File size: 24,094 Bytes
103bcc3 |
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 |
2023-10-20 00:21:21,464 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 128)
(position_embeddings): Embedding(512, 128)
(token_type_embeddings): Embedding(2, 128)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-1): 2 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=128, out_features=128, bias=True)
(key): Linear(in_features=128, out_features=128, bias=True)
(value): Linear(in_features=128, out_features=128, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=128, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=128, out_features=512, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=512, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=128, out_features=128, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=128, out_features=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 MultiCorpus: 1085 train + 148 dev + 364 test sentences
- NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Train: 1085 sentences
2023-10-20 00:21:21,465 (train_with_dev=False, train_with_test=False)
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Training Params:
2023-10-20 00:21:21,465 - learning_rate: "5e-05"
2023-10-20 00:21:21,465 - mini_batch_size: "4"
2023-10-20 00:21:21,465 - max_epochs: "10"
2023-10-20 00:21:21,465 - shuffle: "True"
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Plugins:
2023-10-20 00:21:21,465 - TensorboardLogger
2023-10-20 00:21:21,465 - LinearScheduler | warmup_fraction: '0.1'
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Final evaluation on model from best epoch (best-model.pt)
2023-10-20 00:21:21,465 - metric: "('micro avg', 'f1-score')"
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,465 Computation:
2023-10-20 00:21:21,465 - compute on device: cuda:0
2023-10-20 00:21:21,465 - embedding storage: none
2023-10-20 00:21:21,465 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,466 Model training base path: "hmbench-newseye/sv-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-20 00:21:21,466 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,466 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:21,466 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-20 00:21:21,957 epoch 1 - iter 27/272 - loss 3.46711403 - time (sec): 0.49 - samples/sec: 10461.58 - lr: 0.000005 - momentum: 0.000000
2023-10-20 00:21:22,439 epoch 1 - iter 54/272 - loss 3.46171750 - time (sec): 0.97 - samples/sec: 10681.11 - lr: 0.000010 - momentum: 0.000000
2023-10-20 00:21:22,883 epoch 1 - iter 81/272 - loss 3.28534633 - time (sec): 1.42 - samples/sec: 10814.77 - lr: 0.000015 - momentum: 0.000000
2023-10-20 00:21:23,443 epoch 1 - iter 108/272 - loss 3.01861422 - time (sec): 1.98 - samples/sec: 10633.83 - lr: 0.000020 - momentum: 0.000000
2023-10-20 00:21:23,941 epoch 1 - iter 135/272 - loss 2.80909491 - time (sec): 2.48 - samples/sec: 10406.50 - lr: 0.000025 - momentum: 0.000000
2023-10-20 00:21:24,476 epoch 1 - iter 162/272 - loss 2.54231157 - time (sec): 3.01 - samples/sec: 10303.95 - lr: 0.000030 - momentum: 0.000000
2023-10-20 00:21:24,983 epoch 1 - iter 189/272 - loss 2.31826568 - time (sec): 3.52 - samples/sec: 10208.09 - lr: 0.000035 - momentum: 0.000000
2023-10-20 00:21:25,506 epoch 1 - iter 216/272 - loss 2.08682730 - time (sec): 4.04 - samples/sec: 10358.94 - lr: 0.000040 - momentum: 0.000000
2023-10-20 00:21:26,020 epoch 1 - iter 243/272 - loss 1.91212120 - time (sec): 4.55 - samples/sec: 10466.68 - lr: 0.000044 - momentum: 0.000000
2023-10-20 00:21:26,487 epoch 1 - iter 270/272 - loss 1.80967208 - time (sec): 5.02 - samples/sec: 10325.73 - lr: 0.000049 - momentum: 0.000000
2023-10-20 00:21:26,520 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:26,520 EPOCH 1 done: loss 1.8069 - lr: 0.000049
2023-10-20 00:21:26,937 DEV : loss 0.4722510874271393 - f1-score (micro avg) 0.0
2023-10-20 00:21:26,940 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:27,456 epoch 2 - iter 27/272 - loss 0.61178694 - time (sec): 0.52 - samples/sec: 10248.65 - lr: 0.000049 - momentum: 0.000000
2023-10-20 00:21:27,965 epoch 2 - iter 54/272 - loss 0.57067838 - time (sec): 1.02 - samples/sec: 9816.81 - lr: 0.000049 - momentum: 0.000000
2023-10-20 00:21:28,449 epoch 2 - iter 81/272 - loss 0.56029945 - time (sec): 1.51 - samples/sec: 10217.88 - lr: 0.000048 - momentum: 0.000000
2023-10-20 00:21:28,950 epoch 2 - iter 108/272 - loss 0.54873035 - time (sec): 2.01 - samples/sec: 10325.13 - lr: 0.000048 - momentum: 0.000000
2023-10-20 00:21:29,435 epoch 2 - iter 135/272 - loss 0.55233991 - time (sec): 2.49 - samples/sec: 10424.92 - lr: 0.000047 - momentum: 0.000000
2023-10-20 00:21:29,953 epoch 2 - iter 162/272 - loss 0.54109234 - time (sec): 3.01 - samples/sec: 10331.23 - lr: 0.000047 - momentum: 0.000000
2023-10-20 00:21:30,466 epoch 2 - iter 189/272 - loss 0.52309886 - time (sec): 3.53 - samples/sec: 10393.81 - lr: 0.000046 - momentum: 0.000000
2023-10-20 00:21:30,960 epoch 2 - iter 216/272 - loss 0.51818871 - time (sec): 4.02 - samples/sec: 10345.08 - lr: 0.000046 - momentum: 0.000000
2023-10-20 00:21:31,472 epoch 2 - iter 243/272 - loss 0.51911854 - time (sec): 4.53 - samples/sec: 10371.98 - lr: 0.000045 - momentum: 0.000000
2023-10-20 00:21:31,966 epoch 2 - iter 270/272 - loss 0.52018264 - time (sec): 5.03 - samples/sec: 10319.19 - lr: 0.000045 - momentum: 0.000000
2023-10-20 00:21:31,994 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:31,995 EPOCH 2 done: loss 0.5211 - lr: 0.000045
2023-10-20 00:21:32,748 DEV : loss 0.3575037121772766 - f1-score (micro avg) 0.0408
2023-10-20 00:21:32,752 saving best model
2023-10-20 00:21:32,779 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:33,275 epoch 3 - iter 27/272 - loss 0.40786242 - time (sec): 0.50 - samples/sec: 10258.65 - lr: 0.000044 - momentum: 0.000000
2023-10-20 00:21:33,777 epoch 3 - iter 54/272 - loss 0.42946260 - time (sec): 1.00 - samples/sec: 10855.41 - lr: 0.000043 - momentum: 0.000000
2023-10-20 00:21:34,302 epoch 3 - iter 81/272 - loss 0.41328076 - time (sec): 1.52 - samples/sec: 10338.48 - lr: 0.000043 - momentum: 0.000000
2023-10-20 00:21:34,828 epoch 3 - iter 108/272 - loss 0.41615591 - time (sec): 2.05 - samples/sec: 10115.61 - lr: 0.000042 - momentum: 0.000000
2023-10-20 00:21:35,349 epoch 3 - iter 135/272 - loss 0.41543348 - time (sec): 2.57 - samples/sec: 10345.89 - lr: 0.000042 - momentum: 0.000000
2023-10-20 00:21:35,842 epoch 3 - iter 162/272 - loss 0.41142926 - time (sec): 3.06 - samples/sec: 10218.54 - lr: 0.000041 - momentum: 0.000000
2023-10-20 00:21:36,336 epoch 3 - iter 189/272 - loss 0.40845834 - time (sec): 3.56 - samples/sec: 10363.90 - lr: 0.000041 - momentum: 0.000000
2023-10-20 00:21:36,841 epoch 3 - iter 216/272 - loss 0.42242963 - time (sec): 4.06 - samples/sec: 10316.37 - lr: 0.000040 - momentum: 0.000000
2023-10-20 00:21:37,327 epoch 3 - iter 243/272 - loss 0.42454515 - time (sec): 4.55 - samples/sec: 10234.41 - lr: 0.000040 - momentum: 0.000000
2023-10-20 00:21:37,837 epoch 3 - iter 270/272 - loss 0.42731990 - time (sec): 5.06 - samples/sec: 10207.20 - lr: 0.000039 - momentum: 0.000000
2023-10-20 00:21:37,871 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:37,871 EPOCH 3 done: loss 0.4266 - lr: 0.000039
2023-10-20 00:21:38,629 DEV : loss 0.3016860783100128 - f1-score (micro avg) 0.1798
2023-10-20 00:21:38,633 saving best model
2023-10-20 00:21:38,664 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:39,141 epoch 4 - iter 27/272 - loss 0.39020834 - time (sec): 0.48 - samples/sec: 9628.52 - lr: 0.000038 - momentum: 0.000000
2023-10-20 00:21:39,583 epoch 4 - iter 54/272 - loss 0.38305660 - time (sec): 0.92 - samples/sec: 9183.83 - lr: 0.000038 - momentum: 0.000000
2023-10-20 00:21:40,088 epoch 4 - iter 81/272 - loss 0.38108401 - time (sec): 1.42 - samples/sec: 9963.30 - lr: 0.000037 - momentum: 0.000000
2023-10-20 00:21:40,568 epoch 4 - iter 108/272 - loss 0.37152231 - time (sec): 1.90 - samples/sec: 10128.14 - lr: 0.000037 - momentum: 0.000000
2023-10-20 00:21:41,090 epoch 4 - iter 135/272 - loss 0.37083389 - time (sec): 2.43 - samples/sec: 9998.37 - lr: 0.000036 - momentum: 0.000000
2023-10-20 00:21:41,640 epoch 4 - iter 162/272 - loss 0.37693631 - time (sec): 2.97 - samples/sec: 10410.48 - lr: 0.000036 - momentum: 0.000000
2023-10-20 00:21:42,164 epoch 4 - iter 189/272 - loss 0.37660175 - time (sec): 3.50 - samples/sec: 10495.63 - lr: 0.000035 - momentum: 0.000000
2023-10-20 00:21:42,659 epoch 4 - iter 216/272 - loss 0.38496790 - time (sec): 3.99 - samples/sec: 10395.82 - lr: 0.000034 - momentum: 0.000000
2023-10-20 00:21:43,184 epoch 4 - iter 243/272 - loss 0.38842763 - time (sec): 4.52 - samples/sec: 10340.72 - lr: 0.000034 - momentum: 0.000000
2023-10-20 00:21:43,684 epoch 4 - iter 270/272 - loss 0.38100025 - time (sec): 5.02 - samples/sec: 10307.69 - lr: 0.000033 - momentum: 0.000000
2023-10-20 00:21:43,717 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:43,717 EPOCH 4 done: loss 0.3806 - lr: 0.000033
2023-10-20 00:21:44,623 DEV : loss 0.28507402539253235 - f1-score (micro avg) 0.3513
2023-10-20 00:21:44,626 saving best model
2023-10-20 00:21:44,658 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:45,175 epoch 5 - iter 27/272 - loss 0.30924673 - time (sec): 0.52 - samples/sec: 10765.09 - lr: 0.000033 - momentum: 0.000000
2023-10-20 00:21:45,704 epoch 5 - iter 54/272 - loss 0.34869346 - time (sec): 1.04 - samples/sec: 9934.41 - lr: 0.000032 - momentum: 0.000000
2023-10-20 00:21:46,261 epoch 5 - iter 81/272 - loss 0.34272748 - time (sec): 1.60 - samples/sec: 9845.49 - lr: 0.000032 - momentum: 0.000000
2023-10-20 00:21:46,824 epoch 5 - iter 108/272 - loss 0.33624812 - time (sec): 2.16 - samples/sec: 9475.98 - lr: 0.000031 - momentum: 0.000000
2023-10-20 00:21:47,321 epoch 5 - iter 135/272 - loss 0.34768000 - time (sec): 2.66 - samples/sec: 9471.14 - lr: 0.000031 - momentum: 0.000000
2023-10-20 00:21:47,841 epoch 5 - iter 162/272 - loss 0.34735833 - time (sec): 3.18 - samples/sec: 9453.30 - lr: 0.000030 - momentum: 0.000000
2023-10-20 00:21:48,385 epoch 5 - iter 189/272 - loss 0.34992901 - time (sec): 3.73 - samples/sec: 9530.67 - lr: 0.000029 - momentum: 0.000000
2023-10-20 00:21:48,899 epoch 5 - iter 216/272 - loss 0.34923380 - time (sec): 4.24 - samples/sec: 9511.06 - lr: 0.000029 - momentum: 0.000000
2023-10-20 00:21:49,410 epoch 5 - iter 243/272 - loss 0.34680989 - time (sec): 4.75 - samples/sec: 9621.44 - lr: 0.000028 - momentum: 0.000000
2023-10-20 00:21:49,910 epoch 5 - iter 270/272 - loss 0.34720474 - time (sec): 5.25 - samples/sec: 9831.66 - lr: 0.000028 - momentum: 0.000000
2023-10-20 00:21:49,942 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:49,942 EPOCH 5 done: loss 0.3483 - lr: 0.000028
2023-10-20 00:21:50,740 DEV : loss 0.27170366048812866 - f1-score (micro avg) 0.4177
2023-10-20 00:21:50,744 saving best model
2023-10-20 00:21:50,777 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:51,258 epoch 6 - iter 27/272 - loss 0.34835965 - time (sec): 0.48 - samples/sec: 10640.77 - lr: 0.000027 - momentum: 0.000000
2023-10-20 00:21:51,754 epoch 6 - iter 54/272 - loss 0.35236544 - time (sec): 0.98 - samples/sec: 10347.26 - lr: 0.000027 - momentum: 0.000000
2023-10-20 00:21:52,225 epoch 6 - iter 81/272 - loss 0.34898421 - time (sec): 1.45 - samples/sec: 10363.93 - lr: 0.000026 - momentum: 0.000000
2023-10-20 00:21:52,743 epoch 6 - iter 108/272 - loss 0.34103544 - time (sec): 1.97 - samples/sec: 10239.48 - lr: 0.000026 - momentum: 0.000000
2023-10-20 00:21:53,267 epoch 6 - iter 135/272 - loss 0.34258782 - time (sec): 2.49 - samples/sec: 10292.90 - lr: 0.000025 - momentum: 0.000000
2023-10-20 00:21:53,748 epoch 6 - iter 162/272 - loss 0.34092986 - time (sec): 2.97 - samples/sec: 10268.06 - lr: 0.000024 - momentum: 0.000000
2023-10-20 00:21:54,282 epoch 6 - iter 189/272 - loss 0.33967518 - time (sec): 3.50 - samples/sec: 10554.34 - lr: 0.000024 - momentum: 0.000000
2023-10-20 00:21:54,766 epoch 6 - iter 216/272 - loss 0.34503779 - time (sec): 3.99 - samples/sec: 10493.61 - lr: 0.000023 - momentum: 0.000000
2023-10-20 00:21:55,274 epoch 6 - iter 243/272 - loss 0.33713653 - time (sec): 4.50 - samples/sec: 10472.18 - lr: 0.000023 - momentum: 0.000000
2023-10-20 00:21:55,750 epoch 6 - iter 270/272 - loss 0.33500603 - time (sec): 4.97 - samples/sec: 10390.02 - lr: 0.000022 - momentum: 0.000000
2023-10-20 00:21:55,782 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:55,783 EPOCH 6 done: loss 0.3345 - lr: 0.000022
2023-10-20 00:21:56,555 DEV : loss 0.2611343264579773 - f1-score (micro avg) 0.4743
2023-10-20 00:21:56,559 saving best model
2023-10-20 00:21:56,590 ----------------------------------------------------------------------------------------------------
2023-10-20 00:21:57,104 epoch 7 - iter 27/272 - loss 0.26414586 - time (sec): 0.51 - samples/sec: 10785.15 - lr: 0.000022 - momentum: 0.000000
2023-10-20 00:21:57,653 epoch 7 - iter 54/272 - loss 0.28507475 - time (sec): 1.06 - samples/sec: 10182.43 - lr: 0.000021 - momentum: 0.000000
2023-10-20 00:21:58,174 epoch 7 - iter 81/272 - loss 0.32465150 - time (sec): 1.58 - samples/sec: 10141.41 - lr: 0.000021 - momentum: 0.000000
2023-10-20 00:21:58,684 epoch 7 - iter 108/272 - loss 0.33301144 - time (sec): 2.09 - samples/sec: 9808.71 - lr: 0.000020 - momentum: 0.000000
2023-10-20 00:21:59,201 epoch 7 - iter 135/272 - loss 0.31522540 - time (sec): 2.61 - samples/sec: 9762.86 - lr: 0.000019 - momentum: 0.000000
2023-10-20 00:21:59,708 epoch 7 - iter 162/272 - loss 0.31244099 - time (sec): 3.12 - samples/sec: 9829.27 - lr: 0.000019 - momentum: 0.000000
2023-10-20 00:22:00,198 epoch 7 - iter 189/272 - loss 0.30460946 - time (sec): 3.61 - samples/sec: 9951.47 - lr: 0.000018 - momentum: 0.000000
2023-10-20 00:22:00,681 epoch 7 - iter 216/272 - loss 0.30823837 - time (sec): 4.09 - samples/sec: 9918.18 - lr: 0.000018 - momentum: 0.000000
2023-10-20 00:22:01,195 epoch 7 - iter 243/272 - loss 0.31442376 - time (sec): 4.60 - samples/sec: 10046.22 - lr: 0.000017 - momentum: 0.000000
2023-10-20 00:22:01,687 epoch 7 - iter 270/272 - loss 0.31608757 - time (sec): 5.10 - samples/sec: 10151.04 - lr: 0.000017 - momentum: 0.000000
2023-10-20 00:22:01,717 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:01,717 EPOCH 7 done: loss 0.3156 - lr: 0.000017
2023-10-20 00:22:02,477 DEV : loss 0.25722736120224 - f1-score (micro avg) 0.4912
2023-10-20 00:22:02,481 saving best model
2023-10-20 00:22:02,511 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:03,016 epoch 8 - iter 27/272 - loss 0.35861152 - time (sec): 0.50 - samples/sec: 9876.68 - lr: 0.000016 - momentum: 0.000000
2023-10-20 00:22:03,506 epoch 8 - iter 54/272 - loss 0.32562148 - time (sec): 0.99 - samples/sec: 10259.78 - lr: 0.000016 - momentum: 0.000000
2023-10-20 00:22:04,042 epoch 8 - iter 81/272 - loss 0.29992941 - time (sec): 1.53 - samples/sec: 10360.30 - lr: 0.000015 - momentum: 0.000000
2023-10-20 00:22:04,546 epoch 8 - iter 108/272 - loss 0.30456466 - time (sec): 2.03 - samples/sec: 10210.32 - lr: 0.000014 - momentum: 0.000000
2023-10-20 00:22:05,050 epoch 8 - iter 135/272 - loss 0.30766248 - time (sec): 2.54 - samples/sec: 10207.99 - lr: 0.000014 - momentum: 0.000000
2023-10-20 00:22:05,558 epoch 8 - iter 162/272 - loss 0.30300256 - time (sec): 3.05 - samples/sec: 10223.82 - lr: 0.000013 - momentum: 0.000000
2023-10-20 00:22:06,057 epoch 8 - iter 189/272 - loss 0.29664404 - time (sec): 3.55 - samples/sec: 10395.75 - lr: 0.000013 - momentum: 0.000000
2023-10-20 00:22:06,577 epoch 8 - iter 216/272 - loss 0.29539590 - time (sec): 4.07 - samples/sec: 10466.18 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:22:07,059 epoch 8 - iter 243/272 - loss 0.29947757 - time (sec): 4.55 - samples/sec: 10330.59 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:22:07,541 epoch 8 - iter 270/272 - loss 0.30317529 - time (sec): 5.03 - samples/sec: 10286.12 - lr: 0.000011 - momentum: 0.000000
2023-10-20 00:22:07,570 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:07,570 EPOCH 8 done: loss 0.3029 - lr: 0.000011
2023-10-20 00:22:08,345 DEV : loss 0.25111961364746094 - f1-score (micro avg) 0.5085
2023-10-20 00:22:08,348 saving best model
2023-10-20 00:22:08,384 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:08,889 epoch 9 - iter 27/272 - loss 0.29468874 - time (sec): 0.50 - samples/sec: 10627.07 - lr: 0.000011 - momentum: 0.000000
2023-10-20 00:22:09,377 epoch 9 - iter 54/272 - loss 0.28721000 - time (sec): 0.99 - samples/sec: 10287.41 - lr: 0.000010 - momentum: 0.000000
2023-10-20 00:22:09,867 epoch 9 - iter 81/272 - loss 0.30800265 - time (sec): 1.48 - samples/sec: 10078.94 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:22:10,363 epoch 9 - iter 108/272 - loss 0.30773883 - time (sec): 1.98 - samples/sec: 10143.35 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:22:10,880 epoch 9 - iter 135/272 - loss 0.30764331 - time (sec): 2.49 - samples/sec: 10622.48 - lr: 0.000008 - momentum: 0.000000
2023-10-20 00:22:11,333 epoch 9 - iter 162/272 - loss 0.30584889 - time (sec): 2.95 - samples/sec: 10761.15 - lr: 0.000008 - momentum: 0.000000
2023-10-20 00:22:11,816 epoch 9 - iter 189/272 - loss 0.30001539 - time (sec): 3.43 - samples/sec: 10584.33 - lr: 0.000007 - momentum: 0.000000
2023-10-20 00:22:12,318 epoch 9 - iter 216/272 - loss 0.29759046 - time (sec): 3.93 - samples/sec: 10478.54 - lr: 0.000007 - momentum: 0.000000
2023-10-20 00:22:12,847 epoch 9 - iter 243/272 - loss 0.29325136 - time (sec): 4.46 - samples/sec: 10481.70 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:22:13,356 epoch 9 - iter 270/272 - loss 0.29409257 - time (sec): 4.97 - samples/sec: 10419.18 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:22:13,385 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:13,385 EPOCH 9 done: loss 0.2944 - lr: 0.000006
2023-10-20 00:22:14,303 DEV : loss 0.24987336993217468 - f1-score (micro avg) 0.5047
2023-10-20 00:22:14,307 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:14,773 epoch 10 - iter 27/272 - loss 0.32141785 - time (sec): 0.47 - samples/sec: 10482.29 - lr: 0.000005 - momentum: 0.000000
2023-10-20 00:22:15,272 epoch 10 - iter 54/272 - loss 0.31702834 - time (sec): 0.96 - samples/sec: 10922.56 - lr: 0.000004 - momentum: 0.000000
2023-10-20 00:22:15,739 epoch 10 - iter 81/272 - loss 0.29843000 - time (sec): 1.43 - samples/sec: 10748.54 - lr: 0.000004 - momentum: 0.000000
2023-10-20 00:22:16,241 epoch 10 - iter 108/272 - loss 0.29486713 - time (sec): 1.93 - samples/sec: 10407.84 - lr: 0.000003 - momentum: 0.000000
2023-10-20 00:22:16,724 epoch 10 - iter 135/272 - loss 0.30815187 - time (sec): 2.42 - samples/sec: 10305.36 - lr: 0.000003 - momentum: 0.000000
2023-10-20 00:22:17,232 epoch 10 - iter 162/272 - loss 0.30545146 - time (sec): 2.92 - samples/sec: 10301.34 - lr: 0.000002 - momentum: 0.000000
2023-10-20 00:22:17,717 epoch 10 - iter 189/272 - loss 0.29883950 - time (sec): 3.41 - samples/sec: 10355.45 - lr: 0.000002 - momentum: 0.000000
2023-10-20 00:22:18,228 epoch 10 - iter 216/272 - loss 0.29494759 - time (sec): 3.92 - samples/sec: 10502.29 - lr: 0.000001 - momentum: 0.000000
2023-10-20 00:22:18,754 epoch 10 - iter 243/272 - loss 0.28921084 - time (sec): 4.45 - samples/sec: 10547.46 - lr: 0.000001 - momentum: 0.000000
2023-10-20 00:22:19,264 epoch 10 - iter 270/272 - loss 0.28845308 - time (sec): 4.96 - samples/sec: 10461.24 - lr: 0.000000 - momentum: 0.000000
2023-10-20 00:22:19,292 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:19,292 EPOCH 10 done: loss 0.2903 - lr: 0.000000
2023-10-20 00:22:20,053 DEV : loss 0.2502773106098175 - f1-score (micro avg) 0.4971
2023-10-20 00:22:20,083 ----------------------------------------------------------------------------------------------------
2023-10-20 00:22:20,083 Loading model from best epoch ...
2023-10-20 00:22:20,162 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-20 00:22:20,978
Results:
- F-score (micro) 0.3892
- F-score (macro) 0.199
- Accuracy 0.2555
By class:
precision recall f1-score support
LOC 0.4795 0.5609 0.5170 312
PER 0.2359 0.3413 0.2790 208
ORG 0.0000 0.0000 0.0000 55
HumanProd 0.0000 0.0000 0.0000 22
micro avg 0.3688 0.4121 0.3892 597
macro avg 0.1788 0.2256 0.1990 597
weighted avg 0.3328 0.4121 0.3674 597
2023-10-20 00:22:20,979 ----------------------------------------------------------------------------------------------------
|