File size: 24,015 Bytes
e0e8840 |
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 |
2023-10-19 23:58:32,450 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 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()
)"
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 MultiCorpus: 1166 train + 165 dev + 415 test sentences
- NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 Train: 1166 sentences
2023-10-19 23:58:32,451 (train_with_dev=False, train_with_test=False)
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 Training Params:
2023-10-19 23:58:32,451 - learning_rate: "5e-05"
2023-10-19 23:58:32,451 - mini_batch_size: "4"
2023-10-19 23:58:32,451 - max_epochs: "10"
2023-10-19 23:58:32,451 - shuffle: "True"
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 Plugins:
2023-10-19 23:58:32,451 - TensorboardLogger
2023-10-19 23:58:32,451 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 23:58:32,451 - metric: "('micro avg', 'f1-score')"
2023-10-19 23:58:32,451 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,451 Computation:
2023-10-19 23:58:32,451 - compute on device: cuda:0
2023-10-19 23:58:32,451 - embedding storage: none
2023-10-19 23:58:32,452 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,452 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-19 23:58:32,452 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,452 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:32,452 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 23:58:32,922 epoch 1 - iter 29/292 - loss 3.14779499 - time (sec): 0.47 - samples/sec: 8417.41 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:58:33,371 epoch 1 - iter 58/292 - loss 3.07959948 - time (sec): 0.92 - samples/sec: 8375.04 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:58:33,854 epoch 1 - iter 87/292 - loss 2.99636841 - time (sec): 1.40 - samples/sec: 8658.66 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:58:34,361 epoch 1 - iter 116/292 - loss 2.81136763 - time (sec): 1.91 - samples/sec: 8448.44 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:58:34,874 epoch 1 - iter 145/292 - loss 2.57856572 - time (sec): 2.42 - samples/sec: 8523.19 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:58:35,405 epoch 1 - iter 174/292 - loss 2.34135925 - time (sec): 2.95 - samples/sec: 8378.57 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:58:35,938 epoch 1 - iter 203/292 - loss 2.04834995 - time (sec): 3.49 - samples/sec: 8631.55 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:58:36,449 epoch 1 - iter 232/292 - loss 1.87569980 - time (sec): 4.00 - samples/sec: 8640.24 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:58:36,995 epoch 1 - iter 261/292 - loss 1.72976459 - time (sec): 4.54 - samples/sec: 8700.50 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:58:37,512 epoch 1 - iter 290/292 - loss 1.62662447 - time (sec): 5.06 - samples/sec: 8755.13 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:58:37,540 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:37,540 EPOCH 1 done: loss 1.6226 - lr: 0.000049
2023-10-19 23:58:37,807 DEV : loss 0.46307969093322754 - f1-score (micro avg) 0.0
2023-10-19 23:58:37,811 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:38,333 epoch 2 - iter 29/292 - loss 0.82866034 - time (sec): 0.52 - samples/sec: 9421.74 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:58:38,857 epoch 2 - iter 58/292 - loss 0.77057818 - time (sec): 1.05 - samples/sec: 9203.30 - lr: 0.000049 - momentum: 0.000000
2023-10-19 23:58:39,364 epoch 2 - iter 87/292 - loss 0.72915775 - time (sec): 1.55 - samples/sec: 8858.99 - lr: 0.000048 - momentum: 0.000000
2023-10-19 23:58:39,867 epoch 2 - iter 116/292 - loss 0.72394303 - time (sec): 2.06 - samples/sec: 8546.65 - lr: 0.000048 - momentum: 0.000000
2023-10-19 23:58:40,382 epoch 2 - iter 145/292 - loss 0.69723734 - time (sec): 2.57 - samples/sec: 8424.58 - lr: 0.000047 - momentum: 0.000000
2023-10-19 23:58:40,892 epoch 2 - iter 174/292 - loss 0.67216825 - time (sec): 3.08 - samples/sec: 8432.93 - lr: 0.000047 - momentum: 0.000000
2023-10-19 23:58:41,418 epoch 2 - iter 203/292 - loss 0.65219976 - time (sec): 3.61 - samples/sec: 8329.25 - lr: 0.000046 - momentum: 0.000000
2023-10-19 23:58:41,947 epoch 2 - iter 232/292 - loss 0.61740936 - time (sec): 4.14 - samples/sec: 8592.86 - lr: 0.000046 - momentum: 0.000000
2023-10-19 23:58:42,474 epoch 2 - iter 261/292 - loss 0.60180613 - time (sec): 4.66 - samples/sec: 8681.15 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:58:42,967 epoch 2 - iter 290/292 - loss 0.60028304 - time (sec): 5.16 - samples/sec: 8555.21 - lr: 0.000045 - momentum: 0.000000
2023-10-19 23:58:42,998 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:42,999 EPOCH 2 done: loss 0.5990 - lr: 0.000045
2023-10-19 23:58:43,626 DEV : loss 0.3582861125469208 - f1-score (micro avg) 0.0085
2023-10-19 23:58:43,630 saving best model
2023-10-19 23:58:43,661 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:44,166 epoch 3 - iter 29/292 - loss 0.42071781 - time (sec): 0.50 - samples/sec: 8686.20 - lr: 0.000044 - momentum: 0.000000
2023-10-19 23:58:44,684 epoch 3 - iter 58/292 - loss 0.43984250 - time (sec): 1.02 - samples/sec: 8569.64 - lr: 0.000043 - momentum: 0.000000
2023-10-19 23:58:45,207 epoch 3 - iter 87/292 - loss 0.46328548 - time (sec): 1.55 - samples/sec: 8822.27 - lr: 0.000043 - momentum: 0.000000
2023-10-19 23:58:45,733 epoch 3 - iter 116/292 - loss 0.49552322 - time (sec): 2.07 - samples/sec: 8657.57 - lr: 0.000042 - momentum: 0.000000
2023-10-19 23:58:46,403 epoch 3 - iter 145/292 - loss 0.49277663 - time (sec): 2.74 - samples/sec: 8130.26 - lr: 0.000042 - momentum: 0.000000
2023-10-19 23:58:46,912 epoch 3 - iter 174/292 - loss 0.48425229 - time (sec): 3.25 - samples/sec: 8346.84 - lr: 0.000041 - momentum: 0.000000
2023-10-19 23:58:47,345 epoch 3 - iter 203/292 - loss 0.47920464 - time (sec): 3.68 - samples/sec: 8445.19 - lr: 0.000041 - momentum: 0.000000
2023-10-19 23:58:47,790 epoch 3 - iter 232/292 - loss 0.47196920 - time (sec): 4.13 - samples/sec: 8656.03 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:58:48,225 epoch 3 - iter 261/292 - loss 0.46824817 - time (sec): 4.56 - samples/sec: 8662.99 - lr: 0.000040 - momentum: 0.000000
2023-10-19 23:58:48,718 epoch 3 - iter 290/292 - loss 0.46590176 - time (sec): 5.06 - samples/sec: 8723.29 - lr: 0.000039 - momentum: 0.000000
2023-10-19 23:58:48,759 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:48,759 EPOCH 3 done: loss 0.4648 - lr: 0.000039
2023-10-19 23:58:49,392 DEV : loss 0.3454797565937042 - f1-score (micro avg) 0.0561
2023-10-19 23:58:49,396 saving best model
2023-10-19 23:58:49,434 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:49,923 epoch 4 - iter 29/292 - loss 0.37633271 - time (sec): 0.49 - samples/sec: 8019.09 - lr: 0.000038 - momentum: 0.000000
2023-10-19 23:58:50,428 epoch 4 - iter 58/292 - loss 0.39081668 - time (sec): 0.99 - samples/sec: 8129.96 - lr: 0.000038 - momentum: 0.000000
2023-10-19 23:58:50,948 epoch 4 - iter 87/292 - loss 0.38739784 - time (sec): 1.51 - samples/sec: 8446.57 - lr: 0.000037 - momentum: 0.000000
2023-10-19 23:58:51,445 epoch 4 - iter 116/292 - loss 0.38345280 - time (sec): 2.01 - samples/sec: 8461.51 - lr: 0.000037 - momentum: 0.000000
2023-10-19 23:58:51,973 epoch 4 - iter 145/292 - loss 0.38672167 - time (sec): 2.54 - samples/sec: 8359.16 - lr: 0.000036 - momentum: 0.000000
2023-10-19 23:58:52,487 epoch 4 - iter 174/292 - loss 0.39123246 - time (sec): 3.05 - samples/sec: 8332.83 - lr: 0.000036 - momentum: 0.000000
2023-10-19 23:58:53,015 epoch 4 - iter 203/292 - loss 0.40684055 - time (sec): 3.58 - samples/sec: 8599.45 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:58:53,514 epoch 4 - iter 232/292 - loss 0.40715733 - time (sec): 4.08 - samples/sec: 8461.76 - lr: 0.000035 - momentum: 0.000000
2023-10-19 23:58:54,020 epoch 4 - iter 261/292 - loss 0.40395442 - time (sec): 4.58 - samples/sec: 8452.62 - lr: 0.000034 - momentum: 0.000000
2023-10-19 23:58:54,583 epoch 4 - iter 290/292 - loss 0.40765257 - time (sec): 5.15 - samples/sec: 8610.09 - lr: 0.000033 - momentum: 0.000000
2023-10-19 23:58:54,610 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:54,611 EPOCH 4 done: loss 0.4075 - lr: 0.000033
2023-10-19 23:58:55,258 DEV : loss 0.31024691462516785 - f1-score (micro avg) 0.2088
2023-10-19 23:58:55,262 saving best model
2023-10-19 23:58:55,296 ----------------------------------------------------------------------------------------------------
2023-10-19 23:58:55,802 epoch 5 - iter 29/292 - loss 0.38537138 - time (sec): 0.51 - samples/sec: 10355.27 - lr: 0.000033 - momentum: 0.000000
2023-10-19 23:58:56,323 epoch 5 - iter 58/292 - loss 0.43876506 - time (sec): 1.03 - samples/sec: 9554.92 - lr: 0.000032 - momentum: 0.000000
2023-10-19 23:58:56,823 epoch 5 - iter 87/292 - loss 0.40671441 - time (sec): 1.53 - samples/sec: 8982.40 - lr: 0.000032 - momentum: 0.000000
2023-10-19 23:58:57,330 epoch 5 - iter 116/292 - loss 0.40007945 - time (sec): 2.03 - samples/sec: 8784.42 - lr: 0.000031 - momentum: 0.000000
2023-10-19 23:58:57,858 epoch 5 - iter 145/292 - loss 0.39158917 - time (sec): 2.56 - samples/sec: 8880.38 - lr: 0.000031 - momentum: 0.000000
2023-10-19 23:58:58,371 epoch 5 - iter 174/292 - loss 0.37921891 - time (sec): 3.07 - samples/sec: 8775.96 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:58:58,855 epoch 5 - iter 203/292 - loss 0.38011427 - time (sec): 3.56 - samples/sec: 8685.58 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:58:59,389 epoch 5 - iter 232/292 - loss 0.39053655 - time (sec): 4.09 - samples/sec: 8676.83 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:58:59,890 epoch 5 - iter 261/292 - loss 0.38870844 - time (sec): 4.59 - samples/sec: 8575.24 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:59:00,411 epoch 5 - iter 290/292 - loss 0.37911182 - time (sec): 5.11 - samples/sec: 8672.12 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:59:00,439 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:00,439 EPOCH 5 done: loss 0.3785 - lr: 0.000028
2023-10-19 23:59:01,076 DEV : loss 0.3215314745903015 - f1-score (micro avg) 0.2246
2023-10-19 23:59:01,080 saving best model
2023-10-19 23:59:01,113 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:01,632 epoch 6 - iter 29/292 - loss 0.38224130 - time (sec): 0.52 - samples/sec: 9011.08 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:59:02,088 epoch 6 - iter 58/292 - loss 0.36144289 - time (sec): 0.97 - samples/sec: 8652.39 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:59:02,532 epoch 6 - iter 87/292 - loss 0.37097587 - time (sec): 1.42 - samples/sec: 8935.31 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:02,976 epoch 6 - iter 116/292 - loss 0.36235103 - time (sec): 1.86 - samples/sec: 9274.47 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:03,426 epoch 6 - iter 145/292 - loss 0.35004386 - time (sec): 2.31 - samples/sec: 9520.28 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:59:03,894 epoch 6 - iter 174/292 - loss 0.35006772 - time (sec): 2.78 - samples/sec: 9664.14 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:59:04,370 epoch 6 - iter 203/292 - loss 0.33807395 - time (sec): 3.26 - samples/sec: 9664.13 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:59:04,858 epoch 6 - iter 232/292 - loss 0.33896877 - time (sec): 3.74 - samples/sec: 9609.82 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:59:05,390 epoch 6 - iter 261/292 - loss 0.34191111 - time (sec): 4.28 - samples/sec: 9355.23 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:59:05,897 epoch 6 - iter 290/292 - loss 0.34950655 - time (sec): 4.78 - samples/sec: 9240.88 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:59:05,928 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:05,928 EPOCH 6 done: loss 0.3515 - lr: 0.000022
2023-10-19 23:59:06,570 DEV : loss 0.31194955110549927 - f1-score (micro avg) 0.2452
2023-10-19 23:59:06,574 saving best model
2023-10-19 23:59:06,608 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:07,151 epoch 7 - iter 29/292 - loss 0.26753793 - time (sec): 0.54 - samples/sec: 10262.20 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:59:07,637 epoch 7 - iter 58/292 - loss 0.33094214 - time (sec): 1.03 - samples/sec: 9137.23 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:08,121 epoch 7 - iter 87/292 - loss 0.34593265 - time (sec): 1.51 - samples/sec: 8884.86 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:08,643 epoch 7 - iter 116/292 - loss 0.32828561 - time (sec): 2.03 - samples/sec: 8790.71 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:59:09,166 epoch 7 - iter 145/292 - loss 0.33425252 - time (sec): 2.56 - samples/sec: 8462.47 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:59:09,718 epoch 7 - iter 174/292 - loss 0.34544164 - time (sec): 3.11 - samples/sec: 8606.96 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:59:10,245 epoch 7 - iter 203/292 - loss 0.33684443 - time (sec): 3.64 - samples/sec: 8692.09 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:10,742 epoch 7 - iter 232/292 - loss 0.34217880 - time (sec): 4.13 - samples/sec: 8692.34 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:11,257 epoch 7 - iter 261/292 - loss 0.33355551 - time (sec): 4.65 - samples/sec: 8615.33 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:59:11,785 epoch 7 - iter 290/292 - loss 0.32942474 - time (sec): 5.18 - samples/sec: 8527.00 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:59:11,817 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:11,818 EPOCH 7 done: loss 0.3300 - lr: 0.000017
2023-10-19 23:59:12,459 DEV : loss 0.2952404320240021 - f1-score (micro avg) 0.2941
2023-10-19 23:59:12,463 saving best model
2023-10-19 23:59:12,495 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:12,988 epoch 8 - iter 29/292 - loss 0.30565935 - time (sec): 0.49 - samples/sec: 8828.66 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:59:13,524 epoch 8 - iter 58/292 - loss 0.34043801 - time (sec): 1.03 - samples/sec: 8887.12 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:59:14,090 epoch 8 - iter 87/292 - loss 0.30212031 - time (sec): 1.59 - samples/sec: 9162.88 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:59:14,615 epoch 8 - iter 116/292 - loss 0.31110236 - time (sec): 2.12 - samples/sec: 8676.70 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:59:15,118 epoch 8 - iter 145/292 - loss 0.31665402 - time (sec): 2.62 - samples/sec: 8340.54 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:59:15,650 epoch 8 - iter 174/292 - loss 0.32087859 - time (sec): 3.15 - samples/sec: 8269.51 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:59:16,189 epoch 8 - iter 203/292 - loss 0.31580278 - time (sec): 3.69 - samples/sec: 8200.91 - lr: 0.000013 - momentum: 0.000000
2023-10-19 23:59:16,730 epoch 8 - iter 232/292 - loss 0.32171904 - time (sec): 4.23 - samples/sec: 8120.26 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:59:17,272 epoch 8 - iter 261/292 - loss 0.31735134 - time (sec): 4.78 - samples/sec: 8118.22 - lr: 0.000012 - momentum: 0.000000
2023-10-19 23:59:17,799 epoch 8 - iter 290/292 - loss 0.33042954 - time (sec): 5.30 - samples/sec: 8319.87 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:59:17,831 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:17,831 EPOCH 8 done: loss 0.3287 - lr: 0.000011
2023-10-19 23:59:18,470 DEV : loss 0.300225168466568 - f1-score (micro avg) 0.274
2023-10-19 23:59:18,474 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:18,946 epoch 9 - iter 29/292 - loss 0.33105087 - time (sec): 0.47 - samples/sec: 8533.89 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:59:19,435 epoch 9 - iter 58/292 - loss 0.30511678 - time (sec): 0.96 - samples/sec: 8494.20 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:59:19,961 epoch 9 - iter 87/292 - loss 0.30860155 - time (sec): 1.49 - samples/sec: 8654.05 - lr: 0.000010 - momentum: 0.000000
2023-10-19 23:59:20,608 epoch 9 - iter 116/292 - loss 0.29350432 - time (sec): 2.13 - samples/sec: 8002.46 - lr: 0.000009 - momentum: 0.000000
2023-10-19 23:59:21,087 epoch 9 - iter 145/292 - loss 0.30324049 - time (sec): 2.61 - samples/sec: 8017.85 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:59:21,607 epoch 9 - iter 174/292 - loss 0.30397607 - time (sec): 3.13 - samples/sec: 8139.04 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:59:22,126 epoch 9 - iter 203/292 - loss 0.30607357 - time (sec): 3.65 - samples/sec: 8231.07 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:59:22,674 epoch 9 - iter 232/292 - loss 0.31419985 - time (sec): 4.20 - samples/sec: 8426.15 - lr: 0.000007 - momentum: 0.000000
2023-10-19 23:59:23,183 epoch 9 - iter 261/292 - loss 0.31077284 - time (sec): 4.71 - samples/sec: 8428.15 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:59:23,693 epoch 9 - iter 290/292 - loss 0.31676368 - time (sec): 5.22 - samples/sec: 8487.29 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:59:23,722 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:23,722 EPOCH 9 done: loss 0.3177 - lr: 0.000006
2023-10-19 23:59:24,359 DEV : loss 0.30219903588294983 - f1-score (micro avg) 0.2727
2023-10-19 23:59:24,364 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:24,907 epoch 10 - iter 29/292 - loss 0.26410275 - time (sec): 0.54 - samples/sec: 9510.14 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:59:25,492 epoch 10 - iter 58/292 - loss 0.29335365 - time (sec): 1.13 - samples/sec: 9521.29 - lr: 0.000005 - momentum: 0.000000
2023-10-19 23:59:26,015 epoch 10 - iter 87/292 - loss 0.30417325 - time (sec): 1.65 - samples/sec: 8740.51 - lr: 0.000004 - momentum: 0.000000
2023-10-19 23:59:26,576 epoch 10 - iter 116/292 - loss 0.30083326 - time (sec): 2.21 - samples/sec: 8421.16 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:59:27,105 epoch 10 - iter 145/292 - loss 0.30274681 - time (sec): 2.74 - samples/sec: 8203.33 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:59:27,633 epoch 10 - iter 174/292 - loss 0.30387774 - time (sec): 3.27 - samples/sec: 8146.14 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:59:28,112 epoch 10 - iter 203/292 - loss 0.30407753 - time (sec): 3.75 - samples/sec: 8142.22 - lr: 0.000002 - momentum: 0.000000
2023-10-19 23:59:28,631 epoch 10 - iter 232/292 - loss 0.30962134 - time (sec): 4.27 - samples/sec: 8163.95 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:59:29,152 epoch 10 - iter 261/292 - loss 0.31082971 - time (sec): 4.79 - samples/sec: 8096.13 - lr: 0.000001 - momentum: 0.000000
2023-10-19 23:59:29,705 epoch 10 - iter 290/292 - loss 0.31152913 - time (sec): 5.34 - samples/sec: 8290.69 - lr: 0.000000 - momentum: 0.000000
2023-10-19 23:59:29,733 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:29,733 EPOCH 10 done: loss 0.3108 - lr: 0.000000
2023-10-19 23:59:30,397 DEV : loss 0.2987516224384308 - f1-score (micro avg) 0.2961
2023-10-19 23:59:30,401 saving best model
2023-10-19 23:59:30,468 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:30,468 Loading model from best epoch ...
2023-10-19 23:59:30,544 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
2023-10-19 23:59:31,512
Results:
- F-score (micro) 0.377
- F-score (macro) 0.1977
- Accuracy 0.243
By class:
precision recall f1-score support
PER 0.4282 0.4368 0.4324 348
LOC 0.3185 0.4100 0.3585 261
ORG 0.0000 0.0000 0.0000 52
HumanProd 0.0000 0.0000 0.0000 22
micro avg 0.3748 0.3792 0.3770 683
macro avg 0.1867 0.2117 0.1977 683
weighted avg 0.3399 0.3792 0.3573 683
2023-10-19 23:59:31,512 ----------------------------------------------------------------------------------------------------
|