File size: 24,075 Bytes
0ba8991 |
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 |
2023-10-13 11:37:23,100 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 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=21, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
- NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 Train: 3575 sentences
2023-10-13 11:37:23,101 (train_with_dev=False, train_with_test=False)
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 Training Params:
2023-10-13 11:37:23,101 - learning_rate: "3e-05"
2023-10-13 11:37:23,101 - mini_batch_size: "8"
2023-10-13 11:37:23,101 - max_epochs: "10"
2023-10-13 11:37:23,101 - shuffle: "True"
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 Plugins:
2023-10-13 11:37:23,101 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 11:37:23,101 - metric: "('micro avg', 'f1-score')"
2023-10-13 11:37:23,101 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,101 Computation:
2023-10-13 11:37:23,101 - compute on device: cuda:0
2023-10-13 11:37:23,102 - embedding storage: none
2023-10-13 11:37:23,102 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,102 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-13 11:37:23,102 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:23,102 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:27,202 epoch 1 - iter 44/447 - loss 3.14196282 - time (sec): 4.10 - samples/sec: 2319.10 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:37:29,895 epoch 1 - iter 88/447 - loss 2.47803589 - time (sec): 6.79 - samples/sec: 2559.07 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:37:32,432 epoch 1 - iter 132/447 - loss 1.88263805 - time (sec): 9.33 - samples/sec: 2683.04 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:37:35,166 epoch 1 - iter 176/447 - loss 1.52213191 - time (sec): 12.06 - samples/sec: 2772.84 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:37:37,858 epoch 1 - iter 220/447 - loss 1.30514887 - time (sec): 14.75 - samples/sec: 2816.89 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:37:40,687 epoch 1 - iter 264/447 - loss 1.13508816 - time (sec): 17.58 - samples/sec: 2865.93 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:37:43,389 epoch 1 - iter 308/447 - loss 1.01636293 - time (sec): 20.29 - samples/sec: 2907.63 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:37:46,313 epoch 1 - iter 352/447 - loss 0.91617799 - time (sec): 23.21 - samples/sec: 2931.05 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:37:49,109 epoch 1 - iter 396/447 - loss 0.84517290 - time (sec): 26.01 - samples/sec: 2934.25 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:37:52,076 epoch 1 - iter 440/447 - loss 0.78671462 - time (sec): 28.97 - samples/sec: 2948.06 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:37:52,494 ----------------------------------------------------------------------------------------------------
2023-10-13 11:37:52,495 EPOCH 1 done: loss 0.7797 - lr: 0.000029
2023-10-13 11:37:57,330 DEV : loss 0.18337313830852509 - f1-score (micro avg) 0.6258
2023-10-13 11:37:57,355 saving best model
2023-10-13 11:37:57,656 ----------------------------------------------------------------------------------------------------
2023-10-13 11:38:00,311 epoch 2 - iter 44/447 - loss 0.18448565 - time (sec): 2.65 - samples/sec: 3222.29 - lr: 0.000030 - momentum: 0.000000
2023-10-13 11:38:03,060 epoch 2 - iter 88/447 - loss 0.20795048 - time (sec): 5.40 - samples/sec: 3154.56 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:38:05,773 epoch 2 - iter 132/447 - loss 0.19839698 - time (sec): 8.12 - samples/sec: 3166.50 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:38:08,634 epoch 2 - iter 176/447 - loss 0.19080864 - time (sec): 10.98 - samples/sec: 3105.64 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:38:11,210 epoch 2 - iter 220/447 - loss 0.18472852 - time (sec): 13.55 - samples/sec: 3096.46 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:38:14,043 epoch 2 - iter 264/447 - loss 0.17431429 - time (sec): 16.39 - samples/sec: 3085.73 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:38:16,896 epoch 2 - iter 308/447 - loss 0.17213378 - time (sec): 19.24 - samples/sec: 3110.09 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:38:19,523 epoch 2 - iter 352/447 - loss 0.17060590 - time (sec): 21.86 - samples/sec: 3102.96 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:38:22,075 epoch 2 - iter 396/447 - loss 0.16910987 - time (sec): 24.42 - samples/sec: 3108.60 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:38:25,003 epoch 2 - iter 440/447 - loss 0.16480794 - time (sec): 27.34 - samples/sec: 3120.88 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:38:25,414 ----------------------------------------------------------------------------------------------------
2023-10-13 11:38:25,415 EPOCH 2 done: loss 0.1637 - lr: 0.000027
2023-10-13 11:38:33,914 DEV : loss 0.1275636851787567 - f1-score (micro avg) 0.6914
2023-10-13 11:38:33,954 saving best model
2023-10-13 11:38:34,472 ----------------------------------------------------------------------------------------------------
2023-10-13 11:38:37,334 epoch 3 - iter 44/447 - loss 0.09103184 - time (sec): 2.86 - samples/sec: 2697.32 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:38:40,169 epoch 3 - iter 88/447 - loss 0.08197685 - time (sec): 5.69 - samples/sec: 2802.74 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:38:43,026 epoch 3 - iter 132/447 - loss 0.08754244 - time (sec): 8.55 - samples/sec: 2808.32 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:38:46,171 epoch 3 - iter 176/447 - loss 0.08248814 - time (sec): 11.70 - samples/sec: 2810.03 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:38:49,406 epoch 3 - iter 220/447 - loss 0.08252264 - time (sec): 14.93 - samples/sec: 2808.58 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:38:52,266 epoch 3 - iter 264/447 - loss 0.07964287 - time (sec): 17.79 - samples/sec: 2840.47 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:38:55,261 epoch 3 - iter 308/447 - loss 0.08228040 - time (sec): 20.79 - samples/sec: 2845.47 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:38:58,300 epoch 3 - iter 352/447 - loss 0.08248586 - time (sec): 23.83 - samples/sec: 2845.71 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:39:01,073 epoch 3 - iter 396/447 - loss 0.08367732 - time (sec): 26.60 - samples/sec: 2862.02 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:39:04,286 epoch 3 - iter 440/447 - loss 0.08345599 - time (sec): 29.81 - samples/sec: 2866.59 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:39:04,678 ----------------------------------------------------------------------------------------------------
2023-10-13 11:39:04,679 EPOCH 3 done: loss 0.0835 - lr: 0.000023
2023-10-13 11:39:13,300 DEV : loss 0.12531331181526184 - f1-score (micro avg) 0.736
2023-10-13 11:39:13,334 saving best model
2023-10-13 11:39:13,819 ----------------------------------------------------------------------------------------------------
2023-10-13 11:39:16,553 epoch 4 - iter 44/447 - loss 0.06081512 - time (sec): 2.73 - samples/sec: 3280.70 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:39:19,128 epoch 4 - iter 88/447 - loss 0.06130093 - time (sec): 5.31 - samples/sec: 3203.74 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:39:22,055 epoch 4 - iter 132/447 - loss 0.05727770 - time (sec): 8.23 - samples/sec: 3163.36 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:39:25,097 epoch 4 - iter 176/447 - loss 0.05437708 - time (sec): 11.28 - samples/sec: 3164.29 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:39:27,953 epoch 4 - iter 220/447 - loss 0.05094653 - time (sec): 14.13 - samples/sec: 3138.28 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:39:30,798 epoch 4 - iter 264/447 - loss 0.05163494 - time (sec): 16.98 - samples/sec: 3120.94 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:39:33,386 epoch 4 - iter 308/447 - loss 0.05153137 - time (sec): 19.57 - samples/sec: 3133.65 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:39:36,130 epoch 4 - iter 352/447 - loss 0.05076236 - time (sec): 22.31 - samples/sec: 3123.62 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:39:38,564 epoch 4 - iter 396/447 - loss 0.04840169 - time (sec): 24.74 - samples/sec: 3106.57 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:39:41,393 epoch 4 - iter 440/447 - loss 0.04853069 - time (sec): 27.57 - samples/sec: 3096.09 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:39:41,794 ----------------------------------------------------------------------------------------------------
2023-10-13 11:39:41,794 EPOCH 4 done: loss 0.0484 - lr: 0.000020
2023-10-13 11:39:50,889 DEV : loss 0.1411086916923523 - f1-score (micro avg) 0.7523
2023-10-13 11:39:50,925 saving best model
2023-10-13 11:39:51,411 ----------------------------------------------------------------------------------------------------
2023-10-13 11:39:54,906 epoch 5 - iter 44/447 - loss 0.03860730 - time (sec): 3.49 - samples/sec: 2760.43 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:39:57,725 epoch 5 - iter 88/447 - loss 0.03556237 - time (sec): 6.31 - samples/sec: 2793.51 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:40:00,832 epoch 5 - iter 132/447 - loss 0.03253877 - time (sec): 9.42 - samples/sec: 2787.23 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:40:03,721 epoch 5 - iter 176/447 - loss 0.03527827 - time (sec): 12.31 - samples/sec: 2792.55 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:40:06,971 epoch 5 - iter 220/447 - loss 0.03375370 - time (sec): 15.56 - samples/sec: 2788.49 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:40:09,908 epoch 5 - iter 264/447 - loss 0.03389079 - time (sec): 18.50 - samples/sec: 2812.29 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:40:12,805 epoch 5 - iter 308/447 - loss 0.03159410 - time (sec): 21.39 - samples/sec: 2808.51 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:40:15,843 epoch 5 - iter 352/447 - loss 0.03133658 - time (sec): 24.43 - samples/sec: 2814.90 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:40:18,798 epoch 5 - iter 396/447 - loss 0.03185176 - time (sec): 27.38 - samples/sec: 2799.64 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:40:21,613 epoch 5 - iter 440/447 - loss 0.03293362 - time (sec): 30.20 - samples/sec: 2823.75 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:40:22,058 ----------------------------------------------------------------------------------------------------
2023-10-13 11:40:22,058 EPOCH 5 done: loss 0.0331 - lr: 0.000017
2023-10-13 11:40:30,534 DEV : loss 0.17277590930461884 - f1-score (micro avg) 0.775
2023-10-13 11:40:30,562 saving best model
2023-10-13 11:40:31,156 ----------------------------------------------------------------------------------------------------
2023-10-13 11:40:34,245 epoch 6 - iter 44/447 - loss 0.01641274 - time (sec): 3.09 - samples/sec: 2782.37 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:40:36,970 epoch 6 - iter 88/447 - loss 0.02088310 - time (sec): 5.81 - samples/sec: 2784.85 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:40:40,026 epoch 6 - iter 132/447 - loss 0.02059010 - time (sec): 8.87 - samples/sec: 2823.72 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:40:43,022 epoch 6 - iter 176/447 - loss 0.02145822 - time (sec): 11.87 - samples/sec: 2862.37 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:40:45,676 epoch 6 - iter 220/447 - loss 0.02167903 - time (sec): 14.52 - samples/sec: 2861.66 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:40:48,507 epoch 6 - iter 264/447 - loss 0.02226561 - time (sec): 17.35 - samples/sec: 2858.77 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:40:51,255 epoch 6 - iter 308/447 - loss 0.02320899 - time (sec): 20.10 - samples/sec: 2855.54 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:40:54,001 epoch 6 - iter 352/447 - loss 0.02387174 - time (sec): 22.84 - samples/sec: 2888.48 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:40:57,475 epoch 6 - iter 396/447 - loss 0.02377590 - time (sec): 26.32 - samples/sec: 2894.39 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:41:00,559 epoch 6 - iter 440/447 - loss 0.02324946 - time (sec): 29.40 - samples/sec: 2898.65 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:41:00,995 ----------------------------------------------------------------------------------------------------
2023-10-13 11:41:00,995 EPOCH 6 done: loss 0.0233 - lr: 0.000013
2023-10-13 11:41:09,443 DEV : loss 0.18894143402576447 - f1-score (micro avg) 0.7728
2023-10-13 11:41:09,472 ----------------------------------------------------------------------------------------------------
2023-10-13 11:41:12,375 epoch 7 - iter 44/447 - loss 0.02022617 - time (sec): 2.90 - samples/sec: 3011.72 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:41:15,181 epoch 7 - iter 88/447 - loss 0.01788001 - time (sec): 5.71 - samples/sec: 2957.18 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:41:18,744 epoch 7 - iter 132/447 - loss 0.01554472 - time (sec): 9.27 - samples/sec: 2910.05 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:41:21,757 epoch 7 - iter 176/447 - loss 0.01521381 - time (sec): 12.28 - samples/sec: 2875.62 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:41:24,670 epoch 7 - iter 220/447 - loss 0.01618997 - time (sec): 15.20 - samples/sec: 2899.60 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:41:27,422 epoch 7 - iter 264/447 - loss 0.01631437 - time (sec): 17.95 - samples/sec: 2899.23 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:41:30,376 epoch 7 - iter 308/447 - loss 0.01443128 - time (sec): 20.90 - samples/sec: 2878.30 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:41:33,306 epoch 7 - iter 352/447 - loss 0.01478556 - time (sec): 23.83 - samples/sec: 2873.89 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:41:36,079 epoch 7 - iter 396/447 - loss 0.01588076 - time (sec): 26.61 - samples/sec: 2862.24 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:41:38,818 epoch 7 - iter 440/447 - loss 0.01554793 - time (sec): 29.35 - samples/sec: 2872.11 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:41:39,547 ----------------------------------------------------------------------------------------------------
2023-10-13 11:41:39,548 EPOCH 7 done: loss 0.0151 - lr: 0.000010
2023-10-13 11:41:48,012 DEV : loss 0.20179197192192078 - f1-score (micro avg) 0.7745
2023-10-13 11:41:48,038 ----------------------------------------------------------------------------------------------------
2023-10-13 11:41:51,122 epoch 8 - iter 44/447 - loss 0.01174812 - time (sec): 3.08 - samples/sec: 2779.76 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:41:54,327 epoch 8 - iter 88/447 - loss 0.01125552 - time (sec): 6.29 - samples/sec: 2797.47 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:41:57,342 epoch 8 - iter 132/447 - loss 0.01066657 - time (sec): 9.30 - samples/sec: 2866.41 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:42:00,586 epoch 8 - iter 176/447 - loss 0.00942978 - time (sec): 12.55 - samples/sec: 2878.82 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:42:03,430 epoch 8 - iter 220/447 - loss 0.01169514 - time (sec): 15.39 - samples/sec: 2852.35 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:42:06,472 epoch 8 - iter 264/447 - loss 0.01206510 - time (sec): 18.43 - samples/sec: 2820.51 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:42:09,416 epoch 8 - iter 308/447 - loss 0.01170503 - time (sec): 21.38 - samples/sec: 2850.99 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:42:12,188 epoch 8 - iter 352/447 - loss 0.01173590 - time (sec): 24.15 - samples/sec: 2867.64 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:42:15,076 epoch 8 - iter 396/447 - loss 0.01118873 - time (sec): 27.04 - samples/sec: 2862.49 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:42:17,941 epoch 8 - iter 440/447 - loss 0.01135881 - time (sec): 29.90 - samples/sec: 2852.70 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:42:18,361 ----------------------------------------------------------------------------------------------------
2023-10-13 11:42:18,361 EPOCH 8 done: loss 0.0112 - lr: 0.000007
2023-10-13 11:42:26,959 DEV : loss 0.20578144490718842 - f1-score (micro avg) 0.7819
2023-10-13 11:42:26,984 saving best model
2023-10-13 11:42:27,452 ----------------------------------------------------------------------------------------------------
2023-10-13 11:42:30,327 epoch 9 - iter 44/447 - loss 0.01161954 - time (sec): 2.87 - samples/sec: 2837.49 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:42:33,371 epoch 9 - iter 88/447 - loss 0.00638656 - time (sec): 5.92 - samples/sec: 2937.51 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:42:36,454 epoch 9 - iter 132/447 - loss 0.00666210 - time (sec): 9.00 - samples/sec: 2858.86 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:42:39,560 epoch 9 - iter 176/447 - loss 0.00568668 - time (sec): 12.10 - samples/sec: 2879.22 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:42:42,889 epoch 9 - iter 220/447 - loss 0.00591880 - time (sec): 15.43 - samples/sec: 2829.31 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:42:45,648 epoch 9 - iter 264/447 - loss 0.00762558 - time (sec): 18.19 - samples/sec: 2851.85 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:42:48,749 epoch 9 - iter 308/447 - loss 0.00714813 - time (sec): 21.29 - samples/sec: 2886.12 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:42:51,467 epoch 9 - iter 352/447 - loss 0.00676372 - time (sec): 24.01 - samples/sec: 2893.55 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:42:54,092 epoch 9 - iter 396/447 - loss 0.00645925 - time (sec): 26.64 - samples/sec: 2905.73 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:42:56,930 epoch 9 - iter 440/447 - loss 0.00653268 - time (sec): 29.47 - samples/sec: 2894.96 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:42:57,338 ----------------------------------------------------------------------------------------------------
2023-10-13 11:42:57,338 EPOCH 9 done: loss 0.0066 - lr: 0.000003
2023-10-13 11:43:05,394 DEV : loss 0.22298528254032135 - f1-score (micro avg) 0.7826
2023-10-13 11:43:05,420 saving best model
2023-10-13 11:43:05,878 ----------------------------------------------------------------------------------------------------
2023-10-13 11:43:08,761 epoch 10 - iter 44/447 - loss 0.00685104 - time (sec): 2.88 - samples/sec: 3017.48 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:43:11,462 epoch 10 - iter 88/447 - loss 0.00441715 - time (sec): 5.58 - samples/sec: 2963.15 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:43:14,101 epoch 10 - iter 132/447 - loss 0.00480244 - time (sec): 8.22 - samples/sec: 3045.37 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:43:16,895 epoch 10 - iter 176/447 - loss 0.00463435 - time (sec): 11.01 - samples/sec: 3056.83 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:43:19,970 epoch 10 - iter 220/447 - loss 0.00571713 - time (sec): 14.09 - samples/sec: 3038.35 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:43:23,223 epoch 10 - iter 264/447 - loss 0.00547250 - time (sec): 17.34 - samples/sec: 2971.42 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:43:26,251 epoch 10 - iter 308/447 - loss 0.00523613 - time (sec): 20.37 - samples/sec: 2963.30 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:43:28,858 epoch 10 - iter 352/447 - loss 0.00531243 - time (sec): 22.98 - samples/sec: 2974.47 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:43:31,533 epoch 10 - iter 396/447 - loss 0.00545590 - time (sec): 25.65 - samples/sec: 2979.26 - lr: 0.000000 - momentum: 0.000000
2023-10-13 11:43:34,543 epoch 10 - iter 440/447 - loss 0.00532315 - time (sec): 28.66 - samples/sec: 2963.33 - lr: 0.000000 - momentum: 0.000000
2023-10-13 11:43:35,033 ----------------------------------------------------------------------------------------------------
2023-10-13 11:43:35,034 EPOCH 10 done: loss 0.0052 - lr: 0.000000
2023-10-13 11:43:43,137 DEV : loss 0.2202497124671936 - f1-score (micro avg) 0.7904
2023-10-13 11:43:43,163 saving best model
2023-10-13 11:43:44,012 ----------------------------------------------------------------------------------------------------
2023-10-13 11:43:44,013 Loading model from best epoch ...
2023-10-13 11:43:45,811 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
2023-10-13 11:43:50,442
Results:
- F-score (micro) 0.7564
- F-score (macro) 0.6816
- Accuracy 0.6279
By class:
precision recall f1-score support
loc 0.8413 0.8540 0.8476 596
pers 0.6805 0.7868 0.7298 333
org 0.4885 0.4848 0.4867 132
prod 0.6852 0.5606 0.6167 66
time 0.7200 0.7347 0.7273 49
micro avg 0.7412 0.7721 0.7564 1176
macro avg 0.6831 0.6842 0.6816 1176
weighted avg 0.7424 0.7721 0.7558 1176
2023-10-13 11:43:50,442 ----------------------------------------------------------------------------------------------------
|