File size: 24,223 Bytes
888acf8 |
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 |
2023-10-18 18:03:46,090 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 128)
(position_embeddings): Embedding(512, 128)
(token_type_embeddings): Embedding(2, 128)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-1): 2 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=128, out_features=128, bias=True)
(key): Linear(in_features=128, out_features=128, bias=True)
(value): Linear(in_features=128, out_features=128, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=128, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=128, out_features=512, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=512, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=128, out_features=128, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=128, out_features=21, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
- NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 Train: 3575 sentences
2023-10-18 18:03:46,091 (train_with_dev=False, train_with_test=False)
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 Training Params:
2023-10-18 18:03:46,091 - learning_rate: "5e-05"
2023-10-18 18:03:46,091 - mini_batch_size: "4"
2023-10-18 18:03:46,091 - max_epochs: "10"
2023-10-18 18:03:46,091 - shuffle: "True"
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 Plugins:
2023-10-18 18:03:46,091 - TensorboardLogger
2023-10-18 18:03:46,091 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,091 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 18:03:46,091 - metric: "('micro avg', 'f1-score')"
2023-10-18 18:03:46,091 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,092 Computation:
2023-10-18 18:03:46,092 - compute on device: cuda:0
2023-10-18 18:03:46,092 - embedding storage: none
2023-10-18 18:03:46,092 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,092 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-18 18:03:46,092 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,092 ----------------------------------------------------------------------------------------------------
2023-10-18 18:03:46,092 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 18:03:47,533 epoch 1 - iter 89/894 - loss 3.43498959 - time (sec): 1.44 - samples/sec: 5610.49 - lr: 0.000005 - momentum: 0.000000
2023-10-18 18:03:48,952 epoch 1 - iter 178/894 - loss 3.08753148 - time (sec): 2.86 - samples/sec: 5738.36 - lr: 0.000010 - momentum: 0.000000
2023-10-18 18:03:50,382 epoch 1 - iter 267/894 - loss 2.60861970 - time (sec): 4.29 - samples/sec: 5938.06 - lr: 0.000015 - momentum: 0.000000
2023-10-18 18:03:51,817 epoch 1 - iter 356/894 - loss 2.13729872 - time (sec): 5.72 - samples/sec: 6025.76 - lr: 0.000020 - momentum: 0.000000
2023-10-18 18:03:53,195 epoch 1 - iter 445/894 - loss 1.85618622 - time (sec): 7.10 - samples/sec: 6050.11 - lr: 0.000025 - momentum: 0.000000
2023-10-18 18:03:54,589 epoch 1 - iter 534/894 - loss 1.65953709 - time (sec): 8.50 - samples/sec: 6001.19 - lr: 0.000030 - momentum: 0.000000
2023-10-18 18:03:55,981 epoch 1 - iter 623/894 - loss 1.50846636 - time (sec): 9.89 - samples/sec: 5992.96 - lr: 0.000035 - momentum: 0.000000
2023-10-18 18:03:57,429 epoch 1 - iter 712/894 - loss 1.38521735 - time (sec): 11.34 - samples/sec: 6015.28 - lr: 0.000040 - momentum: 0.000000
2023-10-18 18:03:58,878 epoch 1 - iter 801/894 - loss 1.28793964 - time (sec): 12.79 - samples/sec: 6076.01 - lr: 0.000045 - momentum: 0.000000
2023-10-18 18:04:00,261 epoch 1 - iter 890/894 - loss 1.21448172 - time (sec): 14.17 - samples/sec: 6079.72 - lr: 0.000050 - momentum: 0.000000
2023-10-18 18:04:00,318 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:00,318 EPOCH 1 done: loss 1.2137 - lr: 0.000050
2023-10-18 18:04:02,580 DEV : loss 0.4263085424900055 - f1-score (micro avg) 0.0
2023-10-18 18:04:02,608 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:03,972 epoch 2 - iter 89/894 - loss 0.49713747 - time (sec): 1.36 - samples/sec: 6507.15 - lr: 0.000049 - momentum: 0.000000
2023-10-18 18:04:05,345 epoch 2 - iter 178/894 - loss 0.49185097 - time (sec): 2.74 - samples/sec: 6351.21 - lr: 0.000049 - momentum: 0.000000
2023-10-18 18:04:06,690 epoch 2 - iter 267/894 - loss 0.48800476 - time (sec): 4.08 - samples/sec: 6272.11 - lr: 0.000048 - momentum: 0.000000
2023-10-18 18:04:08,046 epoch 2 - iter 356/894 - loss 0.48445397 - time (sec): 5.44 - samples/sec: 6185.52 - lr: 0.000048 - momentum: 0.000000
2023-10-18 18:04:09,394 epoch 2 - iter 445/894 - loss 0.48238418 - time (sec): 6.79 - samples/sec: 6194.15 - lr: 0.000047 - momentum: 0.000000
2023-10-18 18:04:10,800 epoch 2 - iter 534/894 - loss 0.46700383 - time (sec): 8.19 - samples/sec: 6204.76 - lr: 0.000047 - momentum: 0.000000
2023-10-18 18:04:12,210 epoch 2 - iter 623/894 - loss 0.46662532 - time (sec): 9.60 - samples/sec: 6141.59 - lr: 0.000046 - momentum: 0.000000
2023-10-18 18:04:13,680 epoch 2 - iter 712/894 - loss 0.45539541 - time (sec): 11.07 - samples/sec: 6208.94 - lr: 0.000046 - momentum: 0.000000
2023-10-18 18:04:15,109 epoch 2 - iter 801/894 - loss 0.45446600 - time (sec): 12.50 - samples/sec: 6221.45 - lr: 0.000045 - momentum: 0.000000
2023-10-18 18:04:16,525 epoch 2 - iter 890/894 - loss 0.44765225 - time (sec): 13.92 - samples/sec: 6199.65 - lr: 0.000044 - momentum: 0.000000
2023-10-18 18:04:16,582 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:16,582 EPOCH 2 done: loss 0.4482 - lr: 0.000044
2023-10-18 18:04:21,878 DEV : loss 0.34765392541885376 - f1-score (micro avg) 0.243
2023-10-18 18:04:21,905 saving best model
2023-10-18 18:04:21,941 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:23,330 epoch 3 - iter 89/894 - loss 0.41805770 - time (sec): 1.39 - samples/sec: 5959.90 - lr: 0.000044 - momentum: 0.000000
2023-10-18 18:04:24,759 epoch 3 - iter 178/894 - loss 0.43276993 - time (sec): 2.82 - samples/sec: 6072.98 - lr: 0.000043 - momentum: 0.000000
2023-10-18 18:04:26,230 epoch 3 - iter 267/894 - loss 0.41738376 - time (sec): 4.29 - samples/sec: 6161.21 - lr: 0.000043 - momentum: 0.000000
2023-10-18 18:04:27,684 epoch 3 - iter 356/894 - loss 0.41407899 - time (sec): 5.74 - samples/sec: 6145.33 - lr: 0.000042 - momentum: 0.000000
2023-10-18 18:04:29,116 epoch 3 - iter 445/894 - loss 0.40637262 - time (sec): 7.17 - samples/sec: 6093.57 - lr: 0.000042 - momentum: 0.000000
2023-10-18 18:04:30,550 epoch 3 - iter 534/894 - loss 0.38982328 - time (sec): 8.61 - samples/sec: 6103.09 - lr: 0.000041 - momentum: 0.000000
2023-10-18 18:04:32,011 epoch 3 - iter 623/894 - loss 0.38362119 - time (sec): 10.07 - samples/sec: 6074.46 - lr: 0.000041 - momentum: 0.000000
2023-10-18 18:04:33,369 epoch 3 - iter 712/894 - loss 0.37912964 - time (sec): 11.43 - samples/sec: 6056.07 - lr: 0.000040 - momentum: 0.000000
2023-10-18 18:04:34,763 epoch 3 - iter 801/894 - loss 0.37858686 - time (sec): 12.82 - samples/sec: 6078.61 - lr: 0.000039 - momentum: 0.000000
2023-10-18 18:04:36,131 epoch 3 - iter 890/894 - loss 0.37562114 - time (sec): 14.19 - samples/sec: 6068.41 - lr: 0.000039 - momentum: 0.000000
2023-10-18 18:04:36,190 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:36,190 EPOCH 3 done: loss 0.3755 - lr: 0.000039
2023-10-18 18:04:41,515 DEV : loss 0.3211207091808319 - f1-score (micro avg) 0.3142
2023-10-18 18:04:41,542 saving best model
2023-10-18 18:04:41,581 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:42,998 epoch 4 - iter 89/894 - loss 0.32635474 - time (sec): 1.42 - samples/sec: 6060.62 - lr: 0.000038 - momentum: 0.000000
2023-10-18 18:04:44,429 epoch 4 - iter 178/894 - loss 0.35437975 - time (sec): 2.85 - samples/sec: 6088.53 - lr: 0.000038 - momentum: 0.000000
2023-10-18 18:04:45,831 epoch 4 - iter 267/894 - loss 0.35089723 - time (sec): 4.25 - samples/sec: 6157.04 - lr: 0.000037 - momentum: 0.000000
2023-10-18 18:04:47,232 epoch 4 - iter 356/894 - loss 0.33648000 - time (sec): 5.65 - samples/sec: 6280.87 - lr: 0.000037 - momentum: 0.000000
2023-10-18 18:04:48,680 epoch 4 - iter 445/894 - loss 0.33816098 - time (sec): 7.10 - samples/sec: 6355.06 - lr: 0.000036 - momentum: 0.000000
2023-10-18 18:04:50,092 epoch 4 - iter 534/894 - loss 0.34098676 - time (sec): 8.51 - samples/sec: 6224.61 - lr: 0.000036 - momentum: 0.000000
2023-10-18 18:04:51,451 epoch 4 - iter 623/894 - loss 0.33157366 - time (sec): 9.87 - samples/sec: 6234.07 - lr: 0.000035 - momentum: 0.000000
2023-10-18 18:04:52,819 epoch 4 - iter 712/894 - loss 0.33569841 - time (sec): 11.24 - samples/sec: 6211.82 - lr: 0.000034 - momentum: 0.000000
2023-10-18 18:04:54,194 epoch 4 - iter 801/894 - loss 0.33458161 - time (sec): 12.61 - samples/sec: 6141.90 - lr: 0.000034 - momentum: 0.000000
2023-10-18 18:04:55,599 epoch 4 - iter 890/894 - loss 0.33097427 - time (sec): 14.02 - samples/sec: 6154.52 - lr: 0.000033 - momentum: 0.000000
2023-10-18 18:04:55,654 ----------------------------------------------------------------------------------------------------
2023-10-18 18:04:55,654 EPOCH 4 done: loss 0.3311 - lr: 0.000033
2023-10-18 18:05:00,985 DEV : loss 0.3120403289794922 - f1-score (micro avg) 0.324
2023-10-18 18:05:01,015 saving best model
2023-10-18 18:05:01,058 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:02,483 epoch 5 - iter 89/894 - loss 0.30524145 - time (sec): 1.43 - samples/sec: 5936.06 - lr: 0.000033 - momentum: 0.000000
2023-10-18 18:05:03,938 epoch 5 - iter 178/894 - loss 0.30512104 - time (sec): 2.88 - samples/sec: 6353.14 - lr: 0.000032 - momentum: 0.000000
2023-10-18 18:05:05,364 epoch 5 - iter 267/894 - loss 0.31020994 - time (sec): 4.31 - samples/sec: 6345.63 - lr: 0.000032 - momentum: 0.000000
2023-10-18 18:05:06,758 epoch 5 - iter 356/894 - loss 0.30779353 - time (sec): 5.70 - samples/sec: 6257.62 - lr: 0.000031 - momentum: 0.000000
2023-10-18 18:05:08,055 epoch 5 - iter 445/894 - loss 0.31278385 - time (sec): 7.00 - samples/sec: 6241.21 - lr: 0.000031 - momentum: 0.000000
2023-10-18 18:05:09,427 epoch 5 - iter 534/894 - loss 0.31087426 - time (sec): 8.37 - samples/sec: 6201.39 - lr: 0.000030 - momentum: 0.000000
2023-10-18 18:05:10,775 epoch 5 - iter 623/894 - loss 0.30915571 - time (sec): 9.72 - samples/sec: 6240.06 - lr: 0.000029 - momentum: 0.000000
2023-10-18 18:05:12,195 epoch 5 - iter 712/894 - loss 0.30863944 - time (sec): 11.14 - samples/sec: 6265.60 - lr: 0.000029 - momentum: 0.000000
2023-10-18 18:05:13,587 epoch 5 - iter 801/894 - loss 0.30557407 - time (sec): 12.53 - samples/sec: 6240.28 - lr: 0.000028 - momentum: 0.000000
2023-10-18 18:05:14,822 epoch 5 - iter 890/894 - loss 0.30351739 - time (sec): 13.76 - samples/sec: 6264.59 - lr: 0.000028 - momentum: 0.000000
2023-10-18 18:05:14,878 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:14,878 EPOCH 5 done: loss 0.3034 - lr: 0.000028
2023-10-18 18:05:19,904 DEV : loss 0.30890053510665894 - f1-score (micro avg) 0.3343
2023-10-18 18:05:19,931 saving best model
2023-10-18 18:05:19,967 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:21,381 epoch 6 - iter 89/894 - loss 0.24665018 - time (sec): 1.41 - samples/sec: 6563.05 - lr: 0.000027 - momentum: 0.000000
2023-10-18 18:05:22,749 epoch 6 - iter 178/894 - loss 0.27338459 - time (sec): 2.78 - samples/sec: 6371.40 - lr: 0.000027 - momentum: 0.000000
2023-10-18 18:05:24,465 epoch 6 - iter 267/894 - loss 0.29310495 - time (sec): 4.50 - samples/sec: 5780.54 - lr: 0.000026 - momentum: 0.000000
2023-10-18 18:05:25,850 epoch 6 - iter 356/894 - loss 0.29432340 - time (sec): 5.88 - samples/sec: 5880.07 - lr: 0.000026 - momentum: 0.000000
2023-10-18 18:05:27,252 epoch 6 - iter 445/894 - loss 0.29662643 - time (sec): 7.28 - samples/sec: 5994.72 - lr: 0.000025 - momentum: 0.000000
2023-10-18 18:05:28,571 epoch 6 - iter 534/894 - loss 0.29414115 - time (sec): 8.60 - samples/sec: 6051.60 - lr: 0.000024 - momentum: 0.000000
2023-10-18 18:05:29,952 epoch 6 - iter 623/894 - loss 0.28659247 - time (sec): 9.98 - samples/sec: 6043.06 - lr: 0.000024 - momentum: 0.000000
2023-10-18 18:05:31,338 epoch 6 - iter 712/894 - loss 0.28157192 - time (sec): 11.37 - samples/sec: 6063.04 - lr: 0.000023 - momentum: 0.000000
2023-10-18 18:05:32,733 epoch 6 - iter 801/894 - loss 0.27671928 - time (sec): 12.77 - samples/sec: 6091.72 - lr: 0.000023 - momentum: 0.000000
2023-10-18 18:05:34,087 epoch 6 - iter 890/894 - loss 0.28086399 - time (sec): 14.12 - samples/sec: 6101.38 - lr: 0.000022 - momentum: 0.000000
2023-10-18 18:05:34,151 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:34,152 EPOCH 6 done: loss 0.2806 - lr: 0.000022
2023-10-18 18:05:39,129 DEV : loss 0.31113117933273315 - f1-score (micro avg) 0.342
2023-10-18 18:05:39,156 saving best model
2023-10-18 18:05:39,193 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:40,640 epoch 7 - iter 89/894 - loss 0.23315533 - time (sec): 1.45 - samples/sec: 5639.23 - lr: 0.000022 - momentum: 0.000000
2023-10-18 18:05:42,111 epoch 7 - iter 178/894 - loss 0.26534915 - time (sec): 2.92 - samples/sec: 6063.91 - lr: 0.000021 - momentum: 0.000000
2023-10-18 18:05:43,499 epoch 7 - iter 267/894 - loss 0.26302261 - time (sec): 4.31 - samples/sec: 6038.79 - lr: 0.000021 - momentum: 0.000000
2023-10-18 18:05:44,942 epoch 7 - iter 356/894 - loss 0.26080884 - time (sec): 5.75 - samples/sec: 6263.67 - lr: 0.000020 - momentum: 0.000000
2023-10-18 18:05:46,327 epoch 7 - iter 445/894 - loss 0.26482923 - time (sec): 7.13 - samples/sec: 6225.72 - lr: 0.000019 - momentum: 0.000000
2023-10-18 18:05:47,756 epoch 7 - iter 534/894 - loss 0.26287988 - time (sec): 8.56 - samples/sec: 6286.91 - lr: 0.000019 - momentum: 0.000000
2023-10-18 18:05:49,126 epoch 7 - iter 623/894 - loss 0.26066862 - time (sec): 9.93 - samples/sec: 6195.50 - lr: 0.000018 - momentum: 0.000000
2023-10-18 18:05:50,531 epoch 7 - iter 712/894 - loss 0.26624906 - time (sec): 11.34 - samples/sec: 6200.49 - lr: 0.000018 - momentum: 0.000000
2023-10-18 18:05:51,901 epoch 7 - iter 801/894 - loss 0.26615665 - time (sec): 12.71 - samples/sec: 6142.77 - lr: 0.000017 - momentum: 0.000000
2023-10-18 18:05:53,286 epoch 7 - iter 890/894 - loss 0.26606576 - time (sec): 14.09 - samples/sec: 6113.64 - lr: 0.000017 - momentum: 0.000000
2023-10-18 18:05:53,353 ----------------------------------------------------------------------------------------------------
2023-10-18 18:05:53,353 EPOCH 7 done: loss 0.2655 - lr: 0.000017
2023-10-18 18:05:58,659 DEV : loss 0.30758559703826904 - f1-score (micro avg) 0.3511
2023-10-18 18:05:58,686 saving best model
2023-10-18 18:05:58,729 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:00,114 epoch 8 - iter 89/894 - loss 0.24002002 - time (sec): 1.38 - samples/sec: 5734.34 - lr: 0.000016 - momentum: 0.000000
2023-10-18 18:06:01,442 epoch 8 - iter 178/894 - loss 0.24034680 - time (sec): 2.71 - samples/sec: 5644.66 - lr: 0.000016 - momentum: 0.000000
2023-10-18 18:06:02,825 epoch 8 - iter 267/894 - loss 0.24390847 - time (sec): 4.10 - samples/sec: 5864.69 - lr: 0.000015 - momentum: 0.000000
2023-10-18 18:06:04,244 epoch 8 - iter 356/894 - loss 0.25396324 - time (sec): 5.51 - samples/sec: 5878.33 - lr: 0.000014 - momentum: 0.000000
2023-10-18 18:06:05,606 epoch 8 - iter 445/894 - loss 0.24715195 - time (sec): 6.88 - samples/sec: 5878.94 - lr: 0.000014 - momentum: 0.000000
2023-10-18 18:06:06,987 epoch 8 - iter 534/894 - loss 0.24673498 - time (sec): 8.26 - samples/sec: 5870.15 - lr: 0.000013 - momentum: 0.000000
2023-10-18 18:06:08,382 epoch 8 - iter 623/894 - loss 0.24348441 - time (sec): 9.65 - samples/sec: 6027.05 - lr: 0.000013 - momentum: 0.000000
2023-10-18 18:06:09,817 epoch 8 - iter 712/894 - loss 0.25278893 - time (sec): 11.09 - samples/sec: 6105.49 - lr: 0.000012 - momentum: 0.000000
2023-10-18 18:06:11,196 epoch 8 - iter 801/894 - loss 0.25276481 - time (sec): 12.47 - samples/sec: 6088.28 - lr: 0.000012 - momentum: 0.000000
2023-10-18 18:06:12,626 epoch 8 - iter 890/894 - loss 0.25135174 - time (sec): 13.90 - samples/sec: 6126.30 - lr: 0.000011 - momentum: 0.000000
2023-10-18 18:06:12,718 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:12,718 EPOCH 8 done: loss 0.2508 - lr: 0.000011
2023-10-18 18:06:18,040 DEV : loss 0.3025902807712555 - f1-score (micro avg) 0.3614
2023-10-18 18:06:18,068 saving best model
2023-10-18 18:06:18,109 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:19,549 epoch 9 - iter 89/894 - loss 0.26937101 - time (sec): 1.44 - samples/sec: 6843.28 - lr: 0.000011 - momentum: 0.000000
2023-10-18 18:06:20,950 epoch 9 - iter 178/894 - loss 0.27973157 - time (sec): 2.84 - samples/sec: 6485.42 - lr: 0.000010 - momentum: 0.000000
2023-10-18 18:06:22,254 epoch 9 - iter 267/894 - loss 0.26986158 - time (sec): 4.14 - samples/sec: 6628.31 - lr: 0.000009 - momentum: 0.000000
2023-10-18 18:06:23,627 epoch 9 - iter 356/894 - loss 0.26383497 - time (sec): 5.52 - samples/sec: 6341.42 - lr: 0.000009 - momentum: 0.000000
2023-10-18 18:06:24,991 epoch 9 - iter 445/894 - loss 0.24995919 - time (sec): 6.88 - samples/sec: 6305.16 - lr: 0.000008 - momentum: 0.000000
2023-10-18 18:06:26,386 epoch 9 - iter 534/894 - loss 0.25955274 - time (sec): 8.28 - samples/sec: 6287.82 - lr: 0.000008 - momentum: 0.000000
2023-10-18 18:06:27,769 epoch 9 - iter 623/894 - loss 0.25421326 - time (sec): 9.66 - samples/sec: 6256.93 - lr: 0.000007 - momentum: 0.000000
2023-10-18 18:06:29,187 epoch 9 - iter 712/894 - loss 0.24978285 - time (sec): 11.08 - samples/sec: 6238.94 - lr: 0.000007 - momentum: 0.000000
2023-10-18 18:06:30,545 epoch 9 - iter 801/894 - loss 0.24720986 - time (sec): 12.44 - samples/sec: 6240.93 - lr: 0.000006 - momentum: 0.000000
2023-10-18 18:06:31,938 epoch 9 - iter 890/894 - loss 0.24696720 - time (sec): 13.83 - samples/sec: 6227.11 - lr: 0.000006 - momentum: 0.000000
2023-10-18 18:06:31,997 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:31,997 EPOCH 9 done: loss 0.2480 - lr: 0.000006
2023-10-18 18:06:37,345 DEV : loss 0.30696946382522583 - f1-score (micro avg) 0.3654
2023-10-18 18:06:37,372 saving best model
2023-10-18 18:06:37,412 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:38,837 epoch 10 - iter 89/894 - loss 0.27149473 - time (sec): 1.42 - samples/sec: 6264.84 - lr: 0.000005 - momentum: 0.000000
2023-10-18 18:06:40,241 epoch 10 - iter 178/894 - loss 0.26748895 - time (sec): 2.83 - samples/sec: 6289.23 - lr: 0.000004 - momentum: 0.000000
2023-10-18 18:06:41,607 epoch 10 - iter 267/894 - loss 0.25190229 - time (sec): 4.19 - samples/sec: 6163.76 - lr: 0.000004 - momentum: 0.000000
2023-10-18 18:06:42,959 epoch 10 - iter 356/894 - loss 0.25823080 - time (sec): 5.55 - samples/sec: 6079.28 - lr: 0.000003 - momentum: 0.000000
2023-10-18 18:06:44,375 epoch 10 - iter 445/894 - loss 0.25629453 - time (sec): 6.96 - samples/sec: 6145.82 - lr: 0.000003 - momentum: 0.000000
2023-10-18 18:06:45,752 epoch 10 - iter 534/894 - loss 0.25065215 - time (sec): 8.34 - samples/sec: 6081.34 - lr: 0.000002 - momentum: 0.000000
2023-10-18 18:06:47,190 epoch 10 - iter 623/894 - loss 0.24408374 - time (sec): 9.78 - samples/sec: 6129.24 - lr: 0.000002 - momentum: 0.000000
2023-10-18 18:06:48,545 epoch 10 - iter 712/894 - loss 0.24020067 - time (sec): 11.13 - samples/sec: 6179.73 - lr: 0.000001 - momentum: 0.000000
2023-10-18 18:06:49,811 epoch 10 - iter 801/894 - loss 0.23988736 - time (sec): 12.40 - samples/sec: 6246.35 - lr: 0.000001 - momentum: 0.000000
2023-10-18 18:06:51,221 epoch 10 - iter 890/894 - loss 0.24026831 - time (sec): 13.81 - samples/sec: 6243.75 - lr: 0.000000 - momentum: 0.000000
2023-10-18 18:06:51,281 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:51,281 EPOCH 10 done: loss 0.2399 - lr: 0.000000
2023-10-18 18:06:56,279 DEV : loss 0.30754354596138 - f1-score (micro avg) 0.3655
2023-10-18 18:06:56,305 saving best model
2023-10-18 18:06:56,371 ----------------------------------------------------------------------------------------------------
2023-10-18 18:06:56,372 Loading model from best epoch ...
2023-10-18 18:06:56,446 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
2023-10-18 18:06:58,721
Results:
- F-score (micro) 0.357
- F-score (macro) 0.1876
- Accuracy 0.2303
By class:
precision recall f1-score support
loc 0.4760 0.5654 0.5169 596
pers 0.1696 0.2282 0.1946 333
org 0.5000 0.0076 0.0149 132
time 0.2500 0.1837 0.2118 49
prod 0.0000 0.0000 0.0000 66
micro avg 0.3543 0.3597 0.3570 1176
macro avg 0.2791 0.1970 0.1876 1176
weighted avg 0.3558 0.3597 0.3276 1176
2023-10-18 18:06:58,722 ----------------------------------------------------------------------------------------------------
|