 - time (sec): 46.49 - samples/sec: 395.42 - lr: 0.000026 - momentum: 0.000000
2023-10-19 01:18:20,430 epoch 3 - iter 172/432 - loss 0.30542878 - time (sec): 62.47 - samples/sec: 388.42 - lr: 0.000025 - momentum: 0.000000
2023-10-19 01:18:35,450 epoch 3 - iter 215/432 - loss 0.30005019 - time (sec): 77.49 - samples/sec: 392.10 - lr: 0.000025 - momentum: 0.000000
2023-10-19 01:18:50,219 epoch 3 - iter 258/432 - loss 0.30250277 - time (sec): 92.26 - samples/sec: 398.49 - lr: 0.000025 - momentum: 0.000000
2023-10-19 01:19:05,708 epoch 3 - iter 301/432 - loss 0.30560660 - time (sec): 107.75 - samples/sec: 397.21 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:19:20,037 epoch 3 - iter 344/432 - loss 0.30515807 - time (sec): 122.07 - samples/sec: 402.40 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:19:34,892 epoch 3 - iter 387/432 - loss 0.30122812 - time (sec): 136.93 - samples/sec: 403.45 - lr: 0.000024 - momentum: 0.000000
2023-10-19 01:19:50,610 epoch 3 - iter 430/432 - loss 0.29729232 - time (sec): 152.65 - samples/sec: 403.63 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:19:51,120 ----------------------------------------------------------------------------------------------------
2023-10-19 01:19:51,120 EPOCH 3 done: loss 0.2972 - lr: 0.000023
2023-10-19 01:20:04,739 DEV : loss 0.3239019811153412 - f1-score (micro avg) 0.8084
2023-10-19 01:20:04,763 saving best model
2023-10-19 01:20:06,054 ----------------------------------------------------------------------------------------------------
2023-10-19 01:20:20,480 epoch 4 - iter 43/432 - loss 0.21669863 - time (sec): 14.42 - samples/sec: 428.02 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:20:35,146 epoch 4 - iter 86/432 - loss 0.20451815 - time (sec): 29.09 - samples/sec: 426.60 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:20:50,293 epoch 4 - iter 129/432 - loss 0.21364175 - time (sec): 44.24 - samples/sec: 421.20 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:21:05,859 epoch 4 - iter 172/432 - loss 0.21881045 - time (sec): 59.80 - samples/sec: 415.69 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:21:21,185 epoch 4 - iter 215/432 - loss 0.22071577 - time (sec): 75.13 - samples/sec: 408.92 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:21:35,428 epoch 4 - iter 258/432 - loss 0.21878871 - time (sec): 89.37 - samples/sec: 411.30 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:21:50,207 epoch 4 - iter 301/432 - loss 0.21383356 - time (sec): 104.15 - samples/sec: 410.97 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:22:04,657 epoch 4 - iter 344/432 - loss 0.21198471 - time (sec): 118.60 - samples/sec: 417.17 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:22:20,290 epoch 4 - iter 387/432 - loss 0.21285777 - time (sec): 134.24 - samples/sec: 411.41 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:22:35,747 epoch 4 - iter 430/432 - loss 0.21143223 - time (sec): 149.69 - samples/sec: 411.26 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:22:36,321 ----------------------------------------------------------------------------------------------------
2023-10-19 01:22:36,322 EPOCH 4 done: loss 0.2117 - lr: 0.000020
2023-10-19 01:22:49,686 DEV : loss 0.30530545115470886 - f1-score (micro avg) 0.8194
2023-10-19 01:22:49,710 saving best model
2023-10-19 01:22:51,003 ----------------------------------------------------------------------------------------------------
2023-10-19 01:23:05,732 epoch 5 - iter 43/432 - loss 0.15718174 - time (sec): 14.73 - samples/sec: 394.91 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:23:20,374 epoch 5 - iter 86/432 - loss 0.15300782 - time (sec): 29.37 - samples/sec: 406.10 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:23:34,910 epoch 5 - iter 129/432 - loss 0.15938683 - time (sec): 43.91 - samples/sec: 417.94 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:23:48,967 epoch 5 - iter 172/432 - loss 0.15808067 - time (sec): 57.96 - samples/sec: 426.26 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:24:03,719 epoch 5 - iter 215/432 - loss 0.16506791 - time (sec): 72.71 - samples/sec: 424.28 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:24:19,437 epoch 5 - iter 258/432 - loss 0.16346937 - time (sec): 88.43 - samples/sec: 417.81 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:24:34,321 epoch 5 - iter 301/432 - loss 0.16131309 - time (sec): 103.32 - samples/sec: 416.84 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:24:49,426 epoch 5 - iter 344/432 - loss 0.16170570 - time (sec): 118.42 - samples/sec: 415.27 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:25:03,964 epoch 5 - iter 387/432 - loss 0.16232398 - time (sec): 132.96 - samples/sec: 417.96 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:25:19,256 epoch 5 - iter 430/432 - loss 0.16167487 - time (sec): 148.25 - samples/sec: 416.09 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:25:19,736 ----------------------------------------------------------------------------------------------------
2023-10-19 01:25:19,736 EPOCH 5 done: loss 0.1620 - lr: 0.000017
2023-10-19 01:25:32,940 DEV : loss 0.321034699678421 - f1-score (micro avg) 0.8198
2023-10-19 01:25:32,965 saving best model
2023-10-19 01:25:34,290 ----------------------------------------------------------------------------------------------------
2023-10-19 01:25:50,079 epoch 6 - iter 43/432 - loss 0.11198163 - time (sec): 15.79 - samples/sec: 387.46 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:26:05,066 epoch 6 - iter 86/432 - loss 0.11365943 - time (sec): 30.77 - samples/sec: 396.18 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:26:20,043 epoch 6 - iter 129/432 - loss 0.11579195 - time (sec): 45.75 - samples/sec: 408.71 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:26:34,245 epoch 6 - iter 172/432 - loss 0.12052255 - time (sec): 59.95 - samples/sec: 415.39 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:26:48,584 epoch 6 - iter 215/432 - loss 0.12402843 - time (sec): 74.29 - samples/sec: 417.44 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:27:03,787 epoch 6 - iter 258/432 - loss 0.12002060 - time (sec): 89.50 - samples/sec: 414.34 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:27:19,177 epoch 6 - iter 301/432 - loss 0.12019028 - time (sec): 104.89 - samples/sec: 411.10 - lr: 0.000014 - momentum: 0.000000
2023-10-19 01:27:34,518 epoch 6 - iter 344/432 - loss 0.12027080 - time (sec): 120.23 - samples/sec: 412.59 - lr: 0.000014 - momentum: 0.000000
2023-10-19 01:27:50,024 epoch 6 - iter 387/432 - loss 0.12168734 - time (sec): 135.73 - samples/sec: 409.94 - lr: 0.000014 - momentum: 0.000000
2023-10-19 01:28:04,990 epoch 6 - iter 430/432 - loss 0.12485490 - time (sec): 150.70 - samples/sec: 409.14 - lr: 0.000013 - momentum: 0.000000
2023-10-19 01:28:05,672 ----------------------------------------------------------------------------------------------------
2023-10-19 01:28:05,673 EPOCH 6 done: loss 0.1248 - lr: 0.000013
2023-10-19 01:28:18,762 DEV : loss 0.33496347069740295 - f1-score (micro avg) 0.8301
2023-10-19 01:28:18,786 saving best model
2023-10-19 01:28:20,656 ----------------------------------------------------------------------------------------------------
2023-10-19 01:28:36,296 epoch 7 - iter 43/432 - loss 0.09890459 - time (sec): 15.64 - samples/sec: 398.70 - lr: 0.000013 - momentum: 0.000000
2023-10-19 01:28:50,948 epoch 7 - iter 86/432 - loss 0.09672663 - time (sec): 30.29 - samples/sec: 424.23 - lr: 0.000013 - momentum: 0.000000
2023-10-19 01:29:05,164 epoch 7 - iter 129/432 - loss 0.10195590 - time (sec): 44.51 - samples/sec: 420.61 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:29:20,590 epoch 7 - iter 172/432 - loss 0.10025118 - time (sec): 59.93 - samples/sec: 414.40 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:29:36,554 epoch 7 - iter 215/432 - loss 0.10219041 - time (sec): 75.90 - samples/sec: 409.06 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:29:52,459 epoch 7 - iter 258/432 - loss 0.10239845 - time (sec): 91.80 - samples/sec: 402.76 - lr: 0.000011 - momentum: 0.000000
2023-10-19 01:30:07,118 epoch 7 - iter 301/432 - loss 0.10348027 - time (sec): 106.46 - samples/sec: 404.05 - lr: 0.000011 - momentum: 0.000000
2023-10-19 01:30:21,327 epoch 7 - iter 344/432 - loss 0.10248971 - time (sec): 120.67 - samples/sec: 406.93 - lr: 0.000011 - momentum: 0.000000
2023-10-19 01:30:36,374 epoch 7 - iter 387/432 - loss 0.10201551 - time (sec): 135.72 - samples/sec: 407.72 - lr: 0.000010 - momentum: 0.000000
2023-10-19 01:30:51,938 epoch 7 - iter 430/432 - loss 0.10240589 - time (sec): 151.28 - samples/sec: 407.48 - lr: 0.000010 - momentum: 0.000000
2023-10-19 01:30:52,652 ----------------------------------------------------------------------------------------------------
2023-10-19 01:30:52,653 EPOCH 7 done: loss 0.1023 - lr: 0.000010
2023-10-19 01:31:05,779 DEV : loss 0.3334580063819885 - f1-score (micro avg) 0.841
2023-10-19 01:31:05,803 saving best model
2023-10-19 01:31:07,095 ----------------------------------------------------------------------------------------------------
2023-10-19 01:31:21,749 epoch 8 - iter 43/432 - loss 0.07715346 - time (sec): 14.65 - samples/sec: 397.05 - lr: 0.000010 - momentum: 0.000000
2023-10-19 01:31:36,808 epoch 8 - iter 86/432 - loss 0.08026845 - time (sec): 29.71 - samples/sec: 406.77 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:31:51,972 epoch 8 - iter 129/432 - loss 0.07932378 - time (sec): 44.88 - samples/sec: 418.29 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:32:06,196 epoch 8 - iter 172/432 - loss 0.07970603 - time (sec): 59.10 - samples/sec: 418.22 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:32:22,269 epoch 8 - iter 215/432 - loss 0.08310639 - time (sec): 75.17 - samples/sec: 411.59 - lr: 0.000008 - momentum: 0.000000
2023-10-19 01:32:38,561 epoch 8 - iter 258/432 - loss 0.08405516 - time (sec): 91.46 - samples/sec: 410.16 - lr: 0.000008 - momentum: 0.000000
2023-10-19 01:32:55,145 epoch 8 - iter 301/432 - loss 0.08440344 - time (sec): 108.05 - samples/sec: 405.80 - lr: 0.000008 - momentum: 0.000000
2023-10-19 01:33:09,512 epoch 8 - iter 344/432 - loss 0.08349681 - time (sec): 122.42 - samples/sec: 408.17 - lr: 0.000007 - momentum: 0.000000
2023-10-19 01:33:23,875 epoch 8 - iter 387/432 - loss 0.08301177 - time (sec): 136.78 - samples/sec: 408.43 - lr: 0.000007 - momentum: 0.000000
2023-10-19 01:33:38,932 epoch 8 - iter 430/432 - loss 0.08343770 - time (sec): 151.84 - samples/sec: 405.83 - lr: 0.000007 - momentum: 0.000000
2023-10-19 01:33:39,452 ----------------------------------------------------------------------------------------------------
2023-10-19 01:33:39,452 EPOCH 8 done: loss 0.0833 - lr: 0.000007
2023-10-19 01:33:53,260 DEV : loss 0.353408545255661 - f1-score (micro avg) 0.8389
2023-10-19 01:33:53,290 ----------------------------------------------------------------------------------------------------
2023-10-19 01:34:07,214 epoch 9 - iter 43/432 - loss 0.06833600 - time (sec): 13.92 - samples/sec: 438.65 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:34:21,380 epoch 9 - iter 86/432 - loss 0.05877407 - time (sec): 28.09 - samples/sec: 445.31 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:34:35,471 epoch 9 - iter 129/432 - loss 0.05787196 - time (sec): 42.18 - samples/sec: 437.56 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:34:50,284 epoch 9 - iter 172/432 - loss 0.06129648 - time (sec): 56.99 - samples/sec: 435.62 - lr: 0.000005 - momentum: 0.000000
2023-10-19 01:35:05,160 epoch 9 - iter 215/432 - loss 0.06250295 - time (sec): 71.87 - samples/sec: 432.52 - lr: 0.000005 - momentum: 0.000000
2023-10-19 01:35:20,325 epoch 9 - iter 258/432 - loss 0.06541137 - time (sec): 87.03 - samples/sec: 428.16 - lr: 0.000005 - momentum: 0.000000
2023-10-19 01:35:35,910 epoch 9 - iter 301/432 - loss 0.06884328 - time (sec): 102.62 - samples/sec: 422.22 - lr: 0.000004 - momentum: 0.000000
2023-10-19 01:35:50,902 epoch 9 - iter 344/432 - loss 0.07066233 - time (sec): 117.61 - samples/sec: 419.43 - lr: 0.000004 - momentum: 0.000000
2023-10-19 01:36:06,777 epoch 9 - iter 387/432 - loss 0.07187549 - time (sec): 133.49 - samples/sec: 414.04 - lr: 0.000004 - momentum: 0.000000
2023-10-19 01:36:21,720 epoch 9 - iter 430/432 - loss 0.07149832 - time (sec): 148.43 - samples/sec: 415.86 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:36:22,264 ----------------------------------------------------------------------------------------------------
2023-10-19 01:36:22,264 EPOCH 9 done: loss 0.0716 - lr: 0.000003
2023-10-19 01:36:35,557 DEV : loss 0.3648279905319214 - f1-score (micro avg) 0.8495
2023-10-19 01:36:35,582 saving best model
2023-10-19 01:36:36,891 ----------------------------------------------------------------------------------------------------
2023-10-19 01:36:52,640 epoch 10 - iter 43/432 - loss 0.04889939 - time (sec): 15.75 - samples/sec: 402.72 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:37:07,560 epoch 10 - iter 86/432 - loss 0.05311027 - time (sec): 30.67 - samples/sec: 413.88 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:37:21,347 epoch 10 - iter 129/432 - loss 0.05478559 - time (sec): 44.45 - samples/sec: 418.04 - lr: 0.000002 - momentum: 0.000000
2023-10-19 01:37:36,295 epoch 10 - iter 172/432 - loss 0.05290573 - time (sec): 59.40 - samples/sec: 418.92 - lr: 0.000002 - momentum: 0.000000
2023-10-19 01:37:50,899 epoch 10 - iter 215/432 - loss 0.05619202 - time (sec): 74.01 - samples/sec: 417.36 - lr: 0.000002 - momentum: 0.000000
2023-10-19 01:38:05,622 epoch 10 - iter 258/432 - loss 0.05730337 - time (sec): 88.73 - samples/sec: 415.93 - lr: 0.000001 - momentum: 0.000000
2023-10-19 01:38:20,801 epoch 10 - iter 301/432 - loss 0.05650763 - time (sec): 103.91 - samples/sec: 416.31 - lr: 0.000001 - momentum: 0.000000
2023-10-19 01:38:36,560 epoch 10 - iter 344/432 - loss 0.05713604 - time (sec): 119.67 - samples/sec: 412.30 - lr: 0.000001 - momentum: 0.000000
2023-10-19 01:38:50,599 epoch 10 - iter 387/432 - loss 0.05915272 - time (sec): 133.71 - samples/sec: 416.97 - lr: 0.000000 - momentum: 0.000000
2023-10-19 01:39:06,390 epoch 10 - iter 430/432 - loss 0.05855833 - time (sec): 149.50 - samples/sec: 412.06 - lr: 0.000000 - momentum: 0.000000
2023-10-19 01:39:06,987 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:06,987 EPOCH 10 done: loss 0.0588 - lr: 0.000000
2023-10-19 01:39:20,265 DEV : loss 0.3677222728729248 - f1-score (micro avg) 0.848
2023-10-19 01:39:20,773 ----------------------------------------------------------------------------------------------------
2023-10-19 01:39:20,775 Loading model from best epoch ...
2023-10-19 01:39:23,129 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 01:39:41,029
Results:
- F-score (micro) 0.7588
- F-score (macro) 0.5671
- Accuracy 0.6563
By class:
precision recall f1-score support
trigger 0.7137 0.5954 0.6492 833
location-stop 0.8420 0.8288 0.8353 765
location 0.8053 0.8271 0.8160 665
location-city 0.7987 0.8834 0.8389 566
date 0.8773 0.8350 0.8557 394
location-street 0.9366 0.8808 0.9079 386
time 0.7766 0.8828 0.8263 256
location-route 0.8025 0.6866 0.7400 284
organization-company 0.7936 0.6865 0.7362 252
number 0.6632 0.8456 0.7434 149
distance 0.9824 1.0000 0.9911 167
duration 0.3205 0.3067 0.3135 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.7826 0.2609 0.3913 69
organization 0.4839 0.5357 0.5085 28
person 0.4737 0.9000 0.6207 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 0.7504 0.7674 0.7588 4988
macro avg 0.5817 0.5766 0.5671 4988
weighted avg 0.7914 0.7674 0.7752 4988
2023-10-19 01:39:41,029 ----------------------------------------------------------------------------------------------------
|