File size: 23,919 Bytes
e41286f |
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 09:17:33,545 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,546 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 09:17:33,546 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,546 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 09:17:33,546 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,546 Train: 1214 sentences
2023-10-13 09:17:33,546 (train_with_dev=False, train_with_test=False)
2023-10-13 09:17:33,546 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,546 Training Params:
2023-10-13 09:17:33,546 - learning_rate: "3e-05"
2023-10-13 09:17:33,546 - mini_batch_size: "8"
2023-10-13 09:17:33,546 - max_epochs: "10"
2023-10-13 09:17:33,547 - shuffle: "True"
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,547 Plugins:
2023-10-13 09:17:33,547 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,547 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 09:17:33,547 - metric: "('micro avg', 'f1-score')"
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,547 Computation:
2023-10-13 09:17:33,547 - compute on device: cuda:0
2023-10-13 09:17:33,547 - embedding storage: none
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,547 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:33,547 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:34,442 epoch 1 - iter 15/152 - loss 3.43231563 - time (sec): 0.89 - samples/sec: 3438.53 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:17:35,325 epoch 1 - iter 30/152 - loss 3.17528117 - time (sec): 1.78 - samples/sec: 3557.69 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:17:36,192 epoch 1 - iter 45/152 - loss 2.71015130 - time (sec): 2.64 - samples/sec: 3561.95 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:17:37,060 epoch 1 - iter 60/152 - loss 2.25976386 - time (sec): 3.51 - samples/sec: 3494.66 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:17:37,946 epoch 1 - iter 75/152 - loss 1.95193778 - time (sec): 4.40 - samples/sec: 3526.36 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:17:38,764 epoch 1 - iter 90/152 - loss 1.74550379 - time (sec): 5.22 - samples/sec: 3532.06 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:17:39,597 epoch 1 - iter 105/152 - loss 1.56936473 - time (sec): 6.05 - samples/sec: 3532.03 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:17:40,463 epoch 1 - iter 120/152 - loss 1.43321747 - time (sec): 6.92 - samples/sec: 3528.73 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:17:41,309 epoch 1 - iter 135/152 - loss 1.32080472 - time (sec): 7.76 - samples/sec: 3524.44 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:17:42,179 epoch 1 - iter 150/152 - loss 1.21944501 - time (sec): 8.63 - samples/sec: 3543.93 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:17:42,288 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:42,288 EPOCH 1 done: loss 1.2094 - lr: 0.000029
2023-10-13 09:17:43,170 DEV : loss 0.30928874015808105 - f1-score (micro avg) 0.3768
2023-10-13 09:17:43,176 saving best model
2023-10-13 09:17:43,548 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:44,408 epoch 2 - iter 15/152 - loss 0.31603838 - time (sec): 0.86 - samples/sec: 3465.75 - lr: 0.000030 - momentum: 0.000000
2023-10-13 09:17:45,290 epoch 2 - iter 30/152 - loss 0.28922810 - time (sec): 1.74 - samples/sec: 3460.63 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:17:46,164 epoch 2 - iter 45/152 - loss 0.25182527 - time (sec): 2.61 - samples/sec: 3470.65 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:17:47,025 epoch 2 - iter 60/152 - loss 0.24330164 - time (sec): 3.48 - samples/sec: 3492.24 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:17:47,887 epoch 2 - iter 75/152 - loss 0.23361289 - time (sec): 4.34 - samples/sec: 3538.17 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:17:48,767 epoch 2 - iter 90/152 - loss 0.22340757 - time (sec): 5.22 - samples/sec: 3499.67 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:17:49,643 epoch 2 - iter 105/152 - loss 0.21549916 - time (sec): 6.09 - samples/sec: 3535.82 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:17:50,465 epoch 2 - iter 120/152 - loss 0.20648760 - time (sec): 6.92 - samples/sec: 3574.98 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:17:51,320 epoch 2 - iter 135/152 - loss 0.20531334 - time (sec): 7.77 - samples/sec: 3578.15 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:17:52,131 epoch 2 - iter 150/152 - loss 0.19773529 - time (sec): 8.58 - samples/sec: 3587.60 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:17:52,223 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:52,224 EPOCH 2 done: loss 0.1982 - lr: 0.000027
2023-10-13 09:17:53,124 DEV : loss 0.1611824333667755 - f1-score (micro avg) 0.7323
2023-10-13 09:17:53,130 saving best model
2023-10-13 09:17:53,626 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:54,497 epoch 3 - iter 15/152 - loss 0.08185510 - time (sec): 0.86 - samples/sec: 3517.84 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:17:55,365 epoch 3 - iter 30/152 - loss 0.08955699 - time (sec): 1.73 - samples/sec: 3515.77 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:17:56,218 epoch 3 - iter 45/152 - loss 0.09014888 - time (sec): 2.59 - samples/sec: 3630.68 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:17:57,035 epoch 3 - iter 60/152 - loss 0.08782678 - time (sec): 3.40 - samples/sec: 3619.08 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:17:57,904 epoch 3 - iter 75/152 - loss 0.08919998 - time (sec): 4.27 - samples/sec: 3586.16 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:17:58,721 epoch 3 - iter 90/152 - loss 0.09539873 - time (sec): 5.09 - samples/sec: 3573.56 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:17:59,573 epoch 3 - iter 105/152 - loss 0.09778693 - time (sec): 5.94 - samples/sec: 3594.24 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:18:00,418 epoch 3 - iter 120/152 - loss 0.10010355 - time (sec): 6.79 - samples/sec: 3588.60 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:18:01,286 epoch 3 - iter 135/152 - loss 0.09879299 - time (sec): 7.65 - samples/sec: 3627.52 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:18:02,080 epoch 3 - iter 150/152 - loss 0.09827156 - time (sec): 8.45 - samples/sec: 3616.48 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:18:02,194 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:02,194 EPOCH 3 done: loss 0.0976 - lr: 0.000023
2023-10-13 09:18:03,122 DEV : loss 0.14934414625167847 - f1-score (micro avg) 0.8032
2023-10-13 09:18:03,128 saving best model
2023-10-13 09:18:03,646 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:04,483 epoch 4 - iter 15/152 - loss 0.05991201 - time (sec): 0.83 - samples/sec: 3853.13 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:18:05,336 epoch 4 - iter 30/152 - loss 0.04771997 - time (sec): 1.69 - samples/sec: 3725.25 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:18:06,146 epoch 4 - iter 45/152 - loss 0.06036223 - time (sec): 2.50 - samples/sec: 3708.98 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:18:06,978 epoch 4 - iter 60/152 - loss 0.05672872 - time (sec): 3.33 - samples/sec: 3657.19 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:18:07,813 epoch 4 - iter 75/152 - loss 0.05143727 - time (sec): 4.16 - samples/sec: 3687.89 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:18:08,615 epoch 4 - iter 90/152 - loss 0.05838143 - time (sec): 4.96 - samples/sec: 3696.18 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:18:09,430 epoch 4 - iter 105/152 - loss 0.06027114 - time (sec): 5.78 - samples/sec: 3706.01 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:18:10,329 epoch 4 - iter 120/152 - loss 0.06281418 - time (sec): 6.68 - samples/sec: 3681.47 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:18:11,212 epoch 4 - iter 135/152 - loss 0.06135023 - time (sec): 7.56 - samples/sec: 3661.94 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:18:12,058 epoch 4 - iter 150/152 - loss 0.06515964 - time (sec): 8.41 - samples/sec: 3638.70 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:18:12,167 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:12,167 EPOCH 4 done: loss 0.0646 - lr: 0.000020
2023-10-13 09:18:13,062 DEV : loss 0.14927834272384644 - f1-score (micro avg) 0.7995
2023-10-13 09:18:13,067 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:13,928 epoch 5 - iter 15/152 - loss 0.04878445 - time (sec): 0.86 - samples/sec: 3694.55 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:18:14,754 epoch 5 - iter 30/152 - loss 0.03806395 - time (sec): 1.69 - samples/sec: 3794.04 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:18:15,616 epoch 5 - iter 45/152 - loss 0.03909102 - time (sec): 2.55 - samples/sec: 3703.43 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:18:16,456 epoch 5 - iter 60/152 - loss 0.04305523 - time (sec): 3.39 - samples/sec: 3680.61 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:18:17,327 epoch 5 - iter 75/152 - loss 0.05026496 - time (sec): 4.26 - samples/sec: 3644.88 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:18:18,172 epoch 5 - iter 90/152 - loss 0.04943306 - time (sec): 5.10 - samples/sec: 3641.02 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:18:19,049 epoch 5 - iter 105/152 - loss 0.04630032 - time (sec): 5.98 - samples/sec: 3600.12 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:18:19,943 epoch 5 - iter 120/152 - loss 0.04904589 - time (sec): 6.87 - samples/sec: 3582.56 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:18:20,801 epoch 5 - iter 135/152 - loss 0.04979173 - time (sec): 7.73 - samples/sec: 3570.64 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:18:21,666 epoch 5 - iter 150/152 - loss 0.04824478 - time (sec): 8.60 - samples/sec: 3566.34 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:18:21,764 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:21,765 EPOCH 5 done: loss 0.0484 - lr: 0.000017
2023-10-13 09:18:22,679 DEV : loss 0.16671518981456757 - f1-score (micro avg) 0.8139
2023-10-13 09:18:22,686 saving best model
2023-10-13 09:18:23,199 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:24,023 epoch 6 - iter 15/152 - loss 0.04722034 - time (sec): 0.82 - samples/sec: 3413.25 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:18:24,920 epoch 6 - iter 30/152 - loss 0.04572734 - time (sec): 1.72 - samples/sec: 3529.59 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:18:25,798 epoch 6 - iter 45/152 - loss 0.03835916 - time (sec): 2.60 - samples/sec: 3510.91 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:18:26,712 epoch 6 - iter 60/152 - loss 0.03559348 - time (sec): 3.51 - samples/sec: 3475.21 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:18:27,558 epoch 6 - iter 75/152 - loss 0.03219426 - time (sec): 4.36 - samples/sec: 3438.71 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:18:28,449 epoch 6 - iter 90/152 - loss 0.03079567 - time (sec): 5.25 - samples/sec: 3447.47 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:18:29,314 epoch 6 - iter 105/152 - loss 0.03234725 - time (sec): 6.11 - samples/sec: 3480.92 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:18:30,187 epoch 6 - iter 120/152 - loss 0.03590374 - time (sec): 6.98 - samples/sec: 3483.67 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:18:31,026 epoch 6 - iter 135/152 - loss 0.03478735 - time (sec): 7.82 - samples/sec: 3494.52 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:18:31,866 epoch 6 - iter 150/152 - loss 0.03481313 - time (sec): 8.66 - samples/sec: 3535.53 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:18:31,972 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:31,972 EPOCH 6 done: loss 0.0346 - lr: 0.000013
2023-10-13 09:18:33,026 DEV : loss 0.1832340508699417 - f1-score (micro avg) 0.8253
2023-10-13 09:18:33,032 saving best model
2023-10-13 09:18:33,662 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:34,512 epoch 7 - iter 15/152 - loss 0.01599971 - time (sec): 0.85 - samples/sec: 3634.74 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:18:35,406 epoch 7 - iter 30/152 - loss 0.03165204 - time (sec): 1.74 - samples/sec: 3515.19 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:18:36,250 epoch 7 - iter 45/152 - loss 0.03534164 - time (sec): 2.59 - samples/sec: 3512.02 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:18:37,207 epoch 7 - iter 60/152 - loss 0.03177575 - time (sec): 3.54 - samples/sec: 3534.56 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:18:38,052 epoch 7 - iter 75/152 - loss 0.02705708 - time (sec): 4.39 - samples/sec: 3527.06 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:18:38,924 epoch 7 - iter 90/152 - loss 0.02402478 - time (sec): 5.26 - samples/sec: 3541.44 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:18:39,833 epoch 7 - iter 105/152 - loss 0.02218151 - time (sec): 6.17 - samples/sec: 3523.68 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:18:40,789 epoch 7 - iter 120/152 - loss 0.02623768 - time (sec): 7.13 - samples/sec: 3521.49 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:18:41,689 epoch 7 - iter 135/152 - loss 0.02470530 - time (sec): 8.03 - samples/sec: 3466.18 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:18:42,533 epoch 7 - iter 150/152 - loss 0.02588736 - time (sec): 8.87 - samples/sec: 3463.01 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:18:42,636 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:42,637 EPOCH 7 done: loss 0.0257 - lr: 0.000010
2023-10-13 09:18:43,609 DEV : loss 0.17377883195877075 - f1-score (micro avg) 0.8494
2023-10-13 09:18:43,616 saving best model
2023-10-13 09:18:44,083 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:45,035 epoch 8 - iter 15/152 - loss 0.01736505 - time (sec): 0.95 - samples/sec: 3556.07 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:18:45,963 epoch 8 - iter 30/152 - loss 0.01369969 - time (sec): 1.88 - samples/sec: 3366.16 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:18:46,890 epoch 8 - iter 45/152 - loss 0.01979052 - time (sec): 2.80 - samples/sec: 3353.73 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:18:47,777 epoch 8 - iter 60/152 - loss 0.01937442 - time (sec): 3.69 - samples/sec: 3366.62 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:18:48,714 epoch 8 - iter 75/152 - loss 0.02290668 - time (sec): 4.63 - samples/sec: 3373.47 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:18:49,587 epoch 8 - iter 90/152 - loss 0.01974080 - time (sec): 5.50 - samples/sec: 3403.86 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:18:50,414 epoch 8 - iter 105/152 - loss 0.02119474 - time (sec): 6.33 - samples/sec: 3425.66 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:18:51,293 epoch 8 - iter 120/152 - loss 0.02094552 - time (sec): 7.21 - samples/sec: 3434.56 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:18:52,114 epoch 8 - iter 135/152 - loss 0.01963669 - time (sec): 8.03 - samples/sec: 3446.71 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:18:52,924 epoch 8 - iter 150/152 - loss 0.02179370 - time (sec): 8.84 - samples/sec: 3462.58 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:18:53,040 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:53,041 EPOCH 8 done: loss 0.0215 - lr: 0.000007
2023-10-13 09:18:54,003 DEV : loss 0.18849490582942963 - f1-score (micro avg) 0.838
2023-10-13 09:18:54,011 ----------------------------------------------------------------------------------------------------
2023-10-13 09:18:54,833 epoch 9 - iter 15/152 - loss 0.02677392 - time (sec): 0.82 - samples/sec: 3359.94 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:18:55,712 epoch 9 - iter 30/152 - loss 0.01698186 - time (sec): 1.70 - samples/sec: 3474.31 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:18:56,607 epoch 9 - iter 45/152 - loss 0.02630750 - time (sec): 2.59 - samples/sec: 3547.44 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:18:57,507 epoch 9 - iter 60/152 - loss 0.02453081 - time (sec): 3.50 - samples/sec: 3541.92 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:18:58,379 epoch 9 - iter 75/152 - loss 0.02057650 - time (sec): 4.37 - samples/sec: 3518.05 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:18:59,191 epoch 9 - iter 90/152 - loss 0.02152942 - time (sec): 5.18 - samples/sec: 3547.14 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:19:00,021 epoch 9 - iter 105/152 - loss 0.01914940 - time (sec): 6.01 - samples/sec: 3530.03 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:19:00,889 epoch 9 - iter 120/152 - loss 0.01790542 - time (sec): 6.88 - samples/sec: 3577.36 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:19:01,715 epoch 9 - iter 135/152 - loss 0.01832648 - time (sec): 7.70 - samples/sec: 3583.55 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:19:02,570 epoch 9 - iter 150/152 - loss 0.01715611 - time (sec): 8.56 - samples/sec: 3577.64 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:19:02,675 ----------------------------------------------------------------------------------------------------
2023-10-13 09:19:02,675 EPOCH 9 done: loss 0.0170 - lr: 0.000004
2023-10-13 09:19:03,622 DEV : loss 0.19795483350753784 - f1-score (micro avg) 0.8398
2023-10-13 09:19:03,628 ----------------------------------------------------------------------------------------------------
2023-10-13 09:19:04,453 epoch 10 - iter 15/152 - loss 0.00109153 - time (sec): 0.82 - samples/sec: 3542.74 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:19:05,322 epoch 10 - iter 30/152 - loss 0.00873862 - time (sec): 1.69 - samples/sec: 3624.20 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:19:06,181 epoch 10 - iter 45/152 - loss 0.01216745 - time (sec): 2.55 - samples/sec: 3725.19 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:19:07,041 epoch 10 - iter 60/152 - loss 0.01687381 - time (sec): 3.41 - samples/sec: 3669.22 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:19:07,850 epoch 10 - iter 75/152 - loss 0.01763652 - time (sec): 4.22 - samples/sec: 3638.35 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:19:08,754 epoch 10 - iter 90/152 - loss 0.01536798 - time (sec): 5.12 - samples/sec: 3646.73 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:19:09,570 epoch 10 - iter 105/152 - loss 0.01651864 - time (sec): 5.94 - samples/sec: 3667.72 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:19:10,413 epoch 10 - iter 120/152 - loss 0.01655194 - time (sec): 6.78 - samples/sec: 3626.65 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:19:11,294 epoch 10 - iter 135/152 - loss 0.01594330 - time (sec): 7.66 - samples/sec: 3614.00 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:19:12,107 epoch 10 - iter 150/152 - loss 0.01593639 - time (sec): 8.48 - samples/sec: 3630.91 - lr: 0.000000 - momentum: 0.000000
2023-10-13 09:19:12,201 ----------------------------------------------------------------------------------------------------
2023-10-13 09:19:12,201 EPOCH 10 done: loss 0.0158 - lr: 0.000000
2023-10-13 09:19:13,219 DEV : loss 0.20332136750221252 - f1-score (micro avg) 0.8303
2023-10-13 09:19:13,605 ----------------------------------------------------------------------------------------------------
2023-10-13 09:19:13,606 Loading model from best epoch ...
2023-10-13 09:19:15,087 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 09:19:16,153
Results:
- F-score (micro) 0.7936
- F-score (macro) 0.6407
- Accuracy 0.6667
By class:
precision recall f1-score support
scope 0.7546 0.8146 0.7834 151
work 0.6484 0.8737 0.7444 95
pers 0.8381 0.9167 0.8756 96
loc 1.0000 0.6667 0.8000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7437 0.8506 0.7936 348
macro avg 0.6482 0.6543 0.6407 348
weighted avg 0.7443 0.8506 0.7916 348
2023-10-13 09:19:16,153 ----------------------------------------------------------------------------------------------------
|