File size: 23,848 Bytes
304cf88 |
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 |
2023-10-17 17:58:07,427 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,428 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 17:58:07,428 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,428 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
2023-10-17 17:58:07,428 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,428 Train: 1166 sentences
2023-10-17 17:58:07,428 (train_with_dev=False, train_with_test=False)
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Training Params:
2023-10-17 17:58:07,429 - learning_rate: "5e-05"
2023-10-17 17:58:07,429 - mini_batch_size: "4"
2023-10-17 17:58:07,429 - max_epochs: "10"
2023-10-17 17:58:07,429 - shuffle: "True"
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Plugins:
2023-10-17 17:58:07,429 - TensorboardLogger
2023-10-17 17:58:07,429 - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 17:58:07,429 - metric: "('micro avg', 'f1-score')"
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Computation:
2023-10-17 17:58:07,429 - compute on device: cuda:0
2023-10-17 17:58:07,429 - embedding storage: none
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Model training base path: "hmbench-newseye/fi-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:07,429 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 17:58:08,948 epoch 1 - iter 29/292 - loss 3.35693242 - time (sec): 1.52 - samples/sec: 2481.07 - lr: 0.000005 - momentum: 0.000000
2023-10-17 17:58:10,706 epoch 1 - iter 58/292 - loss 2.40158772 - time (sec): 3.28 - samples/sec: 2746.46 - lr: 0.000010 - momentum: 0.000000
2023-10-17 17:58:12,378 epoch 1 - iter 87/292 - loss 1.81703963 - time (sec): 4.95 - samples/sec: 2780.63 - lr: 0.000015 - momentum: 0.000000
2023-10-17 17:58:14,242 epoch 1 - iter 116/292 - loss 1.50647114 - time (sec): 6.81 - samples/sec: 2755.93 - lr: 0.000020 - momentum: 0.000000
2023-10-17 17:58:15,845 epoch 1 - iter 145/292 - loss 1.30749839 - time (sec): 8.41 - samples/sec: 2710.21 - lr: 0.000025 - momentum: 0.000000
2023-10-17 17:58:17,535 epoch 1 - iter 174/292 - loss 1.14398900 - time (sec): 10.10 - samples/sec: 2704.56 - lr: 0.000030 - momentum: 0.000000
2023-10-17 17:58:19,202 epoch 1 - iter 203/292 - loss 1.02388352 - time (sec): 11.77 - samples/sec: 2705.79 - lr: 0.000035 - momentum: 0.000000
2023-10-17 17:58:20,739 epoch 1 - iter 232/292 - loss 0.95215720 - time (sec): 13.31 - samples/sec: 2692.50 - lr: 0.000040 - momentum: 0.000000
2023-10-17 17:58:22,437 epoch 1 - iter 261/292 - loss 0.87431897 - time (sec): 15.01 - samples/sec: 2663.32 - lr: 0.000045 - momentum: 0.000000
2023-10-17 17:58:24,018 epoch 1 - iter 290/292 - loss 0.81843563 - time (sec): 16.59 - samples/sec: 2663.35 - lr: 0.000049 - momentum: 0.000000
2023-10-17 17:58:24,125 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:24,125 EPOCH 1 done: loss 0.8153 - lr: 0.000049
2023-10-17 17:58:24,983 DEV : loss 0.16816182434558868 - f1-score (micro avg) 0.4943
2023-10-17 17:58:24,997 saving best model
2023-10-17 17:58:25,403 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:27,070 epoch 2 - iter 29/292 - loss 0.20843227 - time (sec): 1.66 - samples/sec: 2647.59 - lr: 0.000049 - momentum: 0.000000
2023-10-17 17:58:28,672 epoch 2 - iter 58/292 - loss 0.18562051 - time (sec): 3.27 - samples/sec: 2576.35 - lr: 0.000049 - momentum: 0.000000
2023-10-17 17:58:30,295 epoch 2 - iter 87/292 - loss 0.18807184 - time (sec): 4.89 - samples/sec: 2638.19 - lr: 0.000048 - momentum: 0.000000
2023-10-17 17:58:32,156 epoch 2 - iter 116/292 - loss 0.19178363 - time (sec): 6.75 - samples/sec: 2679.90 - lr: 0.000048 - momentum: 0.000000
2023-10-17 17:58:33,681 epoch 2 - iter 145/292 - loss 0.19660908 - time (sec): 8.28 - samples/sec: 2649.53 - lr: 0.000047 - momentum: 0.000000
2023-10-17 17:58:35,401 epoch 2 - iter 174/292 - loss 0.18834867 - time (sec): 10.00 - samples/sec: 2642.70 - lr: 0.000047 - momentum: 0.000000
2023-10-17 17:58:37,236 epoch 2 - iter 203/292 - loss 0.18795088 - time (sec): 11.83 - samples/sec: 2676.70 - lr: 0.000046 - momentum: 0.000000
2023-10-17 17:58:39,005 epoch 2 - iter 232/292 - loss 0.18476687 - time (sec): 13.60 - samples/sec: 2698.36 - lr: 0.000046 - momentum: 0.000000
2023-10-17 17:58:40,512 epoch 2 - iter 261/292 - loss 0.18398307 - time (sec): 15.11 - samples/sec: 2659.83 - lr: 0.000045 - momentum: 0.000000
2023-10-17 17:58:42,146 epoch 2 - iter 290/292 - loss 0.18080703 - time (sec): 16.74 - samples/sec: 2645.78 - lr: 0.000045 - momentum: 0.000000
2023-10-17 17:58:42,237 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:42,238 EPOCH 2 done: loss 0.1807 - lr: 0.000045
2023-10-17 17:58:43,941 DEV : loss 0.15552328526973724 - f1-score (micro avg) 0.6562
2023-10-17 17:58:43,947 saving best model
2023-10-17 17:58:44,403 ----------------------------------------------------------------------------------------------------
2023-10-17 17:58:46,086 epoch 3 - iter 29/292 - loss 0.10474185 - time (sec): 1.68 - samples/sec: 2898.39 - lr: 0.000044 - momentum: 0.000000
2023-10-17 17:58:47,922 epoch 3 - iter 58/292 - loss 0.10398762 - time (sec): 3.52 - samples/sec: 2759.49 - lr: 0.000043 - momentum: 0.000000
2023-10-17 17:58:49,548 epoch 3 - iter 87/292 - loss 0.12767526 - time (sec): 5.14 - samples/sec: 2718.62 - lr: 0.000043 - momentum: 0.000000
2023-10-17 17:58:51,123 epoch 3 - iter 116/292 - loss 0.12096457 - time (sec): 6.72 - samples/sec: 2666.56 - lr: 0.000042 - momentum: 0.000000
2023-10-17 17:58:52,826 epoch 3 - iter 145/292 - loss 0.11567654 - time (sec): 8.42 - samples/sec: 2657.83 - lr: 0.000042 - momentum: 0.000000
2023-10-17 17:58:54,601 epoch 3 - iter 174/292 - loss 0.11268765 - time (sec): 10.20 - samples/sec: 2654.12 - lr: 0.000041 - momentum: 0.000000
2023-10-17 17:58:56,170 epoch 3 - iter 203/292 - loss 0.10757754 - time (sec): 11.76 - samples/sec: 2657.91 - lr: 0.000041 - momentum: 0.000000
2023-10-17 17:58:57,967 epoch 3 - iter 232/292 - loss 0.10369889 - time (sec): 13.56 - samples/sec: 2639.60 - lr: 0.000040 - momentum: 0.000000
2023-10-17 17:58:59,651 epoch 3 - iter 261/292 - loss 0.10296987 - time (sec): 15.25 - samples/sec: 2626.33 - lr: 0.000040 - momentum: 0.000000
2023-10-17 17:59:01,340 epoch 3 - iter 290/292 - loss 0.10510734 - time (sec): 16.93 - samples/sec: 2614.92 - lr: 0.000039 - momentum: 0.000000
2023-10-17 17:59:01,427 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:01,428 EPOCH 3 done: loss 0.1050 - lr: 0.000039
2023-10-17 17:59:02,790 DEV : loss 0.10585162043571472 - f1-score (micro avg) 0.7419
2023-10-17 17:59:02,798 saving best model
2023-10-17 17:59:03,250 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:04,919 epoch 4 - iter 29/292 - loss 0.05183600 - time (sec): 1.66 - samples/sec: 2769.70 - lr: 0.000038 - momentum: 0.000000
2023-10-17 17:59:06,661 epoch 4 - iter 58/292 - loss 0.05491146 - time (sec): 3.41 - samples/sec: 2750.09 - lr: 0.000038 - momentum: 0.000000
2023-10-17 17:59:08,204 epoch 4 - iter 87/292 - loss 0.05566885 - time (sec): 4.95 - samples/sec: 2676.73 - lr: 0.000037 - momentum: 0.000000
2023-10-17 17:59:10,045 epoch 4 - iter 116/292 - loss 0.05537419 - time (sec): 6.79 - samples/sec: 2710.16 - lr: 0.000037 - momentum: 0.000000
2023-10-17 17:59:11,681 epoch 4 - iter 145/292 - loss 0.06564170 - time (sec): 8.43 - samples/sec: 2711.35 - lr: 0.000036 - momentum: 0.000000
2023-10-17 17:59:13,443 epoch 4 - iter 174/292 - loss 0.07091282 - time (sec): 10.19 - samples/sec: 2697.24 - lr: 0.000036 - momentum: 0.000000
2023-10-17 17:59:15,062 epoch 4 - iter 203/292 - loss 0.06947365 - time (sec): 11.81 - samples/sec: 2665.38 - lr: 0.000035 - momentum: 0.000000
2023-10-17 17:59:16,819 epoch 4 - iter 232/292 - loss 0.07485098 - time (sec): 13.56 - samples/sec: 2647.81 - lr: 0.000035 - momentum: 0.000000
2023-10-17 17:59:18,435 epoch 4 - iter 261/292 - loss 0.07325834 - time (sec): 15.18 - samples/sec: 2646.67 - lr: 0.000034 - momentum: 0.000000
2023-10-17 17:59:20,007 epoch 4 - iter 290/292 - loss 0.07071229 - time (sec): 16.75 - samples/sec: 2644.73 - lr: 0.000033 - momentum: 0.000000
2023-10-17 17:59:20,091 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:20,092 EPOCH 4 done: loss 0.0705 - lr: 0.000033
2023-10-17 17:59:21,397 DEV : loss 0.15273110568523407 - f1-score (micro avg) 0.7775
2023-10-17 17:59:21,403 saving best model
2023-10-17 17:59:21,837 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:23,539 epoch 5 - iter 29/292 - loss 0.03385877 - time (sec): 1.70 - samples/sec: 2504.93 - lr: 0.000033 - momentum: 0.000000
2023-10-17 17:59:25,093 epoch 5 - iter 58/292 - loss 0.04827007 - time (sec): 3.25 - samples/sec: 2622.66 - lr: 0.000032 - momentum: 0.000000
2023-10-17 17:59:26,808 epoch 5 - iter 87/292 - loss 0.04812479 - time (sec): 4.97 - samples/sec: 2736.37 - lr: 0.000032 - momentum: 0.000000
2023-10-17 17:59:28,532 epoch 5 - iter 116/292 - loss 0.04989877 - time (sec): 6.69 - samples/sec: 2676.73 - lr: 0.000031 - momentum: 0.000000
2023-10-17 17:59:30,292 epoch 5 - iter 145/292 - loss 0.05178593 - time (sec): 8.45 - samples/sec: 2646.29 - lr: 0.000031 - momentum: 0.000000
2023-10-17 17:59:31,921 epoch 5 - iter 174/292 - loss 0.04817322 - time (sec): 10.08 - samples/sec: 2640.85 - lr: 0.000030 - momentum: 0.000000
2023-10-17 17:59:33,512 epoch 5 - iter 203/292 - loss 0.04781243 - time (sec): 11.67 - samples/sec: 2643.03 - lr: 0.000030 - momentum: 0.000000
2023-10-17 17:59:35,227 epoch 5 - iter 232/292 - loss 0.04594962 - time (sec): 13.39 - samples/sec: 2631.40 - lr: 0.000029 - momentum: 0.000000
2023-10-17 17:59:36,905 epoch 5 - iter 261/292 - loss 0.04519214 - time (sec): 15.07 - samples/sec: 2644.65 - lr: 0.000028 - momentum: 0.000000
2023-10-17 17:59:38,544 epoch 5 - iter 290/292 - loss 0.04462130 - time (sec): 16.71 - samples/sec: 2652.22 - lr: 0.000028 - momentum: 0.000000
2023-10-17 17:59:38,636 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:38,637 EPOCH 5 done: loss 0.0446 - lr: 0.000028
2023-10-17 17:59:39,971 DEV : loss 0.1602601408958435 - f1-score (micro avg) 0.7296
2023-10-17 17:59:39,978 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:41,745 epoch 6 - iter 29/292 - loss 0.03117945 - time (sec): 1.77 - samples/sec: 2448.91 - lr: 0.000027 - momentum: 0.000000
2023-10-17 17:59:43,627 epoch 6 - iter 58/292 - loss 0.02884635 - time (sec): 3.65 - samples/sec: 2482.68 - lr: 0.000027 - momentum: 0.000000
2023-10-17 17:59:45,431 epoch 6 - iter 87/292 - loss 0.02959983 - time (sec): 5.45 - samples/sec: 2387.97 - lr: 0.000026 - momentum: 0.000000
2023-10-17 17:59:47,014 epoch 6 - iter 116/292 - loss 0.03130694 - time (sec): 7.03 - samples/sec: 2332.69 - lr: 0.000026 - momentum: 0.000000
2023-10-17 17:59:48,803 epoch 6 - iter 145/292 - loss 0.02949162 - time (sec): 8.82 - samples/sec: 2410.79 - lr: 0.000025 - momentum: 0.000000
2023-10-17 17:59:50,550 epoch 6 - iter 174/292 - loss 0.03282502 - time (sec): 10.57 - samples/sec: 2485.60 - lr: 0.000025 - momentum: 0.000000
2023-10-17 17:59:52,093 epoch 6 - iter 203/292 - loss 0.03369730 - time (sec): 12.11 - samples/sec: 2487.82 - lr: 0.000024 - momentum: 0.000000
2023-10-17 17:59:53,748 epoch 6 - iter 232/292 - loss 0.03273151 - time (sec): 13.77 - samples/sec: 2494.63 - lr: 0.000023 - momentum: 0.000000
2023-10-17 17:59:55,348 epoch 6 - iter 261/292 - loss 0.03486864 - time (sec): 15.37 - samples/sec: 2521.05 - lr: 0.000023 - momentum: 0.000000
2023-10-17 17:59:57,157 epoch 6 - iter 290/292 - loss 0.03165586 - time (sec): 17.18 - samples/sec: 2573.35 - lr: 0.000022 - momentum: 0.000000
2023-10-17 17:59:57,250 ----------------------------------------------------------------------------------------------------
2023-10-17 17:59:57,250 EPOCH 6 done: loss 0.0319 - lr: 0.000022
2023-10-17 17:59:58,554 DEV : loss 0.1713484823703766 - f1-score (micro avg) 0.773
2023-10-17 17:59:58,561 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:00,155 epoch 7 - iter 29/292 - loss 0.02059682 - time (sec): 1.59 - samples/sec: 2614.99 - lr: 0.000022 - momentum: 0.000000
2023-10-17 18:00:01,684 epoch 7 - iter 58/292 - loss 0.02743531 - time (sec): 3.12 - samples/sec: 2516.97 - lr: 0.000021 - momentum: 0.000000
2023-10-17 18:00:03,380 epoch 7 - iter 87/292 - loss 0.02412808 - time (sec): 4.82 - samples/sec: 2563.43 - lr: 0.000021 - momentum: 0.000000
2023-10-17 18:00:04,976 epoch 7 - iter 116/292 - loss 0.02556567 - time (sec): 6.41 - samples/sec: 2576.34 - lr: 0.000020 - momentum: 0.000000
2023-10-17 18:00:06,649 epoch 7 - iter 145/292 - loss 0.03034182 - time (sec): 8.09 - samples/sec: 2638.95 - lr: 0.000020 - momentum: 0.000000
2023-10-17 18:00:08,341 epoch 7 - iter 174/292 - loss 0.02823755 - time (sec): 9.78 - samples/sec: 2600.27 - lr: 0.000019 - momentum: 0.000000
2023-10-17 18:00:10,116 epoch 7 - iter 203/292 - loss 0.02560592 - time (sec): 11.55 - samples/sec: 2602.05 - lr: 0.000018 - momentum: 0.000000
2023-10-17 18:00:11,803 epoch 7 - iter 232/292 - loss 0.02413585 - time (sec): 13.24 - samples/sec: 2583.25 - lr: 0.000018 - momentum: 0.000000
2023-10-17 18:00:13,524 epoch 7 - iter 261/292 - loss 0.02391633 - time (sec): 14.96 - samples/sec: 2594.87 - lr: 0.000017 - momentum: 0.000000
2023-10-17 18:00:15,255 epoch 7 - iter 290/292 - loss 0.02352649 - time (sec): 16.69 - samples/sec: 2626.34 - lr: 0.000017 - momentum: 0.000000
2023-10-17 18:00:15,455 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:15,456 EPOCH 7 done: loss 0.0234 - lr: 0.000017
2023-10-17 18:00:16,783 DEV : loss 0.1889658421278 - f1-score (micro avg) 0.756
2023-10-17 18:00:16,790 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:18,494 epoch 8 - iter 29/292 - loss 0.01156358 - time (sec): 1.70 - samples/sec: 2576.80 - lr: 0.000016 - momentum: 0.000000
2023-10-17 18:00:20,203 epoch 8 - iter 58/292 - loss 0.01363486 - time (sec): 3.41 - samples/sec: 2579.01 - lr: 0.000016 - momentum: 0.000000
2023-10-17 18:00:21,863 epoch 8 - iter 87/292 - loss 0.01449766 - time (sec): 5.07 - samples/sec: 2619.98 - lr: 0.000015 - momentum: 0.000000
2023-10-17 18:00:23,775 epoch 8 - iter 116/292 - loss 0.01864699 - time (sec): 6.98 - samples/sec: 2550.16 - lr: 0.000015 - momentum: 0.000000
2023-10-17 18:00:25,440 epoch 8 - iter 145/292 - loss 0.01972188 - time (sec): 8.65 - samples/sec: 2588.01 - lr: 0.000014 - momentum: 0.000000
2023-10-17 18:00:27,084 epoch 8 - iter 174/292 - loss 0.01866095 - time (sec): 10.29 - samples/sec: 2627.52 - lr: 0.000013 - momentum: 0.000000
2023-10-17 18:00:28,834 epoch 8 - iter 203/292 - loss 0.01727761 - time (sec): 12.04 - samples/sec: 2658.79 - lr: 0.000013 - momentum: 0.000000
2023-10-17 18:00:30,336 epoch 8 - iter 232/292 - loss 0.01740192 - time (sec): 13.54 - samples/sec: 2627.55 - lr: 0.000012 - momentum: 0.000000
2023-10-17 18:00:32,062 epoch 8 - iter 261/292 - loss 0.01627368 - time (sec): 15.27 - samples/sec: 2641.10 - lr: 0.000012 - momentum: 0.000000
2023-10-17 18:00:33,679 epoch 8 - iter 290/292 - loss 0.01606708 - time (sec): 16.89 - samples/sec: 2620.90 - lr: 0.000011 - momentum: 0.000000
2023-10-17 18:00:33,770 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:33,770 EPOCH 8 done: loss 0.0160 - lr: 0.000011
2023-10-17 18:00:35,012 DEV : loss 0.20527206361293793 - f1-score (micro avg) 0.7478
2023-10-17 18:00:35,018 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:36,610 epoch 9 - iter 29/292 - loss 0.01233241 - time (sec): 1.59 - samples/sec: 2518.86 - lr: 0.000011 - momentum: 0.000000
2023-10-17 18:00:38,511 epoch 9 - iter 58/292 - loss 0.01637592 - time (sec): 3.49 - samples/sec: 2727.71 - lr: 0.000010 - momentum: 0.000000
2023-10-17 18:00:40,332 epoch 9 - iter 87/292 - loss 0.02791061 - time (sec): 5.31 - samples/sec: 2765.82 - lr: 0.000010 - momentum: 0.000000
2023-10-17 18:00:41,916 epoch 9 - iter 116/292 - loss 0.02442203 - time (sec): 6.90 - samples/sec: 2697.63 - lr: 0.000009 - momentum: 0.000000
2023-10-17 18:00:43,406 epoch 9 - iter 145/292 - loss 0.02208196 - time (sec): 8.39 - samples/sec: 2646.99 - lr: 0.000008 - momentum: 0.000000
2023-10-17 18:00:45,075 epoch 9 - iter 174/292 - loss 0.01999989 - time (sec): 10.06 - samples/sec: 2666.89 - lr: 0.000008 - momentum: 0.000000
2023-10-17 18:00:46,681 epoch 9 - iter 203/292 - loss 0.01804618 - time (sec): 11.66 - samples/sec: 2648.58 - lr: 0.000007 - momentum: 0.000000
2023-10-17 18:00:48,397 epoch 9 - iter 232/292 - loss 0.01685413 - time (sec): 13.38 - samples/sec: 2684.23 - lr: 0.000007 - momentum: 0.000000
2023-10-17 18:00:49,945 epoch 9 - iter 261/292 - loss 0.01630731 - time (sec): 14.93 - samples/sec: 2653.53 - lr: 0.000006 - momentum: 0.000000
2023-10-17 18:00:51,498 epoch 9 - iter 290/292 - loss 0.01472446 - time (sec): 16.48 - samples/sec: 2667.85 - lr: 0.000006 - momentum: 0.000000
2023-10-17 18:00:51,635 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:51,635 EPOCH 9 done: loss 0.0146 - lr: 0.000006
2023-10-17 18:00:52,961 DEV : loss 0.19456231594085693 - f1-score (micro avg) 0.7682
2023-10-17 18:00:52,968 ----------------------------------------------------------------------------------------------------
2023-10-17 18:00:54,993 epoch 10 - iter 29/292 - loss 0.01092397 - time (sec): 2.02 - samples/sec: 2646.57 - lr: 0.000005 - momentum: 0.000000
2023-10-17 18:00:56,816 epoch 10 - iter 58/292 - loss 0.00845707 - time (sec): 3.85 - samples/sec: 2558.88 - lr: 0.000005 - momentum: 0.000000
2023-10-17 18:00:58,489 epoch 10 - iter 87/292 - loss 0.00773468 - time (sec): 5.52 - samples/sec: 2551.82 - lr: 0.000004 - momentum: 0.000000
2023-10-17 18:01:00,138 epoch 10 - iter 116/292 - loss 0.00801451 - time (sec): 7.17 - samples/sec: 2554.52 - lr: 0.000003 - momentum: 0.000000
2023-10-17 18:01:01,812 epoch 10 - iter 145/292 - loss 0.00771078 - time (sec): 8.84 - samples/sec: 2498.95 - lr: 0.000003 - momentum: 0.000000
2023-10-17 18:01:03,554 epoch 10 - iter 174/292 - loss 0.00748683 - time (sec): 10.58 - samples/sec: 2490.12 - lr: 0.000002 - momentum: 0.000000
2023-10-17 18:01:05,404 epoch 10 - iter 203/292 - loss 0.00738807 - time (sec): 12.43 - samples/sec: 2525.12 - lr: 0.000002 - momentum: 0.000000
2023-10-17 18:01:07,056 epoch 10 - iter 232/292 - loss 0.00744920 - time (sec): 14.09 - samples/sec: 2533.47 - lr: 0.000001 - momentum: 0.000000
2023-10-17 18:01:08,664 epoch 10 - iter 261/292 - loss 0.00703627 - time (sec): 15.69 - samples/sec: 2522.98 - lr: 0.000001 - momentum: 0.000000
2023-10-17 18:01:10,405 epoch 10 - iter 290/292 - loss 0.00754299 - time (sec): 17.44 - samples/sec: 2529.90 - lr: 0.000000 - momentum: 0.000000
2023-10-17 18:01:10,507 ----------------------------------------------------------------------------------------------------
2023-10-17 18:01:10,507 EPOCH 10 done: loss 0.0075 - lr: 0.000000
2023-10-17 18:01:11,756 DEV : loss 0.20955659449100494 - f1-score (micro avg) 0.7639
2023-10-17 18:01:12,085 ----------------------------------------------------------------------------------------------------
2023-10-17 18:01:12,086 Loading model from best epoch ...
2023-10-17 18:01:13,492 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
2023-10-17 18:01:15,926
Results:
- F-score (micro) 0.7333
- F-score (macro) 0.6735
- Accuracy 0.6027
By class:
precision recall f1-score support
PER 0.7995 0.8362 0.8174 348
LOC 0.6030 0.7739 0.6779 261
ORG 0.4884 0.4038 0.4421 52
HumanProd 0.9333 0.6364 0.7568 22
micro avg 0.6975 0.7731 0.7333 683
macro avg 0.7060 0.6626 0.6735 683
weighted avg 0.7050 0.7731 0.7336 683
2023-10-17 18:01:15,926 ----------------------------------------------------------------------------------------------------
|