File size: 24,063 Bytes
988531e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 |
2023-10-23 15:45:20,702 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,703 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-23 15:45:20,703 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,703 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-23 15:45:20,703 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,703 Train: 1100 sentences
2023-10-23 15:45:20,703 (train_with_dev=False, train_with_test=False)
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Training Params:
2023-10-23 15:45:20,704 - learning_rate: "3e-05"
2023-10-23 15:45:20,704 - mini_batch_size: "8"
2023-10-23 15:45:20,704 - max_epochs: "10"
2023-10-23 15:45:20,704 - shuffle: "True"
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Plugins:
2023-10-23 15:45:20,704 - TensorboardLogger
2023-10-23 15:45:20,704 - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 15:45:20,704 - metric: "('micro avg', 'f1-score')"
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Computation:
2023-10-23 15:45:20,704 - compute on device: cuda:0
2023-10-23 15:45:20,704 - embedding storage: none
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:20,704 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 15:45:21,458 epoch 1 - iter 13/138 - loss 3.19724143 - time (sec): 0.75 - samples/sec: 2797.24 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:45:22,219 epoch 1 - iter 26/138 - loss 2.76719642 - time (sec): 1.51 - samples/sec: 2812.76 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:45:22,939 epoch 1 - iter 39/138 - loss 2.27990881 - time (sec): 2.23 - samples/sec: 2769.62 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:45:23,707 epoch 1 - iter 52/138 - loss 1.87919582 - time (sec): 3.00 - samples/sec: 2883.32 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:45:24,444 epoch 1 - iter 65/138 - loss 1.68296880 - time (sec): 3.74 - samples/sec: 2837.09 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:45:25,198 epoch 1 - iter 78/138 - loss 1.47784903 - time (sec): 4.49 - samples/sec: 2858.47 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:45:25,974 epoch 1 - iter 91/138 - loss 1.33890195 - time (sec): 5.27 - samples/sec: 2799.70 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:45:26,758 epoch 1 - iter 104/138 - loss 1.19646330 - time (sec): 6.05 - samples/sec: 2862.84 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:45:27,491 epoch 1 - iter 117/138 - loss 1.09649998 - time (sec): 6.79 - samples/sec: 2869.11 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:45:28,210 epoch 1 - iter 130/138 - loss 1.02207775 - time (sec): 7.50 - samples/sec: 2888.81 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:45:28,673 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:28,673 EPOCH 1 done: loss 0.9842 - lr: 0.000028
2023-10-23 15:45:29,262 DEV : loss 0.2637031376361847 - f1-score (micro avg) 0.6608
2023-10-23 15:45:29,268 saving best model
2023-10-23 15:45:29,668 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:30,399 epoch 2 - iter 13/138 - loss 0.28211232 - time (sec): 0.73 - samples/sec: 2905.37 - lr: 0.000030 - momentum: 0.000000
2023-10-23 15:45:31,138 epoch 2 - iter 26/138 - loss 0.23645117 - time (sec): 1.47 - samples/sec: 3020.01 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:45:31,865 epoch 2 - iter 39/138 - loss 0.22703358 - time (sec): 2.20 - samples/sec: 3079.58 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:45:32,595 epoch 2 - iter 52/138 - loss 0.20824501 - time (sec): 2.93 - samples/sec: 3097.73 - lr: 0.000029 - momentum: 0.000000
2023-10-23 15:45:33,325 epoch 2 - iter 65/138 - loss 0.20724269 - time (sec): 3.66 - samples/sec: 3049.60 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:45:34,054 epoch 2 - iter 78/138 - loss 0.19916937 - time (sec): 4.38 - samples/sec: 3051.76 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:45:34,793 epoch 2 - iter 91/138 - loss 0.19649440 - time (sec): 5.12 - samples/sec: 3032.09 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:45:35,531 epoch 2 - iter 104/138 - loss 0.19268046 - time (sec): 5.86 - samples/sec: 3006.97 - lr: 0.000028 - momentum: 0.000000
2023-10-23 15:45:36,270 epoch 2 - iter 117/138 - loss 0.18827503 - time (sec): 6.60 - samples/sec: 2961.56 - lr: 0.000027 - momentum: 0.000000
2023-10-23 15:45:36,989 epoch 2 - iter 130/138 - loss 0.18348349 - time (sec): 7.32 - samples/sec: 2951.24 - lr: 0.000027 - momentum: 0.000000
2023-10-23 15:45:37,429 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:37,429 EPOCH 2 done: loss 0.1787 - lr: 0.000027
2023-10-23 15:45:37,959 DEV : loss 0.11417855322360992 - f1-score (micro avg) 0.8383
2023-10-23 15:45:37,965 saving best model
2023-10-23 15:45:38,486 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:39,203 epoch 3 - iter 13/138 - loss 0.10319665 - time (sec): 0.72 - samples/sec: 2882.11 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:45:39,918 epoch 3 - iter 26/138 - loss 0.12345856 - time (sec): 1.43 - samples/sec: 2842.55 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:45:40,633 epoch 3 - iter 39/138 - loss 0.10479944 - time (sec): 2.15 - samples/sec: 2931.77 - lr: 0.000026 - momentum: 0.000000
2023-10-23 15:45:41,366 epoch 3 - iter 52/138 - loss 0.09914611 - time (sec): 2.88 - samples/sec: 2899.42 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:45:42,091 epoch 3 - iter 65/138 - loss 0.09899777 - time (sec): 3.60 - samples/sec: 2853.25 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:45:42,825 epoch 3 - iter 78/138 - loss 0.09442590 - time (sec): 4.34 - samples/sec: 2890.44 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:45:43,552 epoch 3 - iter 91/138 - loss 0.09932234 - time (sec): 5.06 - samples/sec: 2903.82 - lr: 0.000025 - momentum: 0.000000
2023-10-23 15:45:44,285 epoch 3 - iter 104/138 - loss 0.09677320 - time (sec): 5.80 - samples/sec: 2914.91 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:45:45,028 epoch 3 - iter 117/138 - loss 0.09735892 - time (sec): 6.54 - samples/sec: 2929.20 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:45:45,787 epoch 3 - iter 130/138 - loss 0.09842761 - time (sec): 7.30 - samples/sec: 2957.18 - lr: 0.000024 - momentum: 0.000000
2023-10-23 15:45:46,248 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:46,248 EPOCH 3 done: loss 0.0976 - lr: 0.000024
2023-10-23 15:45:46,785 DEV : loss 0.11052478104829788 - f1-score (micro avg) 0.8561
2023-10-23 15:45:46,791 saving best model
2023-10-23 15:45:47,338 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:48,055 epoch 4 - iter 13/138 - loss 0.05429172 - time (sec): 0.72 - samples/sec: 3108.04 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:45:48,769 epoch 4 - iter 26/138 - loss 0.06880590 - time (sec): 1.43 - samples/sec: 2926.31 - lr: 0.000023 - momentum: 0.000000
2023-10-23 15:45:49,509 epoch 4 - iter 39/138 - loss 0.06536197 - time (sec): 2.17 - samples/sec: 2878.70 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:45:50,329 epoch 4 - iter 52/138 - loss 0.06633934 - time (sec): 2.99 - samples/sec: 2785.88 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:45:51,093 epoch 4 - iter 65/138 - loss 0.05923637 - time (sec): 3.75 - samples/sec: 2732.95 - lr: 0.000022 - momentum: 0.000000
2023-10-23 15:45:51,893 epoch 4 - iter 78/138 - loss 0.06130330 - time (sec): 4.55 - samples/sec: 2740.28 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:45:52,664 epoch 4 - iter 91/138 - loss 0.06339566 - time (sec): 5.32 - samples/sec: 2772.24 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:45:53,410 epoch 4 - iter 104/138 - loss 0.06287406 - time (sec): 6.07 - samples/sec: 2804.47 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:45:54,195 epoch 4 - iter 117/138 - loss 0.06738814 - time (sec): 6.86 - samples/sec: 2815.45 - lr: 0.000021 - momentum: 0.000000
2023-10-23 15:45:54,976 epoch 4 - iter 130/138 - loss 0.06977085 - time (sec): 7.64 - samples/sec: 2801.72 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:45:55,461 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:55,462 EPOCH 4 done: loss 0.0682 - lr: 0.000020
2023-10-23 15:45:56,002 DEV : loss 0.12191484868526459 - f1-score (micro avg) 0.8525
2023-10-23 15:45:56,008 ----------------------------------------------------------------------------------------------------
2023-10-23 15:45:56,772 epoch 5 - iter 13/138 - loss 0.05204482 - time (sec): 0.76 - samples/sec: 2725.06 - lr: 0.000020 - momentum: 0.000000
2023-10-23 15:45:57,535 epoch 5 - iter 26/138 - loss 0.04270482 - time (sec): 1.53 - samples/sec: 2765.10 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:45:58,316 epoch 5 - iter 39/138 - loss 0.05189148 - time (sec): 2.31 - samples/sec: 2775.05 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:45:59,077 epoch 5 - iter 52/138 - loss 0.05066165 - time (sec): 3.07 - samples/sec: 2810.13 - lr: 0.000019 - momentum: 0.000000
2023-10-23 15:45:59,823 epoch 5 - iter 65/138 - loss 0.04849827 - time (sec): 3.81 - samples/sec: 2810.73 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:46:00,558 epoch 5 - iter 78/138 - loss 0.05075800 - time (sec): 4.55 - samples/sec: 2872.86 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:46:01,281 epoch 5 - iter 91/138 - loss 0.05255442 - time (sec): 5.27 - samples/sec: 2855.43 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:46:02,021 epoch 5 - iter 104/138 - loss 0.05109410 - time (sec): 6.01 - samples/sec: 2826.82 - lr: 0.000018 - momentum: 0.000000
2023-10-23 15:46:02,759 epoch 5 - iter 117/138 - loss 0.05205831 - time (sec): 6.75 - samples/sec: 2876.34 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:46:03,501 epoch 5 - iter 130/138 - loss 0.05049339 - time (sec): 7.49 - samples/sec: 2884.60 - lr: 0.000017 - momentum: 0.000000
2023-10-23 15:46:03,952 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:03,952 EPOCH 5 done: loss 0.0485 - lr: 0.000017
2023-10-23 15:46:04,497 DEV : loss 0.13699379563331604 - f1-score (micro avg) 0.8779
2023-10-23 15:46:04,503 saving best model
2023-10-23 15:46:05,045 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:05,792 epoch 6 - iter 13/138 - loss 0.02970998 - time (sec): 0.74 - samples/sec: 2833.02 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:46:06,563 epoch 6 - iter 26/138 - loss 0.04688615 - time (sec): 1.51 - samples/sec: 2901.61 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:46:07,321 epoch 6 - iter 39/138 - loss 0.04223240 - time (sec): 2.27 - samples/sec: 2860.93 - lr: 0.000016 - momentum: 0.000000
2023-10-23 15:46:08,072 epoch 6 - iter 52/138 - loss 0.03535856 - time (sec): 3.02 - samples/sec: 2838.96 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:46:08,804 epoch 6 - iter 65/138 - loss 0.03293734 - time (sec): 3.75 - samples/sec: 2851.14 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:46:09,564 epoch 6 - iter 78/138 - loss 0.03132917 - time (sec): 4.51 - samples/sec: 2937.99 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:46:10,329 epoch 6 - iter 91/138 - loss 0.03035412 - time (sec): 5.28 - samples/sec: 2925.95 - lr: 0.000015 - momentum: 0.000000
2023-10-23 15:46:11,059 epoch 6 - iter 104/138 - loss 0.03635085 - time (sec): 6.01 - samples/sec: 2897.63 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:46:11,799 epoch 6 - iter 117/138 - loss 0.03792811 - time (sec): 6.75 - samples/sec: 2906.81 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:46:12,534 epoch 6 - iter 130/138 - loss 0.03734866 - time (sec): 7.48 - samples/sec: 2868.22 - lr: 0.000014 - momentum: 0.000000
2023-10-23 15:46:12,987 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:12,988 EPOCH 6 done: loss 0.0372 - lr: 0.000014
2023-10-23 15:46:13,519 DEV : loss 0.139994814991951 - f1-score (micro avg) 0.8785
2023-10-23 15:46:13,524 saving best model
2023-10-23 15:46:14,054 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:14,817 epoch 7 - iter 13/138 - loss 0.00842643 - time (sec): 0.76 - samples/sec: 2797.23 - lr: 0.000013 - momentum: 0.000000
2023-10-23 15:46:15,575 epoch 7 - iter 26/138 - loss 0.01783786 - time (sec): 1.52 - samples/sec: 2846.49 - lr: 0.000013 - momentum: 0.000000
2023-10-23 15:46:16,341 epoch 7 - iter 39/138 - loss 0.04117613 - time (sec): 2.28 - samples/sec: 2841.39 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:46:17,120 epoch 7 - iter 52/138 - loss 0.03560924 - time (sec): 3.06 - samples/sec: 2927.84 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:46:17,877 epoch 7 - iter 65/138 - loss 0.03352044 - time (sec): 3.82 - samples/sec: 2870.05 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:46:18,622 epoch 7 - iter 78/138 - loss 0.03277726 - time (sec): 4.56 - samples/sec: 2886.77 - lr: 0.000012 - momentum: 0.000000
2023-10-23 15:46:19,352 epoch 7 - iter 91/138 - loss 0.03439841 - time (sec): 5.29 - samples/sec: 2866.31 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:46:20,108 epoch 7 - iter 104/138 - loss 0.03154978 - time (sec): 6.05 - samples/sec: 2891.32 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:46:20,868 epoch 7 - iter 117/138 - loss 0.03023976 - time (sec): 6.81 - samples/sec: 2891.55 - lr: 0.000011 - momentum: 0.000000
2023-10-23 15:46:21,610 epoch 7 - iter 130/138 - loss 0.02991660 - time (sec): 7.55 - samples/sec: 2868.59 - lr: 0.000010 - momentum: 0.000000
2023-10-23 15:46:22,079 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:22,079 EPOCH 7 done: loss 0.0299 - lr: 0.000010
2023-10-23 15:46:22,617 DEV : loss 0.14777213335037231 - f1-score (micro avg) 0.897
2023-10-23 15:46:22,623 saving best model
2023-10-23 15:46:23,152 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:23,905 epoch 8 - iter 13/138 - loss 0.00644670 - time (sec): 0.75 - samples/sec: 2716.21 - lr: 0.000010 - momentum: 0.000000
2023-10-23 15:46:24,659 epoch 8 - iter 26/138 - loss 0.01964341 - time (sec): 1.50 - samples/sec: 2951.47 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:46:25,389 epoch 8 - iter 39/138 - loss 0.01628448 - time (sec): 2.23 - samples/sec: 2947.00 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:46:26,144 epoch 8 - iter 52/138 - loss 0.02420344 - time (sec): 2.99 - samples/sec: 2926.35 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:46:26,896 epoch 8 - iter 65/138 - loss 0.02319288 - time (sec): 3.74 - samples/sec: 2863.46 - lr: 0.000009 - momentum: 0.000000
2023-10-23 15:46:27,676 epoch 8 - iter 78/138 - loss 0.02179369 - time (sec): 4.52 - samples/sec: 2866.48 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:46:28,411 epoch 8 - iter 91/138 - loss 0.02597878 - time (sec): 5.26 - samples/sec: 2886.46 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:46:29,155 epoch 8 - iter 104/138 - loss 0.02487449 - time (sec): 6.00 - samples/sec: 2852.95 - lr: 0.000008 - momentum: 0.000000
2023-10-23 15:46:29,879 epoch 8 - iter 117/138 - loss 0.02372089 - time (sec): 6.72 - samples/sec: 2861.21 - lr: 0.000007 - momentum: 0.000000
2023-10-23 15:46:30,603 epoch 8 - iter 130/138 - loss 0.02257563 - time (sec): 7.45 - samples/sec: 2886.61 - lr: 0.000007 - momentum: 0.000000
2023-10-23 15:46:31,039 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:31,039 EPOCH 8 done: loss 0.0222 - lr: 0.000007
2023-10-23 15:46:31,571 DEV : loss 0.15574227273464203 - f1-score (micro avg) 0.8838
2023-10-23 15:46:31,577 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:32,300 epoch 9 - iter 13/138 - loss 0.00660491 - time (sec): 0.72 - samples/sec: 2887.41 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:46:33,022 epoch 9 - iter 26/138 - loss 0.01041455 - time (sec): 1.44 - samples/sec: 2851.88 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:46:33,740 epoch 9 - iter 39/138 - loss 0.01005111 - time (sec): 2.16 - samples/sec: 2913.14 - lr: 0.000006 - momentum: 0.000000
2023-10-23 15:46:34,486 epoch 9 - iter 52/138 - loss 0.01334769 - time (sec): 2.91 - samples/sec: 2895.30 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:46:35,204 epoch 9 - iter 65/138 - loss 0.01186627 - time (sec): 3.63 - samples/sec: 2936.89 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:46:35,960 epoch 9 - iter 78/138 - loss 0.01168564 - time (sec): 4.38 - samples/sec: 2939.27 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:46:36,703 epoch 9 - iter 91/138 - loss 0.01330314 - time (sec): 5.13 - samples/sec: 2952.30 - lr: 0.000005 - momentum: 0.000000
2023-10-23 15:46:37,441 epoch 9 - iter 104/138 - loss 0.01202213 - time (sec): 5.86 - samples/sec: 2950.18 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:46:38,187 epoch 9 - iter 117/138 - loss 0.01286806 - time (sec): 6.61 - samples/sec: 2935.01 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:46:38,919 epoch 9 - iter 130/138 - loss 0.01425818 - time (sec): 7.34 - samples/sec: 2935.17 - lr: 0.000004 - momentum: 0.000000
2023-10-23 15:46:39,337 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:39,337 EPOCH 9 done: loss 0.0178 - lr: 0.000004
2023-10-23 15:46:39,872 DEV : loss 0.16283106803894043 - f1-score (micro avg) 0.8916
2023-10-23 15:46:39,877 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:40,602 epoch 10 - iter 13/138 - loss 0.00433738 - time (sec): 0.72 - samples/sec: 2968.37 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:46:41,333 epoch 10 - iter 26/138 - loss 0.00331970 - time (sec): 1.45 - samples/sec: 2916.40 - lr: 0.000003 - momentum: 0.000000
2023-10-23 15:46:42,080 epoch 10 - iter 39/138 - loss 0.00840588 - time (sec): 2.20 - samples/sec: 3008.39 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:46:42,816 epoch 10 - iter 52/138 - loss 0.00903499 - time (sec): 2.94 - samples/sec: 2948.34 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:46:43,536 epoch 10 - iter 65/138 - loss 0.01232935 - time (sec): 3.66 - samples/sec: 2906.92 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:46:44,266 epoch 10 - iter 78/138 - loss 0.01223517 - time (sec): 4.39 - samples/sec: 2933.48 - lr: 0.000002 - momentum: 0.000000
2023-10-23 15:46:44,999 epoch 10 - iter 91/138 - loss 0.01251053 - time (sec): 5.12 - samples/sec: 2922.86 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:46:45,750 epoch 10 - iter 104/138 - loss 0.01268933 - time (sec): 5.87 - samples/sec: 2919.33 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:46:46,455 epoch 10 - iter 117/138 - loss 0.01157601 - time (sec): 6.58 - samples/sec: 2928.72 - lr: 0.000001 - momentum: 0.000000
2023-10-23 15:46:47,182 epoch 10 - iter 130/138 - loss 0.01176484 - time (sec): 7.30 - samples/sec: 2944.52 - lr: 0.000000 - momentum: 0.000000
2023-10-23 15:46:47,618 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:47,619 EPOCH 10 done: loss 0.0140 - lr: 0.000000
2023-10-23 15:46:48,151 DEV : loss 0.16455598175525665 - f1-score (micro avg) 0.8926
2023-10-23 15:46:48,549 ----------------------------------------------------------------------------------------------------
2023-10-23 15:46:48,550 Loading model from best epoch ...
2023-10-23 15:46:50,228 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
2023-10-23 15:46:50,881
Results:
- F-score (micro) 0.9084
- F-score (macro) 0.8767
- Accuracy 0.8382
By class:
precision recall f1-score support
scope 0.8771 0.8920 0.8845 176
pers 0.9542 0.9766 0.9653 128
work 0.8986 0.8378 0.8671 74
object 1.0000 1.0000 1.0000 2
loc 1.0000 0.5000 0.6667 2
micro avg 0.9084 0.9084 0.9084 382
macro avg 0.9460 0.8413 0.8767 382
weighted avg 0.9084 0.9084 0.9077 382
2023-10-23 15:46:50,881 ----------------------------------------------------------------------------------------------------
|