File size: 23,970 Bytes
2678cf0 |
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 |
2023-10-17 20:22:26,600 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,601 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): ElectraModel(
(embeddings): ElectraEmbeddings(
(word_embeddings): Embedding(32001, 768)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): ElectraEncoder(
(layer): ModuleList(
(0-11): 12 x ElectraLayer(
(attention): ElectraAttention(
(self): ElectraSelfAttention(
(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): ElectraSelfOutput(
(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): ElectraIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): ElectraOutput(
(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)
)
)
)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-17 20:22:26,601 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,601 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
2023-10-17 20:22:26,601 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,601 Train: 1085 sentences
2023-10-17 20:22:26,601 (train_with_dev=False, train_with_test=False)
2023-10-17 20:22:26,601 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,601 Training Params:
2023-10-17 20:22:26,601 - learning_rate: "5e-05"
2023-10-17 20:22:26,601 - mini_batch_size: "4"
2023-10-17 20:22:26,601 - max_epochs: "10"
2023-10-17 20:22:26,601 - shuffle: "True"
2023-10-17 20:22:26,601 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,601 Plugins:
2023-10-17 20:22:26,602 - TensorboardLogger
2023-10-17 20:22:26,602 - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 20:22:26,602 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,602 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 20:22:26,602 - metric: "('micro avg', 'f1-score')"
2023-10-17 20:22:26,602 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,602 Computation:
2023-10-17 20:22:26,602 - compute on device: cuda:0
2023-10-17 20:22:26,602 - embedding storage: none
2023-10-17 20:22:26,602 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,602 Model training base path: "hmbench-newseye/sv-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-17 20:22:26,602 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,602 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:26,602 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 20:22:28,205 epoch 1 - iter 27/272 - loss 3.40623895 - time (sec): 1.60 - samples/sec: 3386.92 - lr: 0.000005 - momentum: 0.000000
2023-10-17 20:22:29,850 epoch 1 - iter 54/272 - loss 2.64778140 - time (sec): 3.25 - samples/sec: 3205.45 - lr: 0.000010 - momentum: 0.000000
2023-10-17 20:22:31,678 epoch 1 - iter 81/272 - loss 1.89470970 - time (sec): 5.07 - samples/sec: 3228.54 - lr: 0.000015 - momentum: 0.000000
2023-10-17 20:22:33,184 epoch 1 - iter 108/272 - loss 1.55945154 - time (sec): 6.58 - samples/sec: 3243.02 - lr: 0.000020 - momentum: 0.000000
2023-10-17 20:22:34,720 epoch 1 - iter 135/272 - loss 1.32041644 - time (sec): 8.12 - samples/sec: 3280.25 - lr: 0.000025 - momentum: 0.000000
2023-10-17 20:22:36,310 epoch 1 - iter 162/272 - loss 1.17756978 - time (sec): 9.71 - samples/sec: 3206.49 - lr: 0.000030 - momentum: 0.000000
2023-10-17 20:22:37,849 epoch 1 - iter 189/272 - loss 1.04336124 - time (sec): 11.25 - samples/sec: 3227.97 - lr: 0.000035 - momentum: 0.000000
2023-10-17 20:22:39,527 epoch 1 - iter 216/272 - loss 0.92669269 - time (sec): 12.92 - samples/sec: 3249.42 - lr: 0.000040 - momentum: 0.000000
2023-10-17 20:22:41,040 epoch 1 - iter 243/272 - loss 0.86162728 - time (sec): 14.44 - samples/sec: 3223.74 - lr: 0.000044 - momentum: 0.000000
2023-10-17 20:22:42,626 epoch 1 - iter 270/272 - loss 0.79081358 - time (sec): 16.02 - samples/sec: 3238.48 - lr: 0.000049 - momentum: 0.000000
2023-10-17 20:22:42,723 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:42,723 EPOCH 1 done: loss 0.7899 - lr: 0.000049
2023-10-17 20:22:43,970 DEV : loss 0.16378863155841827 - f1-score (micro avg) 0.6164
2023-10-17 20:22:43,974 saving best model
2023-10-17 20:22:44,399 ----------------------------------------------------------------------------------------------------
2023-10-17 20:22:45,968 epoch 2 - iter 27/272 - loss 0.25767374 - time (sec): 1.57 - samples/sec: 3194.61 - lr: 0.000049 - momentum: 0.000000
2023-10-17 20:22:47,585 epoch 2 - iter 54/272 - loss 0.18763097 - time (sec): 3.18 - samples/sec: 3270.50 - lr: 0.000049 - momentum: 0.000000
2023-10-17 20:22:49,123 epoch 2 - iter 81/272 - loss 0.17973790 - time (sec): 4.72 - samples/sec: 3435.04 - lr: 0.000048 - momentum: 0.000000
2023-10-17 20:22:50,626 epoch 2 - iter 108/272 - loss 0.16187387 - time (sec): 6.22 - samples/sec: 3516.89 - lr: 0.000048 - momentum: 0.000000
2023-10-17 20:22:52,065 epoch 2 - iter 135/272 - loss 0.16105113 - time (sec): 7.66 - samples/sec: 3368.57 - lr: 0.000047 - momentum: 0.000000
2023-10-17 20:22:53,717 epoch 2 - iter 162/272 - loss 0.15784438 - time (sec): 9.32 - samples/sec: 3373.16 - lr: 0.000047 - momentum: 0.000000
2023-10-17 20:22:55,227 epoch 2 - iter 189/272 - loss 0.15170985 - time (sec): 10.83 - samples/sec: 3379.62 - lr: 0.000046 - momentum: 0.000000
2023-10-17 20:22:56,786 epoch 2 - iter 216/272 - loss 0.14931401 - time (sec): 12.39 - samples/sec: 3346.42 - lr: 0.000046 - momentum: 0.000000
2023-10-17 20:22:58,384 epoch 2 - iter 243/272 - loss 0.14546742 - time (sec): 13.98 - samples/sec: 3377.89 - lr: 0.000045 - momentum: 0.000000
2023-10-17 20:22:59,861 epoch 2 - iter 270/272 - loss 0.14667348 - time (sec): 15.46 - samples/sec: 3338.96 - lr: 0.000045 - momentum: 0.000000
2023-10-17 20:23:00,006 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:00,006 EPOCH 2 done: loss 0.1460 - lr: 0.000045
2023-10-17 20:23:01,511 DEV : loss 0.13631020486354828 - f1-score (micro avg) 0.7405
2023-10-17 20:23:01,515 saving best model
2023-10-17 20:23:02,008 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:03,542 epoch 3 - iter 27/272 - loss 0.12873334 - time (sec): 1.53 - samples/sec: 3222.01 - lr: 0.000044 - momentum: 0.000000
2023-10-17 20:23:05,152 epoch 3 - iter 54/272 - loss 0.09958223 - time (sec): 3.14 - samples/sec: 3055.89 - lr: 0.000043 - momentum: 0.000000
2023-10-17 20:23:06,773 epoch 3 - iter 81/272 - loss 0.08615905 - time (sec): 4.76 - samples/sec: 3113.14 - lr: 0.000043 - momentum: 0.000000
2023-10-17 20:23:08,467 epoch 3 - iter 108/272 - loss 0.09050520 - time (sec): 6.46 - samples/sec: 3123.51 - lr: 0.000042 - momentum: 0.000000
2023-10-17 20:23:10,010 epoch 3 - iter 135/272 - loss 0.10892810 - time (sec): 8.00 - samples/sec: 3119.86 - lr: 0.000042 - momentum: 0.000000
2023-10-17 20:23:11,605 epoch 3 - iter 162/272 - loss 0.10570646 - time (sec): 9.59 - samples/sec: 3156.75 - lr: 0.000041 - momentum: 0.000000
2023-10-17 20:23:13,179 epoch 3 - iter 189/272 - loss 0.09847848 - time (sec): 11.17 - samples/sec: 3149.61 - lr: 0.000041 - momentum: 0.000000
2023-10-17 20:23:14,859 epoch 3 - iter 216/272 - loss 0.09658563 - time (sec): 12.85 - samples/sec: 3226.18 - lr: 0.000040 - momentum: 0.000000
2023-10-17 20:23:16,369 epoch 3 - iter 243/272 - loss 0.09713728 - time (sec): 14.36 - samples/sec: 3209.44 - lr: 0.000040 - momentum: 0.000000
2023-10-17 20:23:18,084 epoch 3 - iter 270/272 - loss 0.09473854 - time (sec): 16.07 - samples/sec: 3218.02 - lr: 0.000039 - momentum: 0.000000
2023-10-17 20:23:18,185 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:18,185 EPOCH 3 done: loss 0.0946 - lr: 0.000039
2023-10-17 20:23:19,896 DEV : loss 0.12857291102409363 - f1-score (micro avg) 0.7695
2023-10-17 20:23:19,901 saving best model
2023-10-17 20:23:20,369 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:22,050 epoch 4 - iter 27/272 - loss 0.04863011 - time (sec): 1.68 - samples/sec: 3532.90 - lr: 0.000038 - momentum: 0.000000
2023-10-17 20:23:23,565 epoch 4 - iter 54/272 - loss 0.04952118 - time (sec): 3.19 - samples/sec: 3365.08 - lr: 0.000038 - momentum: 0.000000
2023-10-17 20:23:25,299 epoch 4 - iter 81/272 - loss 0.04821615 - time (sec): 4.93 - samples/sec: 3464.45 - lr: 0.000037 - momentum: 0.000000
2023-10-17 20:23:26,994 epoch 4 - iter 108/272 - loss 0.04656621 - time (sec): 6.62 - samples/sec: 3432.94 - lr: 0.000037 - momentum: 0.000000
2023-10-17 20:23:28,582 epoch 4 - iter 135/272 - loss 0.04950359 - time (sec): 8.21 - samples/sec: 3362.25 - lr: 0.000036 - momentum: 0.000000
2023-10-17 20:23:30,082 epoch 4 - iter 162/272 - loss 0.05105052 - time (sec): 9.71 - samples/sec: 3296.71 - lr: 0.000036 - momentum: 0.000000
2023-10-17 20:23:31,689 epoch 4 - iter 189/272 - loss 0.05366686 - time (sec): 11.32 - samples/sec: 3237.27 - lr: 0.000035 - momentum: 0.000000
2023-10-17 20:23:33,411 epoch 4 - iter 216/272 - loss 0.05164999 - time (sec): 13.04 - samples/sec: 3240.84 - lr: 0.000034 - momentum: 0.000000
2023-10-17 20:23:34,963 epoch 4 - iter 243/272 - loss 0.05133109 - time (sec): 14.59 - samples/sec: 3225.19 - lr: 0.000034 - momentum: 0.000000
2023-10-17 20:23:36,481 epoch 4 - iter 270/272 - loss 0.05924423 - time (sec): 16.11 - samples/sec: 3216.17 - lr: 0.000033 - momentum: 0.000000
2023-10-17 20:23:36,568 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:36,568 EPOCH 4 done: loss 0.0591 - lr: 0.000033
2023-10-17 20:23:38,107 DEV : loss 0.14095589518547058 - f1-score (micro avg) 0.8248
2023-10-17 20:23:38,115 saving best model
2023-10-17 20:23:38,647 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:40,181 epoch 5 - iter 27/272 - loss 0.04161918 - time (sec): 1.53 - samples/sec: 3371.72 - lr: 0.000033 - momentum: 0.000000
2023-10-17 20:23:41,797 epoch 5 - iter 54/272 - loss 0.03906740 - time (sec): 3.15 - samples/sec: 3286.92 - lr: 0.000032 - momentum: 0.000000
2023-10-17 20:23:43,295 epoch 5 - iter 81/272 - loss 0.03980555 - time (sec): 4.65 - samples/sec: 3305.42 - lr: 0.000032 - momentum: 0.000000
2023-10-17 20:23:44,934 epoch 5 - iter 108/272 - loss 0.04222380 - time (sec): 6.29 - samples/sec: 3294.55 - lr: 0.000031 - momentum: 0.000000
2023-10-17 20:23:46,547 epoch 5 - iter 135/272 - loss 0.04134787 - time (sec): 7.90 - samples/sec: 3329.13 - lr: 0.000031 - momentum: 0.000000
2023-10-17 20:23:48,180 epoch 5 - iter 162/272 - loss 0.03847928 - time (sec): 9.53 - samples/sec: 3319.66 - lr: 0.000030 - momentum: 0.000000
2023-10-17 20:23:49,690 epoch 5 - iter 189/272 - loss 0.04003670 - time (sec): 11.04 - samples/sec: 3326.51 - lr: 0.000029 - momentum: 0.000000
2023-10-17 20:23:51,339 epoch 5 - iter 216/272 - loss 0.03896642 - time (sec): 12.69 - samples/sec: 3324.71 - lr: 0.000029 - momentum: 0.000000
2023-10-17 20:23:52,752 epoch 5 - iter 243/272 - loss 0.03875774 - time (sec): 14.10 - samples/sec: 3286.69 - lr: 0.000028 - momentum: 0.000000
2023-10-17 20:23:54,441 epoch 5 - iter 270/272 - loss 0.03752829 - time (sec): 15.79 - samples/sec: 3275.49 - lr: 0.000028 - momentum: 0.000000
2023-10-17 20:23:54,552 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:54,552 EPOCH 5 done: loss 0.0375 - lr: 0.000028
2023-10-17 20:23:56,053 DEV : loss 0.14450490474700928 - f1-score (micro avg) 0.8303
2023-10-17 20:23:56,057 saving best model
2023-10-17 20:23:56,529 ----------------------------------------------------------------------------------------------------
2023-10-17 20:23:58,265 epoch 6 - iter 27/272 - loss 0.02331958 - time (sec): 1.73 - samples/sec: 3400.01 - lr: 0.000027 - momentum: 0.000000
2023-10-17 20:23:59,798 epoch 6 - iter 54/272 - loss 0.02778531 - time (sec): 3.27 - samples/sec: 3378.82 - lr: 0.000027 - momentum: 0.000000
2023-10-17 20:24:01,382 epoch 6 - iter 81/272 - loss 0.02856352 - time (sec): 4.85 - samples/sec: 3399.05 - lr: 0.000026 - momentum: 0.000000
2023-10-17 20:24:02,988 epoch 6 - iter 108/272 - loss 0.02887330 - time (sec): 6.46 - samples/sec: 3419.07 - lr: 0.000026 - momentum: 0.000000
2023-10-17 20:24:04,498 epoch 6 - iter 135/272 - loss 0.02445293 - time (sec): 7.97 - samples/sec: 3406.75 - lr: 0.000025 - momentum: 0.000000
2023-10-17 20:24:06,001 epoch 6 - iter 162/272 - loss 0.02445139 - time (sec): 9.47 - samples/sec: 3355.78 - lr: 0.000024 - momentum: 0.000000
2023-10-17 20:24:07,542 epoch 6 - iter 189/272 - loss 0.02422895 - time (sec): 11.01 - samples/sec: 3360.71 - lr: 0.000024 - momentum: 0.000000
2023-10-17 20:24:09,131 epoch 6 - iter 216/272 - loss 0.02456752 - time (sec): 12.60 - samples/sec: 3357.57 - lr: 0.000023 - momentum: 0.000000
2023-10-17 20:24:10,700 epoch 6 - iter 243/272 - loss 0.02951527 - time (sec): 14.17 - samples/sec: 3303.46 - lr: 0.000023 - momentum: 0.000000
2023-10-17 20:24:12,292 epoch 6 - iter 270/272 - loss 0.02803499 - time (sec): 15.76 - samples/sec: 3294.17 - lr: 0.000022 - momentum: 0.000000
2023-10-17 20:24:12,377 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:12,378 EPOCH 6 done: loss 0.0280 - lr: 0.000022
2023-10-17 20:24:13,893 DEV : loss 0.164916530251503 - f1-score (micro avg) 0.8349
2023-10-17 20:24:13,898 saving best model
2023-10-17 20:24:14,377 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:16,001 epoch 7 - iter 27/272 - loss 0.02600591 - time (sec): 1.62 - samples/sec: 3156.24 - lr: 0.000022 - momentum: 0.000000
2023-10-17 20:24:17,553 epoch 7 - iter 54/272 - loss 0.02176704 - time (sec): 3.17 - samples/sec: 3042.50 - lr: 0.000021 - momentum: 0.000000
2023-10-17 20:24:19,116 epoch 7 - iter 81/272 - loss 0.02312263 - time (sec): 4.74 - samples/sec: 3180.06 - lr: 0.000021 - momentum: 0.000000
2023-10-17 20:24:20,639 epoch 7 - iter 108/272 - loss 0.02098405 - time (sec): 6.26 - samples/sec: 3186.77 - lr: 0.000020 - momentum: 0.000000
2023-10-17 20:24:22,295 epoch 7 - iter 135/272 - loss 0.02136903 - time (sec): 7.92 - samples/sec: 3168.51 - lr: 0.000019 - momentum: 0.000000
2023-10-17 20:24:23,839 epoch 7 - iter 162/272 - loss 0.01922451 - time (sec): 9.46 - samples/sec: 3247.84 - lr: 0.000019 - momentum: 0.000000
2023-10-17 20:24:25,360 epoch 7 - iter 189/272 - loss 0.01820994 - time (sec): 10.98 - samples/sec: 3232.36 - lr: 0.000018 - momentum: 0.000000
2023-10-17 20:24:27,097 epoch 7 - iter 216/272 - loss 0.01760377 - time (sec): 12.72 - samples/sec: 3252.49 - lr: 0.000018 - momentum: 0.000000
2023-10-17 20:24:28,705 epoch 7 - iter 243/272 - loss 0.01983655 - time (sec): 14.32 - samples/sec: 3285.53 - lr: 0.000017 - momentum: 0.000000
2023-10-17 20:24:30,192 epoch 7 - iter 270/272 - loss 0.02082722 - time (sec): 15.81 - samples/sec: 3267.16 - lr: 0.000017 - momentum: 0.000000
2023-10-17 20:24:30,289 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:30,289 EPOCH 7 done: loss 0.0214 - lr: 0.000017
2023-10-17 20:24:31,970 DEV : loss 0.1378893107175827 - f1-score (micro avg) 0.8466
2023-10-17 20:24:31,974 saving best model
2023-10-17 20:24:32,437 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:34,194 epoch 8 - iter 27/272 - loss 0.02138210 - time (sec): 1.76 - samples/sec: 3402.72 - lr: 0.000016 - momentum: 0.000000
2023-10-17 20:24:35,940 epoch 8 - iter 54/272 - loss 0.01603143 - time (sec): 3.50 - samples/sec: 3511.78 - lr: 0.000016 - momentum: 0.000000
2023-10-17 20:24:37,649 epoch 8 - iter 81/272 - loss 0.01321229 - time (sec): 5.21 - samples/sec: 3438.41 - lr: 0.000015 - momentum: 0.000000
2023-10-17 20:24:39,220 epoch 8 - iter 108/272 - loss 0.01354273 - time (sec): 6.78 - samples/sec: 3379.13 - lr: 0.000014 - momentum: 0.000000
2023-10-17 20:24:40,760 epoch 8 - iter 135/272 - loss 0.01494549 - time (sec): 8.32 - samples/sec: 3317.33 - lr: 0.000014 - momentum: 0.000000
2023-10-17 20:24:42,340 epoch 8 - iter 162/272 - loss 0.01356546 - time (sec): 9.90 - samples/sec: 3302.23 - lr: 0.000013 - momentum: 0.000000
2023-10-17 20:24:44,005 epoch 8 - iter 189/272 - loss 0.01223719 - time (sec): 11.57 - samples/sec: 3292.22 - lr: 0.000013 - momentum: 0.000000
2023-10-17 20:24:45,450 epoch 8 - iter 216/272 - loss 0.01234719 - time (sec): 13.01 - samples/sec: 3226.97 - lr: 0.000012 - momentum: 0.000000
2023-10-17 20:24:47,009 epoch 8 - iter 243/272 - loss 0.01158905 - time (sec): 14.57 - samples/sec: 3223.70 - lr: 0.000012 - momentum: 0.000000
2023-10-17 20:24:48,502 epoch 8 - iter 270/272 - loss 0.01164301 - time (sec): 16.06 - samples/sec: 3227.93 - lr: 0.000011 - momentum: 0.000000
2023-10-17 20:24:48,584 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:48,584 EPOCH 8 done: loss 0.0116 - lr: 0.000011
2023-10-17 20:24:50,133 DEV : loss 0.17313425242900848 - f1-score (micro avg) 0.8411
2023-10-17 20:24:50,139 ----------------------------------------------------------------------------------------------------
2023-10-17 20:24:51,767 epoch 9 - iter 27/272 - loss 0.01050858 - time (sec): 1.63 - samples/sec: 3239.68 - lr: 0.000011 - momentum: 0.000000
2023-10-17 20:24:53,284 epoch 9 - iter 54/272 - loss 0.00816307 - time (sec): 3.14 - samples/sec: 3430.50 - lr: 0.000010 - momentum: 0.000000
2023-10-17 20:24:55,016 epoch 9 - iter 81/272 - loss 0.00563877 - time (sec): 4.88 - samples/sec: 3331.55 - lr: 0.000009 - momentum: 0.000000
2023-10-17 20:24:56,573 epoch 9 - iter 108/272 - loss 0.00751326 - time (sec): 6.43 - samples/sec: 3319.73 - lr: 0.000009 - momentum: 0.000000
2023-10-17 20:24:58,184 epoch 9 - iter 135/272 - loss 0.00746821 - time (sec): 8.04 - samples/sec: 3333.63 - lr: 0.000008 - momentum: 0.000000
2023-10-17 20:24:59,745 epoch 9 - iter 162/272 - loss 0.00835793 - time (sec): 9.60 - samples/sec: 3302.04 - lr: 0.000008 - momentum: 0.000000
2023-10-17 20:25:01,328 epoch 9 - iter 189/272 - loss 0.00843661 - time (sec): 11.19 - samples/sec: 3278.39 - lr: 0.000007 - momentum: 0.000000
2023-10-17 20:25:03,008 epoch 9 - iter 216/272 - loss 0.00844583 - time (sec): 12.87 - samples/sec: 3268.37 - lr: 0.000007 - momentum: 0.000000
2023-10-17 20:25:04,632 epoch 9 - iter 243/272 - loss 0.00798675 - time (sec): 14.49 - samples/sec: 3245.09 - lr: 0.000006 - momentum: 0.000000
2023-10-17 20:25:06,262 epoch 9 - iter 270/272 - loss 0.00914489 - time (sec): 16.12 - samples/sec: 3208.36 - lr: 0.000006 - momentum: 0.000000
2023-10-17 20:25:06,364 ----------------------------------------------------------------------------------------------------
2023-10-17 20:25:06,364 EPOCH 9 done: loss 0.0091 - lr: 0.000006
2023-10-17 20:25:07,842 DEV : loss 0.16325917840003967 - f1-score (micro avg) 0.8454
2023-10-17 20:25:07,848 ----------------------------------------------------------------------------------------------------
2023-10-17 20:25:09,333 epoch 10 - iter 27/272 - loss 0.01177117 - time (sec): 1.48 - samples/sec: 3150.74 - lr: 0.000005 - momentum: 0.000000
2023-10-17 20:25:10,839 epoch 10 - iter 54/272 - loss 0.00588272 - time (sec): 2.99 - samples/sec: 3203.39 - lr: 0.000004 - momentum: 0.000000
2023-10-17 20:25:12,334 epoch 10 - iter 81/272 - loss 0.00422933 - time (sec): 4.49 - samples/sec: 3248.98 - lr: 0.000004 - momentum: 0.000000
2023-10-17 20:25:13,912 epoch 10 - iter 108/272 - loss 0.00469858 - time (sec): 6.06 - samples/sec: 3231.54 - lr: 0.000003 - momentum: 0.000000
2023-10-17 20:25:15,425 epoch 10 - iter 135/272 - loss 0.00590915 - time (sec): 7.58 - samples/sec: 3187.05 - lr: 0.000003 - momentum: 0.000000
2023-10-17 20:25:16,981 epoch 10 - iter 162/272 - loss 0.00571912 - time (sec): 9.13 - samples/sec: 3238.99 - lr: 0.000002 - momentum: 0.000000
2023-10-17 20:25:18,598 epoch 10 - iter 189/272 - loss 0.00575909 - time (sec): 10.75 - samples/sec: 3253.20 - lr: 0.000002 - momentum: 0.000000
2023-10-17 20:25:20,320 epoch 10 - iter 216/272 - loss 0.00592286 - time (sec): 12.47 - samples/sec: 3244.35 - lr: 0.000001 - momentum: 0.000000
2023-10-17 20:25:22,153 epoch 10 - iter 243/272 - loss 0.00637850 - time (sec): 14.30 - samples/sec: 3226.88 - lr: 0.000001 - momentum: 0.000000
2023-10-17 20:25:23,793 epoch 10 - iter 270/272 - loss 0.00590127 - time (sec): 15.94 - samples/sec: 3246.86 - lr: 0.000000 - momentum: 0.000000
2023-10-17 20:25:23,884 ----------------------------------------------------------------------------------------------------
2023-10-17 20:25:23,885 EPOCH 10 done: loss 0.0059 - lr: 0.000000
2023-10-17 20:25:25,440 DEV : loss 0.16820533573627472 - f1-score (micro avg) 0.8296
2023-10-17 20:25:25,843 ----------------------------------------------------------------------------------------------------
2023-10-17 20:25:25,844 Loading model from best epoch ...
2023-10-17 20:25:27,361 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
2023-10-17 20:25:29,711
Results:
- F-score (micro) 0.7984
- F-score (macro) 0.7542
- Accuracy 0.6809
By class:
precision recall f1-score support
LOC 0.8439 0.8141 0.8287 312
PER 0.7541 0.8846 0.8142 208
ORG 0.5500 0.6000 0.5739 55
HumanProd 0.6667 1.0000 0.8000 22
micro avg 0.7727 0.8258 0.7984 597
macro avg 0.7037 0.8247 0.7542 597
weighted avg 0.7790 0.8258 0.7991 597
2023-10-17 20:25:29,711 ----------------------------------------------------------------------------------------------------
|