File size: 23,935 Bytes
9ae9027 |
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 |
2023-10-13 09:14:37,108 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,109 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 09:14:37,109 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,109 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 09:14:37,109 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,109 Train: 1214 sentences
2023-10-13 09:14:37,109 (train_with_dev=False, train_with_test=False)
2023-10-13 09:14:37,109 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,109 Training Params:
2023-10-13 09:14:37,109 - learning_rate: "5e-05"
2023-10-13 09:14:37,109 - mini_batch_size: "4"
2023-10-13 09:14:37,109 - max_epochs: "10"
2023-10-13 09:14:37,109 - shuffle: "True"
2023-10-13 09:14:37,109 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,109 Plugins:
2023-10-13 09:14:37,110 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 09:14:37,110 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,110 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 09:14:37,110 - metric: "('micro avg', 'f1-score')"
2023-10-13 09:14:37,110 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,110 Computation:
2023-10-13 09:14:37,110 - compute on device: cuda:0
2023-10-13 09:14:37,110 - embedding storage: none
2023-10-13 09:14:37,110 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,110 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-13 09:14:37,110 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:37,110 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:38,509 epoch 1 - iter 30/304 - loss 3.26533625 - time (sec): 1.40 - samples/sec: 2197.51 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:14:39,836 epoch 1 - iter 60/304 - loss 2.52396187 - time (sec): 2.72 - samples/sec: 2320.21 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:14:41,149 epoch 1 - iter 90/304 - loss 1.91225369 - time (sec): 4.04 - samples/sec: 2332.45 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:14:42,473 epoch 1 - iter 120/304 - loss 1.62800576 - time (sec): 5.36 - samples/sec: 2289.23 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:14:43,787 epoch 1 - iter 150/304 - loss 1.40639103 - time (sec): 6.68 - samples/sec: 2323.03 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:14:45,092 epoch 1 - iter 180/304 - loss 1.24597081 - time (sec): 7.98 - samples/sec: 2308.19 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:14:46,371 epoch 1 - iter 210/304 - loss 1.11152874 - time (sec): 9.26 - samples/sec: 2307.15 - lr: 0.000034 - momentum: 0.000000
2023-10-13 09:14:47,653 epoch 1 - iter 240/304 - loss 1.01243221 - time (sec): 10.54 - samples/sec: 2314.74 - lr: 0.000039 - momentum: 0.000000
2023-10-13 09:14:48,928 epoch 1 - iter 270/304 - loss 0.92964922 - time (sec): 11.82 - samples/sec: 2314.61 - lr: 0.000044 - momentum: 0.000000
2023-10-13 09:14:50,206 epoch 1 - iter 300/304 - loss 0.85739553 - time (sec): 13.10 - samples/sec: 2335.91 - lr: 0.000049 - momentum: 0.000000
2023-10-13 09:14:50,371 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:50,371 EPOCH 1 done: loss 0.8496 - lr: 0.000049
2023-10-13 09:14:51,338 DEV : loss 0.201650470495224 - f1-score (micro avg) 0.6265
2023-10-13 09:14:51,344 saving best model
2023-10-13 09:14:51,717 ----------------------------------------------------------------------------------------------------
2023-10-13 09:14:53,016 epoch 2 - iter 30/304 - loss 0.23233354 - time (sec): 1.30 - samples/sec: 2297.90 - lr: 0.000049 - momentum: 0.000000
2023-10-13 09:14:54,307 epoch 2 - iter 60/304 - loss 0.21378074 - time (sec): 2.59 - samples/sec: 2329.36 - lr: 0.000049 - momentum: 0.000000
2023-10-13 09:14:55,597 epoch 2 - iter 90/304 - loss 0.17494250 - time (sec): 3.88 - samples/sec: 2341.26 - lr: 0.000048 - momentum: 0.000000
2023-10-13 09:14:56,972 epoch 2 - iter 120/304 - loss 0.17535025 - time (sec): 5.25 - samples/sec: 2311.31 - lr: 0.000048 - momentum: 0.000000
2023-10-13 09:14:58,290 epoch 2 - iter 150/304 - loss 0.16287909 - time (sec): 6.57 - samples/sec: 2336.25 - lr: 0.000047 - momentum: 0.000000
2023-10-13 09:14:59,611 epoch 2 - iter 180/304 - loss 0.15875884 - time (sec): 7.89 - samples/sec: 2313.94 - lr: 0.000047 - momentum: 0.000000
2023-10-13 09:15:00,959 epoch 2 - iter 210/304 - loss 0.15246544 - time (sec): 9.24 - samples/sec: 2332.32 - lr: 0.000046 - momentum: 0.000000
2023-10-13 09:15:02,299 epoch 2 - iter 240/304 - loss 0.14503716 - time (sec): 10.58 - samples/sec: 2337.19 - lr: 0.000046 - momentum: 0.000000
2023-10-13 09:15:03,694 epoch 2 - iter 270/304 - loss 0.14762009 - time (sec): 11.97 - samples/sec: 2322.14 - lr: 0.000045 - momentum: 0.000000
2023-10-13 09:15:05,009 epoch 2 - iter 300/304 - loss 0.14227592 - time (sec): 13.29 - samples/sec: 2316.86 - lr: 0.000045 - momentum: 0.000000
2023-10-13 09:15:05,182 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:05,183 EPOCH 2 done: loss 0.1428 - lr: 0.000045
2023-10-13 09:15:06,187 DEV : loss 0.15195277333259583 - f1-score (micro avg) 0.8133
2023-10-13 09:15:06,194 saving best model
2023-10-13 09:15:06,662 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:08,063 epoch 3 - iter 30/304 - loss 0.05676444 - time (sec): 1.40 - samples/sec: 2173.93 - lr: 0.000044 - momentum: 0.000000
2023-10-13 09:15:09,462 epoch 3 - iter 60/304 - loss 0.06761027 - time (sec): 2.80 - samples/sec: 2176.58 - lr: 0.000043 - momentum: 0.000000
2023-10-13 09:15:10,961 epoch 3 - iter 90/304 - loss 0.06873990 - time (sec): 4.30 - samples/sec: 2184.72 - lr: 0.000043 - momentum: 0.000000
2023-10-13 09:15:12,476 epoch 3 - iter 120/304 - loss 0.06757685 - time (sec): 5.81 - samples/sec: 2118.45 - lr: 0.000042 - momentum: 0.000000
2023-10-13 09:15:13,823 epoch 3 - iter 150/304 - loss 0.06996653 - time (sec): 7.16 - samples/sec: 2139.39 - lr: 0.000042 - momentum: 0.000000
2023-10-13 09:15:15,154 epoch 3 - iter 180/304 - loss 0.07913479 - time (sec): 8.49 - samples/sec: 2141.81 - lr: 0.000041 - momentum: 0.000000
2023-10-13 09:15:16,481 epoch 3 - iter 210/304 - loss 0.08228924 - time (sec): 9.82 - samples/sec: 2174.93 - lr: 0.000041 - momentum: 0.000000
2023-10-13 09:15:17,803 epoch 3 - iter 240/304 - loss 0.08984783 - time (sec): 11.14 - samples/sec: 2186.18 - lr: 0.000040 - momentum: 0.000000
2023-10-13 09:15:19,160 epoch 3 - iter 270/304 - loss 0.08913348 - time (sec): 12.50 - samples/sec: 2221.62 - lr: 0.000040 - momentum: 0.000000
2023-10-13 09:15:20,497 epoch 3 - iter 300/304 - loss 0.09116194 - time (sec): 13.83 - samples/sec: 2208.35 - lr: 0.000039 - momentum: 0.000000
2023-10-13 09:15:20,681 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:20,681 EPOCH 3 done: loss 0.0903 - lr: 0.000039
2023-10-13 09:15:21,660 DEV : loss 0.15804360806941986 - f1-score (micro avg) 0.8216
2023-10-13 09:15:21,666 saving best model
2023-10-13 09:15:22,186 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:23,555 epoch 4 - iter 30/304 - loss 0.03604401 - time (sec): 1.37 - samples/sec: 2347.09 - lr: 0.000038 - momentum: 0.000000
2023-10-13 09:15:24,927 epoch 4 - iter 60/304 - loss 0.02876844 - time (sec): 2.74 - samples/sec: 2293.45 - lr: 0.000038 - momentum: 0.000000
2023-10-13 09:15:26,280 epoch 4 - iter 90/304 - loss 0.04362614 - time (sec): 4.09 - samples/sec: 2262.63 - lr: 0.000037 - momentum: 0.000000
2023-10-13 09:15:27,621 epoch 4 - iter 120/304 - loss 0.04360443 - time (sec): 5.43 - samples/sec: 2240.24 - lr: 0.000037 - momentum: 0.000000
2023-10-13 09:15:28,956 epoch 4 - iter 150/304 - loss 0.04145059 - time (sec): 6.77 - samples/sec: 2268.73 - lr: 0.000036 - momentum: 0.000000
2023-10-13 09:15:30,287 epoch 4 - iter 180/304 - loss 0.04960702 - time (sec): 8.10 - samples/sec: 2265.92 - lr: 0.000036 - momentum: 0.000000
2023-10-13 09:15:31,640 epoch 4 - iter 210/304 - loss 0.05541308 - time (sec): 9.45 - samples/sec: 2266.11 - lr: 0.000035 - momentum: 0.000000
2023-10-13 09:15:33,000 epoch 4 - iter 240/304 - loss 0.06095762 - time (sec): 10.81 - samples/sec: 2274.36 - lr: 0.000035 - momentum: 0.000000
2023-10-13 09:15:34,357 epoch 4 - iter 270/304 - loss 0.05985542 - time (sec): 12.17 - samples/sec: 2275.80 - lr: 0.000034 - momentum: 0.000000
2023-10-13 09:15:35,691 epoch 4 - iter 300/304 - loss 0.06489252 - time (sec): 13.50 - samples/sec: 2265.80 - lr: 0.000033 - momentum: 0.000000
2023-10-13 09:15:35,870 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:35,870 EPOCH 4 done: loss 0.0641 - lr: 0.000033
2023-10-13 09:15:37,238 DEV : loss 0.2069637030363083 - f1-score (micro avg) 0.8019
2023-10-13 09:15:37,247 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:38,839 epoch 5 - iter 30/304 - loss 0.04191437 - time (sec): 1.59 - samples/sec: 1998.89 - lr: 0.000033 - momentum: 0.000000
2023-10-13 09:15:40,396 epoch 5 - iter 60/304 - loss 0.03204806 - time (sec): 3.15 - samples/sec: 2031.74 - lr: 0.000032 - momentum: 0.000000
2023-10-13 09:15:41,713 epoch 5 - iter 90/304 - loss 0.03275413 - time (sec): 4.46 - samples/sec: 2113.80 - lr: 0.000032 - momentum: 0.000000
2023-10-13 09:15:42,991 epoch 5 - iter 120/304 - loss 0.04056152 - time (sec): 5.74 - samples/sec: 2171.53 - lr: 0.000031 - momentum: 0.000000
2023-10-13 09:15:44,285 epoch 5 - iter 150/304 - loss 0.05389375 - time (sec): 7.04 - samples/sec: 2205.77 - lr: 0.000031 - momentum: 0.000000
2023-10-13 09:15:45,574 epoch 5 - iter 180/304 - loss 0.05150614 - time (sec): 8.33 - samples/sec: 2232.06 - lr: 0.000030 - momentum: 0.000000
2023-10-13 09:15:46,848 epoch 5 - iter 210/304 - loss 0.05150225 - time (sec): 9.60 - samples/sec: 2242.98 - lr: 0.000030 - momentum: 0.000000
2023-10-13 09:15:48,151 epoch 5 - iter 240/304 - loss 0.05217181 - time (sec): 10.90 - samples/sec: 2259.05 - lr: 0.000029 - momentum: 0.000000
2023-10-13 09:15:49,483 epoch 5 - iter 270/304 - loss 0.05447614 - time (sec): 12.23 - samples/sec: 2256.83 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:15:50,806 epoch 5 - iter 300/304 - loss 0.05138325 - time (sec): 13.56 - samples/sec: 2261.82 - lr: 0.000028 - momentum: 0.000000
2023-10-13 09:15:50,979 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:50,979 EPOCH 5 done: loss 0.0516 - lr: 0.000028
2023-10-13 09:15:51,943 DEV : loss 0.2098654955625534 - f1-score (micro avg) 0.8198
2023-10-13 09:15:51,948 ----------------------------------------------------------------------------------------------------
2023-10-13 09:15:53,206 epoch 6 - iter 30/304 - loss 0.05555524 - time (sec): 1.26 - samples/sec: 2228.63 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:15:54,494 epoch 6 - iter 60/304 - loss 0.05040596 - time (sec): 2.54 - samples/sec: 2381.04 - lr: 0.000027 - momentum: 0.000000
2023-10-13 09:15:55,812 epoch 6 - iter 90/304 - loss 0.03898913 - time (sec): 3.86 - samples/sec: 2358.92 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:15:57,152 epoch 6 - iter 120/304 - loss 0.03712618 - time (sec): 5.20 - samples/sec: 2343.91 - lr: 0.000026 - momentum: 0.000000
2023-10-13 09:15:58,457 epoch 6 - iter 150/304 - loss 0.03224463 - time (sec): 6.51 - samples/sec: 2301.40 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:15:59,782 epoch 6 - iter 180/304 - loss 0.03203376 - time (sec): 7.83 - samples/sec: 2309.02 - lr: 0.000025 - momentum: 0.000000
2023-10-13 09:16:01,115 epoch 6 - iter 210/304 - loss 0.03430597 - time (sec): 9.17 - samples/sec: 2320.87 - lr: 0.000024 - momentum: 0.000000
2023-10-13 09:16:02,446 epoch 6 - iter 240/304 - loss 0.03929362 - time (sec): 10.50 - samples/sec: 2317.97 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:16:03,775 epoch 6 - iter 270/304 - loss 0.03687403 - time (sec): 11.83 - samples/sec: 2311.64 - lr: 0.000023 - momentum: 0.000000
2023-10-13 09:16:05,087 epoch 6 - iter 300/304 - loss 0.03657846 - time (sec): 13.14 - samples/sec: 2331.31 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:16:05,266 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:05,267 EPOCH 6 done: loss 0.0368 - lr: 0.000022
2023-10-13 09:16:06,246 DEV : loss 0.22034451365470886 - f1-score (micro avg) 0.8221
2023-10-13 09:16:06,252 saving best model
2023-10-13 09:16:06,730 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:08,099 epoch 7 - iter 30/304 - loss 0.02239979 - time (sec): 1.36 - samples/sec: 2260.37 - lr: 0.000022 - momentum: 0.000000
2023-10-13 09:16:09,399 epoch 7 - iter 60/304 - loss 0.03115877 - time (sec): 2.66 - samples/sec: 2298.72 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:16:10,685 epoch 7 - iter 90/304 - loss 0.03771206 - time (sec): 3.95 - samples/sec: 2299.27 - lr: 0.000021 - momentum: 0.000000
2023-10-13 09:16:12,011 epoch 7 - iter 120/304 - loss 0.03515986 - time (sec): 5.28 - samples/sec: 2373.43 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:16:13,437 epoch 7 - iter 150/304 - loss 0.03089837 - time (sec): 6.70 - samples/sec: 2309.39 - lr: 0.000020 - momentum: 0.000000
2023-10-13 09:16:14,917 epoch 7 - iter 180/304 - loss 0.02684988 - time (sec): 8.18 - samples/sec: 2276.56 - lr: 0.000019 - momentum: 0.000000
2023-10-13 09:16:16,275 epoch 7 - iter 210/304 - loss 0.02627693 - time (sec): 9.54 - samples/sec: 2278.53 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:16:17,630 epoch 7 - iter 240/304 - loss 0.03001494 - time (sec): 10.90 - samples/sec: 2303.15 - lr: 0.000018 - momentum: 0.000000
2023-10-13 09:16:18,969 epoch 7 - iter 270/304 - loss 0.02826276 - time (sec): 12.23 - samples/sec: 2273.72 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:16:20,296 epoch 7 - iter 300/304 - loss 0.02865291 - time (sec): 13.56 - samples/sec: 2264.87 - lr: 0.000017 - momentum: 0.000000
2023-10-13 09:16:20,474 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:20,474 EPOCH 7 done: loss 0.0288 - lr: 0.000017
2023-10-13 09:16:21,466 DEV : loss 0.23426471650600433 - f1-score (micro avg) 0.8168
2023-10-13 09:16:21,473 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:22,877 epoch 8 - iter 30/304 - loss 0.02224755 - time (sec): 1.40 - samples/sec: 2401.89 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:16:24,263 epoch 8 - iter 60/304 - loss 0.01525236 - time (sec): 2.79 - samples/sec: 2263.66 - lr: 0.000016 - momentum: 0.000000
2023-10-13 09:16:25,635 epoch 8 - iter 90/304 - loss 0.02329187 - time (sec): 4.16 - samples/sec: 2258.57 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:16:26,976 epoch 8 - iter 120/304 - loss 0.02334889 - time (sec): 5.50 - samples/sec: 2257.54 - lr: 0.000015 - momentum: 0.000000
2023-10-13 09:16:28,374 epoch 8 - iter 150/304 - loss 0.02386948 - time (sec): 6.90 - samples/sec: 2262.04 - lr: 0.000014 - momentum: 0.000000
2023-10-13 09:16:29,758 epoch 8 - iter 180/304 - loss 0.02048026 - time (sec): 8.28 - samples/sec: 2259.77 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:16:31,110 epoch 8 - iter 210/304 - loss 0.02097907 - time (sec): 9.64 - samples/sec: 2249.01 - lr: 0.000013 - momentum: 0.000000
2023-10-13 09:16:32,423 epoch 8 - iter 240/304 - loss 0.02088416 - time (sec): 10.95 - samples/sec: 2260.29 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:16:33,741 epoch 8 - iter 270/304 - loss 0.02000901 - time (sec): 12.27 - samples/sec: 2255.30 - lr: 0.000012 - momentum: 0.000000
2023-10-13 09:16:35,084 epoch 8 - iter 300/304 - loss 0.02079615 - time (sec): 13.61 - samples/sec: 2248.16 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:16:35,257 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:35,257 EPOCH 8 done: loss 0.0205 - lr: 0.000011
2023-10-13 09:16:36,170 DEV : loss 0.2336961030960083 - f1-score (micro avg) 0.8088
2023-10-13 09:16:36,176 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:37,480 epoch 9 - iter 30/304 - loss 0.03185151 - time (sec): 1.30 - samples/sec: 2118.20 - lr: 0.000011 - momentum: 0.000000
2023-10-13 09:16:38,805 epoch 9 - iter 60/304 - loss 0.01941022 - time (sec): 2.63 - samples/sec: 2248.26 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:16:40,114 epoch 9 - iter 90/304 - loss 0.02418827 - time (sec): 3.94 - samples/sec: 2338.22 - lr: 0.000010 - momentum: 0.000000
2023-10-13 09:16:41,423 epoch 9 - iter 120/304 - loss 0.02236864 - time (sec): 5.25 - samples/sec: 2360.29 - lr: 0.000009 - momentum: 0.000000
2023-10-13 09:16:42,747 epoch 9 - iter 150/304 - loss 0.01936117 - time (sec): 6.57 - samples/sec: 2338.84 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:16:44,042 epoch 9 - iter 180/304 - loss 0.02011720 - time (sec): 7.86 - samples/sec: 2336.05 - lr: 0.000008 - momentum: 0.000000
2023-10-13 09:16:45,349 epoch 9 - iter 210/304 - loss 0.01822278 - time (sec): 9.17 - samples/sec: 2312.70 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:16:46,676 epoch 9 - iter 240/304 - loss 0.01633974 - time (sec): 10.50 - samples/sec: 2343.24 - lr: 0.000007 - momentum: 0.000000
2023-10-13 09:16:47,986 epoch 9 - iter 270/304 - loss 0.01538783 - time (sec): 11.81 - samples/sec: 2337.67 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:16:49,306 epoch 9 - iter 300/304 - loss 0.01441047 - time (sec): 13.13 - samples/sec: 2332.01 - lr: 0.000006 - momentum: 0.000000
2023-10-13 09:16:49,476 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:49,476 EPOCH 9 done: loss 0.0142 - lr: 0.000006
2023-10-13 09:16:50,451 DEV : loss 0.23067596554756165 - f1-score (micro avg) 0.8341
2023-10-13 09:16:50,457 saving best model
2023-10-13 09:16:50,946 ----------------------------------------------------------------------------------------------------
2023-10-13 09:16:52,223 epoch 10 - iter 30/304 - loss 0.00042546 - time (sec): 1.28 - samples/sec: 2287.84 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:16:53,505 epoch 10 - iter 60/304 - loss 0.00653303 - time (sec): 2.56 - samples/sec: 2398.84 - lr: 0.000005 - momentum: 0.000000
2023-10-13 09:16:54,777 epoch 10 - iter 90/304 - loss 0.00676046 - time (sec): 3.83 - samples/sec: 2481.73 - lr: 0.000004 - momentum: 0.000000
2023-10-13 09:16:56,053 epoch 10 - iter 120/304 - loss 0.01082980 - time (sec): 5.11 - samples/sec: 2451.59 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:16:57,352 epoch 10 - iter 150/304 - loss 0.01160425 - time (sec): 6.40 - samples/sec: 2397.63 - lr: 0.000003 - momentum: 0.000000
2023-10-13 09:16:58,713 epoch 10 - iter 180/304 - loss 0.00964747 - time (sec): 7.76 - samples/sec: 2406.44 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:17:00,034 epoch 10 - iter 210/304 - loss 0.01238947 - time (sec): 9.09 - samples/sec: 2398.10 - lr: 0.000002 - momentum: 0.000000
2023-10-13 09:17:01,355 epoch 10 - iter 240/304 - loss 0.01215384 - time (sec): 10.41 - samples/sec: 2363.73 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:17:02,681 epoch 10 - iter 270/304 - loss 0.01161439 - time (sec): 11.73 - samples/sec: 2360.65 - lr: 0.000001 - momentum: 0.000000
2023-10-13 09:17:04,067 epoch 10 - iter 300/304 - loss 0.01123309 - time (sec): 13.12 - samples/sec: 2346.33 - lr: 0.000000 - momentum: 0.000000
2023-10-13 09:17:04,242 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:04,242 EPOCH 10 done: loss 0.0112 - lr: 0.000000
2023-10-13 09:17:05,216 DEV : loss 0.22761297225952148 - f1-score (micro avg) 0.8253
2023-10-13 09:17:05,622 ----------------------------------------------------------------------------------------------------
2023-10-13 09:17:05,624 Loading model from best epoch ...
2023-10-13 09:17:07,074 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 09:17:08,140
Results:
- F-score (micro) 0.7847
- F-score (macro) 0.6101
- Accuracy 0.6556
By class:
precision recall f1-score support
scope 0.7278 0.8146 0.7687 151
pers 0.7607 0.9271 0.8357 96
work 0.7034 0.8737 0.7793 95
loc 0.6667 0.6667 0.6667 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7262 0.8534 0.7847 348
macro avg 0.5717 0.6564 0.6101 348
weighted avg 0.7234 0.8534 0.7826 348
2023-10-13 09:17:08,140 ----------------------------------------------------------------------------------------------------
|