File size: 23,786 Bytes
2f1cd5d |
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 |
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(31103, 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=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Corpus: 758 train + 94 dev + 96 test sentences
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Train: 758 sentences
2024-03-26 16:33:19,133 (train_with_dev=False, train_with_test=False)
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Training Params:
2024-03-26 16:33:19,133 - learning_rate: "5e-05"
2024-03-26 16:33:19,133 - mini_batch_size: "8"
2024-03-26 16:33:19,133 - max_epochs: "10"
2024-03-26 16:33:19,133 - shuffle: "True"
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Plugins:
2024-03-26 16:33:19,133 - TensorboardLogger
2024-03-26 16:33:19,133 - LinearScheduler | warmup_fraction: '0.1'
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Final evaluation on model from best epoch (best-model.pt)
2024-03-26 16:33:19,133 - metric: "('micro avg', 'f1-score')"
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,133 Computation:
2024-03-26 16:33:19,133 - compute on device: cuda:0
2024-03-26 16:33:19,133 - embedding storage: none
2024-03-26 16:33:19,133 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,134 Model training base path: "flair-co-funer-german_dbmdz_bert_base-bs8-e10-lr5e-05-5"
2024-03-26 16:33:19,134 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,134 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:19,134 Logging anything other than scalars to TensorBoard is currently not supported.
2024-03-26 16:33:20,989 epoch 1 - iter 9/95 - loss 3.24854896 - time (sec): 1.86 - samples/sec: 1690.00 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:33:22,856 epoch 1 - iter 18/95 - loss 3.07358066 - time (sec): 3.72 - samples/sec: 1781.85 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:33:25,138 epoch 1 - iter 27/95 - loss 2.80252277 - time (sec): 6.00 - samples/sec: 1727.30 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:33:26,618 epoch 1 - iter 36/95 - loss 2.60668952 - time (sec): 7.48 - samples/sec: 1805.13 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:33:28,762 epoch 1 - iter 45/95 - loss 2.40409254 - time (sec): 9.63 - samples/sec: 1784.79 - lr: 0.000023 - momentum: 0.000000
2024-03-26 16:33:30,337 epoch 1 - iter 54/95 - loss 2.22917451 - time (sec): 11.20 - samples/sec: 1806.10 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:33:31,959 epoch 1 - iter 63/95 - loss 2.07783198 - time (sec): 12.83 - samples/sec: 1824.75 - lr: 0.000033 - momentum: 0.000000
2024-03-26 16:33:33,831 epoch 1 - iter 72/95 - loss 1.92712496 - time (sec): 14.70 - samples/sec: 1816.59 - lr: 0.000037 - momentum: 0.000000
2024-03-26 16:33:35,888 epoch 1 - iter 81/95 - loss 1.77489410 - time (sec): 16.75 - samples/sec: 1799.51 - lr: 0.000042 - momentum: 0.000000
2024-03-26 16:33:37,515 epoch 1 - iter 90/95 - loss 1.66711022 - time (sec): 18.38 - samples/sec: 1791.34 - lr: 0.000047 - momentum: 0.000000
2024-03-26 16:33:38,262 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:38,262 EPOCH 1 done: loss 1.6139 - lr: 0.000047
2024-03-26 16:33:39,161 DEV : loss 0.4351406395435333 - f1-score (micro avg) 0.7212
2024-03-26 16:33:39,162 saving best model
2024-03-26 16:33:39,430 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:41,682 epoch 2 - iter 9/95 - loss 0.45840955 - time (sec): 2.25 - samples/sec: 1694.88 - lr: 0.000050 - momentum: 0.000000
2024-03-26 16:33:43,575 epoch 2 - iter 18/95 - loss 0.41958130 - time (sec): 4.14 - samples/sec: 1687.67 - lr: 0.000049 - momentum: 0.000000
2024-03-26 16:33:45,878 epoch 2 - iter 27/95 - loss 0.38281852 - time (sec): 6.45 - samples/sec: 1659.07 - lr: 0.000048 - momentum: 0.000000
2024-03-26 16:33:47,237 epoch 2 - iter 36/95 - loss 0.38193994 - time (sec): 7.81 - samples/sec: 1770.34 - lr: 0.000048 - momentum: 0.000000
2024-03-26 16:33:49,178 epoch 2 - iter 45/95 - loss 0.35971712 - time (sec): 9.75 - samples/sec: 1731.63 - lr: 0.000047 - momentum: 0.000000
2024-03-26 16:33:50,489 epoch 2 - iter 54/95 - loss 0.35603409 - time (sec): 11.06 - samples/sec: 1777.46 - lr: 0.000047 - momentum: 0.000000
2024-03-26 16:33:52,045 epoch 2 - iter 63/95 - loss 0.34355218 - time (sec): 12.61 - samples/sec: 1794.13 - lr: 0.000046 - momentum: 0.000000
2024-03-26 16:33:54,098 epoch 2 - iter 72/95 - loss 0.33787014 - time (sec): 14.67 - samples/sec: 1786.93 - lr: 0.000046 - momentum: 0.000000
2024-03-26 16:33:55,994 epoch 2 - iter 81/95 - loss 0.34238730 - time (sec): 16.56 - samples/sec: 1786.65 - lr: 0.000045 - momentum: 0.000000
2024-03-26 16:33:57,912 epoch 2 - iter 90/95 - loss 0.32998840 - time (sec): 18.48 - samples/sec: 1789.66 - lr: 0.000045 - momentum: 0.000000
2024-03-26 16:33:58,495 ----------------------------------------------------------------------------------------------------
2024-03-26 16:33:58,495 EPOCH 2 done: loss 0.3291 - lr: 0.000045
2024-03-26 16:33:59,391 DEV : loss 0.27971890568733215 - f1-score (micro avg) 0.8157
2024-03-26 16:33:59,394 saving best model
2024-03-26 16:33:59,877 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:01,083 epoch 3 - iter 9/95 - loss 0.28513758 - time (sec): 1.20 - samples/sec: 2154.65 - lr: 0.000044 - momentum: 0.000000
2024-03-26 16:34:03,315 epoch 3 - iter 18/95 - loss 0.21533520 - time (sec): 3.44 - samples/sec: 1868.50 - lr: 0.000043 - momentum: 0.000000
2024-03-26 16:34:05,003 epoch 3 - iter 27/95 - loss 0.21474052 - time (sec): 5.12 - samples/sec: 1904.62 - lr: 0.000043 - momentum: 0.000000
2024-03-26 16:34:06,685 epoch 3 - iter 36/95 - loss 0.19999637 - time (sec): 6.81 - samples/sec: 1935.08 - lr: 0.000042 - momentum: 0.000000
2024-03-26 16:34:08,123 epoch 3 - iter 45/95 - loss 0.18922890 - time (sec): 8.24 - samples/sec: 1926.51 - lr: 0.000042 - momentum: 0.000000
2024-03-26 16:34:10,232 epoch 3 - iter 54/95 - loss 0.18514483 - time (sec): 10.35 - samples/sec: 1866.13 - lr: 0.000041 - momentum: 0.000000
2024-03-26 16:34:11,896 epoch 3 - iter 63/95 - loss 0.18888961 - time (sec): 12.02 - samples/sec: 1852.20 - lr: 0.000041 - momentum: 0.000000
2024-03-26 16:34:14,159 epoch 3 - iter 72/95 - loss 0.17931067 - time (sec): 14.28 - samples/sec: 1816.53 - lr: 0.000040 - momentum: 0.000000
2024-03-26 16:34:16,324 epoch 3 - iter 81/95 - loss 0.18087446 - time (sec): 16.44 - samples/sec: 1810.10 - lr: 0.000040 - momentum: 0.000000
2024-03-26 16:34:18,062 epoch 3 - iter 90/95 - loss 0.17560689 - time (sec): 18.18 - samples/sec: 1799.62 - lr: 0.000039 - momentum: 0.000000
2024-03-26 16:34:18,932 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:18,932 EPOCH 3 done: loss 0.1744 - lr: 0.000039
2024-03-26 16:34:19,825 DEV : loss 0.23761968314647675 - f1-score (micro avg) 0.8655
2024-03-26 16:34:19,826 saving best model
2024-03-26 16:34:20,292 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:23,059 epoch 4 - iter 9/95 - loss 0.09834786 - time (sec): 2.76 - samples/sec: 1543.55 - lr: 0.000039 - momentum: 0.000000
2024-03-26 16:34:24,091 epoch 4 - iter 18/95 - loss 0.13033853 - time (sec): 3.80 - samples/sec: 1752.42 - lr: 0.000038 - momentum: 0.000000
2024-03-26 16:34:26,586 epoch 4 - iter 27/95 - loss 0.11939331 - time (sec): 6.29 - samples/sec: 1690.80 - lr: 0.000037 - momentum: 0.000000
2024-03-26 16:34:29,194 epoch 4 - iter 36/95 - loss 0.11628526 - time (sec): 8.90 - samples/sec: 1630.71 - lr: 0.000037 - momentum: 0.000000
2024-03-26 16:34:30,888 epoch 4 - iter 45/95 - loss 0.10860399 - time (sec): 10.59 - samples/sec: 1662.50 - lr: 0.000036 - momentum: 0.000000
2024-03-26 16:34:32,590 epoch 4 - iter 54/95 - loss 0.11019024 - time (sec): 12.30 - samples/sec: 1675.39 - lr: 0.000036 - momentum: 0.000000
2024-03-26 16:34:34,490 epoch 4 - iter 63/95 - loss 0.10937511 - time (sec): 14.20 - samples/sec: 1701.64 - lr: 0.000035 - momentum: 0.000000
2024-03-26 16:34:36,158 epoch 4 - iter 72/95 - loss 0.11112580 - time (sec): 15.86 - samples/sec: 1749.69 - lr: 0.000035 - momentum: 0.000000
2024-03-26 16:34:37,187 epoch 4 - iter 81/95 - loss 0.11246023 - time (sec): 16.89 - samples/sec: 1788.59 - lr: 0.000034 - momentum: 0.000000
2024-03-26 16:34:38,590 epoch 4 - iter 90/95 - loss 0.11310225 - time (sec): 18.30 - samples/sec: 1813.96 - lr: 0.000034 - momentum: 0.000000
2024-03-26 16:34:39,123 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:39,123 EPOCH 4 done: loss 0.1155 - lr: 0.000034
2024-03-26 16:34:40,019 DEV : loss 0.1822824329137802 - f1-score (micro avg) 0.8987
2024-03-26 16:34:40,020 saving best model
2024-03-26 16:34:40,469 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:42,116 epoch 5 - iter 9/95 - loss 0.10147143 - time (sec): 1.65 - samples/sec: 1990.52 - lr: 0.000033 - momentum: 0.000000
2024-03-26 16:34:44,068 epoch 5 - iter 18/95 - loss 0.09338652 - time (sec): 3.60 - samples/sec: 1979.21 - lr: 0.000032 - momentum: 0.000000
2024-03-26 16:34:46,183 epoch 5 - iter 27/95 - loss 0.07607096 - time (sec): 5.71 - samples/sec: 1853.46 - lr: 0.000032 - momentum: 0.000000
2024-03-26 16:34:47,507 epoch 5 - iter 36/95 - loss 0.08827446 - time (sec): 7.04 - samples/sec: 1910.63 - lr: 0.000031 - momentum: 0.000000
2024-03-26 16:34:49,587 epoch 5 - iter 45/95 - loss 0.08470804 - time (sec): 9.12 - samples/sec: 1869.04 - lr: 0.000031 - momentum: 0.000000
2024-03-26 16:34:50,755 epoch 5 - iter 54/95 - loss 0.08922696 - time (sec): 10.28 - samples/sec: 1903.76 - lr: 0.000030 - momentum: 0.000000
2024-03-26 16:34:52,219 epoch 5 - iter 63/95 - loss 0.09288529 - time (sec): 11.75 - samples/sec: 1918.98 - lr: 0.000030 - momentum: 0.000000
2024-03-26 16:34:54,145 epoch 5 - iter 72/95 - loss 0.09210498 - time (sec): 13.67 - samples/sec: 1888.50 - lr: 0.000029 - momentum: 0.000000
2024-03-26 16:34:55,901 epoch 5 - iter 81/95 - loss 0.08981069 - time (sec): 15.43 - samples/sec: 1877.15 - lr: 0.000029 - momentum: 0.000000
2024-03-26 16:34:58,305 epoch 5 - iter 90/95 - loss 0.08713307 - time (sec): 17.83 - samples/sec: 1843.54 - lr: 0.000028 - momentum: 0.000000
2024-03-26 16:34:59,269 ----------------------------------------------------------------------------------------------------
2024-03-26 16:34:59,269 EPOCH 5 done: loss 0.0848 - lr: 0.000028
2024-03-26 16:35:00,165 DEV : loss 0.20745961368083954 - f1-score (micro avg) 0.9146
2024-03-26 16:35:00,166 saving best model
2024-03-26 16:35:00,613 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:02,546 epoch 6 - iter 9/95 - loss 0.06298504 - time (sec): 1.93 - samples/sec: 1688.35 - lr: 0.000027 - momentum: 0.000000
2024-03-26 16:35:05,041 epoch 6 - iter 18/95 - loss 0.06865678 - time (sec): 4.43 - samples/sec: 1675.17 - lr: 0.000027 - momentum: 0.000000
2024-03-26 16:35:06,182 epoch 6 - iter 27/95 - loss 0.08561234 - time (sec): 5.57 - samples/sec: 1775.90 - lr: 0.000026 - momentum: 0.000000
2024-03-26 16:35:07,777 epoch 6 - iter 36/95 - loss 0.07632065 - time (sec): 7.16 - samples/sec: 1801.53 - lr: 0.000026 - momentum: 0.000000
2024-03-26 16:35:09,716 epoch 6 - iter 45/95 - loss 0.07129585 - time (sec): 9.10 - samples/sec: 1795.11 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:35:11,849 epoch 6 - iter 54/95 - loss 0.06756906 - time (sec): 11.23 - samples/sec: 1761.43 - lr: 0.000025 - momentum: 0.000000
2024-03-26 16:35:13,520 epoch 6 - iter 63/95 - loss 0.07022057 - time (sec): 12.91 - samples/sec: 1779.73 - lr: 0.000024 - momentum: 0.000000
2024-03-26 16:35:15,066 epoch 6 - iter 72/95 - loss 0.06980907 - time (sec): 14.45 - samples/sec: 1802.03 - lr: 0.000024 - momentum: 0.000000
2024-03-26 16:35:16,293 epoch 6 - iter 81/95 - loss 0.06957376 - time (sec): 15.68 - samples/sec: 1833.37 - lr: 0.000023 - momentum: 0.000000
2024-03-26 16:35:18,155 epoch 6 - iter 90/95 - loss 0.06638177 - time (sec): 17.54 - samples/sec: 1831.90 - lr: 0.000023 - momentum: 0.000000
2024-03-26 16:35:19,658 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:19,658 EPOCH 6 done: loss 0.0642 - lr: 0.000023
2024-03-26 16:35:20,560 DEV : loss 0.23903107643127441 - f1-score (micro avg) 0.8977
2024-03-26 16:35:20,561 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:22,226 epoch 7 - iter 9/95 - loss 0.03188809 - time (sec): 1.66 - samples/sec: 1891.74 - lr: 0.000022 - momentum: 0.000000
2024-03-26 16:35:23,710 epoch 7 - iter 18/95 - loss 0.03992625 - time (sec): 3.15 - samples/sec: 1868.11 - lr: 0.000021 - momentum: 0.000000
2024-03-26 16:35:24,993 epoch 7 - iter 27/95 - loss 0.05762778 - time (sec): 4.43 - samples/sec: 1910.82 - lr: 0.000021 - momentum: 0.000000
2024-03-26 16:35:27,221 epoch 7 - iter 36/95 - loss 0.05070152 - time (sec): 6.66 - samples/sec: 1908.52 - lr: 0.000020 - momentum: 0.000000
2024-03-26 16:35:29,115 epoch 7 - iter 45/95 - loss 0.05323369 - time (sec): 8.55 - samples/sec: 1903.57 - lr: 0.000020 - momentum: 0.000000
2024-03-26 16:35:30,786 epoch 7 - iter 54/95 - loss 0.05403030 - time (sec): 10.22 - samples/sec: 1896.56 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:35:32,336 epoch 7 - iter 63/95 - loss 0.05286632 - time (sec): 11.77 - samples/sec: 1914.22 - lr: 0.000019 - momentum: 0.000000
2024-03-26 16:35:33,836 epoch 7 - iter 72/95 - loss 0.05383539 - time (sec): 13.27 - samples/sec: 1904.23 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:35:36,517 epoch 7 - iter 81/95 - loss 0.05219211 - time (sec): 15.96 - samples/sec: 1841.30 - lr: 0.000018 - momentum: 0.000000
2024-03-26 16:35:38,113 epoch 7 - iter 90/95 - loss 0.05217584 - time (sec): 17.55 - samples/sec: 1850.36 - lr: 0.000017 - momentum: 0.000000
2024-03-26 16:35:39,273 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:39,273 EPOCH 7 done: loss 0.0517 - lr: 0.000017
2024-03-26 16:35:40,170 DEV : loss 0.20635825395584106 - f1-score (micro avg) 0.9314
2024-03-26 16:35:40,171 saving best model
2024-03-26 16:35:40,618 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:42,763 epoch 8 - iter 9/95 - loss 0.05102066 - time (sec): 2.14 - samples/sec: 1577.33 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:35:44,258 epoch 8 - iter 18/95 - loss 0.03497137 - time (sec): 3.64 - samples/sec: 1677.58 - lr: 0.000016 - momentum: 0.000000
2024-03-26 16:35:46,235 epoch 8 - iter 27/95 - loss 0.03720698 - time (sec): 5.61 - samples/sec: 1747.52 - lr: 0.000015 - momentum: 0.000000
2024-03-26 16:35:48,192 epoch 8 - iter 36/95 - loss 0.03472594 - time (sec): 7.57 - samples/sec: 1778.05 - lr: 0.000015 - momentum: 0.000000
2024-03-26 16:35:49,597 epoch 8 - iter 45/95 - loss 0.03123332 - time (sec): 8.98 - samples/sec: 1833.42 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:35:51,078 epoch 8 - iter 54/95 - loss 0.03271144 - time (sec): 10.46 - samples/sec: 1900.25 - lr: 0.000014 - momentum: 0.000000
2024-03-26 16:35:52,630 epoch 8 - iter 63/95 - loss 0.03378471 - time (sec): 12.01 - samples/sec: 1893.53 - lr: 0.000013 - momentum: 0.000000
2024-03-26 16:35:54,701 epoch 8 - iter 72/95 - loss 0.03345516 - time (sec): 14.08 - samples/sec: 1859.48 - lr: 0.000013 - momentum: 0.000000
2024-03-26 16:35:56,255 epoch 8 - iter 81/95 - loss 0.03613973 - time (sec): 15.63 - samples/sec: 1883.43 - lr: 0.000012 - momentum: 0.000000
2024-03-26 16:35:58,309 epoch 8 - iter 90/95 - loss 0.03668683 - time (sec): 17.69 - samples/sec: 1858.78 - lr: 0.000012 - momentum: 0.000000
2024-03-26 16:35:58,941 ----------------------------------------------------------------------------------------------------
2024-03-26 16:35:58,941 EPOCH 8 done: loss 0.0367 - lr: 0.000012
2024-03-26 16:35:59,840 DEV : loss 0.21807697415351868 - f1-score (micro avg) 0.9353
2024-03-26 16:35:59,841 saving best model
2024-03-26 16:36:00,324 ----------------------------------------------------------------------------------------------------
2024-03-26 16:36:02,854 epoch 9 - iter 9/95 - loss 0.01698379 - time (sec): 2.53 - samples/sec: 1706.11 - lr: 0.000011 - momentum: 0.000000
2024-03-26 16:36:04,400 epoch 9 - iter 18/95 - loss 0.02484097 - time (sec): 4.07 - samples/sec: 1775.05 - lr: 0.000010 - momentum: 0.000000
2024-03-26 16:36:06,866 epoch 9 - iter 27/95 - loss 0.02660767 - time (sec): 6.54 - samples/sec: 1728.36 - lr: 0.000010 - momentum: 0.000000
2024-03-26 16:36:08,677 epoch 9 - iter 36/95 - loss 0.03340323 - time (sec): 8.35 - samples/sec: 1735.27 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:36:09,836 epoch 9 - iter 45/95 - loss 0.03134273 - time (sec): 9.51 - samples/sec: 1793.48 - lr: 0.000009 - momentum: 0.000000
2024-03-26 16:36:11,581 epoch 9 - iter 54/95 - loss 0.02840040 - time (sec): 11.26 - samples/sec: 1782.53 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:36:12,959 epoch 9 - iter 63/95 - loss 0.02914536 - time (sec): 12.63 - samples/sec: 1828.49 - lr: 0.000008 - momentum: 0.000000
2024-03-26 16:36:14,120 epoch 9 - iter 72/95 - loss 0.02916945 - time (sec): 13.80 - samples/sec: 1878.07 - lr: 0.000007 - momentum: 0.000000
2024-03-26 16:36:15,647 epoch 9 - iter 81/95 - loss 0.02734729 - time (sec): 15.32 - samples/sec: 1874.96 - lr: 0.000007 - momentum: 0.000000
2024-03-26 16:36:18,381 epoch 9 - iter 90/95 - loss 0.03042663 - time (sec): 18.06 - samples/sec: 1826.28 - lr: 0.000006 - momentum: 0.000000
2024-03-26 16:36:19,146 ----------------------------------------------------------------------------------------------------
2024-03-26 16:36:19,146 EPOCH 9 done: loss 0.0293 - lr: 0.000006
2024-03-26 16:36:20,074 DEV : loss 0.2363407462835312 - f1-score (micro avg) 0.9318
2024-03-26 16:36:20,075 ----------------------------------------------------------------------------------------------------
2024-03-26 16:36:22,516 epoch 10 - iter 9/95 - loss 0.01719432 - time (sec): 2.44 - samples/sec: 1653.22 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:36:24,089 epoch 10 - iter 18/95 - loss 0.01636941 - time (sec): 4.01 - samples/sec: 1737.00 - lr: 0.000005 - momentum: 0.000000
2024-03-26 16:36:26,052 epoch 10 - iter 27/95 - loss 0.01537360 - time (sec): 5.98 - samples/sec: 1686.18 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:36:28,118 epoch 10 - iter 36/95 - loss 0.01809330 - time (sec): 8.04 - samples/sec: 1696.81 - lr: 0.000004 - momentum: 0.000000
2024-03-26 16:36:29,963 epoch 10 - iter 45/95 - loss 0.02032623 - time (sec): 9.89 - samples/sec: 1715.48 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:36:31,080 epoch 10 - iter 54/95 - loss 0.02405996 - time (sec): 11.01 - samples/sec: 1780.21 - lr: 0.000003 - momentum: 0.000000
2024-03-26 16:36:32,694 epoch 10 - iter 63/95 - loss 0.02883736 - time (sec): 12.62 - samples/sec: 1803.44 - lr: 0.000002 - momentum: 0.000000
2024-03-26 16:36:34,495 epoch 10 - iter 72/95 - loss 0.02729134 - time (sec): 14.42 - samples/sec: 1794.00 - lr: 0.000002 - momentum: 0.000000
2024-03-26 16:36:36,161 epoch 10 - iter 81/95 - loss 0.02833043 - time (sec): 16.09 - samples/sec: 1805.05 - lr: 0.000001 - momentum: 0.000000
2024-03-26 16:36:38,922 epoch 10 - iter 90/95 - loss 0.02634051 - time (sec): 18.85 - samples/sec: 1768.96 - lr: 0.000001 - momentum: 0.000000
2024-03-26 16:36:39,478 ----------------------------------------------------------------------------------------------------
2024-03-26 16:36:39,478 EPOCH 10 done: loss 0.0266 - lr: 0.000001
2024-03-26 16:36:40,374 DEV : loss 0.2326352298259735 - f1-score (micro avg) 0.9364
2024-03-26 16:36:40,375 saving best model
2024-03-26 16:36:41,077 ----------------------------------------------------------------------------------------------------
2024-03-26 16:36:41,077 Loading model from best epoch ...
2024-03-26 16:36:41,933 SequenceTagger predicts: Dictionary with 17 tags: O, S-Unternehmen, B-Unternehmen, E-Unternehmen, I-Unternehmen, S-Auslagerung, B-Auslagerung, E-Auslagerung, I-Auslagerung, S-Ort, B-Ort, E-Ort, I-Ort, S-Software, B-Software, E-Software, I-Software
2024-03-26 16:36:42,672
Results:
- F-score (micro) 0.9091
- F-score (macro) 0.6899
- Accuracy 0.8368
By class:
precision recall f1-score support
Unternehmen 0.9119 0.8947 0.9032 266
Auslagerung 0.8687 0.9036 0.8858 249
Ort 0.9565 0.9851 0.9706 134
Software 0.0000 0.0000 0.0000 0
micro avg 0.9015 0.9168 0.9091 649
macro avg 0.6843 0.6959 0.6899 649
weighted avg 0.9045 0.9168 0.9105 649
2024-03-26 16:36:42,672 ----------------------------------------------------------------------------------------------------
|