File size: 25,498 Bytes
48fe87f |
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 23:49:39,844 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,845 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 23:49:39,845 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,845 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-18 23:49:39,846 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,846 Train: 6900 sentences
2023-10-18 23:49:39,846 (train_with_dev=False, train_with_test=False)
2023-10-18 23:49:39,846 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,846 Training Params:
2023-10-18 23:49:39,846 - learning_rate: "5e-05"
2023-10-18 23:49:39,846 - mini_batch_size: "16"
2023-10-18 23:49:39,846 - max_epochs: "10"
2023-10-18 23:49:39,846 - shuffle: "True"
2023-10-18 23:49:39,846 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,846 Plugins:
2023-10-18 23:49:39,846 - TensorboardLogger
2023-10-18 23:49:39,846 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 23:49:39,846 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,846 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 23:49:39,846 - metric: "('micro avg', 'f1-score')"
2023-10-18 23:49:39,846 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,846 Computation:
2023-10-18 23:49:39,846 - compute on device: cuda:0
2023-10-18 23:49:39,847 - embedding storage: none
2023-10-18 23:49:39,847 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,847 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-1"
2023-10-18 23:49:39,847 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,847 ----------------------------------------------------------------------------------------------------
2023-10-18 23:49:39,847 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 23:49:54,007 epoch 1 - iter 43/432 - loss 4.54226396 - time (sec): 14.16 - samples/sec: 427.65 - lr: 0.000005 - momentum: 0.000000
2023-10-18 23:50:08,103 epoch 1 - iter 86/432 - loss 3.39025495 - time (sec): 28.26 - samples/sec: 429.20 - lr: 0.000010 - momentum: 0.000000
2023-10-18 23:50:22,380 epoch 1 - iter 129/432 - loss 2.82298352 - time (sec): 42.53 - samples/sec: 431.35 - lr: 0.000015 - momentum: 0.000000
2023-10-18 23:50:35,740 epoch 1 - iter 172/432 - loss 2.47385817 - time (sec): 55.89 - samples/sec: 437.97 - lr: 0.000020 - momentum: 0.000000
2023-10-18 23:50:49,999 epoch 1 - iter 215/432 - loss 2.21787123 - time (sec): 70.15 - samples/sec: 433.61 - lr: 0.000025 - momentum: 0.000000
2023-10-18 23:51:03,183 epoch 1 - iter 258/432 - loss 2.00329484 - time (sec): 83.33 - samples/sec: 440.26 - lr: 0.000030 - momentum: 0.000000
2023-10-18 23:51:16,381 epoch 1 - iter 301/432 - loss 1.82489643 - time (sec): 96.53 - samples/sec: 447.14 - lr: 0.000035 - momentum: 0.000000
2023-10-18 23:51:30,192 epoch 1 - iter 344/432 - loss 1.69046523 - time (sec): 110.34 - samples/sec: 445.93 - lr: 0.000040 - momentum: 0.000000
2023-10-18 23:51:43,742 epoch 1 - iter 387/432 - loss 1.57702628 - time (sec): 123.89 - samples/sec: 444.99 - lr: 0.000045 - momentum: 0.000000
2023-10-18 23:51:58,002 epoch 1 - iter 430/432 - loss 1.47019726 - time (sec): 138.15 - samples/sec: 446.59 - lr: 0.000050 - momentum: 0.000000
2023-10-18 23:51:58,500 ----------------------------------------------------------------------------------------------------
2023-10-18 23:51:58,501 EPOCH 1 done: loss 1.4681 - lr: 0.000050
2023-10-18 23:52:10,741 DEV : loss 0.48693621158599854 - f1-score (micro avg) 0.7049
2023-10-18 23:52:10,765 saving best model
2023-10-18 23:52:11,236 ----------------------------------------------------------------------------------------------------
2023-10-18 23:52:24,640 epoch 2 - iter 43/432 - loss 0.49120434 - time (sec): 13.40 - samples/sec: 475.14 - lr: 0.000049 - momentum: 0.000000
2023-10-18 23:52:37,470 epoch 2 - iter 86/432 - loss 0.47518885 - time (sec): 26.23 - samples/sec: 473.80 - lr: 0.000049 - momentum: 0.000000
2023-10-18 23:52:50,585 epoch 2 - iter 129/432 - loss 0.46930182 - time (sec): 39.35 - samples/sec: 467.10 - lr: 0.000048 - momentum: 0.000000
2023-10-18 23:53:03,976 epoch 2 - iter 172/432 - loss 0.45056911 - time (sec): 52.74 - samples/sec: 469.05 - lr: 0.000048 - momentum: 0.000000
2023-10-18 23:53:18,853 epoch 2 - iter 215/432 - loss 0.43792445 - time (sec): 67.62 - samples/sec: 458.89 - lr: 0.000047 - momentum: 0.000000
2023-10-18 23:53:32,607 epoch 2 - iter 258/432 - loss 0.43015339 - time (sec): 81.37 - samples/sec: 460.55 - lr: 0.000047 - momentum: 0.000000
2023-10-18 23:53:46,790 epoch 2 - iter 301/432 - loss 0.41739009 - time (sec): 95.55 - samples/sec: 457.84 - lr: 0.000046 - momentum: 0.000000
2023-10-18 23:54:00,936 epoch 2 - iter 344/432 - loss 0.40919722 - time (sec): 109.70 - samples/sec: 452.88 - lr: 0.000046 - momentum: 0.000000
2023-10-18 23:54:15,261 epoch 2 - iter 387/432 - loss 0.39789179 - time (sec): 124.02 - samples/sec: 448.77 - lr: 0.000045 - momentum: 0.000000
2023-10-18 23:54:30,460 epoch 2 - iter 430/432 - loss 0.39342103 - time (sec): 139.22 - samples/sec: 443.36 - lr: 0.000044 - momentum: 0.000000
2023-10-18 23:54:30,977 ----------------------------------------------------------------------------------------------------
2023-10-18 23:54:30,978 EPOCH 2 done: loss 0.3932 - lr: 0.000044
2023-10-18 23:54:43,400 DEV : loss 0.3221401870250702 - f1-score (micro avg) 0.7999
2023-10-18 23:54:43,424 saving best model
2023-10-18 23:54:44,719 ----------------------------------------------------------------------------------------------------
2023-10-18 23:54:58,597 epoch 3 - iter 43/432 - loss 0.26073780 - time (sec): 13.88 - samples/sec: 440.91 - lr: 0.000044 - momentum: 0.000000
2023-10-18 23:55:12,781 epoch 3 - iter 86/432 - loss 0.26640971 - time (sec): 28.06 - samples/sec: 433.46 - lr: 0.000043 - momentum: 0.000000
2023-10-18 23:55:27,533 epoch 3 - iter 129/432 - loss 0.25801074 - time (sec): 42.81 - samples/sec: 424.09 - lr: 0.000043 - momentum: 0.000000
2023-10-18 23:55:42,492 epoch 3 - iter 172/432 - loss 0.24957799 - time (sec): 57.77 - samples/sec: 421.11 - lr: 0.000042 - momentum: 0.000000
2023-10-18 23:55:57,651 epoch 3 - iter 215/432 - loss 0.25398995 - time (sec): 72.93 - samples/sec: 417.81 - lr: 0.000042 - momentum: 0.000000
2023-10-18 23:56:12,408 epoch 3 - iter 258/432 - loss 0.25510902 - time (sec): 87.69 - samples/sec: 421.63 - lr: 0.000041 - momentum: 0.000000
2023-10-18 23:56:27,276 epoch 3 - iter 301/432 - loss 0.25604031 - time (sec): 102.55 - samples/sec: 420.25 - lr: 0.000041 - momentum: 0.000000
2023-10-18 23:56:41,333 epoch 3 - iter 344/432 - loss 0.25487803 - time (sec): 116.61 - samples/sec: 424.44 - lr: 0.000040 - momentum: 0.000000
2023-10-18 23:56:55,954 epoch 3 - iter 387/432 - loss 0.25224648 - time (sec): 131.23 - samples/sec: 425.07 - lr: 0.000039 - momentum: 0.000000
2023-10-18 23:57:10,652 epoch 3 - iter 430/432 - loss 0.24985880 - time (sec): 145.93 - samples/sec: 422.88 - lr: 0.000039 - momentum: 0.000000
2023-10-18 23:57:11,301 ----------------------------------------------------------------------------------------------------
2023-10-18 23:57:11,301 EPOCH 3 done: loss 0.2495 - lr: 0.000039
2023-10-18 23:57:24,474 DEV : loss 0.2786136269569397 - f1-score (micro avg) 0.8259
2023-10-18 23:57:24,498 saving best model
2023-10-18 23:57:25,777 ----------------------------------------------------------------------------------------------------
2023-10-18 23:57:39,701 epoch 4 - iter 43/432 - loss 0.17159693 - time (sec): 13.92 - samples/sec: 472.47 - lr: 0.000038 - momentum: 0.000000
2023-10-18 23:57:55,199 epoch 4 - iter 86/432 - loss 0.17789331 - time (sec): 29.42 - samples/sec: 433.90 - lr: 0.000038 - momentum: 0.000000
2023-10-18 23:58:10,250 epoch 4 - iter 129/432 - loss 0.17886504 - time (sec): 44.47 - samples/sec: 428.99 - lr: 0.000037 - momentum: 0.000000
2023-10-18 23:58:24,351 epoch 4 - iter 172/432 - loss 0.17380496 - time (sec): 58.57 - samples/sec: 428.72 - lr: 0.000037 - momentum: 0.000000
2023-10-18 23:58:40,004 epoch 4 - iter 215/432 - loss 0.17639725 - time (sec): 74.23 - samples/sec: 426.47 - lr: 0.000036 - momentum: 0.000000
2023-10-18 23:58:55,251 epoch 4 - iter 258/432 - loss 0.17695320 - time (sec): 89.47 - samples/sec: 425.05 - lr: 0.000036 - momentum: 0.000000
2023-10-18 23:59:10,163 epoch 4 - iter 301/432 - loss 0.17433887 - time (sec): 104.39 - samples/sec: 422.34 - lr: 0.000035 - momentum: 0.000000
2023-10-18 23:59:24,925 epoch 4 - iter 344/432 - loss 0.17056141 - time (sec): 119.15 - samples/sec: 416.50 - lr: 0.000034 - momentum: 0.000000
2023-10-18 23:59:40,330 epoch 4 - iter 387/432 - loss 0.17233317 - time (sec): 134.55 - samples/sec: 414.20 - lr: 0.000034 - momentum: 0.000000
2023-10-18 23:59:55,682 epoch 4 - iter 430/432 - loss 0.17233952 - time (sec): 149.90 - samples/sec: 411.30 - lr: 0.000033 - momentum: 0.000000
2023-10-18 23:59:56,286 ----------------------------------------------------------------------------------------------------
2023-10-18 23:59:56,286 EPOCH 4 done: loss 0.1719 - lr: 0.000033
2023-10-19 00:00:09,553 DEV : loss 0.3027258515357971 - f1-score (micro avg) 0.833
2023-10-19 00:00:09,578 saving best model
2023-10-19 00:00:10,866 ----------------------------------------------------------------------------------------------------
2023-10-19 00:00:24,962 epoch 5 - iter 43/432 - loss 0.13224073 - time (sec): 14.09 - samples/sec: 412.85 - lr: 0.000033 - momentum: 0.000000
2023-10-19 00:00:40,762 epoch 5 - iter 86/432 - loss 0.12870566 - time (sec): 29.89 - samples/sec: 396.63 - lr: 0.000032 - momentum: 0.000000
2023-10-19 00:00:56,297 epoch 5 - iter 129/432 - loss 0.12680988 - time (sec): 45.43 - samples/sec: 391.33 - lr: 0.000032 - momentum: 0.000000
2023-10-19 00:01:11,298 epoch 5 - iter 172/432 - loss 0.12448631 - time (sec): 60.43 - samples/sec: 397.60 - lr: 0.000031 - momentum: 0.000000
2023-10-19 00:01:25,586 epoch 5 - iter 215/432 - loss 0.12976948 - time (sec): 74.72 - samples/sec: 400.65 - lr: 0.000031 - momentum: 0.000000
2023-10-19 00:01:40,737 epoch 5 - iter 258/432 - loss 0.13032162 - time (sec): 89.87 - samples/sec: 401.15 - lr: 0.000030 - momentum: 0.000000
2023-10-19 00:01:55,989 epoch 5 - iter 301/432 - loss 0.13168277 - time (sec): 105.12 - samples/sec: 405.48 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:02:09,035 epoch 5 - iter 344/432 - loss 0.13191984 - time (sec): 118.17 - samples/sec: 415.52 - lr: 0.000029 - momentum: 0.000000
2023-10-19 00:02:24,258 epoch 5 - iter 387/432 - loss 0.13139996 - time (sec): 133.39 - samples/sec: 414.77 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:02:40,019 epoch 5 - iter 430/432 - loss 0.13241412 - time (sec): 149.15 - samples/sec: 413.75 - lr: 0.000028 - momentum: 0.000000
2023-10-19 00:02:40,513 ----------------------------------------------------------------------------------------------------
2023-10-19 00:02:40,513 EPOCH 5 done: loss 0.1323 - lr: 0.000028
2023-10-19 00:02:53,879 DEV : loss 0.3319297134876251 - f1-score (micro avg) 0.8275
2023-10-19 00:02:53,909 ----------------------------------------------------------------------------------------------------
2023-10-19 00:03:09,440 epoch 6 - iter 43/432 - loss 0.08999368 - time (sec): 15.53 - samples/sec: 399.56 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:03:23,839 epoch 6 - iter 86/432 - loss 0.08539150 - time (sec): 29.93 - samples/sec: 429.70 - lr: 0.000027 - momentum: 0.000000
2023-10-19 00:03:38,488 epoch 6 - iter 129/432 - loss 0.09986893 - time (sec): 44.58 - samples/sec: 422.57 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:03:54,568 epoch 6 - iter 172/432 - loss 0.09913431 - time (sec): 60.66 - samples/sec: 415.33 - lr: 0.000026 - momentum: 0.000000
2023-10-19 00:04:09,161 epoch 6 - iter 215/432 - loss 0.09906129 - time (sec): 75.25 - samples/sec: 409.41 - lr: 0.000025 - momentum: 0.000000
2023-10-19 00:04:23,814 epoch 6 - iter 258/432 - loss 0.09924250 - time (sec): 89.90 - samples/sec: 411.32 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:04:38,652 epoch 6 - iter 301/432 - loss 0.10059479 - time (sec): 104.74 - samples/sec: 412.85 - lr: 0.000024 - momentum: 0.000000
2023-10-19 00:04:53,540 epoch 6 - iter 344/432 - loss 0.09936378 - time (sec): 119.63 - samples/sec: 413.63 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:05:08,991 epoch 6 - iter 387/432 - loss 0.09927245 - time (sec): 135.08 - samples/sec: 410.82 - lr: 0.000023 - momentum: 0.000000
2023-10-19 00:05:25,338 epoch 6 - iter 430/432 - loss 0.09843081 - time (sec): 151.43 - samples/sec: 407.47 - lr: 0.000022 - momentum: 0.000000
2023-10-19 00:05:25,876 ----------------------------------------------------------------------------------------------------
2023-10-19 00:05:25,876 EPOCH 6 done: loss 0.0985 - lr: 0.000022
2023-10-19 00:05:39,277 DEV : loss 0.3483152687549591 - f1-score (micro avg) 0.8353
2023-10-19 00:05:39,301 saving best model
2023-10-19 00:05:41,347 ----------------------------------------------------------------------------------------------------
2023-10-19 00:05:56,804 epoch 7 - iter 43/432 - loss 0.07646855 - time (sec): 15.46 - samples/sec: 383.21 - lr: 0.000022 - momentum: 0.000000
2023-10-19 00:06:12,246 epoch 7 - iter 86/432 - loss 0.07564571 - time (sec): 30.90 - samples/sec: 382.43 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:06:26,486 epoch 7 - iter 129/432 - loss 0.07414267 - time (sec): 45.14 - samples/sec: 405.53 - lr: 0.000021 - momentum: 0.000000
2023-10-19 00:06:41,108 epoch 7 - iter 172/432 - loss 0.07110179 - time (sec): 59.76 - samples/sec: 418.47 - lr: 0.000020 - momentum: 0.000000
2023-10-19 00:06:56,294 epoch 7 - iter 215/432 - loss 0.07443072 - time (sec): 74.95 - samples/sec: 413.30 - lr: 0.000019 - momentum: 0.000000
2023-10-19 00:07:10,672 epoch 7 - iter 258/432 - loss 0.07597555 - time (sec): 89.32 - samples/sec: 417.24 - lr: 0.000019 - momentum: 0.000000
2023-10-19 00:07:25,487 epoch 7 - iter 301/432 - loss 0.07746008 - time (sec): 104.14 - samples/sec: 417.75 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:07:40,229 epoch 7 - iter 344/432 - loss 0.07686569 - time (sec): 118.88 - samples/sec: 417.03 - lr: 0.000018 - momentum: 0.000000
2023-10-19 00:07:55,052 epoch 7 - iter 387/432 - loss 0.07546838 - time (sec): 133.70 - samples/sec: 413.79 - lr: 0.000017 - momentum: 0.000000
2023-10-19 00:08:09,443 epoch 7 - iter 430/432 - loss 0.07435736 - time (sec): 148.09 - samples/sec: 415.90 - lr: 0.000017 - momentum: 0.000000
2023-10-19 00:08:10,004 ----------------------------------------------------------------------------------------------------
2023-10-19 00:08:10,005 EPOCH 7 done: loss 0.0749 - lr: 0.000017
2023-10-19 00:08:22,467 DEV : loss 0.35942888259887695 - f1-score (micro avg) 0.8395
2023-10-19 00:08:22,492 saving best model
2023-10-19 00:08:23,780 ----------------------------------------------------------------------------------------------------
2023-10-19 00:08:37,812 epoch 8 - iter 43/432 - loss 0.05403566 - time (sec): 14.03 - samples/sec: 443.97 - lr: 0.000016 - momentum: 0.000000
2023-10-19 00:08:50,468 epoch 8 - iter 86/432 - loss 0.05416407 - time (sec): 26.69 - samples/sec: 465.48 - lr: 0.000016 - momentum: 0.000000
2023-10-19 00:09:05,136 epoch 8 - iter 129/432 - loss 0.05231093 - time (sec): 41.35 - samples/sec: 445.46 - lr: 0.000015 - momentum: 0.000000
2023-10-19 00:09:19,064 epoch 8 - iter 172/432 - loss 0.05332684 - time (sec): 55.28 - samples/sec: 439.02 - lr: 0.000014 - momentum: 0.000000
2023-10-19 00:09:32,357 epoch 8 - iter 215/432 - loss 0.05490906 - time (sec): 68.58 - samples/sec: 442.24 - lr: 0.000014 - momentum: 0.000000
2023-10-19 00:09:45,819 epoch 8 - iter 258/432 - loss 0.05470571 - time (sec): 82.04 - samples/sec: 445.59 - lr: 0.000013 - momentum: 0.000000
2023-10-19 00:09:59,775 epoch 8 - iter 301/432 - loss 0.05508927 - time (sec): 95.99 - samples/sec: 444.48 - lr: 0.000013 - momentum: 0.000000
2023-10-19 00:10:13,551 epoch 8 - iter 344/432 - loss 0.05696792 - time (sec): 109.77 - samples/sec: 443.76 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:10:28,569 epoch 8 - iter 387/432 - loss 0.05709499 - time (sec): 124.79 - samples/sec: 440.02 - lr: 0.000012 - momentum: 0.000000
2023-10-19 00:10:42,292 epoch 8 - iter 430/432 - loss 0.05606310 - time (sec): 138.51 - samples/sec: 445.16 - lr: 0.000011 - momentum: 0.000000
2023-10-19 00:10:42,821 ----------------------------------------------------------------------------------------------------
2023-10-19 00:10:42,821 EPOCH 8 done: loss 0.0560 - lr: 0.000011
2023-10-19 00:10:55,201 DEV : loss 0.3855433464050293 - f1-score (micro avg) 0.8399
2023-10-19 00:10:55,225 saving best model
2023-10-19 00:10:56,513 ----------------------------------------------------------------------------------------------------
2023-10-19 00:11:09,243 epoch 9 - iter 43/432 - loss 0.04130631 - time (sec): 12.73 - samples/sec: 503.43 - lr: 0.000011 - momentum: 0.000000
2023-10-19 00:11:22,023 epoch 9 - iter 86/432 - loss 0.03767518 - time (sec): 25.51 - samples/sec: 484.19 - lr: 0.000010 - momentum: 0.000000
2023-10-19 00:11:35,992 epoch 9 - iter 129/432 - loss 0.04012592 - time (sec): 39.48 - samples/sec: 467.91 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:11:50,170 epoch 9 - iter 172/432 - loss 0.03874753 - time (sec): 53.66 - samples/sec: 461.63 - lr: 0.000009 - momentum: 0.000000
2023-10-19 00:12:03,449 epoch 9 - iter 215/432 - loss 0.03749511 - time (sec): 66.93 - samples/sec: 465.10 - lr: 0.000008 - momentum: 0.000000
2023-10-19 00:12:17,477 epoch 9 - iter 258/432 - loss 0.03805076 - time (sec): 80.96 - samples/sec: 460.64 - lr: 0.000008 - momentum: 0.000000
2023-10-19 00:12:30,864 epoch 9 - iter 301/432 - loss 0.03919902 - time (sec): 94.35 - samples/sec: 462.58 - lr: 0.000007 - momentum: 0.000000
2023-10-19 00:12:45,129 epoch 9 - iter 344/432 - loss 0.04055903 - time (sec): 108.62 - samples/sec: 455.14 - lr: 0.000007 - momentum: 0.000000
2023-10-19 00:12:59,088 epoch 9 - iter 387/432 - loss 0.04016294 - time (sec): 122.57 - samples/sec: 452.94 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:13:12,844 epoch 9 - iter 430/432 - loss 0.04071803 - time (sec): 136.33 - samples/sec: 452.09 - lr: 0.000006 - momentum: 0.000000
2023-10-19 00:13:13,346 ----------------------------------------------------------------------------------------------------
2023-10-19 00:13:13,346 EPOCH 9 done: loss 0.0406 - lr: 0.000006
2023-10-19 00:13:25,615 DEV : loss 0.398950457572937 - f1-score (micro avg) 0.8446
2023-10-19 00:13:25,640 saving best model
2023-10-19 00:13:26,920 ----------------------------------------------------------------------------------------------------
2023-10-19 00:13:40,602 epoch 10 - iter 43/432 - loss 0.03991636 - time (sec): 13.68 - samples/sec: 438.30 - lr: 0.000005 - momentum: 0.000000
2023-10-19 00:13:54,198 epoch 10 - iter 86/432 - loss 0.03709518 - time (sec): 27.28 - samples/sec: 436.13 - lr: 0.000004 - momentum: 0.000000
2023-10-19 00:14:07,245 epoch 10 - iter 129/432 - loss 0.03665230 - time (sec): 40.32 - samples/sec: 453.56 - lr: 0.000004 - momentum: 0.000000
2023-10-19 00:14:21,656 epoch 10 - iter 172/432 - loss 0.03488483 - time (sec): 54.73 - samples/sec: 449.35 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:14:35,583 epoch 10 - iter 215/432 - loss 0.03260316 - time (sec): 68.66 - samples/sec: 449.20 - lr: 0.000003 - momentum: 0.000000
2023-10-19 00:14:50,542 epoch 10 - iter 258/432 - loss 0.03311250 - time (sec): 83.62 - samples/sec: 442.51 - lr: 0.000002 - momentum: 0.000000
2023-10-19 00:15:04,584 epoch 10 - iter 301/432 - loss 0.03267573 - time (sec): 97.66 - samples/sec: 440.01 - lr: 0.000002 - momentum: 0.000000
2023-10-19 00:15:20,118 epoch 10 - iter 344/432 - loss 0.03135514 - time (sec): 113.20 - samples/sec: 434.14 - lr: 0.000001 - momentum: 0.000000
2023-10-19 00:15:35,441 epoch 10 - iter 387/432 - loss 0.03196909 - time (sec): 128.52 - samples/sec: 431.63 - lr: 0.000001 - momentum: 0.000000
2023-10-19 00:15:50,021 epoch 10 - iter 430/432 - loss 0.03303907 - time (sec): 143.10 - samples/sec: 430.68 - lr: 0.000000 - momentum: 0.000000
2023-10-19 00:15:50,585 ----------------------------------------------------------------------------------------------------
2023-10-19 00:15:50,585 EPOCH 10 done: loss 0.0330 - lr: 0.000000
2023-10-19 00:16:03,688 DEV : loss 0.41425013542175293 - f1-score (micro avg) 0.8446
2023-10-19 00:16:03,714 saving best model
2023-10-19 00:16:05,498 ----------------------------------------------------------------------------------------------------
2023-10-19 00:16:05,500 Loading model from best epoch ...
2023-10-19 00:16:07,893 SequenceTagger predicts: Dictionary with 81 tags: O, S-location-route, B-location-route, E-location-route, I-location-route, S-location-stop, B-location-stop, E-location-stop, I-location-stop, S-trigger, B-trigger, E-trigger, I-trigger, S-organization-company, B-organization-company, E-organization-company, I-organization-company, S-location-city, B-location-city, E-location-city, I-location-city, S-location, B-location, E-location, I-location, S-event-cause, B-event-cause, E-event-cause, I-event-cause, S-location-street, B-location-street, E-location-street, I-location-street, S-time, B-time, E-time, I-time, S-date, B-date, E-date, I-date, S-number, B-number, E-number, I-number, S-duration, B-duration, E-duration, I-duration, S-organization
2023-10-19 00:16:25,689
Results:
- F-score (micro) 0.7706
- F-score (macro) 0.5891
- Accuracy 0.6737
By class:
precision recall f1-score support
trigger 0.7277 0.6062 0.6614 833
location-stop 0.8421 0.8157 0.8287 765
location 0.8096 0.8376 0.8234 665
location-city 0.8068 0.8852 0.8441 566
date 0.9013 0.8579 0.8791 394
location-street 0.9417 0.8782 0.9088 386
time 0.7855 0.8867 0.8330 256
location-route 0.9053 0.7746 0.8349 284
organization-company 0.7838 0.6905 0.7342 252
distance 0.9882 1.0000 0.9940 167
number 0.6760 0.8121 0.7378 149
duration 0.3484 0.3313 0.3396 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.9310 0.3913 0.5510 69
organization 0.5769 0.5357 0.5556 28
person 0.5000 1.0000 0.6667 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 0.7637 0.7777 0.7706 4988
macro avg 0.6065 0.5949 0.5891 4988
weighted avg 0.8075 0.7777 0.7888 4988
2023-10-19 00:16:25,690 ----------------------------------------------------------------------------------------------------
|