File size: 23,940 Bytes
704de54 |
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 |
2023-10-25 21:19:59,894 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(64001, 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=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 MultiCorpus: 1166 train + 165 dev + 415 test sentences
- NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Train: 1166 sentences
2023-10-25 21:19:59,895 (train_with_dev=False, train_with_test=False)
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Training Params:
2023-10-25 21:19:59,895 - learning_rate: "3e-05"
2023-10-25 21:19:59,895 - mini_batch_size: "4"
2023-10-25 21:19:59,895 - max_epochs: "10"
2023-10-25 21:19:59,895 - shuffle: "True"
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Plugins:
2023-10-25 21:19:59,895 - TensorboardLogger
2023-10-25 21:19:59,895 - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 21:19:59,895 - metric: "('micro avg', 'f1-score')"
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,895 Computation:
2023-10-25 21:19:59,895 - compute on device: cuda:0
2023-10-25 21:19:59,895 - embedding storage: none
2023-10-25 21:19:59,895 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,896 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-25 21:19:59,896 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,896 ----------------------------------------------------------------------------------------------------
2023-10-25 21:19:59,896 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 21:20:01,315 epoch 1 - iter 29/292 - loss 3.17590895 - time (sec): 1.42 - samples/sec: 3376.53 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:20:02,583 epoch 1 - iter 58/292 - loss 2.43702185 - time (sec): 2.69 - samples/sec: 3311.36 - lr: 0.000006 - momentum: 0.000000
2023-10-25 21:20:03,832 epoch 1 - iter 87/292 - loss 1.95169503 - time (sec): 3.94 - samples/sec: 3312.69 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:20:05,105 epoch 1 - iter 116/292 - loss 1.62169131 - time (sec): 5.21 - samples/sec: 3296.01 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:20:06,393 epoch 1 - iter 145/292 - loss 1.40877887 - time (sec): 6.50 - samples/sec: 3234.73 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:20:07,807 epoch 1 - iter 174/292 - loss 1.20206482 - time (sec): 7.91 - samples/sec: 3319.44 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:20:09,100 epoch 1 - iter 203/292 - loss 1.07963154 - time (sec): 9.20 - samples/sec: 3305.80 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:20:10,469 epoch 1 - iter 232/292 - loss 0.97153816 - time (sec): 10.57 - samples/sec: 3301.30 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:20:11,772 epoch 1 - iter 261/292 - loss 0.87789158 - time (sec): 11.88 - samples/sec: 3333.01 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:20:13,122 epoch 1 - iter 290/292 - loss 0.80297568 - time (sec): 13.23 - samples/sec: 3338.93 - lr: 0.000030 - momentum: 0.000000
2023-10-25 21:20:13,206 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:13,207 EPOCH 1 done: loss 0.8001 - lr: 0.000030
2023-10-25 21:20:13,864 DEV : loss 0.16615526378154755 - f1-score (micro avg) 0.5011
2023-10-25 21:20:13,868 saving best model
2023-10-25 21:20:14,344 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:15,649 epoch 2 - iter 29/292 - loss 0.22299871 - time (sec): 1.30 - samples/sec: 3330.56 - lr: 0.000030 - momentum: 0.000000
2023-10-25 21:20:16,981 epoch 2 - iter 58/292 - loss 0.17875882 - time (sec): 2.64 - samples/sec: 3515.59 - lr: 0.000029 - momentum: 0.000000
2023-10-25 21:20:18,227 epoch 2 - iter 87/292 - loss 0.17193383 - time (sec): 3.88 - samples/sec: 3453.99 - lr: 0.000029 - momentum: 0.000000
2023-10-25 21:20:19,545 epoch 2 - iter 116/292 - loss 0.18206582 - time (sec): 5.20 - samples/sec: 3451.77 - lr: 0.000029 - momentum: 0.000000
2023-10-25 21:20:20,848 epoch 2 - iter 145/292 - loss 0.17741981 - time (sec): 6.50 - samples/sec: 3404.44 - lr: 0.000028 - momentum: 0.000000
2023-10-25 21:20:22,094 epoch 2 - iter 174/292 - loss 0.17506302 - time (sec): 7.75 - samples/sec: 3334.92 - lr: 0.000028 - momentum: 0.000000
2023-10-25 21:20:23,379 epoch 2 - iter 203/292 - loss 0.17541687 - time (sec): 9.03 - samples/sec: 3311.77 - lr: 0.000028 - momentum: 0.000000
2023-10-25 21:20:24,707 epoch 2 - iter 232/292 - loss 0.17510377 - time (sec): 10.36 - samples/sec: 3327.47 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:20:26,046 epoch 2 - iter 261/292 - loss 0.16765312 - time (sec): 11.70 - samples/sec: 3370.33 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:20:27,363 epoch 2 - iter 290/292 - loss 0.16482145 - time (sec): 13.02 - samples/sec: 3404.67 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:20:27,452 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:27,452 EPOCH 2 done: loss 0.1647 - lr: 0.000027
2023-10-25 21:20:28,362 DEV : loss 0.11898940056562424 - f1-score (micro avg) 0.7314
2023-10-25 21:20:28,366 saving best model
2023-10-25 21:20:28,978 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:30,260 epoch 3 - iter 29/292 - loss 0.08120991 - time (sec): 1.28 - samples/sec: 3746.82 - lr: 0.000026 - momentum: 0.000000
2023-10-25 21:20:31,528 epoch 3 - iter 58/292 - loss 0.08860077 - time (sec): 2.55 - samples/sec: 3614.53 - lr: 0.000026 - momentum: 0.000000
2023-10-25 21:20:32,824 epoch 3 - iter 87/292 - loss 0.09344842 - time (sec): 3.84 - samples/sec: 3526.47 - lr: 0.000026 - momentum: 0.000000
2023-10-25 21:20:34,123 epoch 3 - iter 116/292 - loss 0.10393542 - time (sec): 5.14 - samples/sec: 3433.06 - lr: 0.000025 - momentum: 0.000000
2023-10-25 21:20:35,428 epoch 3 - iter 145/292 - loss 0.11337875 - time (sec): 6.45 - samples/sec: 3415.71 - lr: 0.000025 - momentum: 0.000000
2023-10-25 21:20:36,671 epoch 3 - iter 174/292 - loss 0.10761336 - time (sec): 7.69 - samples/sec: 3336.96 - lr: 0.000025 - momentum: 0.000000
2023-10-25 21:20:37,957 epoch 3 - iter 203/292 - loss 0.10181384 - time (sec): 8.98 - samples/sec: 3356.72 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:20:39,290 epoch 3 - iter 232/292 - loss 0.10275434 - time (sec): 10.31 - samples/sec: 3364.72 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:20:40,687 epoch 3 - iter 261/292 - loss 0.10297989 - time (sec): 11.71 - samples/sec: 3372.52 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:20:41,981 epoch 3 - iter 290/292 - loss 0.09953734 - time (sec): 13.00 - samples/sec: 3408.36 - lr: 0.000023 - momentum: 0.000000
2023-10-25 21:20:42,060 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:42,060 EPOCH 3 done: loss 0.0995 - lr: 0.000023
2023-10-25 21:20:43,120 DEV : loss 0.11886752396821976 - f1-score (micro avg) 0.7387
2023-10-25 21:20:43,124 saving best model
2023-10-25 21:20:43,739 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:45,076 epoch 4 - iter 29/292 - loss 0.06595635 - time (sec): 1.34 - samples/sec: 3335.83 - lr: 0.000023 - momentum: 0.000000
2023-10-25 21:20:46,414 epoch 4 - iter 58/292 - loss 0.07118520 - time (sec): 2.67 - samples/sec: 3534.73 - lr: 0.000023 - momentum: 0.000000
2023-10-25 21:20:47,757 epoch 4 - iter 87/292 - loss 0.06789459 - time (sec): 4.02 - samples/sec: 3575.75 - lr: 0.000022 - momentum: 0.000000
2023-10-25 21:20:49,027 epoch 4 - iter 116/292 - loss 0.06211278 - time (sec): 5.29 - samples/sec: 3547.81 - lr: 0.000022 - momentum: 0.000000
2023-10-25 21:20:50,305 epoch 4 - iter 145/292 - loss 0.06537711 - time (sec): 6.56 - samples/sec: 3522.30 - lr: 0.000022 - momentum: 0.000000
2023-10-25 21:20:51,507 epoch 4 - iter 174/292 - loss 0.06560146 - time (sec): 7.77 - samples/sec: 3445.44 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:20:52,761 epoch 4 - iter 203/292 - loss 0.06457142 - time (sec): 9.02 - samples/sec: 3419.07 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:20:54,091 epoch 4 - iter 232/292 - loss 0.06534614 - time (sec): 10.35 - samples/sec: 3443.05 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:20:55,340 epoch 4 - iter 261/292 - loss 0.06405753 - time (sec): 11.60 - samples/sec: 3419.94 - lr: 0.000020 - momentum: 0.000000
2023-10-25 21:20:56,667 epoch 4 - iter 290/292 - loss 0.06209047 - time (sec): 12.93 - samples/sec: 3423.10 - lr: 0.000020 - momentum: 0.000000
2023-10-25 21:20:56,757 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:56,757 EPOCH 4 done: loss 0.0619 - lr: 0.000020
2023-10-25 21:20:57,676 DEV : loss 0.11910221725702286 - f1-score (micro avg) 0.7722
2023-10-25 21:20:57,680 saving best model
2023-10-25 21:20:58,296 ----------------------------------------------------------------------------------------------------
2023-10-25 21:20:59,656 epoch 5 - iter 29/292 - loss 0.02417236 - time (sec): 1.36 - samples/sec: 3453.26 - lr: 0.000020 - momentum: 0.000000
2023-10-25 21:21:00,977 epoch 5 - iter 58/292 - loss 0.04141239 - time (sec): 2.68 - samples/sec: 3487.81 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:21:02,248 epoch 5 - iter 87/292 - loss 0.03995571 - time (sec): 3.95 - samples/sec: 3508.83 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:21:03,535 epoch 5 - iter 116/292 - loss 0.04020180 - time (sec): 5.24 - samples/sec: 3553.70 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:21:04,810 epoch 5 - iter 145/292 - loss 0.03664786 - time (sec): 6.51 - samples/sec: 3607.13 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:21:06,022 epoch 5 - iter 174/292 - loss 0.03846683 - time (sec): 7.72 - samples/sec: 3515.50 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:21:07,249 epoch 5 - iter 203/292 - loss 0.03939697 - time (sec): 8.95 - samples/sec: 3532.53 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:21:08,412 epoch 5 - iter 232/292 - loss 0.04260414 - time (sec): 10.11 - samples/sec: 3502.45 - lr: 0.000017 - momentum: 0.000000
2023-10-25 21:21:09,613 epoch 5 - iter 261/292 - loss 0.04150922 - time (sec): 11.31 - samples/sec: 3508.40 - lr: 0.000017 - momentum: 0.000000
2023-10-25 21:21:10,816 epoch 5 - iter 290/292 - loss 0.04161576 - time (sec): 12.52 - samples/sec: 3534.13 - lr: 0.000017 - momentum: 0.000000
2023-10-25 21:21:10,893 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:10,893 EPOCH 5 done: loss 0.0415 - lr: 0.000017
2023-10-25 21:21:11,809 DEV : loss 0.13558463752269745 - f1-score (micro avg) 0.7706
2023-10-25 21:21:11,814 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:13,067 epoch 6 - iter 29/292 - loss 0.02684862 - time (sec): 1.25 - samples/sec: 3466.34 - lr: 0.000016 - momentum: 0.000000
2023-10-25 21:21:14,380 epoch 6 - iter 58/292 - loss 0.02943289 - time (sec): 2.57 - samples/sec: 3272.73 - lr: 0.000016 - momentum: 0.000000
2023-10-25 21:21:15,709 epoch 6 - iter 87/292 - loss 0.02812073 - time (sec): 3.89 - samples/sec: 3249.93 - lr: 0.000016 - momentum: 0.000000
2023-10-25 21:21:16,969 epoch 6 - iter 116/292 - loss 0.03204096 - time (sec): 5.15 - samples/sec: 3224.49 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:21:18,298 epoch 6 - iter 145/292 - loss 0.02999566 - time (sec): 6.48 - samples/sec: 3268.79 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:21:19,687 epoch 6 - iter 174/292 - loss 0.03172843 - time (sec): 7.87 - samples/sec: 3286.22 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:21:20,979 epoch 6 - iter 203/292 - loss 0.03002027 - time (sec): 9.16 - samples/sec: 3300.22 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:21:22,397 epoch 6 - iter 232/292 - loss 0.03059791 - time (sec): 10.58 - samples/sec: 3369.61 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:21:23,678 epoch 6 - iter 261/292 - loss 0.02908626 - time (sec): 11.86 - samples/sec: 3344.93 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:21:25,027 epoch 6 - iter 290/292 - loss 0.02740269 - time (sec): 13.21 - samples/sec: 3352.52 - lr: 0.000013 - momentum: 0.000000
2023-10-25 21:21:25,113 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:25,113 EPOCH 6 done: loss 0.0274 - lr: 0.000013
2023-10-25 21:21:26,037 DEV : loss 0.15638913214206696 - f1-score (micro avg) 0.7679
2023-10-25 21:21:26,042 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:27,313 epoch 7 - iter 29/292 - loss 0.01451795 - time (sec): 1.27 - samples/sec: 2997.89 - lr: 0.000013 - momentum: 0.000000
2023-10-25 21:21:28,737 epoch 7 - iter 58/292 - loss 0.03043042 - time (sec): 2.69 - samples/sec: 3010.82 - lr: 0.000013 - momentum: 0.000000
2023-10-25 21:21:30,145 epoch 7 - iter 87/292 - loss 0.02516600 - time (sec): 4.10 - samples/sec: 3245.65 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:21:31,430 epoch 7 - iter 116/292 - loss 0.02158147 - time (sec): 5.39 - samples/sec: 3157.27 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:21:32,717 epoch 7 - iter 145/292 - loss 0.02062496 - time (sec): 6.67 - samples/sec: 3169.32 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:21:34,061 epoch 7 - iter 174/292 - loss 0.01787927 - time (sec): 8.02 - samples/sec: 3250.37 - lr: 0.000011 - momentum: 0.000000
2023-10-25 21:21:35,385 epoch 7 - iter 203/292 - loss 0.01848142 - time (sec): 9.34 - samples/sec: 3297.63 - lr: 0.000011 - momentum: 0.000000
2023-10-25 21:21:36,709 epoch 7 - iter 232/292 - loss 0.01855890 - time (sec): 10.67 - samples/sec: 3308.28 - lr: 0.000011 - momentum: 0.000000
2023-10-25 21:21:38,062 epoch 7 - iter 261/292 - loss 0.01791828 - time (sec): 12.02 - samples/sec: 3265.53 - lr: 0.000010 - momentum: 0.000000
2023-10-25 21:21:39,423 epoch 7 - iter 290/292 - loss 0.01785400 - time (sec): 13.38 - samples/sec: 3297.27 - lr: 0.000010 - momentum: 0.000000
2023-10-25 21:21:39,515 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:39,516 EPOCH 7 done: loss 0.0180 - lr: 0.000010
2023-10-25 21:21:40,597 DEV : loss 0.18467850983142853 - f1-score (micro avg) 0.7632
2023-10-25 21:21:40,601 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:41,860 epoch 8 - iter 29/292 - loss 0.00890727 - time (sec): 1.26 - samples/sec: 3364.75 - lr: 0.000010 - momentum: 0.000000
2023-10-25 21:21:43,217 epoch 8 - iter 58/292 - loss 0.01626205 - time (sec): 2.61 - samples/sec: 3650.22 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:21:44,484 epoch 8 - iter 87/292 - loss 0.01503426 - time (sec): 3.88 - samples/sec: 3519.28 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:21:45,740 epoch 8 - iter 116/292 - loss 0.01367778 - time (sec): 5.14 - samples/sec: 3430.14 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:21:47,040 epoch 8 - iter 145/292 - loss 0.01407450 - time (sec): 6.44 - samples/sec: 3444.56 - lr: 0.000008 - momentum: 0.000000
2023-10-25 21:21:48,396 epoch 8 - iter 174/292 - loss 0.01584846 - time (sec): 7.79 - samples/sec: 3459.37 - lr: 0.000008 - momentum: 0.000000
2023-10-25 21:21:49,716 epoch 8 - iter 203/292 - loss 0.01528952 - time (sec): 9.11 - samples/sec: 3405.25 - lr: 0.000008 - momentum: 0.000000
2023-10-25 21:21:51,000 epoch 8 - iter 232/292 - loss 0.01505405 - time (sec): 10.40 - samples/sec: 3346.87 - lr: 0.000007 - momentum: 0.000000
2023-10-25 21:21:52,312 epoch 8 - iter 261/292 - loss 0.01625469 - time (sec): 11.71 - samples/sec: 3367.76 - lr: 0.000007 - momentum: 0.000000
2023-10-25 21:21:53,621 epoch 8 - iter 290/292 - loss 0.01598943 - time (sec): 13.02 - samples/sec: 3400.48 - lr: 0.000007 - momentum: 0.000000
2023-10-25 21:21:53,697 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:53,697 EPOCH 8 done: loss 0.0160 - lr: 0.000007
2023-10-25 21:21:54,623 DEV : loss 0.18894101679325104 - f1-score (micro avg) 0.7505
2023-10-25 21:21:54,628 ----------------------------------------------------------------------------------------------------
2023-10-25 21:21:55,912 epoch 9 - iter 29/292 - loss 0.00813305 - time (sec): 1.28 - samples/sec: 3571.13 - lr: 0.000006 - momentum: 0.000000
2023-10-25 21:21:57,150 epoch 9 - iter 58/292 - loss 0.00977612 - time (sec): 2.52 - samples/sec: 3468.56 - lr: 0.000006 - momentum: 0.000000
2023-10-25 21:21:58,365 epoch 9 - iter 87/292 - loss 0.01322378 - time (sec): 3.74 - samples/sec: 3555.01 - lr: 0.000006 - momentum: 0.000000
2023-10-25 21:21:59,642 epoch 9 - iter 116/292 - loss 0.01295467 - time (sec): 5.01 - samples/sec: 3637.29 - lr: 0.000005 - momentum: 0.000000
2023-10-25 21:22:00,834 epoch 9 - iter 145/292 - loss 0.01203134 - time (sec): 6.20 - samples/sec: 3567.96 - lr: 0.000005 - momentum: 0.000000
2023-10-25 21:22:02,159 epoch 9 - iter 174/292 - loss 0.01179165 - time (sec): 7.53 - samples/sec: 3515.78 - lr: 0.000005 - momentum: 0.000000
2023-10-25 21:22:03,457 epoch 9 - iter 203/292 - loss 0.01078956 - time (sec): 8.83 - samples/sec: 3470.82 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:22:04,698 epoch 9 - iter 232/292 - loss 0.00998269 - time (sec): 10.07 - samples/sec: 3414.02 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:22:06,032 epoch 9 - iter 261/292 - loss 0.00887687 - time (sec): 11.40 - samples/sec: 3443.18 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:22:07,378 epoch 9 - iter 290/292 - loss 0.01054438 - time (sec): 12.75 - samples/sec: 3454.51 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:22:07,467 ----------------------------------------------------------------------------------------------------
2023-10-25 21:22:07,467 EPOCH 9 done: loss 0.0105 - lr: 0.000003
2023-10-25 21:22:08,374 DEV : loss 0.19431500136852264 - f1-score (micro avg) 0.757
2023-10-25 21:22:08,379 ----------------------------------------------------------------------------------------------------
2023-10-25 21:22:09,708 epoch 10 - iter 29/292 - loss 0.01082939 - time (sec): 1.33 - samples/sec: 3453.25 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:22:10,945 epoch 10 - iter 58/292 - loss 0.00934277 - time (sec): 2.57 - samples/sec: 3316.40 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:22:12,197 epoch 10 - iter 87/292 - loss 0.00832350 - time (sec): 3.82 - samples/sec: 3224.24 - lr: 0.000002 - momentum: 0.000000
2023-10-25 21:22:13,561 epoch 10 - iter 116/292 - loss 0.01106584 - time (sec): 5.18 - samples/sec: 3359.73 - lr: 0.000002 - momentum: 0.000000
2023-10-25 21:22:14,806 epoch 10 - iter 145/292 - loss 0.00926850 - time (sec): 6.43 - samples/sec: 3398.47 - lr: 0.000002 - momentum: 0.000000
2023-10-25 21:22:16,184 epoch 10 - iter 174/292 - loss 0.00795886 - time (sec): 7.80 - samples/sec: 3429.82 - lr: 0.000001 - momentum: 0.000000
2023-10-25 21:22:17,554 epoch 10 - iter 203/292 - loss 0.00803485 - time (sec): 9.17 - samples/sec: 3467.14 - lr: 0.000001 - momentum: 0.000000
2023-10-25 21:22:18,867 epoch 10 - iter 232/292 - loss 0.00888351 - time (sec): 10.49 - samples/sec: 3395.29 - lr: 0.000001 - momentum: 0.000000
2023-10-25 21:22:20,193 epoch 10 - iter 261/292 - loss 0.00841492 - time (sec): 11.81 - samples/sec: 3373.34 - lr: 0.000000 - momentum: 0.000000
2023-10-25 21:22:21,478 epoch 10 - iter 290/292 - loss 0.00810355 - time (sec): 13.10 - samples/sec: 3371.86 - lr: 0.000000 - momentum: 0.000000
2023-10-25 21:22:21,573 ----------------------------------------------------------------------------------------------------
2023-10-25 21:22:21,573 EPOCH 10 done: loss 0.0081 - lr: 0.000000
2023-10-25 21:22:22,489 DEV : loss 0.19873516261577606 - f1-score (micro avg) 0.7592
2023-10-25 21:22:22,963 ----------------------------------------------------------------------------------------------------
2023-10-25 21:22:22,964 Loading model from best epoch ...
2023-10-25 21:22:24,545 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-25 21:22:26,090
Results:
- F-score (micro) 0.7596
- F-score (macro) 0.6635
- Accuracy 0.6407
By class:
precision recall f1-score support
PER 0.8050 0.8305 0.8175 348
LOC 0.7096 0.8238 0.7624 261
ORG 0.3929 0.4231 0.4074 52
HumanProd 0.6154 0.7273 0.6667 22
micro avg 0.7285 0.7936 0.7596 683
macro avg 0.6307 0.7011 0.6635 683
weighted avg 0.7311 0.7936 0.7604 683
2023-10-25 21:22:26,090 ----------------------------------------------------------------------------------------------------
|