File size: 23,737 Bytes
bfc0b70 |
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 |
2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,484 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(30001, 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 11:25:08,484 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,484 Corpus: 758 train + 94 dev + 96 test sentences
2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,484 Train: 758 sentences
2024-03-26 11:25:08,484 (train_with_dev=False, train_with_test=False)
2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,484 Training Params:
2024-03-26 11:25:08,484 - learning_rate: "5e-05"
2024-03-26 11:25:08,484 - mini_batch_size: "8"
2024-03-26 11:25:08,484 - max_epochs: "10"
2024-03-26 11:25:08,484 - shuffle: "True"
2024-03-26 11:25:08,484 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,484 Plugins:
2024-03-26 11:25:08,484 - TensorboardLogger
2024-03-26 11:25:08,485 - LinearScheduler | warmup_fraction: '0.1'
2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,485 Final evaluation on model from best epoch (best-model.pt)
2024-03-26 11:25:08,485 - metric: "('micro avg', 'f1-score')"
2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,485 Computation:
2024-03-26 11:25:08,485 - compute on device: cuda:0
2024-03-26 11:25:08,485 - embedding storage: none
2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,485 Model training base path: "flair-co-funer-german_bert_base-bs8-e10-lr5e-05-2"
2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,485 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:08,485 Logging anything other than scalars to TensorBoard is currently not supported.
2024-03-26 11:25:10,385 epoch 1 - iter 9/95 - loss 3.09716797 - time (sec): 1.90 - samples/sec: 1854.36 - lr: 0.000004 - momentum: 0.000000
2024-03-26 11:25:12,609 epoch 1 - iter 18/95 - loss 2.98425342 - time (sec): 4.12 - samples/sec: 1747.66 - lr: 0.000009 - momentum: 0.000000
2024-03-26 11:25:14,206 epoch 1 - iter 27/95 - loss 2.75626977 - time (sec): 5.72 - samples/sec: 1762.22 - lr: 0.000014 - momentum: 0.000000
2024-03-26 11:25:16,182 epoch 1 - iter 36/95 - loss 2.52340752 - time (sec): 7.70 - samples/sec: 1793.07 - lr: 0.000018 - momentum: 0.000000
2024-03-26 11:25:18,306 epoch 1 - iter 45/95 - loss 2.33537982 - time (sec): 9.82 - samples/sec: 1736.01 - lr: 0.000023 - momentum: 0.000000
2024-03-26 11:25:20,363 epoch 1 - iter 54/95 - loss 2.14784687 - time (sec): 11.88 - samples/sec: 1709.56 - lr: 0.000028 - momentum: 0.000000
2024-03-26 11:25:21,947 epoch 1 - iter 63/95 - loss 1.99895001 - time (sec): 13.46 - samples/sec: 1718.46 - lr: 0.000033 - momentum: 0.000000
2024-03-26 11:25:23,260 epoch 1 - iter 72/95 - loss 1.86613909 - time (sec): 14.77 - samples/sec: 1769.97 - lr: 0.000037 - momentum: 0.000000
2024-03-26 11:25:24,845 epoch 1 - iter 81/95 - loss 1.73720955 - time (sec): 16.36 - samples/sec: 1798.08 - lr: 0.000042 - momentum: 0.000000
2024-03-26 11:25:26,876 epoch 1 - iter 90/95 - loss 1.62324711 - time (sec): 18.39 - samples/sec: 1773.05 - lr: 0.000047 - momentum: 0.000000
2024-03-26 11:25:27,991 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:27,991 EPOCH 1 done: loss 1.5628 - lr: 0.000047
2024-03-26 11:25:28,925 DEV : loss 0.42946571111679077 - f1-score (micro avg) 0.6734
2024-03-26 11:25:28,926 saving best model
2024-03-26 11:25:29,186 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:30,531 epoch 2 - iter 9/95 - loss 0.52425744 - time (sec): 1.34 - samples/sec: 2412.74 - lr: 0.000050 - momentum: 0.000000
2024-03-26 11:25:32,418 epoch 2 - iter 18/95 - loss 0.42454204 - time (sec): 3.23 - samples/sec: 2125.97 - lr: 0.000049 - momentum: 0.000000
2024-03-26 11:25:35,299 epoch 2 - iter 27/95 - loss 0.35787075 - time (sec): 6.11 - samples/sec: 1890.91 - lr: 0.000048 - momentum: 0.000000
2024-03-26 11:25:37,460 epoch 2 - iter 36/95 - loss 0.33935478 - time (sec): 8.27 - samples/sec: 1796.90 - lr: 0.000048 - momentum: 0.000000
2024-03-26 11:25:39,264 epoch 2 - iter 45/95 - loss 0.32453877 - time (sec): 10.08 - samples/sec: 1783.53 - lr: 0.000047 - momentum: 0.000000
2024-03-26 11:25:41,421 epoch 2 - iter 54/95 - loss 0.31681048 - time (sec): 12.23 - samples/sec: 1739.10 - lr: 0.000047 - momentum: 0.000000
2024-03-26 11:25:43,050 epoch 2 - iter 63/95 - loss 0.32280342 - time (sec): 13.86 - samples/sec: 1755.49 - lr: 0.000046 - momentum: 0.000000
2024-03-26 11:25:44,582 epoch 2 - iter 72/95 - loss 0.31919664 - time (sec): 15.40 - samples/sec: 1781.82 - lr: 0.000046 - momentum: 0.000000
2024-03-26 11:25:45,762 epoch 2 - iter 81/95 - loss 0.31666683 - time (sec): 16.58 - samples/sec: 1817.58 - lr: 0.000045 - momentum: 0.000000
2024-03-26 11:25:47,062 epoch 2 - iter 90/95 - loss 0.31133068 - time (sec): 17.88 - samples/sec: 1840.38 - lr: 0.000045 - momentum: 0.000000
2024-03-26 11:25:48,058 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:48,058 EPOCH 2 done: loss 0.3026 - lr: 0.000045
2024-03-26 11:25:48,986 DEV : loss 0.2420356720685959 - f1-score (micro avg) 0.8595
2024-03-26 11:25:48,987 saving best model
2024-03-26 11:25:49,407 ----------------------------------------------------------------------------------------------------
2024-03-26 11:25:51,437 epoch 3 - iter 9/95 - loss 0.16715958 - time (sec): 2.03 - samples/sec: 1641.60 - lr: 0.000044 - momentum: 0.000000
2024-03-26 11:25:53,556 epoch 3 - iter 18/95 - loss 0.17381845 - time (sec): 4.15 - samples/sec: 1751.20 - lr: 0.000043 - momentum: 0.000000
2024-03-26 11:25:54,531 epoch 3 - iter 27/95 - loss 0.17679162 - time (sec): 5.12 - samples/sec: 1878.86 - lr: 0.000043 - momentum: 0.000000
2024-03-26 11:25:56,295 epoch 3 - iter 36/95 - loss 0.18025597 - time (sec): 6.89 - samples/sec: 1842.80 - lr: 0.000042 - momentum: 0.000000
2024-03-26 11:25:57,578 epoch 3 - iter 45/95 - loss 0.19307875 - time (sec): 8.17 - samples/sec: 1885.50 - lr: 0.000042 - momentum: 0.000000
2024-03-26 11:25:59,636 epoch 3 - iter 54/95 - loss 0.19055428 - time (sec): 10.23 - samples/sec: 1828.08 - lr: 0.000041 - momentum: 0.000000
2024-03-26 11:26:01,285 epoch 3 - iter 63/95 - loss 0.18895940 - time (sec): 11.88 - samples/sec: 1837.87 - lr: 0.000041 - momentum: 0.000000
2024-03-26 11:26:02,859 epoch 3 - iter 72/95 - loss 0.18580014 - time (sec): 13.45 - samples/sec: 1842.25 - lr: 0.000040 - momentum: 0.000000
2024-03-26 11:26:04,674 epoch 3 - iter 81/95 - loss 0.17923377 - time (sec): 15.27 - samples/sec: 1831.34 - lr: 0.000040 - momentum: 0.000000
2024-03-26 11:26:07,356 epoch 3 - iter 90/95 - loss 0.16261609 - time (sec): 17.95 - samples/sec: 1822.14 - lr: 0.000039 - momentum: 0.000000
2024-03-26 11:26:08,536 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:08,536 EPOCH 3 done: loss 0.1590 - lr: 0.000039
2024-03-26 11:26:09,461 DEV : loss 0.2054598480463028 - f1-score (micro avg) 0.8766
2024-03-26 11:26:09,462 saving best model
2024-03-26 11:26:09,906 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:11,637 epoch 4 - iter 9/95 - loss 0.14638681 - time (sec): 1.73 - samples/sec: 1859.05 - lr: 0.000039 - momentum: 0.000000
2024-03-26 11:26:13,727 epoch 4 - iter 18/95 - loss 0.12145680 - time (sec): 3.82 - samples/sec: 1763.69 - lr: 0.000038 - momentum: 0.000000
2024-03-26 11:26:14,982 epoch 4 - iter 27/95 - loss 0.11451776 - time (sec): 5.07 - samples/sec: 1854.74 - lr: 0.000037 - momentum: 0.000000
2024-03-26 11:26:16,682 epoch 4 - iter 36/95 - loss 0.11076776 - time (sec): 6.77 - samples/sec: 1832.49 - lr: 0.000037 - momentum: 0.000000
2024-03-26 11:26:18,901 epoch 4 - iter 45/95 - loss 0.11578584 - time (sec): 8.99 - samples/sec: 1775.37 - lr: 0.000036 - momentum: 0.000000
2024-03-26 11:26:20,465 epoch 4 - iter 54/95 - loss 0.12488811 - time (sec): 10.56 - samples/sec: 1787.73 - lr: 0.000036 - momentum: 0.000000
2024-03-26 11:26:22,981 epoch 4 - iter 63/95 - loss 0.12320034 - time (sec): 13.07 - samples/sec: 1743.98 - lr: 0.000035 - momentum: 0.000000
2024-03-26 11:26:25,529 epoch 4 - iter 72/95 - loss 0.11446488 - time (sec): 15.62 - samples/sec: 1712.38 - lr: 0.000035 - momentum: 0.000000
2024-03-26 11:26:26,993 epoch 4 - iter 81/95 - loss 0.11224908 - time (sec): 17.09 - samples/sec: 1720.04 - lr: 0.000034 - momentum: 0.000000
2024-03-26 11:26:28,824 epoch 4 - iter 90/95 - loss 0.11286006 - time (sec): 18.92 - samples/sec: 1719.75 - lr: 0.000034 - momentum: 0.000000
2024-03-26 11:26:29,991 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:29,991 EPOCH 4 done: loss 0.1095 - lr: 0.000034
2024-03-26 11:26:30,941 DEV : loss 0.17261318862438202 - f1-score (micro avg) 0.9079
2024-03-26 11:26:30,942 saving best model
2024-03-26 11:26:31,383 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:32,354 epoch 5 - iter 9/95 - loss 0.06453080 - time (sec): 0.97 - samples/sec: 2125.49 - lr: 0.000033 - momentum: 0.000000
2024-03-26 11:26:33,984 epoch 5 - iter 18/95 - loss 0.08104053 - time (sec): 2.60 - samples/sec: 2047.72 - lr: 0.000032 - momentum: 0.000000
2024-03-26 11:26:36,556 epoch 5 - iter 27/95 - loss 0.08099319 - time (sec): 5.17 - samples/sec: 1762.87 - lr: 0.000032 - momentum: 0.000000
2024-03-26 11:26:38,458 epoch 5 - iter 36/95 - loss 0.07354078 - time (sec): 7.07 - samples/sec: 1753.97 - lr: 0.000031 - momentum: 0.000000
2024-03-26 11:26:40,466 epoch 5 - iter 45/95 - loss 0.07068799 - time (sec): 9.08 - samples/sec: 1721.12 - lr: 0.000031 - momentum: 0.000000
2024-03-26 11:26:42,119 epoch 5 - iter 54/95 - loss 0.07369301 - time (sec): 10.73 - samples/sec: 1755.40 - lr: 0.000030 - momentum: 0.000000
2024-03-26 11:26:44,549 epoch 5 - iter 63/95 - loss 0.07522678 - time (sec): 13.16 - samples/sec: 1739.81 - lr: 0.000030 - momentum: 0.000000
2024-03-26 11:26:45,980 epoch 5 - iter 72/95 - loss 0.08100158 - time (sec): 14.60 - samples/sec: 1759.93 - lr: 0.000029 - momentum: 0.000000
2024-03-26 11:26:47,908 epoch 5 - iter 81/95 - loss 0.07798969 - time (sec): 16.52 - samples/sec: 1737.95 - lr: 0.000029 - momentum: 0.000000
2024-03-26 11:26:49,814 epoch 5 - iter 90/95 - loss 0.07834740 - time (sec): 18.43 - samples/sec: 1739.35 - lr: 0.000028 - momentum: 0.000000
2024-03-26 11:26:51,195 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:51,195 EPOCH 5 done: loss 0.0785 - lr: 0.000028
2024-03-26 11:26:52,138 DEV : loss 0.18624915182590485 - f1-score (micro avg) 0.9194
2024-03-26 11:26:52,141 saving best model
2024-03-26 11:26:52,566 ----------------------------------------------------------------------------------------------------
2024-03-26 11:26:54,098 epoch 6 - iter 9/95 - loss 0.05414098 - time (sec): 1.53 - samples/sec: 1882.26 - lr: 0.000027 - momentum: 0.000000
2024-03-26 11:26:56,308 epoch 6 - iter 18/95 - loss 0.05167176 - time (sec): 3.74 - samples/sec: 1917.26 - lr: 0.000027 - momentum: 0.000000
2024-03-26 11:26:57,907 epoch 6 - iter 27/95 - loss 0.05120337 - time (sec): 5.34 - samples/sec: 1881.23 - lr: 0.000026 - momentum: 0.000000
2024-03-26 11:26:59,948 epoch 6 - iter 36/95 - loss 0.05928124 - time (sec): 7.38 - samples/sec: 1829.62 - lr: 0.000026 - momentum: 0.000000
2024-03-26 11:27:02,159 epoch 6 - iter 45/95 - loss 0.06953449 - time (sec): 9.59 - samples/sec: 1852.31 - lr: 0.000025 - momentum: 0.000000
2024-03-26 11:27:03,364 epoch 6 - iter 54/95 - loss 0.06636505 - time (sec): 10.79 - samples/sec: 1872.73 - lr: 0.000025 - momentum: 0.000000
2024-03-26 11:27:04,452 epoch 6 - iter 63/95 - loss 0.06537325 - time (sec): 11.88 - samples/sec: 1894.58 - lr: 0.000024 - momentum: 0.000000
2024-03-26 11:27:06,016 epoch 6 - iter 72/95 - loss 0.06000050 - time (sec): 13.45 - samples/sec: 1898.69 - lr: 0.000024 - momentum: 0.000000
2024-03-26 11:27:08,069 epoch 6 - iter 81/95 - loss 0.05966242 - time (sec): 15.50 - samples/sec: 1886.10 - lr: 0.000023 - momentum: 0.000000
2024-03-26 11:27:10,124 epoch 6 - iter 90/95 - loss 0.05915014 - time (sec): 17.56 - samples/sec: 1873.42 - lr: 0.000023 - momentum: 0.000000
2024-03-26 11:27:11,088 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:11,088 EPOCH 6 done: loss 0.0573 - lr: 0.000023
2024-03-26 11:27:12,028 DEV : loss 0.19410739839076996 - f1-score (micro avg) 0.9256
2024-03-26 11:27:12,031 saving best model
2024-03-26 11:27:12,463 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:13,906 epoch 7 - iter 9/95 - loss 0.01965996 - time (sec): 1.44 - samples/sec: 1844.63 - lr: 0.000022 - momentum: 0.000000
2024-03-26 11:27:15,772 epoch 7 - iter 18/95 - loss 0.03318242 - time (sec): 3.31 - samples/sec: 1752.16 - lr: 0.000021 - momentum: 0.000000
2024-03-26 11:27:17,412 epoch 7 - iter 27/95 - loss 0.03102681 - time (sec): 4.95 - samples/sec: 1843.86 - lr: 0.000021 - momentum: 0.000000
2024-03-26 11:27:19,183 epoch 7 - iter 36/95 - loss 0.03313823 - time (sec): 6.72 - samples/sec: 1789.96 - lr: 0.000020 - momentum: 0.000000
2024-03-26 11:27:20,563 epoch 7 - iter 45/95 - loss 0.03466366 - time (sec): 8.10 - samples/sec: 1810.58 - lr: 0.000020 - momentum: 0.000000
2024-03-26 11:27:22,675 epoch 7 - iter 54/95 - loss 0.03377152 - time (sec): 10.21 - samples/sec: 1755.65 - lr: 0.000019 - momentum: 0.000000
2024-03-26 11:27:24,978 epoch 7 - iter 63/95 - loss 0.03490540 - time (sec): 12.51 - samples/sec: 1706.02 - lr: 0.000019 - momentum: 0.000000
2024-03-26 11:27:27,678 epoch 7 - iter 72/95 - loss 0.04113555 - time (sec): 15.21 - samples/sec: 1694.55 - lr: 0.000018 - momentum: 0.000000
2024-03-26 11:27:29,683 epoch 7 - iter 81/95 - loss 0.04662207 - time (sec): 17.22 - samples/sec: 1702.18 - lr: 0.000018 - momentum: 0.000000
2024-03-26 11:27:31,707 epoch 7 - iter 90/95 - loss 0.04632564 - time (sec): 19.24 - samples/sec: 1703.41 - lr: 0.000017 - momentum: 0.000000
2024-03-26 11:27:32,660 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:32,660 EPOCH 7 done: loss 0.0458 - lr: 0.000017
2024-03-26 11:27:33,604 DEV : loss 0.19183886051177979 - f1-score (micro avg) 0.9122
2024-03-26 11:27:33,607 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:35,920 epoch 8 - iter 9/95 - loss 0.03236922 - time (sec): 2.31 - samples/sec: 1638.73 - lr: 0.000016 - momentum: 0.000000
2024-03-26 11:27:37,498 epoch 8 - iter 18/95 - loss 0.03529936 - time (sec): 3.89 - samples/sec: 1771.62 - lr: 0.000016 - momentum: 0.000000
2024-03-26 11:27:39,688 epoch 8 - iter 27/95 - loss 0.04103026 - time (sec): 6.08 - samples/sec: 1738.97 - lr: 0.000015 - momentum: 0.000000
2024-03-26 11:27:41,266 epoch 8 - iter 36/95 - loss 0.03739362 - time (sec): 7.66 - samples/sec: 1761.75 - lr: 0.000015 - momentum: 0.000000
2024-03-26 11:27:43,191 epoch 8 - iter 45/95 - loss 0.03747045 - time (sec): 9.58 - samples/sec: 1737.32 - lr: 0.000014 - momentum: 0.000000
2024-03-26 11:27:44,956 epoch 8 - iter 54/95 - loss 0.03977666 - time (sec): 11.35 - samples/sec: 1740.83 - lr: 0.000014 - momentum: 0.000000
2024-03-26 11:27:46,766 epoch 8 - iter 63/95 - loss 0.03873128 - time (sec): 13.16 - samples/sec: 1745.22 - lr: 0.000013 - momentum: 0.000000
2024-03-26 11:27:48,092 epoch 8 - iter 72/95 - loss 0.03720393 - time (sec): 14.48 - samples/sec: 1766.25 - lr: 0.000013 - momentum: 0.000000
2024-03-26 11:27:49,977 epoch 8 - iter 81/95 - loss 0.03735308 - time (sec): 16.37 - samples/sec: 1788.75 - lr: 0.000012 - momentum: 0.000000
2024-03-26 11:27:52,509 epoch 8 - iter 90/95 - loss 0.03457049 - time (sec): 18.90 - samples/sec: 1745.14 - lr: 0.000012 - momentum: 0.000000
2024-03-26 11:27:53,363 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:53,363 EPOCH 8 done: loss 0.0350 - lr: 0.000012
2024-03-26 11:27:54,304 DEV : loss 0.19405929744243622 - f1-score (micro avg) 0.9388
2024-03-26 11:27:54,305 saving best model
2024-03-26 11:27:54,714 ----------------------------------------------------------------------------------------------------
2024-03-26 11:27:56,495 epoch 9 - iter 9/95 - loss 0.03300844 - time (sec): 1.78 - samples/sec: 1907.81 - lr: 0.000011 - momentum: 0.000000
2024-03-26 11:27:58,733 epoch 9 - iter 18/95 - loss 0.02341987 - time (sec): 4.02 - samples/sec: 1725.89 - lr: 0.000010 - momentum: 0.000000
2024-03-26 11:28:00,673 epoch 9 - iter 27/95 - loss 0.03209448 - time (sec): 5.96 - samples/sec: 1751.40 - lr: 0.000010 - momentum: 0.000000
2024-03-26 11:28:02,260 epoch 9 - iter 36/95 - loss 0.03363631 - time (sec): 7.55 - samples/sec: 1759.39 - lr: 0.000009 - momentum: 0.000000
2024-03-26 11:28:03,712 epoch 9 - iter 45/95 - loss 0.02843998 - time (sec): 9.00 - samples/sec: 1792.89 - lr: 0.000009 - momentum: 0.000000
2024-03-26 11:28:05,141 epoch 9 - iter 54/95 - loss 0.02593440 - time (sec): 10.43 - samples/sec: 1844.58 - lr: 0.000008 - momentum: 0.000000
2024-03-26 11:28:07,051 epoch 9 - iter 63/95 - loss 0.03115415 - time (sec): 12.34 - samples/sec: 1842.43 - lr: 0.000008 - momentum: 0.000000
2024-03-26 11:28:09,104 epoch 9 - iter 72/95 - loss 0.03264374 - time (sec): 14.39 - samples/sec: 1815.38 - lr: 0.000007 - momentum: 0.000000
2024-03-26 11:28:11,445 epoch 9 - iter 81/95 - loss 0.03396355 - time (sec): 16.73 - samples/sec: 1774.04 - lr: 0.000007 - momentum: 0.000000
2024-03-26 11:28:13,232 epoch 9 - iter 90/95 - loss 0.03292421 - time (sec): 18.52 - samples/sec: 1787.49 - lr: 0.000006 - momentum: 0.000000
2024-03-26 11:28:13,832 ----------------------------------------------------------------------------------------------------
2024-03-26 11:28:13,832 EPOCH 9 done: loss 0.0325 - lr: 0.000006
2024-03-26 11:28:14,774 DEV : loss 0.18781226873397827 - f1-score (micro avg) 0.9312
2024-03-26 11:28:14,776 ----------------------------------------------------------------------------------------------------
2024-03-26 11:28:16,894 epoch 10 - iter 9/95 - loss 0.00384695 - time (sec): 2.12 - samples/sec: 1823.81 - lr: 0.000005 - momentum: 0.000000
2024-03-26 11:28:18,697 epoch 10 - iter 18/95 - loss 0.01394885 - time (sec): 3.92 - samples/sec: 1812.19 - lr: 0.000005 - momentum: 0.000000
2024-03-26 11:28:19,808 epoch 10 - iter 27/95 - loss 0.01175287 - time (sec): 5.03 - samples/sec: 1893.10 - lr: 0.000004 - momentum: 0.000000
2024-03-26 11:28:21,357 epoch 10 - iter 36/95 - loss 0.01921167 - time (sec): 6.58 - samples/sec: 1902.68 - lr: 0.000004 - momentum: 0.000000
2024-03-26 11:28:23,413 epoch 10 - iter 45/95 - loss 0.02733494 - time (sec): 8.64 - samples/sec: 1827.85 - lr: 0.000003 - momentum: 0.000000
2024-03-26 11:28:24,524 epoch 10 - iter 54/95 - loss 0.03012670 - time (sec): 9.75 - samples/sec: 1878.06 - lr: 0.000003 - momentum: 0.000000
2024-03-26 11:28:25,797 epoch 10 - iter 63/95 - loss 0.02746056 - time (sec): 11.02 - samples/sec: 1904.01 - lr: 0.000002 - momentum: 0.000000
2024-03-26 11:28:27,748 epoch 10 - iter 72/95 - loss 0.02769668 - time (sec): 12.97 - samples/sec: 1903.69 - lr: 0.000002 - momentum: 0.000000
2024-03-26 11:28:30,400 epoch 10 - iter 81/95 - loss 0.02547260 - time (sec): 15.62 - samples/sec: 1874.86 - lr: 0.000001 - momentum: 0.000000
2024-03-26 11:28:32,496 epoch 10 - iter 90/95 - loss 0.02619711 - time (sec): 17.72 - samples/sec: 1851.69 - lr: 0.000001 - momentum: 0.000000
2024-03-26 11:28:33,443 ----------------------------------------------------------------------------------------------------
2024-03-26 11:28:33,443 EPOCH 10 done: loss 0.0255 - lr: 0.000001
2024-03-26 11:28:34,380 DEV : loss 0.2008616179227829 - f1-score (micro avg) 0.9344
2024-03-26 11:28:34,663 ----------------------------------------------------------------------------------------------------
2024-03-26 11:28:34,663 Loading model from best epoch ...
2024-03-26 11:28:35,501 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 11:28:36,262
Results:
- F-score (micro) 0.9159
- F-score (macro) 0.6952
- Accuracy 0.846
By class:
precision recall f1-score support
Unternehmen 0.9157 0.8985 0.9070 266
Auslagerung 0.8769 0.9157 0.8959 249
Ort 0.9706 0.9851 0.9778 134
Software 0.0000 0.0000 0.0000 0
micro avg 0.9090 0.9230 0.9159 649
macro avg 0.6908 0.6998 0.6952 649
weighted avg 0.9122 0.9230 0.9174 649
2024-03-26 11:28:36,263 ----------------------------------------------------------------------------------------------------
|