File size: 23,862 Bytes
415103f |
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 22:32:35,467 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,468 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()
)"
2023-10-13 22:32:35,468 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,468 MultiCorpus: 7936 train + 992 dev + 992 test sentences
- NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Train: 7936 sentences
2023-10-13 22:32:35,469 (train_with_dev=False, train_with_test=False)
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Training Params:
2023-10-13 22:32:35,469 - learning_rate: "5e-05"
2023-10-13 22:32:35,469 - mini_batch_size: "8"
2023-10-13 22:32:35,469 - max_epochs: "10"
2023-10-13 22:32:35,469 - shuffle: "True"
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Plugins:
2023-10-13 22:32:35,469 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 22:32:35,469 - metric: "('micro avg', 'f1-score')"
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Computation:
2023-10-13 22:32:35,469 - compute on device: cuda:0
2023-10-13 22:32:35,469 - embedding storage: none
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:35,469 ----------------------------------------------------------------------------------------------------
2023-10-13 22:32:42,105 epoch 1 - iter 99/992 - loss 1.97625335 - time (sec): 6.63 - samples/sec: 2619.78 - lr: 0.000005 - momentum: 0.000000
2023-10-13 22:32:48,119 epoch 1 - iter 198/992 - loss 1.20445619 - time (sec): 12.65 - samples/sec: 2622.63 - lr: 0.000010 - momentum: 0.000000
2023-10-13 22:32:53,990 epoch 1 - iter 297/992 - loss 0.90127542 - time (sec): 18.52 - samples/sec: 2645.29 - lr: 0.000015 - momentum: 0.000000
2023-10-13 22:32:59,842 epoch 1 - iter 396/992 - loss 0.73031528 - time (sec): 24.37 - samples/sec: 2664.09 - lr: 0.000020 - momentum: 0.000000
2023-10-13 22:33:05,553 epoch 1 - iter 495/992 - loss 0.61732090 - time (sec): 30.08 - samples/sec: 2695.40 - lr: 0.000025 - momentum: 0.000000
2023-10-13 22:33:11,400 epoch 1 - iter 594/992 - loss 0.53727279 - time (sec): 35.93 - samples/sec: 2719.61 - lr: 0.000030 - momentum: 0.000000
2023-10-13 22:33:17,199 epoch 1 - iter 693/992 - loss 0.48213515 - time (sec): 41.73 - samples/sec: 2724.53 - lr: 0.000035 - momentum: 0.000000
2023-10-13 22:33:23,140 epoch 1 - iter 792/992 - loss 0.43768861 - time (sec): 47.67 - samples/sec: 2731.72 - lr: 0.000040 - momentum: 0.000000
2023-10-13 22:33:29,370 epoch 1 - iter 891/992 - loss 0.40269124 - time (sec): 53.90 - samples/sec: 2727.47 - lr: 0.000045 - momentum: 0.000000
2023-10-13 22:33:35,471 epoch 1 - iter 990/992 - loss 0.37457303 - time (sec): 60.00 - samples/sec: 2724.88 - lr: 0.000050 - momentum: 0.000000
2023-10-13 22:33:35,623 ----------------------------------------------------------------------------------------------------
2023-10-13 22:33:35,624 EPOCH 1 done: loss 0.3735 - lr: 0.000050
2023-10-13 22:33:38,899 DEV : loss 0.10837739706039429 - f1-score (micro avg) 0.6822
2023-10-13 22:33:38,924 saving best model
2023-10-13 22:33:39,350 ----------------------------------------------------------------------------------------------------
2023-10-13 22:33:45,003 epoch 2 - iter 99/992 - loss 0.10295012 - time (sec): 5.65 - samples/sec: 2750.21 - lr: 0.000049 - momentum: 0.000000
2023-10-13 22:33:50,901 epoch 2 - iter 198/992 - loss 0.10973798 - time (sec): 11.55 - samples/sec: 2718.58 - lr: 0.000049 - momentum: 0.000000
2023-10-13 22:33:56,904 epoch 2 - iter 297/992 - loss 0.10543489 - time (sec): 17.55 - samples/sec: 2761.93 - lr: 0.000048 - momentum: 0.000000
2023-10-13 22:34:02,862 epoch 2 - iter 396/992 - loss 0.10381763 - time (sec): 23.51 - samples/sec: 2769.50 - lr: 0.000048 - momentum: 0.000000
2023-10-13 22:34:08,919 epoch 2 - iter 495/992 - loss 0.10311459 - time (sec): 29.57 - samples/sec: 2751.80 - lr: 0.000047 - momentum: 0.000000
2023-10-13 22:34:14,729 epoch 2 - iter 594/992 - loss 0.10171878 - time (sec): 35.38 - samples/sec: 2751.64 - lr: 0.000047 - momentum: 0.000000
2023-10-13 22:34:20,492 epoch 2 - iter 693/992 - loss 0.09979812 - time (sec): 41.14 - samples/sec: 2754.11 - lr: 0.000046 - momentum: 0.000000
2023-10-13 22:34:26,580 epoch 2 - iter 792/992 - loss 0.10186744 - time (sec): 47.23 - samples/sec: 2753.33 - lr: 0.000046 - momentum: 0.000000
2023-10-13 22:34:32,670 epoch 2 - iter 891/992 - loss 0.10186196 - time (sec): 53.32 - samples/sec: 2741.16 - lr: 0.000045 - momentum: 0.000000
2023-10-13 22:34:38,791 epoch 2 - iter 990/992 - loss 0.10164595 - time (sec): 59.44 - samples/sec: 2752.43 - lr: 0.000044 - momentum: 0.000000
2023-10-13 22:34:38,920 ----------------------------------------------------------------------------------------------------
2023-10-13 22:34:38,920 EPOCH 2 done: loss 0.1015 - lr: 0.000044
2023-10-13 22:34:43,263 DEV : loss 0.08593912422657013 - f1-score (micro avg) 0.7422
2023-10-13 22:34:43,287 saving best model
2023-10-13 22:34:43,770 ----------------------------------------------------------------------------------------------------
2023-10-13 22:34:49,664 epoch 3 - iter 99/992 - loss 0.08176039 - time (sec): 5.89 - samples/sec: 2717.35 - lr: 0.000044 - momentum: 0.000000
2023-10-13 22:34:55,620 epoch 3 - iter 198/992 - loss 0.07620139 - time (sec): 11.85 - samples/sec: 2720.74 - lr: 0.000043 - momentum: 0.000000
2023-10-13 22:35:01,359 epoch 3 - iter 297/992 - loss 0.07242783 - time (sec): 17.59 - samples/sec: 2743.33 - lr: 0.000043 - momentum: 0.000000
2023-10-13 22:35:07,179 epoch 3 - iter 396/992 - loss 0.07362963 - time (sec): 23.41 - samples/sec: 2759.74 - lr: 0.000042 - momentum: 0.000000
2023-10-13 22:35:13,060 epoch 3 - iter 495/992 - loss 0.07299823 - time (sec): 29.29 - samples/sec: 2761.91 - lr: 0.000042 - momentum: 0.000000
2023-10-13 22:35:19,048 epoch 3 - iter 594/992 - loss 0.07330654 - time (sec): 35.27 - samples/sec: 2761.44 - lr: 0.000041 - momentum: 0.000000
2023-10-13 22:35:25,090 epoch 3 - iter 693/992 - loss 0.07489880 - time (sec): 41.32 - samples/sec: 2747.94 - lr: 0.000041 - momentum: 0.000000
2023-10-13 22:35:31,036 epoch 3 - iter 792/992 - loss 0.07562313 - time (sec): 47.26 - samples/sec: 2760.10 - lr: 0.000040 - momentum: 0.000000
2023-10-13 22:35:37,046 epoch 3 - iter 891/992 - loss 0.07372307 - time (sec): 53.27 - samples/sec: 2766.49 - lr: 0.000039 - momentum: 0.000000
2023-10-13 22:35:42,895 epoch 3 - iter 990/992 - loss 0.07373060 - time (sec): 59.12 - samples/sec: 2769.61 - lr: 0.000039 - momentum: 0.000000
2023-10-13 22:35:42,996 ----------------------------------------------------------------------------------------------------
2023-10-13 22:35:42,996 EPOCH 3 done: loss 0.0737 - lr: 0.000039
2023-10-13 22:35:46,388 DEV : loss 0.10231217741966248 - f1-score (micro avg) 0.7589
2023-10-13 22:35:46,412 saving best model
2023-10-13 22:35:46,925 ----------------------------------------------------------------------------------------------------
2023-10-13 22:35:52,809 epoch 4 - iter 99/992 - loss 0.05134981 - time (sec): 5.88 - samples/sec: 2723.80 - lr: 0.000038 - momentum: 0.000000
2023-10-13 22:35:59,141 epoch 4 - iter 198/992 - loss 0.05017639 - time (sec): 12.21 - samples/sec: 2716.64 - lr: 0.000038 - momentum: 0.000000
2023-10-13 22:36:05,090 epoch 4 - iter 297/992 - loss 0.04727321 - time (sec): 18.16 - samples/sec: 2718.31 - lr: 0.000037 - momentum: 0.000000
2023-10-13 22:36:10,869 epoch 4 - iter 396/992 - loss 0.04808307 - time (sec): 23.94 - samples/sec: 2749.13 - lr: 0.000037 - momentum: 0.000000
2023-10-13 22:36:16,706 epoch 4 - iter 495/992 - loss 0.04713806 - time (sec): 29.78 - samples/sec: 2768.47 - lr: 0.000036 - momentum: 0.000000
2023-10-13 22:36:22,555 epoch 4 - iter 594/992 - loss 0.04822839 - time (sec): 35.63 - samples/sec: 2769.58 - lr: 0.000036 - momentum: 0.000000
2023-10-13 22:36:28,395 epoch 4 - iter 693/992 - loss 0.04982517 - time (sec): 41.47 - samples/sec: 2764.17 - lr: 0.000035 - momentum: 0.000000
2023-10-13 22:36:34,340 epoch 4 - iter 792/992 - loss 0.05129636 - time (sec): 47.41 - samples/sec: 2765.07 - lr: 0.000034 - momentum: 0.000000
2023-10-13 22:36:39,871 epoch 4 - iter 891/992 - loss 0.05132015 - time (sec): 52.94 - samples/sec: 2782.54 - lr: 0.000034 - momentum: 0.000000
2023-10-13 22:36:46,060 epoch 4 - iter 990/992 - loss 0.05099074 - time (sec): 59.13 - samples/sec: 2765.99 - lr: 0.000033 - momentum: 0.000000
2023-10-13 22:36:46,190 ----------------------------------------------------------------------------------------------------
2023-10-13 22:36:46,190 EPOCH 4 done: loss 0.0510 - lr: 0.000033
2023-10-13 22:36:49,798 DEV : loss 0.13146057724952698 - f1-score (micro avg) 0.7587
2023-10-13 22:36:49,822 ----------------------------------------------------------------------------------------------------
2023-10-13 22:36:55,595 epoch 5 - iter 99/992 - loss 0.03914982 - time (sec): 5.77 - samples/sec: 2761.13 - lr: 0.000033 - momentum: 0.000000
2023-10-13 22:37:01,451 epoch 5 - iter 198/992 - loss 0.03993438 - time (sec): 11.63 - samples/sec: 2786.06 - lr: 0.000032 - momentum: 0.000000
2023-10-13 22:37:07,215 epoch 5 - iter 297/992 - loss 0.03848388 - time (sec): 17.39 - samples/sec: 2811.92 - lr: 0.000032 - momentum: 0.000000
2023-10-13 22:37:13,113 epoch 5 - iter 396/992 - loss 0.03928207 - time (sec): 23.29 - samples/sec: 2821.97 - lr: 0.000031 - momentum: 0.000000
2023-10-13 22:37:19,287 epoch 5 - iter 495/992 - loss 0.04014864 - time (sec): 29.46 - samples/sec: 2803.85 - lr: 0.000031 - momentum: 0.000000
2023-10-13 22:37:25,177 epoch 5 - iter 594/992 - loss 0.04251426 - time (sec): 35.35 - samples/sec: 2787.71 - lr: 0.000030 - momentum: 0.000000
2023-10-13 22:37:30,988 epoch 5 - iter 693/992 - loss 0.04162004 - time (sec): 41.17 - samples/sec: 2781.73 - lr: 0.000029 - momentum: 0.000000
2023-10-13 22:37:36,743 epoch 5 - iter 792/992 - loss 0.04073969 - time (sec): 46.92 - samples/sec: 2780.60 - lr: 0.000029 - momentum: 0.000000
2023-10-13 22:37:43,244 epoch 5 - iter 891/992 - loss 0.04252912 - time (sec): 53.42 - samples/sec: 2758.70 - lr: 0.000028 - momentum: 0.000000
2023-10-13 22:37:48,877 epoch 5 - iter 990/992 - loss 0.04211590 - time (sec): 59.05 - samples/sec: 2768.82 - lr: 0.000028 - momentum: 0.000000
2023-10-13 22:37:49,038 ----------------------------------------------------------------------------------------------------
2023-10-13 22:37:49,038 EPOCH 5 done: loss 0.0421 - lr: 0.000028
2023-10-13 22:37:52,595 DEV : loss 0.15390822291374207 - f1-score (micro avg) 0.7563
2023-10-13 22:37:52,618 ----------------------------------------------------------------------------------------------------
2023-10-13 22:37:58,397 epoch 6 - iter 99/992 - loss 0.02447859 - time (sec): 5.78 - samples/sec: 2857.09 - lr: 0.000027 - momentum: 0.000000
2023-10-13 22:38:04,483 epoch 6 - iter 198/992 - loss 0.02281979 - time (sec): 11.86 - samples/sec: 2814.99 - lr: 0.000027 - momentum: 0.000000
2023-10-13 22:38:10,375 epoch 6 - iter 297/992 - loss 0.02449871 - time (sec): 17.76 - samples/sec: 2836.72 - lr: 0.000026 - momentum: 0.000000
2023-10-13 22:38:16,330 epoch 6 - iter 396/992 - loss 0.02562274 - time (sec): 23.71 - samples/sec: 2816.53 - lr: 0.000026 - momentum: 0.000000
2023-10-13 22:38:22,242 epoch 6 - iter 495/992 - loss 0.02613520 - time (sec): 29.62 - samples/sec: 2780.83 - lr: 0.000025 - momentum: 0.000000
2023-10-13 22:38:28,192 epoch 6 - iter 594/992 - loss 0.02619509 - time (sec): 35.57 - samples/sec: 2768.90 - lr: 0.000024 - momentum: 0.000000
2023-10-13 22:38:33,861 epoch 6 - iter 693/992 - loss 0.02665766 - time (sec): 41.24 - samples/sec: 2754.02 - lr: 0.000024 - momentum: 0.000000
2023-10-13 22:38:39,952 epoch 6 - iter 792/992 - loss 0.02787193 - time (sec): 47.33 - samples/sec: 2770.66 - lr: 0.000023 - momentum: 0.000000
2023-10-13 22:38:45,783 epoch 6 - iter 891/992 - loss 0.02982103 - time (sec): 53.16 - samples/sec: 2766.54 - lr: 0.000023 - momentum: 0.000000
2023-10-13 22:38:51,599 epoch 6 - iter 990/992 - loss 0.02967950 - time (sec): 58.98 - samples/sec: 2772.64 - lr: 0.000022 - momentum: 0.000000
2023-10-13 22:38:51,724 ----------------------------------------------------------------------------------------------------
2023-10-13 22:38:51,724 EPOCH 6 done: loss 0.0296 - lr: 0.000022
2023-10-13 22:38:55,149 DEV : loss 0.19599080085754395 - f1-score (micro avg) 0.7572
2023-10-13 22:38:55,170 ----------------------------------------------------------------------------------------------------
2023-10-13 22:39:00,912 epoch 7 - iter 99/992 - loss 0.02376152 - time (sec): 5.74 - samples/sec: 2826.61 - lr: 0.000022 - momentum: 0.000000
2023-10-13 22:39:06,655 epoch 7 - iter 198/992 - loss 0.01958953 - time (sec): 11.48 - samples/sec: 2810.22 - lr: 0.000021 - momentum: 0.000000
2023-10-13 22:39:12,687 epoch 7 - iter 297/992 - loss 0.01962767 - time (sec): 17.52 - samples/sec: 2831.96 - lr: 0.000021 - momentum: 0.000000
2023-10-13 22:39:18,688 epoch 7 - iter 396/992 - loss 0.01948507 - time (sec): 23.52 - samples/sec: 2822.98 - lr: 0.000020 - momentum: 0.000000
2023-10-13 22:39:24,654 epoch 7 - iter 495/992 - loss 0.01985791 - time (sec): 29.48 - samples/sec: 2810.77 - lr: 0.000019 - momentum: 0.000000
2023-10-13 22:39:30,455 epoch 7 - iter 594/992 - loss 0.02068738 - time (sec): 35.28 - samples/sec: 2793.89 - lr: 0.000019 - momentum: 0.000000
2023-10-13 22:39:36,232 epoch 7 - iter 693/992 - loss 0.02241871 - time (sec): 41.06 - samples/sec: 2796.58 - lr: 0.000018 - momentum: 0.000000
2023-10-13 22:39:41,978 epoch 7 - iter 792/992 - loss 0.02181208 - time (sec): 46.81 - samples/sec: 2804.38 - lr: 0.000018 - momentum: 0.000000
2023-10-13 22:39:47,996 epoch 7 - iter 891/992 - loss 0.02217841 - time (sec): 52.83 - samples/sec: 2783.90 - lr: 0.000017 - momentum: 0.000000
2023-10-13 22:39:54,016 epoch 7 - iter 990/992 - loss 0.02172978 - time (sec): 58.84 - samples/sec: 2783.19 - lr: 0.000017 - momentum: 0.000000
2023-10-13 22:39:54,115 ----------------------------------------------------------------------------------------------------
2023-10-13 22:39:54,115 EPOCH 7 done: loss 0.0217 - lr: 0.000017
2023-10-13 22:39:57,955 DEV : loss 0.18885478377342224 - f1-score (micro avg) 0.765
2023-10-13 22:39:57,976 saving best model
2023-10-13 22:39:58,428 ----------------------------------------------------------------------------------------------------
2023-10-13 22:40:04,318 epoch 8 - iter 99/992 - loss 0.02286923 - time (sec): 5.88 - samples/sec: 2805.77 - lr: 0.000016 - momentum: 0.000000
2023-10-13 22:40:10,386 epoch 8 - iter 198/992 - loss 0.01729121 - time (sec): 11.95 - samples/sec: 2800.86 - lr: 0.000016 - momentum: 0.000000
2023-10-13 22:40:16,196 epoch 8 - iter 297/992 - loss 0.01585346 - time (sec): 17.76 - samples/sec: 2818.05 - lr: 0.000015 - momentum: 0.000000
2023-10-13 22:40:22,131 epoch 8 - iter 396/992 - loss 0.01479878 - time (sec): 23.70 - samples/sec: 2838.92 - lr: 0.000014 - momentum: 0.000000
2023-10-13 22:40:27,927 epoch 8 - iter 495/992 - loss 0.01559774 - time (sec): 29.49 - samples/sec: 2832.36 - lr: 0.000014 - momentum: 0.000000
2023-10-13 22:40:33,638 epoch 8 - iter 594/992 - loss 0.01479709 - time (sec): 35.20 - samples/sec: 2821.11 - lr: 0.000013 - momentum: 0.000000
2023-10-13 22:40:39,365 epoch 8 - iter 693/992 - loss 0.01447454 - time (sec): 40.93 - samples/sec: 2808.13 - lr: 0.000013 - momentum: 0.000000
2023-10-13 22:40:45,325 epoch 8 - iter 792/992 - loss 0.01516714 - time (sec): 46.89 - samples/sec: 2803.50 - lr: 0.000012 - momentum: 0.000000
2023-10-13 22:40:51,152 epoch 8 - iter 891/992 - loss 0.01551720 - time (sec): 52.72 - samples/sec: 2801.05 - lr: 0.000012 - momentum: 0.000000
2023-10-13 22:40:56,972 epoch 8 - iter 990/992 - loss 0.01557435 - time (sec): 58.54 - samples/sec: 2798.83 - lr: 0.000011 - momentum: 0.000000
2023-10-13 22:40:57,071 ----------------------------------------------------------------------------------------------------
2023-10-13 22:40:57,072 EPOCH 8 done: loss 0.0159 - lr: 0.000011
2023-10-13 22:41:00,599 DEV : loss 0.19485069811344147 - f1-score (micro avg) 0.7664
2023-10-13 22:41:00,622 saving best model
2023-10-13 22:41:01,122 ----------------------------------------------------------------------------------------------------
2023-10-13 22:41:06,817 epoch 9 - iter 99/992 - loss 0.00725184 - time (sec): 5.69 - samples/sec: 2598.12 - lr: 0.000011 - momentum: 0.000000
2023-10-13 22:41:12,615 epoch 9 - iter 198/992 - loss 0.01324789 - time (sec): 11.49 - samples/sec: 2671.94 - lr: 0.000010 - momentum: 0.000000
2023-10-13 22:41:18,618 epoch 9 - iter 297/992 - loss 0.01262387 - time (sec): 17.49 - samples/sec: 2676.85 - lr: 0.000009 - momentum: 0.000000
2023-10-13 22:41:24,527 epoch 9 - iter 396/992 - loss 0.01078576 - time (sec): 23.40 - samples/sec: 2700.15 - lr: 0.000009 - momentum: 0.000000
2023-10-13 22:41:30,687 epoch 9 - iter 495/992 - loss 0.01086785 - time (sec): 29.56 - samples/sec: 2708.13 - lr: 0.000008 - momentum: 0.000000
2023-10-13 22:41:36,631 epoch 9 - iter 594/992 - loss 0.01119434 - time (sec): 35.50 - samples/sec: 2722.13 - lr: 0.000008 - momentum: 0.000000
2023-10-13 22:41:42,383 epoch 9 - iter 693/992 - loss 0.01095970 - time (sec): 41.26 - samples/sec: 2736.96 - lr: 0.000007 - momentum: 0.000000
2023-10-13 22:41:48,299 epoch 9 - iter 792/992 - loss 0.01070482 - time (sec): 47.17 - samples/sec: 2753.00 - lr: 0.000007 - momentum: 0.000000
2023-10-13 22:41:54,240 epoch 9 - iter 891/992 - loss 0.01101838 - time (sec): 53.11 - samples/sec: 2759.58 - lr: 0.000006 - momentum: 0.000000
2023-10-13 22:42:00,495 epoch 9 - iter 990/992 - loss 0.01099219 - time (sec): 59.37 - samples/sec: 2755.51 - lr: 0.000006 - momentum: 0.000000
2023-10-13 22:42:00,600 ----------------------------------------------------------------------------------------------------
2023-10-13 22:42:00,600 EPOCH 9 done: loss 0.0110 - lr: 0.000006
2023-10-13 22:42:04,597 DEV : loss 0.20399770140647888 - f1-score (micro avg) 0.767
2023-10-13 22:42:04,619 saving best model
2023-10-13 22:42:05,118 ----------------------------------------------------------------------------------------------------
2023-10-13 22:42:11,036 epoch 10 - iter 99/992 - loss 0.00694056 - time (sec): 5.92 - samples/sec: 2777.84 - lr: 0.000005 - momentum: 0.000000
2023-10-13 22:42:17,345 epoch 10 - iter 198/992 - loss 0.00836868 - time (sec): 12.23 - samples/sec: 2802.73 - lr: 0.000004 - momentum: 0.000000
2023-10-13 22:42:22,986 epoch 10 - iter 297/992 - loss 0.00886989 - time (sec): 17.87 - samples/sec: 2785.15 - lr: 0.000004 - momentum: 0.000000
2023-10-13 22:42:28,741 epoch 10 - iter 396/992 - loss 0.00862895 - time (sec): 23.62 - samples/sec: 2804.19 - lr: 0.000003 - momentum: 0.000000
2023-10-13 22:42:35,030 epoch 10 - iter 495/992 - loss 0.00902308 - time (sec): 29.91 - samples/sec: 2785.89 - lr: 0.000003 - momentum: 0.000000
2023-10-13 22:42:40,907 epoch 10 - iter 594/992 - loss 0.00870118 - time (sec): 35.79 - samples/sec: 2776.25 - lr: 0.000002 - momentum: 0.000000
2023-10-13 22:42:46,703 epoch 10 - iter 693/992 - loss 0.00845402 - time (sec): 41.58 - samples/sec: 2756.78 - lr: 0.000002 - momentum: 0.000000
2023-10-13 22:42:52,747 epoch 10 - iter 792/992 - loss 0.00817124 - time (sec): 47.63 - samples/sec: 2751.49 - lr: 0.000001 - momentum: 0.000000
2023-10-13 22:42:58,806 epoch 10 - iter 891/992 - loss 0.00784789 - time (sec): 53.69 - samples/sec: 2751.57 - lr: 0.000001 - momentum: 0.000000
2023-10-13 22:43:04,469 epoch 10 - iter 990/992 - loss 0.00753226 - time (sec): 59.35 - samples/sec: 2757.97 - lr: 0.000000 - momentum: 0.000000
2023-10-13 22:43:04,580 ----------------------------------------------------------------------------------------------------
2023-10-13 22:43:04,580 EPOCH 10 done: loss 0.0075 - lr: 0.000000
2023-10-13 22:43:07,991 DEV : loss 0.20772945880889893 - f1-score (micro avg) 0.7698
2023-10-13 22:43:08,013 saving best model
2023-10-13 22:43:08,849 ----------------------------------------------------------------------------------------------------
2023-10-13 22:43:08,850 Loading model from best epoch ...
2023-10-13 22:43:10,240 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-13 22:43:13,645
Results:
- F-score (micro) 0.7805
- F-score (macro) 0.6917
- Accuracy 0.6599
By class:
precision recall f1-score support
LOC 0.8191 0.8641 0.8410 655
PER 0.7171 0.8296 0.7692 223
ORG 0.4912 0.4409 0.4647 127
micro avg 0.7592 0.8030 0.7805 1005
macro avg 0.6758 0.7116 0.6917 1005
weighted avg 0.7550 0.8030 0.7775 1005
2023-10-13 22:43:13,646 ----------------------------------------------------------------------------------------------------
|