File size: 23,908 Bytes
2899c1f |
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 10:47:53,859 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,860 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 10:47:53,860 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,860 MultiCorpus: 966 train + 219 dev + 204 test sentences
- NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-13 10:47:53,860 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,860 Train: 966 sentences
2023-10-13 10:47:53,860 (train_with_dev=False, train_with_test=False)
2023-10-13 10:47:53,860 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,860 Training Params:
2023-10-13 10:47:53,860 - learning_rate: "3e-05"
2023-10-13 10:47:53,860 - mini_batch_size: "4"
2023-10-13 10:47:53,861 - max_epochs: "10"
2023-10-13 10:47:53,861 - shuffle: "True"
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,861 Plugins:
2023-10-13 10:47:53,861 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,861 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 10:47:53,861 - metric: "('micro avg', 'f1-score')"
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,861 Computation:
2023-10-13 10:47:53,861 - compute on device: cuda:0
2023-10-13 10:47:53,861 - embedding storage: none
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,861 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:53,861 ----------------------------------------------------------------------------------------------------
2023-10-13 10:47:55,015 epoch 1 - iter 24/242 - loss 3.13003262 - time (sec): 1.15 - samples/sec: 2161.80 - lr: 0.000003 - momentum: 0.000000
2023-10-13 10:47:56,148 epoch 1 - iter 48/242 - loss 2.75856781 - time (sec): 2.29 - samples/sec: 2180.16 - lr: 0.000006 - momentum: 0.000000
2023-10-13 10:47:57,299 epoch 1 - iter 72/242 - loss 2.19092998 - time (sec): 3.44 - samples/sec: 2154.66 - lr: 0.000009 - momentum: 0.000000
2023-10-13 10:47:58,447 epoch 1 - iter 96/242 - loss 1.77854119 - time (sec): 4.59 - samples/sec: 2200.86 - lr: 0.000012 - momentum: 0.000000
2023-10-13 10:47:59,545 epoch 1 - iter 120/242 - loss 1.55395191 - time (sec): 5.68 - samples/sec: 2176.25 - lr: 0.000015 - momentum: 0.000000
2023-10-13 10:48:00,641 epoch 1 - iter 144/242 - loss 1.38979327 - time (sec): 6.78 - samples/sec: 2156.02 - lr: 0.000018 - momentum: 0.000000
2023-10-13 10:48:01,874 epoch 1 - iter 168/242 - loss 1.25407378 - time (sec): 8.01 - samples/sec: 2150.68 - lr: 0.000021 - momentum: 0.000000
2023-10-13 10:48:03,164 epoch 1 - iter 192/242 - loss 1.13701640 - time (sec): 9.30 - samples/sec: 2116.67 - lr: 0.000024 - momentum: 0.000000
2023-10-13 10:48:04,450 epoch 1 - iter 216/242 - loss 1.04657703 - time (sec): 10.59 - samples/sec: 2074.49 - lr: 0.000027 - momentum: 0.000000
2023-10-13 10:48:05,698 epoch 1 - iter 240/242 - loss 0.96086965 - time (sec): 11.84 - samples/sec: 2079.63 - lr: 0.000030 - momentum: 0.000000
2023-10-13 10:48:05,794 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:05,794 EPOCH 1 done: loss 0.9579 - lr: 0.000030
2023-10-13 10:48:06,820 DEV : loss 0.2311297208070755 - f1-score (micro avg) 0.5526
2023-10-13 10:48:06,827 saving best model
2023-10-13 10:48:07,175 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:08,412 epoch 2 - iter 24/242 - loss 0.19252288 - time (sec): 1.24 - samples/sec: 1890.40 - lr: 0.000030 - momentum: 0.000000
2023-10-13 10:48:09,585 epoch 2 - iter 48/242 - loss 0.19820910 - time (sec): 2.41 - samples/sec: 2130.51 - lr: 0.000029 - momentum: 0.000000
2023-10-13 10:48:10,665 epoch 2 - iter 72/242 - loss 0.22613094 - time (sec): 3.49 - samples/sec: 2173.82 - lr: 0.000029 - momentum: 0.000000
2023-10-13 10:48:11,757 epoch 2 - iter 96/242 - loss 0.21088375 - time (sec): 4.58 - samples/sec: 2193.77 - lr: 0.000029 - momentum: 0.000000
2023-10-13 10:48:12,828 epoch 2 - iter 120/242 - loss 0.20564494 - time (sec): 5.65 - samples/sec: 2189.72 - lr: 0.000028 - momentum: 0.000000
2023-10-13 10:48:13,904 epoch 2 - iter 144/242 - loss 0.19855435 - time (sec): 6.73 - samples/sec: 2231.35 - lr: 0.000028 - momentum: 0.000000
2023-10-13 10:48:14,998 epoch 2 - iter 168/242 - loss 0.19107056 - time (sec): 7.82 - samples/sec: 2248.92 - lr: 0.000028 - momentum: 0.000000
2023-10-13 10:48:16,041 epoch 2 - iter 192/242 - loss 0.19275419 - time (sec): 8.86 - samples/sec: 2224.91 - lr: 0.000027 - momentum: 0.000000
2023-10-13 10:48:17,056 epoch 2 - iter 216/242 - loss 0.18972065 - time (sec): 9.88 - samples/sec: 2227.16 - lr: 0.000027 - momentum: 0.000000
2023-10-13 10:48:18,077 epoch 2 - iter 240/242 - loss 0.18183087 - time (sec): 10.90 - samples/sec: 2253.42 - lr: 0.000027 - momentum: 0.000000
2023-10-13 10:48:18,160 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:18,160 EPOCH 2 done: loss 0.1813 - lr: 0.000027
2023-10-13 10:48:18,923 DEV : loss 0.1384759545326233 - f1-score (micro avg) 0.797
2023-10-13 10:48:18,927 saving best model
2023-10-13 10:48:19,386 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:20,511 epoch 3 - iter 24/242 - loss 0.11716937 - time (sec): 1.12 - samples/sec: 2225.32 - lr: 0.000026 - momentum: 0.000000
2023-10-13 10:48:21,596 epoch 3 - iter 48/242 - loss 0.10872166 - time (sec): 2.21 - samples/sec: 2158.68 - lr: 0.000026 - momentum: 0.000000
2023-10-13 10:48:22,672 epoch 3 - iter 72/242 - loss 0.10620498 - time (sec): 3.28 - samples/sec: 2178.29 - lr: 0.000026 - momentum: 0.000000
2023-10-13 10:48:23,739 epoch 3 - iter 96/242 - loss 0.11615336 - time (sec): 4.35 - samples/sec: 2193.15 - lr: 0.000025 - momentum: 0.000000
2023-10-13 10:48:24,794 epoch 3 - iter 120/242 - loss 0.11830967 - time (sec): 5.41 - samples/sec: 2205.38 - lr: 0.000025 - momentum: 0.000000
2023-10-13 10:48:25,875 epoch 3 - iter 144/242 - loss 0.11441029 - time (sec): 6.49 - samples/sec: 2235.60 - lr: 0.000025 - momentum: 0.000000
2023-10-13 10:48:26,948 epoch 3 - iter 168/242 - loss 0.10605450 - time (sec): 7.56 - samples/sec: 2240.85 - lr: 0.000024 - momentum: 0.000000
2023-10-13 10:48:28,024 epoch 3 - iter 192/242 - loss 0.10357313 - time (sec): 8.64 - samples/sec: 2269.02 - lr: 0.000024 - momentum: 0.000000
2023-10-13 10:48:29,109 epoch 3 - iter 216/242 - loss 0.10387747 - time (sec): 9.72 - samples/sec: 2239.64 - lr: 0.000024 - momentum: 0.000000
2023-10-13 10:48:30,228 epoch 3 - iter 240/242 - loss 0.10206518 - time (sec): 10.84 - samples/sec: 2270.44 - lr: 0.000023 - momentum: 0.000000
2023-10-13 10:48:30,312 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:30,312 EPOCH 3 done: loss 0.1020 - lr: 0.000023
2023-10-13 10:48:31,102 DEV : loss 0.13693803548812866 - f1-score (micro avg) 0.8128
2023-10-13 10:48:31,107 saving best model
2023-10-13 10:48:31,579 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:32,692 epoch 4 - iter 24/242 - loss 0.05483466 - time (sec): 1.11 - samples/sec: 2277.02 - lr: 0.000023 - momentum: 0.000000
2023-10-13 10:48:33,787 epoch 4 - iter 48/242 - loss 0.06636085 - time (sec): 2.20 - samples/sec: 2195.33 - lr: 0.000023 - momentum: 0.000000
2023-10-13 10:48:34,899 epoch 4 - iter 72/242 - loss 0.05503188 - time (sec): 3.32 - samples/sec: 2227.16 - lr: 0.000022 - momentum: 0.000000
2023-10-13 10:48:35,985 epoch 4 - iter 96/242 - loss 0.06042093 - time (sec): 4.40 - samples/sec: 2291.90 - lr: 0.000022 - momentum: 0.000000
2023-10-13 10:48:37,093 epoch 4 - iter 120/242 - loss 0.07036762 - time (sec): 5.51 - samples/sec: 2266.87 - lr: 0.000022 - momentum: 0.000000
2023-10-13 10:48:38,172 epoch 4 - iter 144/242 - loss 0.06852479 - time (sec): 6.59 - samples/sec: 2218.64 - lr: 0.000021 - momentum: 0.000000
2023-10-13 10:48:39,278 epoch 4 - iter 168/242 - loss 0.07130847 - time (sec): 7.69 - samples/sec: 2209.89 - lr: 0.000021 - momentum: 0.000000
2023-10-13 10:48:40,350 epoch 4 - iter 192/242 - loss 0.07430387 - time (sec): 8.77 - samples/sec: 2230.60 - lr: 0.000021 - momentum: 0.000000
2023-10-13 10:48:41,411 epoch 4 - iter 216/242 - loss 0.07667453 - time (sec): 9.83 - samples/sec: 2252.68 - lr: 0.000020 - momentum: 0.000000
2023-10-13 10:48:42,477 epoch 4 - iter 240/242 - loss 0.07606467 - time (sec): 10.89 - samples/sec: 2265.12 - lr: 0.000020 - momentum: 0.000000
2023-10-13 10:48:42,561 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:42,561 EPOCH 4 done: loss 0.0759 - lr: 0.000020
2023-10-13 10:48:43,344 DEV : loss 0.14181385934352875 - f1-score (micro avg) 0.8294
2023-10-13 10:48:43,349 saving best model
2023-10-13 10:48:43,819 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:45,012 epoch 5 - iter 24/242 - loss 0.04479677 - time (sec): 1.18 - samples/sec: 2163.10 - lr: 0.000020 - momentum: 0.000000
2023-10-13 10:48:46,151 epoch 5 - iter 48/242 - loss 0.04692686 - time (sec): 2.32 - samples/sec: 2227.84 - lr: 0.000019 - momentum: 0.000000
2023-10-13 10:48:47,280 epoch 5 - iter 72/242 - loss 0.05314195 - time (sec): 3.45 - samples/sec: 2217.21 - lr: 0.000019 - momentum: 0.000000
2023-10-13 10:48:48,436 epoch 5 - iter 96/242 - loss 0.05034553 - time (sec): 4.61 - samples/sec: 2169.73 - lr: 0.000019 - momentum: 0.000000
2023-10-13 10:48:49,503 epoch 5 - iter 120/242 - loss 0.05228931 - time (sec): 5.67 - samples/sec: 2198.25 - lr: 0.000018 - momentum: 0.000000
2023-10-13 10:48:50,569 epoch 5 - iter 144/242 - loss 0.05391865 - time (sec): 6.74 - samples/sec: 2187.02 - lr: 0.000018 - momentum: 0.000000
2023-10-13 10:48:51,665 epoch 5 - iter 168/242 - loss 0.05744337 - time (sec): 7.84 - samples/sec: 2170.23 - lr: 0.000018 - momentum: 0.000000
2023-10-13 10:48:52,753 epoch 5 - iter 192/242 - loss 0.05935951 - time (sec): 8.92 - samples/sec: 2181.24 - lr: 0.000017 - momentum: 0.000000
2023-10-13 10:48:53,838 epoch 5 - iter 216/242 - loss 0.05699843 - time (sec): 10.01 - samples/sec: 2211.94 - lr: 0.000017 - momentum: 0.000000
2023-10-13 10:48:54,907 epoch 5 - iter 240/242 - loss 0.05727682 - time (sec): 11.08 - samples/sec: 2222.44 - lr: 0.000017 - momentum: 0.000000
2023-10-13 10:48:54,993 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:54,993 EPOCH 5 done: loss 0.0579 - lr: 0.000017
2023-10-13 10:48:55,769 DEV : loss 0.14726245403289795 - f1-score (micro avg) 0.8434
2023-10-13 10:48:55,774 saving best model
2023-10-13 10:48:56,239 ----------------------------------------------------------------------------------------------------
2023-10-13 10:48:57,364 epoch 6 - iter 24/242 - loss 0.05146366 - time (sec): 1.12 - samples/sec: 2100.14 - lr: 0.000016 - momentum: 0.000000
2023-10-13 10:48:58,596 epoch 6 - iter 48/242 - loss 0.05125553 - time (sec): 2.35 - samples/sec: 2083.72 - lr: 0.000016 - momentum: 0.000000
2023-10-13 10:48:59,752 epoch 6 - iter 72/242 - loss 0.05035674 - time (sec): 3.51 - samples/sec: 1990.82 - lr: 0.000016 - momentum: 0.000000
2023-10-13 10:49:00,948 epoch 6 - iter 96/242 - loss 0.04704035 - time (sec): 4.71 - samples/sec: 2095.76 - lr: 0.000015 - momentum: 0.000000
2023-10-13 10:49:02,045 epoch 6 - iter 120/242 - loss 0.04175777 - time (sec): 5.80 - samples/sec: 2132.85 - lr: 0.000015 - momentum: 0.000000
2023-10-13 10:49:03,120 epoch 6 - iter 144/242 - loss 0.04166679 - time (sec): 6.88 - samples/sec: 2145.67 - lr: 0.000015 - momentum: 0.000000
2023-10-13 10:49:04,186 epoch 6 - iter 168/242 - loss 0.03841489 - time (sec): 7.94 - samples/sec: 2162.85 - lr: 0.000014 - momentum: 0.000000
2023-10-13 10:49:05,276 epoch 6 - iter 192/242 - loss 0.03596465 - time (sec): 9.03 - samples/sec: 2189.29 - lr: 0.000014 - momentum: 0.000000
2023-10-13 10:49:06,351 epoch 6 - iter 216/242 - loss 0.04193606 - time (sec): 10.11 - samples/sec: 2201.00 - lr: 0.000014 - momentum: 0.000000
2023-10-13 10:49:07,421 epoch 6 - iter 240/242 - loss 0.04253577 - time (sec): 11.18 - samples/sec: 2198.84 - lr: 0.000013 - momentum: 0.000000
2023-10-13 10:49:07,509 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:07,509 EPOCH 6 done: loss 0.0429 - lr: 0.000013
2023-10-13 10:49:08,299 DEV : loss 0.17159917950630188 - f1-score (micro avg) 0.8356
2023-10-13 10:49:08,306 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:09,399 epoch 7 - iter 24/242 - loss 0.03111648 - time (sec): 1.09 - samples/sec: 2193.15 - lr: 0.000013 - momentum: 0.000000
2023-10-13 10:49:10,493 epoch 7 - iter 48/242 - loss 0.02717241 - time (sec): 2.19 - samples/sec: 2215.80 - lr: 0.000013 - momentum: 0.000000
2023-10-13 10:49:11,571 epoch 7 - iter 72/242 - loss 0.02752756 - time (sec): 3.26 - samples/sec: 2329.21 - lr: 0.000012 - momentum: 0.000000
2023-10-13 10:49:12,685 epoch 7 - iter 96/242 - loss 0.03236364 - time (sec): 4.38 - samples/sec: 2313.01 - lr: 0.000012 - momentum: 0.000000
2023-10-13 10:49:13,767 epoch 7 - iter 120/242 - loss 0.02918724 - time (sec): 5.46 - samples/sec: 2301.63 - lr: 0.000012 - momentum: 0.000000
2023-10-13 10:49:14,828 epoch 7 - iter 144/242 - loss 0.03104367 - time (sec): 6.52 - samples/sec: 2266.30 - lr: 0.000011 - momentum: 0.000000
2023-10-13 10:49:15,885 epoch 7 - iter 168/242 - loss 0.03112205 - time (sec): 7.58 - samples/sec: 2233.37 - lr: 0.000011 - momentum: 0.000000
2023-10-13 10:49:16,961 epoch 7 - iter 192/242 - loss 0.03365939 - time (sec): 8.65 - samples/sec: 2260.23 - lr: 0.000011 - momentum: 0.000000
2023-10-13 10:49:17,975 epoch 7 - iter 216/242 - loss 0.03144889 - time (sec): 9.67 - samples/sec: 2268.47 - lr: 0.000010 - momentum: 0.000000
2023-10-13 10:49:18,991 epoch 7 - iter 240/242 - loss 0.03122881 - time (sec): 10.68 - samples/sec: 2296.18 - lr: 0.000010 - momentum: 0.000000
2023-10-13 10:49:19,079 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:19,079 EPOCH 7 done: loss 0.0313 - lr: 0.000010
2023-10-13 10:49:19,885 DEV : loss 0.18848736584186554 - f1-score (micro avg) 0.8409
2023-10-13 10:49:19,891 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:20,932 epoch 8 - iter 24/242 - loss 0.01927510 - time (sec): 1.04 - samples/sec: 2347.61 - lr: 0.000010 - momentum: 0.000000
2023-10-13 10:49:22,005 epoch 8 - iter 48/242 - loss 0.02463260 - time (sec): 2.11 - samples/sec: 2330.37 - lr: 0.000009 - momentum: 0.000000
2023-10-13 10:49:23,076 epoch 8 - iter 72/242 - loss 0.02726866 - time (sec): 3.18 - samples/sec: 2233.21 - lr: 0.000009 - momentum: 0.000000
2023-10-13 10:49:24,239 epoch 8 - iter 96/242 - loss 0.02300393 - time (sec): 4.35 - samples/sec: 2168.54 - lr: 0.000009 - momentum: 0.000000
2023-10-13 10:49:25,323 epoch 8 - iter 120/242 - loss 0.02083412 - time (sec): 5.43 - samples/sec: 2200.59 - lr: 0.000008 - momentum: 0.000000
2023-10-13 10:49:26,392 epoch 8 - iter 144/242 - loss 0.02701189 - time (sec): 6.50 - samples/sec: 2212.51 - lr: 0.000008 - momentum: 0.000000
2023-10-13 10:49:27,474 epoch 8 - iter 168/242 - loss 0.02613039 - time (sec): 7.58 - samples/sec: 2248.12 - lr: 0.000008 - momentum: 0.000000
2023-10-13 10:49:28,563 epoch 8 - iter 192/242 - loss 0.02688347 - time (sec): 8.67 - samples/sec: 2248.58 - lr: 0.000007 - momentum: 0.000000
2023-10-13 10:49:29,612 epoch 8 - iter 216/242 - loss 0.02593304 - time (sec): 9.72 - samples/sec: 2235.60 - lr: 0.000007 - momentum: 0.000000
2023-10-13 10:49:30,710 epoch 8 - iter 240/242 - loss 0.02401868 - time (sec): 10.82 - samples/sec: 2268.81 - lr: 0.000007 - momentum: 0.000000
2023-10-13 10:49:30,798 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:30,799 EPOCH 8 done: loss 0.0240 - lr: 0.000007
2023-10-13 10:49:31,591 DEV : loss 0.20379725098609924 - f1-score (micro avg) 0.8309
2023-10-13 10:49:31,603 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:32,940 epoch 9 - iter 24/242 - loss 0.01808826 - time (sec): 1.34 - samples/sec: 1864.21 - lr: 0.000006 - momentum: 0.000000
2023-10-13 10:49:34,165 epoch 9 - iter 48/242 - loss 0.01843967 - time (sec): 2.56 - samples/sec: 1904.33 - lr: 0.000006 - momentum: 0.000000
2023-10-13 10:49:35,239 epoch 9 - iter 72/242 - loss 0.01893930 - time (sec): 3.63 - samples/sec: 2075.55 - lr: 0.000006 - momentum: 0.000000
2023-10-13 10:49:36,320 epoch 9 - iter 96/242 - loss 0.01931122 - time (sec): 4.72 - samples/sec: 2168.66 - lr: 0.000005 - momentum: 0.000000
2023-10-13 10:49:37,392 epoch 9 - iter 120/242 - loss 0.02302219 - time (sec): 5.79 - samples/sec: 2212.05 - lr: 0.000005 - momentum: 0.000000
2023-10-13 10:49:38,448 epoch 9 - iter 144/242 - loss 0.02045805 - time (sec): 6.84 - samples/sec: 2249.74 - lr: 0.000005 - momentum: 0.000000
2023-10-13 10:49:39,497 epoch 9 - iter 168/242 - loss 0.01946463 - time (sec): 7.89 - samples/sec: 2269.78 - lr: 0.000004 - momentum: 0.000000
2023-10-13 10:49:40,554 epoch 9 - iter 192/242 - loss 0.01891538 - time (sec): 8.95 - samples/sec: 2256.21 - lr: 0.000004 - momentum: 0.000000
2023-10-13 10:49:41,607 epoch 9 - iter 216/242 - loss 0.01897938 - time (sec): 10.00 - samples/sec: 2220.33 - lr: 0.000004 - momentum: 0.000000
2023-10-13 10:49:42,685 epoch 9 - iter 240/242 - loss 0.01792783 - time (sec): 11.08 - samples/sec: 2213.06 - lr: 0.000003 - momentum: 0.000000
2023-10-13 10:49:42,784 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:42,784 EPOCH 9 done: loss 0.0178 - lr: 0.000003
2023-10-13 10:49:43,596 DEV : loss 0.21329720318317413 - f1-score (micro avg) 0.8264
2023-10-13 10:49:43,602 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:44,626 epoch 10 - iter 24/242 - loss 0.01256773 - time (sec): 1.02 - samples/sec: 2279.91 - lr: 0.000003 - momentum: 0.000000
2023-10-13 10:49:45,674 epoch 10 - iter 48/242 - loss 0.01101680 - time (sec): 2.07 - samples/sec: 2366.36 - lr: 0.000003 - momentum: 0.000000
2023-10-13 10:49:46,762 epoch 10 - iter 72/242 - loss 0.01117024 - time (sec): 3.16 - samples/sec: 2404.12 - lr: 0.000002 - momentum: 0.000000
2023-10-13 10:49:47,795 epoch 10 - iter 96/242 - loss 0.00960110 - time (sec): 4.19 - samples/sec: 2368.89 - lr: 0.000002 - momentum: 0.000000
2023-10-13 10:49:48,839 epoch 10 - iter 120/242 - loss 0.00973317 - time (sec): 5.24 - samples/sec: 2341.92 - lr: 0.000002 - momentum: 0.000000
2023-10-13 10:49:49,916 epoch 10 - iter 144/242 - loss 0.00905820 - time (sec): 6.31 - samples/sec: 2329.13 - lr: 0.000001 - momentum: 0.000000
2023-10-13 10:49:51,017 epoch 10 - iter 168/242 - loss 0.01208288 - time (sec): 7.41 - samples/sec: 2301.57 - lr: 0.000001 - momentum: 0.000000
2023-10-13 10:49:52,155 epoch 10 - iter 192/242 - loss 0.01328828 - time (sec): 8.55 - samples/sec: 2287.93 - lr: 0.000001 - momentum: 0.000000
2023-10-13 10:49:53,270 epoch 10 - iter 216/242 - loss 0.01311083 - time (sec): 9.67 - samples/sec: 2275.11 - lr: 0.000000 - momentum: 0.000000
2023-10-13 10:49:54,342 epoch 10 - iter 240/242 - loss 0.01454627 - time (sec): 10.74 - samples/sec: 2287.32 - lr: 0.000000 - momentum: 0.000000
2023-10-13 10:49:54,429 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:54,429 EPOCH 10 done: loss 0.0144 - lr: 0.000000
2023-10-13 10:49:55,197 DEV : loss 0.21672213077545166 - f1-score (micro avg) 0.8341
2023-10-13 10:49:55,589 ----------------------------------------------------------------------------------------------------
2023-10-13 10:49:55,590 Loading model from best epoch ...
2023-10-13 10:49:57,041 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-13 10:49:57,941
Results:
- F-score (micro) 0.8136
- F-score (macro) 0.5894
- Accuracy 0.7002
By class:
precision recall f1-score support
pers 0.8333 0.8633 0.8481 139
scope 0.8029 0.8527 0.8271 129
work 0.7253 0.8250 0.7719 80
loc 1.0000 0.3333 0.5000 9
date 0.0000 0.0000 0.0000 3
micro avg 0.7973 0.8306 0.8136 360
macro avg 0.6723 0.5749 0.5894 360
weighted avg 0.7956 0.8306 0.8078 360
2023-10-13 10:49:57,942 ----------------------------------------------------------------------------------------------------
|