File size: 23,820 Bytes
6cf3bbd |
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 |
2023-10-14 11:47:09,968 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,969 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=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-14 11:47:09,969 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,969 MultiCorpus: 5777 train + 722 dev + 723 test sentences
- NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
2023-10-14 11:47:09,969 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,969 Train: 5777 sentences
2023-10-14 11:47:09,969 (train_with_dev=False, train_with_test=False)
2023-10-14 11:47:09,969 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,969 Training Params:
2023-10-14 11:47:09,969 - learning_rate: "3e-05"
2023-10-14 11:47:09,970 - mini_batch_size: "8"
2023-10-14 11:47:09,970 - max_epochs: "10"
2023-10-14 11:47:09,970 - shuffle: "True"
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,970 Plugins:
2023-10-14 11:47:09,970 - LinearScheduler | warmup_fraction: '0.1'
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,970 Final evaluation on model from best epoch (best-model.pt)
2023-10-14 11:47:09,970 - metric: "('micro avg', 'f1-score')"
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,970 Computation:
2023-10-14 11:47:09,970 - compute on device: cuda:0
2023-10-14 11:47:09,970 - embedding storage: none
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,970 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:09,970 ----------------------------------------------------------------------------------------------------
2023-10-14 11:47:16,044 epoch 1 - iter 72/723 - loss 2.17936848 - time (sec): 6.07 - samples/sec: 3053.65 - lr: 0.000003 - momentum: 0.000000
2023-10-14 11:47:22,048 epoch 1 - iter 144/723 - loss 1.30488853 - time (sec): 12.08 - samples/sec: 2974.16 - lr: 0.000006 - momentum: 0.000000
2023-10-14 11:47:27,819 epoch 1 - iter 216/723 - loss 0.96288539 - time (sec): 17.85 - samples/sec: 2988.26 - lr: 0.000009 - momentum: 0.000000
2023-10-14 11:47:34,101 epoch 1 - iter 288/723 - loss 0.77877705 - time (sec): 24.13 - samples/sec: 2957.82 - lr: 0.000012 - momentum: 0.000000
2023-10-14 11:47:40,166 epoch 1 - iter 360/723 - loss 0.66184851 - time (sec): 30.19 - samples/sec: 2937.05 - lr: 0.000015 - momentum: 0.000000
2023-10-14 11:47:46,237 epoch 1 - iter 432/723 - loss 0.58058110 - time (sec): 36.27 - samples/sec: 2929.70 - lr: 0.000018 - momentum: 0.000000
2023-10-14 11:47:52,424 epoch 1 - iter 504/723 - loss 0.52285800 - time (sec): 42.45 - samples/sec: 2920.34 - lr: 0.000021 - momentum: 0.000000
2023-10-14 11:47:58,303 epoch 1 - iter 576/723 - loss 0.47873115 - time (sec): 48.33 - samples/sec: 2901.73 - lr: 0.000024 - momentum: 0.000000
2023-10-14 11:48:04,095 epoch 1 - iter 648/723 - loss 0.43866282 - time (sec): 54.12 - samples/sec: 2916.97 - lr: 0.000027 - momentum: 0.000000
2023-10-14 11:48:10,154 epoch 1 - iter 720/723 - loss 0.40791889 - time (sec): 60.18 - samples/sec: 2918.46 - lr: 0.000030 - momentum: 0.000000
2023-10-14 11:48:10,356 ----------------------------------------------------------------------------------------------------
2023-10-14 11:48:10,356 EPOCH 1 done: loss 0.4072 - lr: 0.000030
2023-10-14 11:48:13,522 DEV : loss 0.13588625192642212 - f1-score (micro avg) 0.6361
2023-10-14 11:48:13,538 saving best model
2023-10-14 11:48:13,953 ----------------------------------------------------------------------------------------------------
2023-10-14 11:48:19,937 epoch 2 - iter 72/723 - loss 0.11712269 - time (sec): 5.98 - samples/sec: 2859.68 - lr: 0.000030 - momentum: 0.000000
2023-10-14 11:48:26,043 epoch 2 - iter 144/723 - loss 0.11668248 - time (sec): 12.09 - samples/sec: 2824.30 - lr: 0.000029 - momentum: 0.000000
2023-10-14 11:48:32,261 epoch 2 - iter 216/723 - loss 0.11217901 - time (sec): 18.31 - samples/sec: 2863.21 - lr: 0.000029 - momentum: 0.000000
2023-10-14 11:48:38,786 epoch 2 - iter 288/723 - loss 0.10925944 - time (sec): 24.83 - samples/sec: 2855.63 - lr: 0.000029 - momentum: 0.000000
2023-10-14 11:48:44,379 epoch 2 - iter 360/723 - loss 0.10959979 - time (sec): 30.43 - samples/sec: 2891.40 - lr: 0.000028 - momentum: 0.000000
2023-10-14 11:48:50,066 epoch 2 - iter 432/723 - loss 0.10627704 - time (sec): 36.11 - samples/sec: 2899.92 - lr: 0.000028 - momentum: 0.000000
2023-10-14 11:48:56,429 epoch 2 - iter 504/723 - loss 0.10609633 - time (sec): 42.48 - samples/sec: 2880.18 - lr: 0.000028 - momentum: 0.000000
2023-10-14 11:49:02,960 epoch 2 - iter 576/723 - loss 0.10378393 - time (sec): 49.01 - samples/sec: 2860.76 - lr: 0.000027 - momentum: 0.000000
2023-10-14 11:49:09,150 epoch 2 - iter 648/723 - loss 0.10374395 - time (sec): 55.20 - samples/sec: 2866.12 - lr: 0.000027 - momentum: 0.000000
2023-10-14 11:49:14,970 epoch 2 - iter 720/723 - loss 0.10227966 - time (sec): 61.02 - samples/sec: 2880.91 - lr: 0.000027 - momentum: 0.000000
2023-10-14 11:49:15,136 ----------------------------------------------------------------------------------------------------
2023-10-14 11:49:15,136 EPOCH 2 done: loss 0.1023 - lr: 0.000027
2023-10-14 11:49:18,826 DEV : loss 0.09264427423477173 - f1-score (micro avg) 0.7781
2023-10-14 11:49:18,843 saving best model
2023-10-14 11:49:19,322 ----------------------------------------------------------------------------------------------------
2023-10-14 11:49:25,171 epoch 3 - iter 72/723 - loss 0.07984702 - time (sec): 5.85 - samples/sec: 2901.93 - lr: 0.000026 - momentum: 0.000000
2023-10-14 11:49:31,011 epoch 3 - iter 144/723 - loss 0.07300924 - time (sec): 11.69 - samples/sec: 2916.01 - lr: 0.000026 - momentum: 0.000000
2023-10-14 11:49:37,186 epoch 3 - iter 216/723 - loss 0.06832100 - time (sec): 17.86 - samples/sec: 2865.29 - lr: 0.000026 - momentum: 0.000000
2023-10-14 11:49:42,899 epoch 3 - iter 288/723 - loss 0.06940238 - time (sec): 23.57 - samples/sec: 2881.77 - lr: 0.000025 - momentum: 0.000000
2023-10-14 11:49:48,505 epoch 3 - iter 360/723 - loss 0.06705455 - time (sec): 29.18 - samples/sec: 2889.13 - lr: 0.000025 - momentum: 0.000000
2023-10-14 11:49:54,710 epoch 3 - iter 432/723 - loss 0.06525111 - time (sec): 35.39 - samples/sec: 2917.74 - lr: 0.000025 - momentum: 0.000000
2023-10-14 11:50:00,599 epoch 3 - iter 504/723 - loss 0.06489497 - time (sec): 41.28 - samples/sec: 2917.45 - lr: 0.000024 - momentum: 0.000000
2023-10-14 11:50:06,623 epoch 3 - iter 576/723 - loss 0.06635288 - time (sec): 47.30 - samples/sec: 2941.51 - lr: 0.000024 - momentum: 0.000000
2023-10-14 11:50:12,929 epoch 3 - iter 648/723 - loss 0.06505342 - time (sec): 53.60 - samples/sec: 2926.74 - lr: 0.000024 - momentum: 0.000000
2023-10-14 11:50:19,279 epoch 3 - iter 720/723 - loss 0.06394731 - time (sec): 59.95 - samples/sec: 2932.02 - lr: 0.000023 - momentum: 0.000000
2023-10-14 11:50:19,444 ----------------------------------------------------------------------------------------------------
2023-10-14 11:50:19,444 EPOCH 3 done: loss 0.0641 - lr: 0.000023
2023-10-14 11:50:24,040 DEV : loss 0.08042255789041519 - f1-score (micro avg) 0.7954
2023-10-14 11:50:24,072 saving best model
2023-10-14 11:50:24,642 ----------------------------------------------------------------------------------------------------
2023-10-14 11:50:30,665 epoch 4 - iter 72/723 - loss 0.03888401 - time (sec): 6.02 - samples/sec: 2815.75 - lr: 0.000023 - momentum: 0.000000
2023-10-14 11:50:36,602 epoch 4 - iter 144/723 - loss 0.04190461 - time (sec): 11.96 - samples/sec: 2998.16 - lr: 0.000023 - momentum: 0.000000
2023-10-14 11:50:42,498 epoch 4 - iter 216/723 - loss 0.04041996 - time (sec): 17.85 - samples/sec: 2969.21 - lr: 0.000022 - momentum: 0.000000
2023-10-14 11:50:48,871 epoch 4 - iter 288/723 - loss 0.04268068 - time (sec): 24.23 - samples/sec: 2917.23 - lr: 0.000022 - momentum: 0.000000
2023-10-14 11:50:54,653 epoch 4 - iter 360/723 - loss 0.04323841 - time (sec): 30.01 - samples/sec: 2913.19 - lr: 0.000022 - momentum: 0.000000
2023-10-14 11:51:00,881 epoch 4 - iter 432/723 - loss 0.04422879 - time (sec): 36.24 - samples/sec: 2899.02 - lr: 0.000021 - momentum: 0.000000
2023-10-14 11:51:07,029 epoch 4 - iter 504/723 - loss 0.04346939 - time (sec): 42.38 - samples/sec: 2903.77 - lr: 0.000021 - momentum: 0.000000
2023-10-14 11:51:12,738 epoch 4 - iter 576/723 - loss 0.04268000 - time (sec): 48.09 - samples/sec: 2905.38 - lr: 0.000021 - momentum: 0.000000
2023-10-14 11:51:18,686 epoch 4 - iter 648/723 - loss 0.04192132 - time (sec): 54.04 - samples/sec: 2920.00 - lr: 0.000020 - momentum: 0.000000
2023-10-14 11:51:24,862 epoch 4 - iter 720/723 - loss 0.04244714 - time (sec): 60.22 - samples/sec: 2919.39 - lr: 0.000020 - momentum: 0.000000
2023-10-14 11:51:25,034 ----------------------------------------------------------------------------------------------------
2023-10-14 11:51:25,034 EPOCH 4 done: loss 0.0424 - lr: 0.000020
2023-10-14 11:51:28,568 DEV : loss 0.09498978406190872 - f1-score (micro avg) 0.7943
2023-10-14 11:51:28,585 ----------------------------------------------------------------------------------------------------
2023-10-14 11:51:34,533 epoch 5 - iter 72/723 - loss 0.02557454 - time (sec): 5.95 - samples/sec: 2796.46 - lr: 0.000020 - momentum: 0.000000
2023-10-14 11:51:40,625 epoch 5 - iter 144/723 - loss 0.02813156 - time (sec): 12.04 - samples/sec: 2775.57 - lr: 0.000019 - momentum: 0.000000
2023-10-14 11:51:47,161 epoch 5 - iter 216/723 - loss 0.03143363 - time (sec): 18.57 - samples/sec: 2722.72 - lr: 0.000019 - momentum: 0.000000
2023-10-14 11:51:53,361 epoch 5 - iter 288/723 - loss 0.03092080 - time (sec): 24.77 - samples/sec: 2791.88 - lr: 0.000019 - momentum: 0.000000
2023-10-14 11:51:59,575 epoch 5 - iter 360/723 - loss 0.03267232 - time (sec): 30.99 - samples/sec: 2813.37 - lr: 0.000018 - momentum: 0.000000
2023-10-14 11:52:05,683 epoch 5 - iter 432/723 - loss 0.03342599 - time (sec): 37.10 - samples/sec: 2839.84 - lr: 0.000018 - momentum: 0.000000
2023-10-14 11:52:12,172 epoch 5 - iter 504/723 - loss 0.03230870 - time (sec): 43.58 - samples/sec: 2848.04 - lr: 0.000018 - momentum: 0.000000
2023-10-14 11:52:18,077 epoch 5 - iter 576/723 - loss 0.03186647 - time (sec): 49.49 - samples/sec: 2846.56 - lr: 0.000017 - momentum: 0.000000
2023-10-14 11:52:23,851 epoch 5 - iter 648/723 - loss 0.03038680 - time (sec): 55.26 - samples/sec: 2860.04 - lr: 0.000017 - momentum: 0.000000
2023-10-14 11:52:30,050 epoch 5 - iter 720/723 - loss 0.03171654 - time (sec): 61.46 - samples/sec: 2853.61 - lr: 0.000017 - momentum: 0.000000
2023-10-14 11:52:30,317 ----------------------------------------------------------------------------------------------------
2023-10-14 11:52:30,317 EPOCH 5 done: loss 0.0319 - lr: 0.000017
2023-10-14 11:52:33,961 DEV : loss 0.11846506595611572 - f1-score (micro avg) 0.8055
2023-10-14 11:52:33,977 saving best model
2023-10-14 11:52:34,393 ----------------------------------------------------------------------------------------------------
2023-10-14 11:52:40,195 epoch 6 - iter 72/723 - loss 0.02635934 - time (sec): 5.80 - samples/sec: 2915.02 - lr: 0.000016 - momentum: 0.000000
2023-10-14 11:52:45,847 epoch 6 - iter 144/723 - loss 0.02567053 - time (sec): 11.45 - samples/sec: 2989.60 - lr: 0.000016 - momentum: 0.000000
2023-10-14 11:52:52,001 epoch 6 - iter 216/723 - loss 0.02594002 - time (sec): 17.61 - samples/sec: 2958.72 - lr: 0.000016 - momentum: 0.000000
2023-10-14 11:52:58,150 epoch 6 - iter 288/723 - loss 0.02839596 - time (sec): 23.76 - samples/sec: 2961.05 - lr: 0.000015 - momentum: 0.000000
2023-10-14 11:53:04,782 epoch 6 - iter 360/723 - loss 0.02953778 - time (sec): 30.39 - samples/sec: 2945.44 - lr: 0.000015 - momentum: 0.000000
2023-10-14 11:53:10,905 epoch 6 - iter 432/723 - loss 0.02804276 - time (sec): 36.51 - samples/sec: 2926.53 - lr: 0.000015 - momentum: 0.000000
2023-10-14 11:53:16,320 epoch 6 - iter 504/723 - loss 0.02683702 - time (sec): 41.92 - samples/sec: 2948.93 - lr: 0.000014 - momentum: 0.000000
2023-10-14 11:53:22,244 epoch 6 - iter 576/723 - loss 0.02562191 - time (sec): 47.85 - samples/sec: 2942.84 - lr: 0.000014 - momentum: 0.000000
2023-10-14 11:53:27,883 epoch 6 - iter 648/723 - loss 0.02530607 - time (sec): 53.49 - samples/sec: 2958.77 - lr: 0.000014 - momentum: 0.000000
2023-10-14 11:53:33,702 epoch 6 - iter 720/723 - loss 0.02457646 - time (sec): 59.31 - samples/sec: 2962.58 - lr: 0.000013 - momentum: 0.000000
2023-10-14 11:53:33,918 ----------------------------------------------------------------------------------------------------
2023-10-14 11:53:33,919 EPOCH 6 done: loss 0.0246 - lr: 0.000013
2023-10-14 11:53:38,487 DEV : loss 0.13894404470920563 - f1-score (micro avg) 0.8147
2023-10-14 11:53:38,512 saving best model
2023-10-14 11:53:39,053 ----------------------------------------------------------------------------------------------------
2023-10-14 11:53:45,100 epoch 7 - iter 72/723 - loss 0.01514089 - time (sec): 6.04 - samples/sec: 2816.37 - lr: 0.000013 - momentum: 0.000000
2023-10-14 11:53:51,034 epoch 7 - iter 144/723 - loss 0.01504761 - time (sec): 11.98 - samples/sec: 2857.79 - lr: 0.000013 - momentum: 0.000000
2023-10-14 11:53:57,277 epoch 7 - iter 216/723 - loss 0.01712868 - time (sec): 18.22 - samples/sec: 2888.95 - lr: 0.000012 - momentum: 0.000000
2023-10-14 11:54:03,341 epoch 7 - iter 288/723 - loss 0.01831387 - time (sec): 24.29 - samples/sec: 2883.50 - lr: 0.000012 - momentum: 0.000000
2023-10-14 11:54:09,339 epoch 7 - iter 360/723 - loss 0.01652720 - time (sec): 30.28 - samples/sec: 2908.98 - lr: 0.000012 - momentum: 0.000000
2023-10-14 11:54:15,105 epoch 7 - iter 432/723 - loss 0.01612436 - time (sec): 36.05 - samples/sec: 2923.73 - lr: 0.000011 - momentum: 0.000000
2023-10-14 11:54:21,245 epoch 7 - iter 504/723 - loss 0.01609187 - time (sec): 42.19 - samples/sec: 2914.96 - lr: 0.000011 - momentum: 0.000000
2023-10-14 11:54:27,377 epoch 7 - iter 576/723 - loss 0.01654164 - time (sec): 48.32 - samples/sec: 2910.10 - lr: 0.000011 - momentum: 0.000000
2023-10-14 11:54:33,068 epoch 7 - iter 648/723 - loss 0.01719631 - time (sec): 54.01 - samples/sec: 2909.29 - lr: 0.000010 - momentum: 0.000000
2023-10-14 11:54:39,697 epoch 7 - iter 720/723 - loss 0.01721697 - time (sec): 60.64 - samples/sec: 2897.14 - lr: 0.000010 - momentum: 0.000000
2023-10-14 11:54:39,934 ----------------------------------------------------------------------------------------------------
2023-10-14 11:54:39,934 EPOCH 7 done: loss 0.0172 - lr: 0.000010
2023-10-14 11:54:43,657 DEV : loss 0.16778483986854553 - f1-score (micro avg) 0.8077
2023-10-14 11:54:43,680 ----------------------------------------------------------------------------------------------------
2023-10-14 11:54:50,765 epoch 8 - iter 72/723 - loss 0.01257707 - time (sec): 7.08 - samples/sec: 2514.43 - lr: 0.000010 - momentum: 0.000000
2023-10-14 11:54:56,831 epoch 8 - iter 144/723 - loss 0.01317721 - time (sec): 13.15 - samples/sec: 2673.46 - lr: 0.000009 - momentum: 0.000000
2023-10-14 11:55:03,315 epoch 8 - iter 216/723 - loss 0.01362361 - time (sec): 19.63 - samples/sec: 2712.80 - lr: 0.000009 - momentum: 0.000000
2023-10-14 11:55:09,075 epoch 8 - iter 288/723 - loss 0.01440453 - time (sec): 25.39 - samples/sec: 2780.28 - lr: 0.000009 - momentum: 0.000000
2023-10-14 11:55:15,429 epoch 8 - iter 360/723 - loss 0.01453039 - time (sec): 31.75 - samples/sec: 2789.63 - lr: 0.000008 - momentum: 0.000000
2023-10-14 11:55:21,249 epoch 8 - iter 432/723 - loss 0.01405394 - time (sec): 37.57 - samples/sec: 2820.91 - lr: 0.000008 - momentum: 0.000000
2023-10-14 11:55:27,058 epoch 8 - iter 504/723 - loss 0.01345119 - time (sec): 43.38 - samples/sec: 2820.92 - lr: 0.000008 - momentum: 0.000000
2023-10-14 11:55:33,497 epoch 8 - iter 576/723 - loss 0.01275603 - time (sec): 49.82 - samples/sec: 2817.53 - lr: 0.000007 - momentum: 0.000000
2023-10-14 11:55:39,761 epoch 8 - iter 648/723 - loss 0.01366196 - time (sec): 56.08 - samples/sec: 2826.80 - lr: 0.000007 - momentum: 0.000000
2023-10-14 11:55:45,544 epoch 8 - iter 720/723 - loss 0.01335513 - time (sec): 61.86 - samples/sec: 2836.20 - lr: 0.000007 - momentum: 0.000000
2023-10-14 11:55:45,852 ----------------------------------------------------------------------------------------------------
2023-10-14 11:55:45,852 EPOCH 8 done: loss 0.0133 - lr: 0.000007
2023-10-14 11:55:49,362 DEV : loss 0.18129222095012665 - f1-score (micro avg) 0.8109
2023-10-14 11:55:49,380 ----------------------------------------------------------------------------------------------------
2023-10-14 11:55:55,373 epoch 9 - iter 72/723 - loss 0.00469641 - time (sec): 5.99 - samples/sec: 2909.93 - lr: 0.000006 - momentum: 0.000000
2023-10-14 11:56:00,990 epoch 9 - iter 144/723 - loss 0.00558362 - time (sec): 11.61 - samples/sec: 2883.12 - lr: 0.000006 - momentum: 0.000000
2023-10-14 11:56:07,785 epoch 9 - iter 216/723 - loss 0.00934811 - time (sec): 18.40 - samples/sec: 2914.61 - lr: 0.000006 - momentum: 0.000000
2023-10-14 11:56:13,316 epoch 9 - iter 288/723 - loss 0.00967709 - time (sec): 23.93 - samples/sec: 2938.46 - lr: 0.000005 - momentum: 0.000000
2023-10-14 11:56:19,287 epoch 9 - iter 360/723 - loss 0.00972270 - time (sec): 29.91 - samples/sec: 2955.84 - lr: 0.000005 - momentum: 0.000000
2023-10-14 11:56:25,175 epoch 9 - iter 432/723 - loss 0.00996302 - time (sec): 35.79 - samples/sec: 2957.64 - lr: 0.000005 - momentum: 0.000000
2023-10-14 11:56:31,060 epoch 9 - iter 504/723 - loss 0.00950339 - time (sec): 41.68 - samples/sec: 2959.25 - lr: 0.000004 - momentum: 0.000000
2023-10-14 11:56:37,078 epoch 9 - iter 576/723 - loss 0.01010530 - time (sec): 47.70 - samples/sec: 2943.69 - lr: 0.000004 - momentum: 0.000000
2023-10-14 11:56:42,906 epoch 9 - iter 648/723 - loss 0.01002914 - time (sec): 53.52 - samples/sec: 2946.96 - lr: 0.000004 - momentum: 0.000000
2023-10-14 11:56:48,906 epoch 9 - iter 720/723 - loss 0.01036201 - time (sec): 59.52 - samples/sec: 2948.08 - lr: 0.000003 - momentum: 0.000000
2023-10-14 11:56:49,182 ----------------------------------------------------------------------------------------------------
2023-10-14 11:56:49,182 EPOCH 9 done: loss 0.0103 - lr: 0.000003
2023-10-14 11:56:53,096 DEV : loss 0.1801426112651825 - f1-score (micro avg) 0.8155
2023-10-14 11:56:53,111 saving best model
2023-10-14 11:56:53,771 ----------------------------------------------------------------------------------------------------
2023-10-14 11:57:00,146 epoch 10 - iter 72/723 - loss 0.00771571 - time (sec): 6.37 - samples/sec: 2841.33 - lr: 0.000003 - momentum: 0.000000
2023-10-14 11:57:05,943 epoch 10 - iter 144/723 - loss 0.00799529 - time (sec): 12.17 - samples/sec: 2929.37 - lr: 0.000003 - momentum: 0.000000
2023-10-14 11:57:12,088 epoch 10 - iter 216/723 - loss 0.00964900 - time (sec): 18.31 - samples/sec: 2909.61 - lr: 0.000002 - momentum: 0.000000
2023-10-14 11:57:18,469 epoch 10 - iter 288/723 - loss 0.00910715 - time (sec): 24.69 - samples/sec: 2908.74 - lr: 0.000002 - momentum: 0.000000
2023-10-14 11:57:24,261 epoch 10 - iter 360/723 - loss 0.00785801 - time (sec): 30.49 - samples/sec: 2927.64 - lr: 0.000002 - momentum: 0.000000
2023-10-14 11:57:29,982 epoch 10 - iter 432/723 - loss 0.00782112 - time (sec): 36.21 - samples/sec: 2949.53 - lr: 0.000001 - momentum: 0.000000
2023-10-14 11:57:36,136 epoch 10 - iter 504/723 - loss 0.00784393 - time (sec): 42.36 - samples/sec: 2934.43 - lr: 0.000001 - momentum: 0.000000
2023-10-14 11:57:41,890 epoch 10 - iter 576/723 - loss 0.00793032 - time (sec): 48.12 - samples/sec: 2940.39 - lr: 0.000001 - momentum: 0.000000
2023-10-14 11:57:47,590 epoch 10 - iter 648/723 - loss 0.00792955 - time (sec): 53.82 - samples/sec: 2936.65 - lr: 0.000000 - momentum: 0.000000
2023-10-14 11:57:53,365 epoch 10 - iter 720/723 - loss 0.00802050 - time (sec): 59.59 - samples/sec: 2946.14 - lr: 0.000000 - momentum: 0.000000
2023-10-14 11:57:53,666 ----------------------------------------------------------------------------------------------------
2023-10-14 11:57:53,667 EPOCH 10 done: loss 0.0080 - lr: 0.000000
2023-10-14 11:57:57,150 DEV : loss 0.1832604557275772 - f1-score (micro avg) 0.8127
2023-10-14 11:57:57,618 ----------------------------------------------------------------------------------------------------
2023-10-14 11:57:57,619 Loading model from best epoch ...
2023-10-14 11:57:59,232 SequenceTagger predicts: Dictionary with 13 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
2023-10-14 11:58:02,393
Results:
- F-score (micro) 0.8004
- F-score (macro) 0.6962
- Accuracy 0.6799
By class:
precision recall f1-score support
PER 0.8323 0.8237 0.8279 482
LOC 0.8741 0.7882 0.8289 458
ORG 0.4286 0.4348 0.4317 69
micro avg 0.8208 0.7810 0.8004 1009
macro avg 0.7116 0.6822 0.6962 1009
weighted avg 0.8237 0.7810 0.8013 1009
2023-10-14 11:58:02,393 ----------------------------------------------------------------------------------------------------
|