File size: 23,918 Bytes
e552db2 |
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 |
2023-10-13 09:07:23,541 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,542 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-13 09:07:23,542 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Train: 1214 sentences
2023-10-13 09:07:23,543 (train_with_dev=False, train_with_test=False)
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Training Params:
2023-10-13 09:07:23,543 - learning_rate: "3e-05"
2023-10-13 09:07:23,543 - mini_batch_size: "8"
2023-10-13 09:07:23,543 - max_epochs: "10"
2023-10-13 09:07:23,543 - shuffle: "True"
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Plugins:
2023-10-13 09:07:23,543 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 09:07:23,543 - metric: "('micro avg', 'f1-score')"
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Computation:
2023-10-13 09:07:23,543 - compute on device: cuda:0
2023-10-13 09:07:23,543 - embedding storage: none
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:23,543 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:24,390 epoch 1 - iter 15/152 - loss 3.40566329 - time (sec): 0.85 - samples/sec: 3826.98 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:07:25,268 epoch 1 - iter 30/152 - loss 3.18432802 - time (sec): 1.72 - samples/sec: 3702.31 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:07:26,155 epoch 1 - iter 45/152 - loss 2.73456322 - time (sec): 2.61 - samples/sec: 3725.54 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:07:27,044 epoch 1 - iter 60/152 - loss 2.26722564 - time (sec): 3.50 - samples/sec: 3674.24 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:07:27,893 epoch 1 - iter 75/152 - loss 1.97343150 - time (sec): 4.35 - samples/sec: 3656.59 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:07:28,710 epoch 1 - iter 90/152 - loss 1.78199051 - time (sec): 5.17 - samples/sec: 3610.25 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:07:29,590 epoch 1 - iter 105/152 - loss 1.59061250 - time (sec): 6.05 - samples/sec: 3623.48 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:07:30,388 epoch 1 - iter 120/152 - loss 1.45635461 - time (sec): 6.84 - samples/sec: 3620.21 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:07:31,255 epoch 1 - iter 135/152 - loss 1.35049222 - time (sec): 7.71 - samples/sec: 3576.02 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:07:32,096 epoch 1 - iter 150/152 - loss 1.25214594 - time (sec): 8.55 - samples/sec: 3581.36 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:07:32,208 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:32,209 EPOCH 1 done: loss 1.2412 - lr: 0.000029
2023-10-13 09:07:33,067 DEV : loss 0.2970544397830963 - f1-score (micro avg) 0.4374
2023-10-13 09:07:33,073 saving best model
2023-10-13 09:07:33,417 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:34,256 epoch 2 - iter 15/152 - loss 0.27318260 - time (sec): 0.84 - samples/sec: 3685.80 - lr: 0.000030 - momentum: 0.000000
2023-10-13 09:07:35,080 epoch 2 - iter 30/152 - loss 0.29477857 - time (sec): 1.66 - samples/sec: 3603.42 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:07:35,984 epoch 2 - iter 45/152 - loss 0.25516486 - time (sec): 2.57 - samples/sec: 3594.95 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:07:36,774 epoch 2 - iter 60/152 - loss 0.24379369 - time (sec): 3.36 - samples/sec: 3598.22 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:07:37,646 epoch 2 - iter 75/152 - loss 0.22531096 - time (sec): 4.23 - samples/sec: 3639.84 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:07:38,484 epoch 2 - iter 90/152 - loss 0.21717476 - time (sec): 5.07 - samples/sec: 3653.41 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:07:39,376 epoch 2 - iter 105/152 - loss 0.21405748 - time (sec): 5.96 - samples/sec: 3661.24 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:07:40,223 epoch 2 - iter 120/152 - loss 0.21384996 - time (sec): 6.81 - samples/sec: 3632.40 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:07:41,065 epoch 2 - iter 135/152 - loss 0.20845651 - time (sec): 7.65 - samples/sec: 3599.52 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:07:41,928 epoch 2 - iter 150/152 - loss 0.19834878 - time (sec): 8.51 - samples/sec: 3611.72 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:07:42,023 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:42,024 EPOCH 2 done: loss 0.1978 - lr: 0.000027
2023-10-13 09:07:42,931 DEV : loss 0.17218922078609467 - f1-score (micro avg) 0.6974
2023-10-13 09:07:42,937 saving best model
2023-10-13 09:07:43,397 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:44,260 epoch 3 - iter 15/152 - loss 0.08307837 - time (sec): 0.86 - samples/sec: 3510.04 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:07:45,168 epoch 3 - iter 30/152 - loss 0.09240108 - time (sec): 1.76 - samples/sec: 3440.09 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:07:46,003 epoch 3 - iter 45/152 - loss 0.10337295 - time (sec): 2.60 - samples/sec: 3469.01 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:07:46,891 epoch 3 - iter 60/152 - loss 0.10160162 - time (sec): 3.49 - samples/sec: 3466.01 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:07:47,760 epoch 3 - iter 75/152 - loss 0.11399711 - time (sec): 4.36 - samples/sec: 3438.64 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:07:48,614 epoch 3 - iter 90/152 - loss 0.10915553 - time (sec): 5.21 - samples/sec: 3464.37 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:07:49,535 epoch 3 - iter 105/152 - loss 0.11030199 - time (sec): 6.13 - samples/sec: 3511.93 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:07:50,336 epoch 3 - iter 120/152 - loss 0.11136644 - time (sec): 6.93 - samples/sec: 3555.21 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:07:51,159 epoch 3 - iter 135/152 - loss 0.10674892 - time (sec): 7.76 - samples/sec: 3546.66 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:07:52,021 epoch 3 - iter 150/152 - loss 0.10428374 - time (sec): 8.62 - samples/sec: 3559.96 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:07:52,124 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:52,124 EPOCH 3 done: loss 0.1064 - lr: 0.000023
2023-10-13 09:07:53,038 DEV : loss 0.14199090003967285 - f1-score (micro avg) 0.8029
2023-10-13 09:07:53,044 saving best model
2023-10-13 09:07:53,478 ----------------------------------------------------------------------------------------------------
2023-10-13 09:07:54,287 epoch 4 - iter 15/152 - loss 0.02904280 - time (sec): 0.81 - samples/sec: 3730.54 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:07:55,131 epoch 4 - iter 30/152 - loss 0.06484752 - time (sec): 1.65 - samples/sec: 3707.39 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:07:55,975 epoch 4 - iter 45/152 - loss 0.06690710 - time (sec): 2.50 - samples/sec: 3687.69 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:07:56,769 epoch 4 - iter 60/152 - loss 0.06903870 - time (sec): 3.29 - samples/sec: 3702.20 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:07:57,583 epoch 4 - iter 75/152 - loss 0.07081261 - time (sec): 4.10 - samples/sec: 3677.20 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:07:58,442 epoch 4 - iter 90/152 - loss 0.06884582 - time (sec): 4.96 - samples/sec: 3672.33 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:07:59,255 epoch 4 - iter 105/152 - loss 0.06524950 - time (sec): 5.78 - samples/sec: 3678.79 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:08:00,090 epoch 4 - iter 120/152 - loss 0.06474971 - time (sec): 6.61 - samples/sec: 3643.35 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:08:00,948 epoch 4 - iter 135/152 - loss 0.06312834 - time (sec): 7.47 - samples/sec: 3678.86 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:08:01,791 epoch 4 - iter 150/152 - loss 0.06782112 - time (sec): 8.31 - samples/sec: 3682.72 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:08:01,897 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:01,897 EPOCH 4 done: loss 0.0680 - lr: 0.000020
2023-10-13 09:08:02,805 DEV : loss 0.1484554409980774 - f1-score (micro avg) 0.8135
2023-10-13 09:08:02,811 saving best model
2023-10-13 09:08:03,238 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:04,147 epoch 5 - iter 15/152 - loss 0.05958663 - time (sec): 0.91 - samples/sec: 3673.77 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:08:05,012 epoch 5 - iter 30/152 - loss 0.05337856 - time (sec): 1.77 - samples/sec: 3483.10 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:08:06,048 epoch 5 - iter 45/152 - loss 0.05133641 - time (sec): 2.81 - samples/sec: 3371.51 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:08:06,858 epoch 5 - iter 60/152 - loss 0.04925455 - time (sec): 3.62 - samples/sec: 3472.88 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:08:07,694 epoch 5 - iter 75/152 - loss 0.04764550 - time (sec): 4.45 - samples/sec: 3487.25 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:08:08,506 epoch 5 - iter 90/152 - loss 0.04909598 - time (sec): 5.27 - samples/sec: 3544.47 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:08:09,318 epoch 5 - iter 105/152 - loss 0.04778141 - time (sec): 6.08 - samples/sec: 3556.08 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:08:10,153 epoch 5 - iter 120/152 - loss 0.04581216 - time (sec): 6.91 - samples/sec: 3612.78 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:08:10,940 epoch 5 - iter 135/152 - loss 0.04684558 - time (sec): 7.70 - samples/sec: 3617.53 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:08:11,753 epoch 5 - iter 150/152 - loss 0.05287046 - time (sec): 8.51 - samples/sec: 3606.44 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:08:11,846 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:11,846 EPOCH 5 done: loss 0.0528 - lr: 0.000017
2023-10-13 09:08:12,777 DEV : loss 0.16037791967391968 - f1-score (micro avg) 0.822
2023-10-13 09:08:12,783 saving best model
2023-10-13 09:08:13,203 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:14,078 epoch 6 - iter 15/152 - loss 0.03099565 - time (sec): 0.87 - samples/sec: 3833.17 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:08:14,868 epoch 6 - iter 30/152 - loss 0.03155409 - time (sec): 1.66 - samples/sec: 3663.52 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:08:15,682 epoch 6 - iter 45/152 - loss 0.03410084 - time (sec): 2.47 - samples/sec: 3711.69 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:08:16,537 epoch 6 - iter 60/152 - loss 0.03370562 - time (sec): 3.33 - samples/sec: 3809.43 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:08:17,352 epoch 6 - iter 75/152 - loss 0.03623556 - time (sec): 4.14 - samples/sec: 3755.41 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:08:18,161 epoch 6 - iter 90/152 - loss 0.03728025 - time (sec): 4.95 - samples/sec: 3744.16 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:08:19,036 epoch 6 - iter 105/152 - loss 0.03447885 - time (sec): 5.83 - samples/sec: 3639.48 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:08:19,926 epoch 6 - iter 120/152 - loss 0.03432150 - time (sec): 6.72 - samples/sec: 3627.54 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:08:20,827 epoch 6 - iter 135/152 - loss 0.03771134 - time (sec): 7.62 - samples/sec: 3619.90 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:08:21,673 epoch 6 - iter 150/152 - loss 0.03806320 - time (sec): 8.47 - samples/sec: 3614.21 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:08:21,769 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:21,770 EPOCH 6 done: loss 0.0380 - lr: 0.000013
2023-10-13 09:08:22,697 DEV : loss 0.16604389250278473 - f1-score (micro avg) 0.8201
2023-10-13 09:08:22,703 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:23,505 epoch 7 - iter 15/152 - loss 0.02004090 - time (sec): 0.80 - samples/sec: 3508.73 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:08:24,369 epoch 7 - iter 30/152 - loss 0.02865142 - time (sec): 1.66 - samples/sec: 3528.96 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:08:25,204 epoch 7 - iter 45/152 - loss 0.04041764 - time (sec): 2.50 - samples/sec: 3556.35 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:08:26,082 epoch 7 - iter 60/152 - loss 0.03524078 - time (sec): 3.38 - samples/sec: 3665.53 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:08:26,904 epoch 7 - iter 75/152 - loss 0.03407011 - time (sec): 4.20 - samples/sec: 3614.62 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:08:27,825 epoch 7 - iter 90/152 - loss 0.03072402 - time (sec): 5.12 - samples/sec: 3588.49 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:08:28,656 epoch 7 - iter 105/152 - loss 0.02920528 - time (sec): 5.95 - samples/sec: 3551.07 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:08:29,500 epoch 7 - iter 120/152 - loss 0.03208956 - time (sec): 6.80 - samples/sec: 3550.35 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:08:30,390 epoch 7 - iter 135/152 - loss 0.03186570 - time (sec): 7.69 - samples/sec: 3551.82 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:08:31,202 epoch 7 - iter 150/152 - loss 0.03292206 - time (sec): 8.50 - samples/sec: 3597.57 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:08:31,327 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:31,327 EPOCH 7 done: loss 0.0325 - lr: 0.000010
2023-10-13 09:08:32,239 DEV : loss 0.17990894615650177 - f1-score (micro avg) 0.8473
2023-10-13 09:08:32,245 saving best model
2023-10-13 09:08:32,672 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:33,459 epoch 8 - iter 15/152 - loss 0.01792334 - time (sec): 0.78 - samples/sec: 3709.73 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:08:34,333 epoch 8 - iter 30/152 - loss 0.01411895 - time (sec): 1.66 - samples/sec: 3527.74 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:08:35,175 epoch 8 - iter 45/152 - loss 0.01501876 - time (sec): 2.50 - samples/sec: 3587.00 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:08:36,029 epoch 8 - iter 60/152 - loss 0.02067936 - time (sec): 3.35 - samples/sec: 3609.56 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:08:36,904 epoch 8 - iter 75/152 - loss 0.01995176 - time (sec): 4.23 - samples/sec: 3618.22 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:08:37,750 epoch 8 - iter 90/152 - loss 0.01867516 - time (sec): 5.08 - samples/sec: 3561.32 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:08:38,580 epoch 8 - iter 105/152 - loss 0.01915858 - time (sec): 5.91 - samples/sec: 3590.07 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:08:39,484 epoch 8 - iter 120/152 - loss 0.01759270 - time (sec): 6.81 - samples/sec: 3578.25 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:08:40,351 epoch 8 - iter 135/152 - loss 0.02335082 - time (sec): 7.68 - samples/sec: 3606.09 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:08:41,196 epoch 8 - iter 150/152 - loss 0.02625407 - time (sec): 8.52 - samples/sec: 3597.79 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:08:41,295 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:41,295 EPOCH 8 done: loss 0.0260 - lr: 0.000007
2023-10-13 09:08:42,188 DEV : loss 0.18495041131973267 - f1-score (micro avg) 0.8359
2023-10-13 09:08:42,194 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:42,993 epoch 9 - iter 15/152 - loss 0.02396427 - time (sec): 0.80 - samples/sec: 4028.98 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:08:43,824 epoch 9 - iter 30/152 - loss 0.01479938 - time (sec): 1.63 - samples/sec: 3823.56 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:08:44,667 epoch 9 - iter 45/152 - loss 0.01197354 - time (sec): 2.47 - samples/sec: 3697.08 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:08:45,538 epoch 9 - iter 60/152 - loss 0.02206406 - time (sec): 3.34 - samples/sec: 3713.68 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:08:46,409 epoch 9 - iter 75/152 - loss 0.02341684 - time (sec): 4.21 - samples/sec: 3703.94 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:08:47,217 epoch 9 - iter 90/152 - loss 0.02270359 - time (sec): 5.02 - samples/sec: 3697.99 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:08:48,041 epoch 9 - iter 105/152 - loss 0.02303371 - time (sec): 5.85 - samples/sec: 3676.32 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:08:48,950 epoch 9 - iter 120/152 - loss 0.02189268 - time (sec): 6.76 - samples/sec: 3671.08 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:08:49,760 epoch 9 - iter 135/152 - loss 0.02187071 - time (sec): 7.57 - samples/sec: 3665.70 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:08:50,610 epoch 9 - iter 150/152 - loss 0.02281646 - time (sec): 8.41 - samples/sec: 3653.29 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:08:50,701 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:50,701 EPOCH 9 done: loss 0.0226 - lr: 0.000004
2023-10-13 09:08:51,602 DEV : loss 0.19286410510540009 - f1-score (micro avg) 0.8343
2023-10-13 09:08:51,608 ----------------------------------------------------------------------------------------------------
2023-10-13 09:08:52,434 epoch 10 - iter 15/152 - loss 0.01360042 - time (sec): 0.82 - samples/sec: 3795.60 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:08:53,296 epoch 10 - iter 30/152 - loss 0.00893190 - time (sec): 1.69 - samples/sec: 3666.43 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:08:54,113 epoch 10 - iter 45/152 - loss 0.01103150 - time (sec): 2.50 - samples/sec: 3649.97 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:08:54,932 epoch 10 - iter 60/152 - loss 0.01025132 - time (sec): 3.32 - samples/sec: 3626.51 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:08:55,757 epoch 10 - iter 75/152 - loss 0.01395742 - time (sec): 4.15 - samples/sec: 3613.59 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:08:56,613 epoch 10 - iter 90/152 - loss 0.01418562 - time (sec): 5.00 - samples/sec: 3633.52 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:08:57,436 epoch 10 - iter 105/152 - loss 0.01456598 - time (sec): 5.83 - samples/sec: 3667.17 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:08:58,272 epoch 10 - iter 120/152 - loss 0.01501693 - time (sec): 6.66 - samples/sec: 3671.50 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:08:59,141 epoch 10 - iter 135/152 - loss 0.01754617 - time (sec): 7.53 - samples/sec: 3650.02 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:08:59,966 epoch 10 - iter 150/152 - loss 0.01803580 - time (sec): 8.36 - samples/sec: 3658.82 - lr: 0.000000 - momentum: 0.000000
2023-10-13 09:09:00,071 ----------------------------------------------------------------------------------------------------
2023-10-13 09:09:00,071 EPOCH 10 done: loss 0.0180 - lr: 0.000000
2023-10-13 09:09:01,010 DEV : loss 0.19247612357139587 - f1-score (micro avg) 0.837
2023-10-13 09:09:01,348 ----------------------------------------------------------------------------------------------------
2023-10-13 09:09:01,349 Loading model from best epoch ...
2023-10-13 09:09:02,755 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
2023-10-13 09:09:03,606
Results:
- F-score (micro) 0.7871
- F-score (macro) 0.4757
- Accuracy 0.6622
By class:
precision recall f1-score support
scope 0.7871 0.8079 0.7974 151
pers 0.7236 0.9271 0.8128 96
work 0.6860 0.8737 0.7685 95
loc 0.0000 0.0000 0.0000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7368 0.8448 0.7871 348
macro avg 0.4393 0.5217 0.4757 348
weighted avg 0.7284 0.8448 0.7800 348
2023-10-13 09:09:03,606 ----------------------------------------------------------------------------------------------------
|