File size: 25,498 Bytes
2e9eea2 |
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 |
2023-10-19 00:44:31,863 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,864 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 00:44:31,864 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,864 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,864 Train: 6900 sentences
2023-10-19 00:44:31,864 (train_with_dev=False, train_with_test=False)
2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,864 Training Params:
2023-10-19 00:44:31,864 - learning_rate: "5e-05"
2023-10-19 00:44:31,864 - mini_batch_size: "16"
2023-10-19 00:44:31,864 - max_epochs: "10"
2023-10-19 00:44:31,864 - shuffle: "True"
2023-10-19 00:44:31,864 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,864 Plugins:
2023-10-19 00:44:31,865 - TensorboardLogger
2023-10-19 00:44:31,865 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,865 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 00:44:31,865 - metric: "('micro avg', 'f1-score')"
2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,865 Computation:
2023-10-19 00:44:31,865 - compute on device: cuda:0
2023-10-19 00:44:31,865 - embedding storage: none
2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,865 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-2"
2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,865 ----------------------------------------------------------------------------------------------------
2023-10-19 00:44:31,865 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 00:44:47,212 epoch 1 - iter 43/432 - loss 4.53411937 - time (sec): 15.35 - samples/sec: 393.73 - lr: 0.000005 - momentum: 0.000000
2023-10-19 00:45:01,344 epoch 1 - iter 86/432 - loss 3.33775768 - time (sec): 29.48 - samples/sec: 416.66 - lr: 0.000010 - momentum: 0.000000
2023-10-19 00:45:16,011 epoch 1 - iter 129/432 - loss 2.84542967 - time (sec): 44.15 - samples/sec: 413.11 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:45:30,003 epoch 1 - iter 172/432 - loss 2.52975191 - time (sec): 58.14 - samples/sec: 418.24 - lr: 0.000020 - momentum: 0.000000
2023-10-19 00:45:45,094 epoch 1 - iter 215/432 - loss 2.29564387 - time (sec): 73.23 - samples/sec: 411.52 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:46:00,541 epoch 1 - iter 258/432 - loss 2.05922596 - time (sec): 88.68 - samples/sec: 413.66 - lr: 0.000030 - momentum: 0.000000
2023-10-19 00:46:15,508 epoch 1 - iter 301/432 - loss 1.88915277 - time (sec): 103.64 - samples/sec: 413.75 - lr: 0.000035 - momentum: 0.000000
2023-10-19 00:46:30,838 epoch 1 - iter 344/432 - loss 1.74992637 - time (sec): 118.97 - samples/sec: 412.05 - lr: 0.000040 - momentum: 0.000000
2023-10-19 00:46:45,525 epoch 1 - iter 387/432 - loss 1.63015802 - time (sec): 133.66 - samples/sec: 411.49 - lr: 0.000045 - momentum: 0.000000
2023-10-19 00:47:01,349 epoch 1 - iter 430/432 - loss 1.51696167 - time (sec): 149.48 - samples/sec: 411.83 - lr: 0.000050 - momentum: 0.000000
2023-10-19 00:47:01,949 ----------------------------------------------------------------------------------------------------
2023-10-19 00:47:01,950 EPOCH 1 done: loss 1.5134 - lr: 0.000050
2023-10-19 00:47:15,678 DEV : loss 0.4629705548286438 - f1-score (micro avg) 0.7131
2023-10-19 00:47:15,701 saving best model
2023-10-19 00:47:16,128 ----------------------------------------------------------------------------------------------------
2023-10-19 00:47:30,352 epoch 2 - iter 43/432 - loss 0.50778740 - time (sec): 14.22 - samples/sec: 457.10 - lr: 0.000049 - momentum: 0.000000
2023-10-19 00:47:44,769 epoch 2 - iter 86/432 - loss 0.47541374 - time (sec): 28.64 - samples/sec: 445.06 - lr: 0.000049 - momentum: 0.000000
2023-10-19 00:48:00,063 epoch 2 - iter 129/432 - loss 0.46875804 - time (sec): 43.93 - samples/sec: 425.92 - lr: 0.000048 - momentum: 0.000000
2023-10-19 00:48:15,298 epoch 2 - iter 172/432 - loss 0.45799863 - time (sec): 59.17 - samples/sec: 423.05 - lr: 0.000048 - momentum: 0.000000
2023-10-19 00:48:30,441 epoch 2 - iter 215/432 - loss 0.44907689 - time (sec): 74.31 - samples/sec: 416.91 - lr: 0.000047 - momentum: 0.000000
2023-10-19 00:48:44,633 epoch 2 - iter 258/432 - loss 0.43929109 - time (sec): 88.50 - samples/sec: 419.49 - lr: 0.000047 - momentum: 0.000000
2023-10-19 00:48:58,777 epoch 2 - iter 301/432 - loss 0.43307480 - time (sec): 102.65 - samples/sec: 418.41 - lr: 0.000046 - momentum: 0.000000
2023-10-19 00:49:12,715 epoch 2 - iter 344/432 - loss 0.42908565 - time (sec): 116.58 - samples/sec: 421.01 - lr: 0.000046 - momentum: 0.000000
2023-10-19 00:49:26,745 epoch 2 - iter 387/432 - loss 0.42075222 - time (sec): 130.62 - samples/sec: 423.33 - lr: 0.000045 - momentum: 0.000000
2023-10-19 00:49:40,040 epoch 2 - iter 430/432 - loss 0.41576500 - time (sec): 143.91 - samples/sec: 427.96 - lr: 0.000044 - momentum: 0.000000
2023-10-19 00:49:40,571 ----------------------------------------------------------------------------------------------------
2023-10-19 00:49:40,571 EPOCH 2 done: loss 0.4159 - lr: 0.000044
2023-10-19 00:49:52,635 DEV : loss 0.3158990442752838 - f1-score (micro avg) 0.7988
2023-10-19 00:49:52,658 saving best model
2023-10-19 00:49:53,913 ----------------------------------------------------------------------------------------------------
2023-10-19 00:50:07,149 epoch 3 - iter 43/432 - loss 0.28934365 - time (sec): 13.23 - samples/sec: 444.45 - lr: 0.000044 - momentum: 0.000000
2023-10-19 00:50:20,635 epoch 3 - iter 86/432 - loss 0.27279891 - time (sec): 26.72 - samples/sec: 440.82 - lr: 0.000043 - momentum: 0.000000
2023-10-19 00:50:34,946 epoch 3 - iter 129/432 - loss 0.25809605 - time (sec): 41.03 - samples/sec: 434.32 - lr: 0.000043 - momentum: 0.000000
2023-10-19 00:50:49,105 epoch 3 - iter 172/432 - loss 0.25877208 - time (sec): 55.19 - samples/sec: 432.01 - lr: 0.000042 - momentum: 0.000000
2023-10-19 00:51:02,303 epoch 3 - iter 215/432 - loss 0.25490899 - time (sec): 68.39 - samples/sec: 439.98 - lr: 0.000042 - momentum: 0.000000
2023-10-19 00:51:15,378 epoch 3 - iter 258/432 - loss 0.25311964 - time (sec): 81.46 - samples/sec: 447.45 - lr: 0.000041 - momentum: 0.000000
2023-10-19 00:51:28,206 epoch 3 - iter 301/432 - loss 0.24979741 - time (sec): 94.29 - samples/sec: 452.91 - lr: 0.000041 - momentum: 0.000000
2023-10-19 00:51:42,585 epoch 3 - iter 344/432 - loss 0.24676564 - time (sec): 108.67 - samples/sec: 451.89 - lr: 0.000040 - momentum: 0.000000
2023-10-19 00:51:55,659 epoch 3 - iter 387/432 - loss 0.24375527 - time (sec): 121.74 - samples/sec: 452.41 - lr: 0.000039 - momentum: 0.000000
2023-10-19 00:52:09,164 epoch 3 - iter 430/432 - loss 0.24783731 - time (sec): 135.25 - samples/sec: 456.10 - lr: 0.000039 - momentum: 0.000000
2023-10-19 00:52:09,637 ----------------------------------------------------------------------------------------------------
2023-10-19 00:52:09,637 EPOCH 3 done: loss 0.2479 - lr: 0.000039
2023-10-19 00:52:22,049 DEV : loss 0.31579792499542236 - f1-score (micro avg) 0.808
2023-10-19 00:52:22,074 saving best model
2023-10-19 00:52:23,320 ----------------------------------------------------------------------------------------------------
2023-10-19 00:52:37,087 epoch 4 - iter 43/432 - loss 0.16644201 - time (sec): 13.77 - samples/sec: 457.00 - lr: 0.000038 - momentum: 0.000000
2023-10-19 00:52:50,583 epoch 4 - iter 86/432 - loss 0.18332177 - time (sec): 27.26 - samples/sec: 456.18 - lr: 0.000038 - momentum: 0.000000
2023-10-19 00:53:04,413 epoch 4 - iter 129/432 - loss 0.18640017 - time (sec): 41.09 - samples/sec: 458.34 - lr: 0.000037 - momentum: 0.000000
2023-10-19 00:53:17,780 epoch 4 - iter 172/432 - loss 0.18492662 - time (sec): 54.46 - samples/sec: 454.60 - lr: 0.000037 - momentum: 0.000000
2023-10-19 00:53:31,940 epoch 4 - iter 215/432 - loss 0.18135848 - time (sec): 68.62 - samples/sec: 451.54 - lr: 0.000036 - momentum: 0.000000
2023-10-19 00:53:46,014 epoch 4 - iter 258/432 - loss 0.18461289 - time (sec): 82.69 - samples/sec: 451.15 - lr: 0.000036 - momentum: 0.000000
2023-10-19 00:53:59,805 epoch 4 - iter 301/432 - loss 0.18702010 - time (sec): 96.48 - samples/sec: 451.95 - lr: 0.000035 - momentum: 0.000000
2023-10-19 00:54:13,646 epoch 4 - iter 344/432 - loss 0.18583796 - time (sec): 110.32 - samples/sec: 450.40 - lr: 0.000034 - momentum: 0.000000
2023-10-19 00:54:26,549 epoch 4 - iter 387/432 - loss 0.18370163 - time (sec): 123.23 - samples/sec: 452.55 - lr: 0.000034 - momentum: 0.000000
2023-10-19 00:54:40,668 epoch 4 - iter 430/432 - loss 0.18206557 - time (sec): 137.35 - samples/sec: 449.35 - lr: 0.000033 - momentum: 0.000000
2023-10-19 00:54:41,284 ----------------------------------------------------------------------------------------------------
2023-10-19 00:54:41,284 EPOCH 4 done: loss 0.1820 - lr: 0.000033
2023-10-19 00:54:53,592 DEV : loss 0.30372321605682373 - f1-score (micro avg) 0.828
2023-10-19 00:54:53,617 saving best model
2023-10-19 00:54:54,870 ----------------------------------------------------------------------------------------------------
2023-10-19 00:55:08,008 epoch 5 - iter 43/432 - loss 0.13612790 - time (sec): 13.14 - samples/sec: 465.32 - lr: 0.000033 - momentum: 0.000000
2023-10-19 00:55:22,047 epoch 5 - iter 86/432 - loss 0.14054460 - time (sec): 27.18 - samples/sec: 447.47 - lr: 0.000032 - momentum: 0.000000
2023-10-19 00:55:37,157 epoch 5 - iter 129/432 - loss 0.13394142 - time (sec): 42.29 - samples/sec: 432.53 - lr: 0.000032 - momentum: 0.000000
2023-10-19 00:55:51,326 epoch 5 - iter 172/432 - loss 0.13270704 - time (sec): 56.45 - samples/sec: 435.38 - lr: 0.000031 - momentum: 0.000000
2023-10-19 00:56:05,579 epoch 5 - iter 215/432 - loss 0.13290468 - time (sec): 70.71 - samples/sec: 432.49 - lr: 0.000031 - momentum: 0.000000
2023-10-19 00:56:19,533 epoch 5 - iter 258/432 - loss 0.13547413 - time (sec): 84.66 - samples/sec: 438.78 - lr: 0.000030 - momentum: 0.000000
2023-10-19 00:56:33,952 epoch 5 - iter 301/432 - loss 0.13486846 - time (sec): 99.08 - samples/sec: 436.52 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:56:48,205 epoch 5 - iter 344/432 - loss 0.13344437 - time (sec): 113.33 - samples/sec: 436.88 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:57:02,971 epoch 5 - iter 387/432 - loss 0.13475190 - time (sec): 128.10 - samples/sec: 434.34 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:57:17,198 epoch 5 - iter 430/432 - loss 0.13409932 - time (sec): 142.33 - samples/sec: 432.98 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:57:17,739 ----------------------------------------------------------------------------------------------------
2023-10-19 00:57:17,740 EPOCH 5 done: loss 0.1340 - lr: 0.000028
2023-10-19 00:57:30,751 DEV : loss 0.32670849561691284 - f1-score (micro avg) 0.8352
2023-10-19 00:57:30,783 saving best model
2023-10-19 00:57:32,032 ----------------------------------------------------------------------------------------------------
2023-10-19 00:57:47,516 epoch 6 - iter 43/432 - loss 0.08687325 - time (sec): 15.48 - samples/sec: 398.91 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:58:02,149 epoch 6 - iter 86/432 - loss 0.09122781 - time (sec): 30.12 - samples/sec: 403.22 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:58:16,671 epoch 6 - iter 129/432 - loss 0.09486365 - time (sec): 44.64 - samples/sec: 404.97 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:58:30,400 epoch 6 - iter 172/432 - loss 0.09596723 - time (sec): 58.37 - samples/sec: 418.15 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:58:44,957 epoch 6 - iter 215/432 - loss 0.09805027 - time (sec): 72.92 - samples/sec: 419.17 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:58:59,364 epoch 6 - iter 258/432 - loss 0.09925226 - time (sec): 87.33 - samples/sec: 422.65 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:59:15,357 epoch 6 - iter 301/432 - loss 0.09985027 - time (sec): 103.32 - samples/sec: 418.87 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:59:30,282 epoch 6 - iter 344/432 - loss 0.09891744 - time (sec): 118.25 - samples/sec: 417.55 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:59:45,039 epoch 6 - iter 387/432 - loss 0.09861899 - time (sec): 133.01 - samples/sec: 415.82 - lr: 0.000023 - momentum: 0.000000
2023-10-19 01:00:00,507 epoch 6 - iter 430/432 - loss 0.09818502 - time (sec): 148.47 - samples/sec: 415.48 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:00:01,244 ----------------------------------------------------------------------------------------------------
2023-10-19 01:00:01,245 EPOCH 6 done: loss 0.0982 - lr: 0.000022
2023-10-19 01:00:14,505 DEV : loss 0.3421052396297455 - f1-score (micro avg) 0.8432
2023-10-19 01:00:14,529 saving best model
2023-10-19 01:00:15,772 ----------------------------------------------------------------------------------------------------
2023-10-19 01:00:29,443 epoch 7 - iter 43/432 - loss 0.06939444 - time (sec): 13.67 - samples/sec: 466.85 - lr: 0.000022 - momentum: 0.000000
2023-10-19 01:00:43,853 epoch 7 - iter 86/432 - loss 0.06747434 - time (sec): 28.08 - samples/sec: 444.91 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:00:59,051 epoch 7 - iter 129/432 - loss 0.06960008 - time (sec): 43.28 - samples/sec: 422.62 - lr: 0.000021 - momentum: 0.000000
2023-10-19 01:01:14,327 epoch 7 - iter 172/432 - loss 0.06786994 - time (sec): 58.55 - samples/sec: 419.32 - lr: 0.000020 - momentum: 0.000000
2023-10-19 01:01:28,754 epoch 7 - iter 215/432 - loss 0.07131507 - time (sec): 72.98 - samples/sec: 422.99 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:01:43,871 epoch 7 - iter 258/432 - loss 0.07531973 - time (sec): 88.10 - samples/sec: 420.42 - lr: 0.000019 - momentum: 0.000000
2023-10-19 01:01:59,085 epoch 7 - iter 301/432 - loss 0.07563695 - time (sec): 103.31 - samples/sec: 417.98 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:02:14,048 epoch 7 - iter 344/432 - loss 0.07673450 - time (sec): 118.28 - samples/sec: 416.50 - lr: 0.000018 - momentum: 0.000000
2023-10-19 01:02:29,624 epoch 7 - iter 387/432 - loss 0.07707972 - time (sec): 133.85 - samples/sec: 414.18 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:02:44,948 epoch 7 - iter 430/432 - loss 0.07751613 - time (sec): 149.17 - samples/sec: 413.46 - lr: 0.000017 - momentum: 0.000000
2023-10-19 01:02:45,737 ----------------------------------------------------------------------------------------------------
2023-10-19 01:02:45,737 EPOCH 7 done: loss 0.0774 - lr: 0.000017
2023-10-19 01:02:59,356 DEV : loss 0.352491557598114 - f1-score (micro avg) 0.8393
2023-10-19 01:02:59,383 ----------------------------------------------------------------------------------------------------
2023-10-19 01:03:13,741 epoch 8 - iter 43/432 - loss 0.05261681 - time (sec): 14.36 - samples/sec: 416.10 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:03:28,728 epoch 8 - iter 86/432 - loss 0.05721217 - time (sec): 29.34 - samples/sec: 428.52 - lr: 0.000016 - momentum: 0.000000
2023-10-19 01:03:42,822 epoch 8 - iter 129/432 - loss 0.05369074 - time (sec): 43.44 - samples/sec: 419.25 - lr: 0.000015 - momentum: 0.000000
2023-10-19 01:03:56,732 epoch 8 - iter 172/432 - loss 0.05678762 - time (sec): 57.35 - samples/sec: 436.78 - lr: 0.000014 - momentum: 0.000000
2023-10-19 01:04:11,247 epoch 8 - iter 215/432 - loss 0.05652943 - time (sec): 71.86 - samples/sec: 437.82 - lr: 0.000014 - momentum: 0.000000
2023-10-19 01:04:26,331 epoch 8 - iter 258/432 - loss 0.05696515 - time (sec): 86.95 - samples/sec: 430.93 - lr: 0.000013 - momentum: 0.000000
2023-10-19 01:04:41,478 epoch 8 - iter 301/432 - loss 0.05623302 - time (sec): 102.09 - samples/sec: 428.45 - lr: 0.000013 - momentum: 0.000000
2023-10-19 01:04:55,979 epoch 8 - iter 344/432 - loss 0.05774074 - time (sec): 116.59 - samples/sec: 429.21 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:05:10,754 epoch 8 - iter 387/432 - loss 0.05776864 - time (sec): 131.37 - samples/sec: 424.98 - lr: 0.000012 - momentum: 0.000000
2023-10-19 01:05:26,178 epoch 8 - iter 430/432 - loss 0.05789217 - time (sec): 146.79 - samples/sec: 419.88 - lr: 0.000011 - momentum: 0.000000
2023-10-19 01:05:27,034 ----------------------------------------------------------------------------------------------------
2023-10-19 01:05:27,034 EPOCH 8 done: loss 0.0581 - lr: 0.000011
2023-10-19 01:05:40,257 DEV : loss 0.38706132769584656 - f1-score (micro avg) 0.8476
2023-10-19 01:05:40,282 saving best model
2023-10-19 01:05:41,538 ----------------------------------------------------------------------------------------------------
2023-10-19 01:05:56,043 epoch 9 - iter 43/432 - loss 0.05079748 - time (sec): 14.50 - samples/sec: 412.31 - lr: 0.000011 - momentum: 0.000000
2023-10-19 01:06:10,747 epoch 9 - iter 86/432 - loss 0.04252692 - time (sec): 29.21 - samples/sec: 426.59 - lr: 0.000010 - momentum: 0.000000
2023-10-19 01:06:26,222 epoch 9 - iter 129/432 - loss 0.03956511 - time (sec): 44.68 - samples/sec: 415.35 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:06:42,255 epoch 9 - iter 172/432 - loss 0.03891272 - time (sec): 60.72 - samples/sec: 400.27 - lr: 0.000009 - momentum: 0.000000
2023-10-19 01:06:56,986 epoch 9 - iter 215/432 - loss 0.03816925 - time (sec): 75.45 - samples/sec: 409.16 - lr: 0.000008 - momentum: 0.000000
2023-10-19 01:07:12,082 epoch 9 - iter 258/432 - loss 0.03904535 - time (sec): 90.54 - samples/sec: 408.11 - lr: 0.000008 - momentum: 0.000000
2023-10-19 01:07:27,198 epoch 9 - iter 301/432 - loss 0.03968716 - time (sec): 105.66 - samples/sec: 410.39 - lr: 0.000007 - momentum: 0.000000
2023-10-19 01:07:42,126 epoch 9 - iter 344/432 - loss 0.04100224 - time (sec): 120.59 - samples/sec: 409.28 - lr: 0.000007 - momentum: 0.000000
2023-10-19 01:07:57,146 epoch 9 - iter 387/432 - loss 0.04208186 - time (sec): 135.61 - samples/sec: 408.46 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:08:12,686 epoch 9 - iter 430/432 - loss 0.04243790 - time (sec): 151.15 - samples/sec: 408.30 - lr: 0.000006 - momentum: 0.000000
2023-10-19 01:08:13,050 ----------------------------------------------------------------------------------------------------
2023-10-19 01:08:13,050 EPOCH 9 done: loss 0.0424 - lr: 0.000006
2023-10-19 01:08:26,197 DEV : loss 0.410501629114151 - f1-score (micro avg) 0.8488
2023-10-19 01:08:26,221 saving best model
2023-10-19 01:08:27,465 ----------------------------------------------------------------------------------------------------
2023-10-19 01:08:41,343 epoch 10 - iter 43/432 - loss 0.04022390 - time (sec): 13.88 - samples/sec: 427.28 - lr: 0.000005 - momentum: 0.000000
2023-10-19 01:08:56,759 epoch 10 - iter 86/432 - loss 0.03411555 - time (sec): 29.29 - samples/sec: 404.61 - lr: 0.000004 - momentum: 0.000000
2023-10-19 01:09:11,614 epoch 10 - iter 129/432 - loss 0.03451278 - time (sec): 44.15 - samples/sec: 409.44 - lr: 0.000004 - momentum: 0.000000
2023-10-19 01:09:26,919 epoch 10 - iter 172/432 - loss 0.03635957 - time (sec): 59.45 - samples/sec: 414.23 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:09:42,287 epoch 10 - iter 215/432 - loss 0.03736899 - time (sec): 74.82 - samples/sec: 417.49 - lr: 0.000003 - momentum: 0.000000
2023-10-19 01:09:57,205 epoch 10 - iter 258/432 - loss 0.03656773 - time (sec): 89.74 - samples/sec: 417.19 - lr: 0.000002 - momentum: 0.000000
2023-10-19 01:10:11,814 epoch 10 - iter 301/432 - loss 0.03588521 - time (sec): 104.35 - samples/sec: 418.34 - lr: 0.000002 - momentum: 0.000000
2023-10-19 01:10:26,748 epoch 10 - iter 344/432 - loss 0.03577744 - time (sec): 119.28 - samples/sec: 417.64 - lr: 0.000001 - momentum: 0.000000
2023-10-19 01:10:40,324 epoch 10 - iter 387/432 - loss 0.03395260 - time (sec): 132.86 - samples/sec: 418.94 - lr: 0.000001 - momentum: 0.000000
2023-10-19 01:10:56,124 epoch 10 - iter 430/432 - loss 0.03336868 - time (sec): 148.66 - samples/sec: 414.75 - lr: 0.000000 - momentum: 0.000000
2023-10-19 01:10:56,799 ----------------------------------------------------------------------------------------------------
2023-10-19 01:10:56,799 EPOCH 10 done: loss 0.0333 - lr: 0.000000
2023-10-19 01:11:10,126 DEV : loss 0.4209924340248108 - f1-score (micro avg) 0.8495
2023-10-19 01:11:10,151 saving best model
2023-10-19 01:11:11,931 ----------------------------------------------------------------------------------------------------
2023-10-19 01:11:11,932 Loading model from best epoch ...
2023-10-19 01:11:14,091 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 01:11:32,197
Results:
- F-score (micro) 0.7756
- F-score (macro) 0.5886
- Accuracy 0.678
By class:
precision recall f1-score support
location-stop 0.8753 0.8444 0.8596 765
trigger 0.7333 0.5810 0.6484 833
location 0.7902 0.8496 0.8188 665
location-city 0.8322 0.8852 0.8579 566
date 0.8912 0.8528 0.8716 394
location-street 0.9449 0.8886 0.9159 386
time 0.7889 0.8906 0.8367 256
location-route 0.9065 0.7852 0.8415 284
organization-company 0.8038 0.6667 0.7289 252
distance 0.9766 1.0000 0.9882 167
number 0.6742 0.8054 0.7339 149
duration 0.3397 0.3252 0.3323 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.9189 0.4928 0.6415 69
organization 0.5600 0.5000 0.5283 28
person 0.4286 0.9000 0.5806 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 0.7713 0.7801 0.7756 4988
macro avg 0.6034 0.5930 0.5886 4988
weighted avg 0.8134 0.7801 0.7929 4988
2023-10-19 01:11:32,197 ----------------------------------------------------------------------------------------------------
|