File size: 23,754 Bytes
b332407 |
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 |
2023-10-16 18:37:27,557 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(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): 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()
)"
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 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
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Train: 1166 sentences
2023-10-16 18:37:27,558 (train_with_dev=False, train_with_test=False)
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Training Params:
2023-10-16 18:37:27,558 - learning_rate: "5e-05"
2023-10-16 18:37:27,558 - mini_batch_size: "4"
2023-10-16 18:37:27,558 - max_epochs: "10"
2023-10-16 18:37:27,558 - shuffle: "True"
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Plugins:
2023-10-16 18:37:27,558 - LinearScheduler | warmup_fraction: '0.1'
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Final evaluation on model from best epoch (best-model.pt)
2023-10-16 18:37:27,558 - metric: "('micro avg', 'f1-score')"
2023-10-16 18:37:27,558 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,558 Computation:
2023-10-16 18:37:27,558 - compute on device: cuda:0
2023-10-16 18:37:27,558 - embedding storage: none
2023-10-16 18:37:27,559 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,559 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-16 18:37:27,559 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:27,559 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:29,222 epoch 1 - iter 29/292 - loss 2.91011187 - time (sec): 1.66 - samples/sec: 2715.94 - lr: 0.000005 - momentum: 0.000000
2023-10-16 18:37:30,705 epoch 1 - iter 58/292 - loss 2.22168904 - time (sec): 3.15 - samples/sec: 2650.68 - lr: 0.000010 - momentum: 0.000000
2023-10-16 18:37:32,423 epoch 1 - iter 87/292 - loss 1.60697027 - time (sec): 4.86 - samples/sec: 2672.46 - lr: 0.000015 - momentum: 0.000000
2023-10-16 18:37:34,276 epoch 1 - iter 116/292 - loss 1.34788026 - time (sec): 6.72 - samples/sec: 2668.82 - lr: 0.000020 - momentum: 0.000000
2023-10-16 18:37:35,860 epoch 1 - iter 145/292 - loss 1.20838293 - time (sec): 8.30 - samples/sec: 2628.47 - lr: 0.000025 - momentum: 0.000000
2023-10-16 18:37:37,675 epoch 1 - iter 174/292 - loss 1.08372999 - time (sec): 10.11 - samples/sec: 2660.03 - lr: 0.000030 - momentum: 0.000000
2023-10-16 18:37:39,244 epoch 1 - iter 203/292 - loss 0.97907216 - time (sec): 11.68 - samples/sec: 2651.97 - lr: 0.000035 - momentum: 0.000000
2023-10-16 18:37:40,953 epoch 1 - iter 232/292 - loss 0.88148784 - time (sec): 13.39 - samples/sec: 2677.37 - lr: 0.000040 - momentum: 0.000000
2023-10-16 18:37:42,632 epoch 1 - iter 261/292 - loss 0.81684973 - time (sec): 15.07 - samples/sec: 2674.36 - lr: 0.000045 - momentum: 0.000000
2023-10-16 18:37:44,197 epoch 1 - iter 290/292 - loss 0.77210022 - time (sec): 16.64 - samples/sec: 2662.04 - lr: 0.000049 - momentum: 0.000000
2023-10-16 18:37:44,290 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:44,290 EPOCH 1 done: loss 0.7702 - lr: 0.000049
2023-10-16 18:37:45,123 DEV : loss 0.19686032831668854 - f1-score (micro avg) 0.493
2023-10-16 18:37:45,131 saving best model
2023-10-16 18:37:45,486 ----------------------------------------------------------------------------------------------------
2023-10-16 18:37:47,222 epoch 2 - iter 29/292 - loss 0.25306732 - time (sec): 1.73 - samples/sec: 2531.79 - lr: 0.000049 - momentum: 0.000000
2023-10-16 18:37:49,128 epoch 2 - iter 58/292 - loss 0.28082060 - time (sec): 3.64 - samples/sec: 2729.34 - lr: 0.000049 - momentum: 0.000000
2023-10-16 18:37:50,890 epoch 2 - iter 87/292 - loss 0.26712309 - time (sec): 5.40 - samples/sec: 2640.62 - lr: 0.000048 - momentum: 0.000000
2023-10-16 18:37:52,650 epoch 2 - iter 116/292 - loss 0.25249370 - time (sec): 7.16 - samples/sec: 2644.03 - lr: 0.000048 - momentum: 0.000000
2023-10-16 18:37:54,152 epoch 2 - iter 145/292 - loss 0.23957595 - time (sec): 8.66 - samples/sec: 2642.03 - lr: 0.000047 - momentum: 0.000000
2023-10-16 18:37:55,790 epoch 2 - iter 174/292 - loss 0.23236470 - time (sec): 10.30 - samples/sec: 2668.36 - lr: 0.000047 - momentum: 0.000000
2023-10-16 18:37:57,259 epoch 2 - iter 203/292 - loss 0.22615504 - time (sec): 11.77 - samples/sec: 2663.40 - lr: 0.000046 - momentum: 0.000000
2023-10-16 18:37:58,791 epoch 2 - iter 232/292 - loss 0.21951834 - time (sec): 13.30 - samples/sec: 2667.54 - lr: 0.000046 - momentum: 0.000000
2023-10-16 18:38:00,470 epoch 2 - iter 261/292 - loss 0.20918561 - time (sec): 14.98 - samples/sec: 2662.81 - lr: 0.000045 - momentum: 0.000000
2023-10-16 18:38:02,029 epoch 2 - iter 290/292 - loss 0.20202252 - time (sec): 16.54 - samples/sec: 2660.35 - lr: 0.000045 - momentum: 0.000000
2023-10-16 18:38:02,141 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:02,142 EPOCH 2 done: loss 0.2003 - lr: 0.000045
2023-10-16 18:38:03,417 DEV : loss 0.158650204539299 - f1-score (micro avg) 0.6542
2023-10-16 18:38:03,421 saving best model
2023-10-16 18:38:04,123 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:05,892 epoch 3 - iter 29/292 - loss 0.10153556 - time (sec): 1.77 - samples/sec: 2802.00 - lr: 0.000044 - momentum: 0.000000
2023-10-16 18:38:07,818 epoch 3 - iter 58/292 - loss 0.10831370 - time (sec): 3.69 - samples/sec: 2690.02 - lr: 0.000043 - momentum: 0.000000
2023-10-16 18:38:09,316 epoch 3 - iter 87/292 - loss 0.10922557 - time (sec): 5.19 - samples/sec: 2642.27 - lr: 0.000043 - momentum: 0.000000
2023-10-16 18:38:10,763 epoch 3 - iter 116/292 - loss 0.10600736 - time (sec): 6.64 - samples/sec: 2584.80 - lr: 0.000042 - momentum: 0.000000
2023-10-16 18:38:12,440 epoch 3 - iter 145/292 - loss 0.10724913 - time (sec): 8.32 - samples/sec: 2589.17 - lr: 0.000042 - momentum: 0.000000
2023-10-16 18:38:14,103 epoch 3 - iter 174/292 - loss 0.10441347 - time (sec): 9.98 - samples/sec: 2655.49 - lr: 0.000041 - momentum: 0.000000
2023-10-16 18:38:15,983 epoch 3 - iter 203/292 - loss 0.10838574 - time (sec): 11.86 - samples/sec: 2713.07 - lr: 0.000041 - momentum: 0.000000
2023-10-16 18:38:17,565 epoch 3 - iter 232/292 - loss 0.10772044 - time (sec): 13.44 - samples/sec: 2683.94 - lr: 0.000040 - momentum: 0.000000
2023-10-16 18:38:19,145 epoch 3 - iter 261/292 - loss 0.10838088 - time (sec): 15.02 - samples/sec: 2670.22 - lr: 0.000040 - momentum: 0.000000
2023-10-16 18:38:20,782 epoch 3 - iter 290/292 - loss 0.11248021 - time (sec): 16.66 - samples/sec: 2645.58 - lr: 0.000039 - momentum: 0.000000
2023-10-16 18:38:20,890 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:20,890 EPOCH 3 done: loss 0.1121 - lr: 0.000039
2023-10-16 18:38:22,165 DEV : loss 0.16866865754127502 - f1-score (micro avg) 0.6454
2023-10-16 18:38:22,169 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:23,948 epoch 4 - iter 29/292 - loss 0.07309028 - time (sec): 1.78 - samples/sec: 2907.31 - lr: 0.000038 - momentum: 0.000000
2023-10-16 18:38:25,692 epoch 4 - iter 58/292 - loss 0.09292286 - time (sec): 3.52 - samples/sec: 2722.63 - lr: 0.000038 - momentum: 0.000000
2023-10-16 18:38:27,438 epoch 4 - iter 87/292 - loss 0.07807604 - time (sec): 5.27 - samples/sec: 2734.45 - lr: 0.000037 - momentum: 0.000000
2023-10-16 18:38:28,839 epoch 4 - iter 116/292 - loss 0.07803060 - time (sec): 6.67 - samples/sec: 2670.69 - lr: 0.000037 - momentum: 0.000000
2023-10-16 18:38:30,525 epoch 4 - iter 145/292 - loss 0.07517713 - time (sec): 8.36 - samples/sec: 2705.98 - lr: 0.000036 - momentum: 0.000000
2023-10-16 18:38:32,284 epoch 4 - iter 174/292 - loss 0.07995214 - time (sec): 10.11 - samples/sec: 2661.50 - lr: 0.000036 - momentum: 0.000000
2023-10-16 18:38:33,865 epoch 4 - iter 203/292 - loss 0.07654734 - time (sec): 11.69 - samples/sec: 2627.69 - lr: 0.000035 - momentum: 0.000000
2023-10-16 18:38:35,747 epoch 4 - iter 232/292 - loss 0.07335699 - time (sec): 13.58 - samples/sec: 2669.63 - lr: 0.000035 - momentum: 0.000000
2023-10-16 18:38:37,270 epoch 4 - iter 261/292 - loss 0.07681713 - time (sec): 15.10 - samples/sec: 2664.75 - lr: 0.000034 - momentum: 0.000000
2023-10-16 18:38:38,836 epoch 4 - iter 290/292 - loss 0.07686933 - time (sec): 16.67 - samples/sec: 2653.19 - lr: 0.000033 - momentum: 0.000000
2023-10-16 18:38:38,925 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:38,925 EPOCH 4 done: loss 0.0769 - lr: 0.000033
2023-10-16 18:38:40,210 DEV : loss 0.15432444214820862 - f1-score (micro avg) 0.6467
2023-10-16 18:38:40,214 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:41,860 epoch 5 - iter 29/292 - loss 0.04301207 - time (sec): 1.64 - samples/sec: 2695.24 - lr: 0.000033 - momentum: 0.000000
2023-10-16 18:38:43,551 epoch 5 - iter 58/292 - loss 0.03809167 - time (sec): 3.34 - samples/sec: 2614.48 - lr: 0.000032 - momentum: 0.000000
2023-10-16 18:38:45,275 epoch 5 - iter 87/292 - loss 0.03839505 - time (sec): 5.06 - samples/sec: 2614.76 - lr: 0.000032 - momentum: 0.000000
2023-10-16 18:38:47,049 epoch 5 - iter 116/292 - loss 0.04375124 - time (sec): 6.83 - samples/sec: 2711.30 - lr: 0.000031 - momentum: 0.000000
2023-10-16 18:38:48,759 epoch 5 - iter 145/292 - loss 0.04266788 - time (sec): 8.54 - samples/sec: 2750.18 - lr: 0.000031 - momentum: 0.000000
2023-10-16 18:38:50,425 epoch 5 - iter 174/292 - loss 0.04535040 - time (sec): 10.21 - samples/sec: 2726.59 - lr: 0.000030 - momentum: 0.000000
2023-10-16 18:38:52,095 epoch 5 - iter 203/292 - loss 0.04546838 - time (sec): 11.88 - samples/sec: 2752.67 - lr: 0.000030 - momentum: 0.000000
2023-10-16 18:38:53,669 epoch 5 - iter 232/292 - loss 0.04687883 - time (sec): 13.45 - samples/sec: 2724.78 - lr: 0.000029 - momentum: 0.000000
2023-10-16 18:38:55,152 epoch 5 - iter 261/292 - loss 0.05118725 - time (sec): 14.94 - samples/sec: 2708.21 - lr: 0.000028 - momentum: 0.000000
2023-10-16 18:38:56,656 epoch 5 - iter 290/292 - loss 0.05214197 - time (sec): 16.44 - samples/sec: 2686.31 - lr: 0.000028 - momentum: 0.000000
2023-10-16 18:38:56,758 ----------------------------------------------------------------------------------------------------
2023-10-16 18:38:56,759 EPOCH 5 done: loss 0.0520 - lr: 0.000028
2023-10-16 18:38:58,008 DEV : loss 0.14177842438220978 - f1-score (micro avg) 0.7619
2023-10-16 18:38:58,013 saving best model
2023-10-16 18:38:58,483 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:00,099 epoch 6 - iter 29/292 - loss 0.05101971 - time (sec): 1.61 - samples/sec: 2737.38 - lr: 0.000027 - momentum: 0.000000
2023-10-16 18:39:01,800 epoch 6 - iter 58/292 - loss 0.04834906 - time (sec): 3.31 - samples/sec: 2802.96 - lr: 0.000027 - momentum: 0.000000
2023-10-16 18:39:03,356 epoch 6 - iter 87/292 - loss 0.04266830 - time (sec): 4.87 - samples/sec: 2789.38 - lr: 0.000026 - momentum: 0.000000
2023-10-16 18:39:04,991 epoch 6 - iter 116/292 - loss 0.04019668 - time (sec): 6.50 - samples/sec: 2730.45 - lr: 0.000026 - momentum: 0.000000
2023-10-16 18:39:06,648 epoch 6 - iter 145/292 - loss 0.03960645 - time (sec): 8.16 - samples/sec: 2712.36 - lr: 0.000025 - momentum: 0.000000
2023-10-16 18:39:08,243 epoch 6 - iter 174/292 - loss 0.03900318 - time (sec): 9.76 - samples/sec: 2670.81 - lr: 0.000025 - momentum: 0.000000
2023-10-16 18:39:09,906 epoch 6 - iter 203/292 - loss 0.03756220 - time (sec): 11.42 - samples/sec: 2689.48 - lr: 0.000024 - momentum: 0.000000
2023-10-16 18:39:11,580 epoch 6 - iter 232/292 - loss 0.03654571 - time (sec): 13.09 - samples/sec: 2710.25 - lr: 0.000023 - momentum: 0.000000
2023-10-16 18:39:13,227 epoch 6 - iter 261/292 - loss 0.03692190 - time (sec): 14.74 - samples/sec: 2708.96 - lr: 0.000023 - momentum: 0.000000
2023-10-16 18:39:14,980 epoch 6 - iter 290/292 - loss 0.03851499 - time (sec): 16.49 - samples/sec: 2683.26 - lr: 0.000022 - momentum: 0.000000
2023-10-16 18:39:15,071 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:15,072 EPOCH 6 done: loss 0.0385 - lr: 0.000022
2023-10-16 18:39:16,426 DEV : loss 0.15027689933776855 - f1-score (micro avg) 0.7458
2023-10-16 18:39:16,432 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:18,171 epoch 7 - iter 29/292 - loss 0.02746134 - time (sec): 1.74 - samples/sec: 2521.73 - lr: 0.000022 - momentum: 0.000000
2023-10-16 18:39:19,827 epoch 7 - iter 58/292 - loss 0.02252500 - time (sec): 3.39 - samples/sec: 2513.96 - lr: 0.000021 - momentum: 0.000000
2023-10-16 18:39:21,484 epoch 7 - iter 87/292 - loss 0.02102995 - time (sec): 5.05 - samples/sec: 2608.39 - lr: 0.000021 - momentum: 0.000000
2023-10-16 18:39:23,481 epoch 7 - iter 116/292 - loss 0.02302638 - time (sec): 7.05 - samples/sec: 2551.46 - lr: 0.000020 - momentum: 0.000000
2023-10-16 18:39:25,058 epoch 7 - iter 145/292 - loss 0.02321526 - time (sec): 8.62 - samples/sec: 2542.08 - lr: 0.000020 - momentum: 0.000000
2023-10-16 18:39:26,976 epoch 7 - iter 174/292 - loss 0.02710328 - time (sec): 10.54 - samples/sec: 2593.33 - lr: 0.000019 - momentum: 0.000000
2023-10-16 18:39:28,492 epoch 7 - iter 203/292 - loss 0.02550259 - time (sec): 12.06 - samples/sec: 2600.79 - lr: 0.000018 - momentum: 0.000000
2023-10-16 18:39:30,206 epoch 7 - iter 232/292 - loss 0.02846380 - time (sec): 13.77 - samples/sec: 2594.47 - lr: 0.000018 - momentum: 0.000000
2023-10-16 18:39:31,916 epoch 7 - iter 261/292 - loss 0.02759356 - time (sec): 15.48 - samples/sec: 2595.48 - lr: 0.000017 - momentum: 0.000000
2023-10-16 18:39:33,466 epoch 7 - iter 290/292 - loss 0.02720347 - time (sec): 17.03 - samples/sec: 2595.07 - lr: 0.000017 - momentum: 0.000000
2023-10-16 18:39:33,565 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:33,565 EPOCH 7 done: loss 0.0271 - lr: 0.000017
2023-10-16 18:39:34,842 DEV : loss 0.16174526512622833 - f1-score (micro avg) 0.7617
2023-10-16 18:39:34,847 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:36,418 epoch 8 - iter 29/292 - loss 0.01140027 - time (sec): 1.57 - samples/sec: 2814.16 - lr: 0.000016 - momentum: 0.000000
2023-10-16 18:39:38,168 epoch 8 - iter 58/292 - loss 0.01308990 - time (sec): 3.32 - samples/sec: 2789.42 - lr: 0.000016 - momentum: 0.000000
2023-10-16 18:39:40,004 epoch 8 - iter 87/292 - loss 0.02439680 - time (sec): 5.16 - samples/sec: 2768.89 - lr: 0.000015 - momentum: 0.000000
2023-10-16 18:39:41,475 epoch 8 - iter 116/292 - loss 0.02707583 - time (sec): 6.63 - samples/sec: 2672.02 - lr: 0.000015 - momentum: 0.000000
2023-10-16 18:39:43,374 epoch 8 - iter 145/292 - loss 0.02509823 - time (sec): 8.53 - samples/sec: 2722.03 - lr: 0.000014 - momentum: 0.000000
2023-10-16 18:39:44,987 epoch 8 - iter 174/292 - loss 0.02364774 - time (sec): 10.14 - samples/sec: 2699.66 - lr: 0.000013 - momentum: 0.000000
2023-10-16 18:39:46,675 epoch 8 - iter 203/292 - loss 0.02165952 - time (sec): 11.83 - samples/sec: 2664.10 - lr: 0.000013 - momentum: 0.000000
2023-10-16 18:39:48,333 epoch 8 - iter 232/292 - loss 0.02096976 - time (sec): 13.49 - samples/sec: 2679.52 - lr: 0.000012 - momentum: 0.000000
2023-10-16 18:39:50,009 epoch 8 - iter 261/292 - loss 0.02043181 - time (sec): 15.16 - samples/sec: 2681.49 - lr: 0.000012 - momentum: 0.000000
2023-10-16 18:39:51,460 epoch 8 - iter 290/292 - loss 0.02046018 - time (sec): 16.61 - samples/sec: 2663.85 - lr: 0.000011 - momentum: 0.000000
2023-10-16 18:39:51,550 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:51,550 EPOCH 8 done: loss 0.0204 - lr: 0.000011
2023-10-16 18:39:52,806 DEV : loss 0.1880948841571808 - f1-score (micro avg) 0.7164
2023-10-16 18:39:52,810 ----------------------------------------------------------------------------------------------------
2023-10-16 18:39:54,412 epoch 9 - iter 29/292 - loss 0.02255474 - time (sec): 1.60 - samples/sec: 2980.03 - lr: 0.000011 - momentum: 0.000000
2023-10-16 18:39:56,208 epoch 9 - iter 58/292 - loss 0.02845919 - time (sec): 3.40 - samples/sec: 2836.44 - lr: 0.000010 - momentum: 0.000000
2023-10-16 18:39:57,808 epoch 9 - iter 87/292 - loss 0.02396023 - time (sec): 5.00 - samples/sec: 2698.78 - lr: 0.000010 - momentum: 0.000000
2023-10-16 18:39:59,390 epoch 9 - iter 116/292 - loss 0.02250170 - time (sec): 6.58 - samples/sec: 2704.33 - lr: 0.000009 - momentum: 0.000000
2023-10-16 18:40:00,927 epoch 9 - iter 145/292 - loss 0.02016379 - time (sec): 8.12 - samples/sec: 2666.79 - lr: 0.000008 - momentum: 0.000000
2023-10-16 18:40:02,535 epoch 9 - iter 174/292 - loss 0.01984362 - time (sec): 9.72 - samples/sec: 2655.54 - lr: 0.000008 - momentum: 0.000000
2023-10-16 18:40:04,175 epoch 9 - iter 203/292 - loss 0.01724021 - time (sec): 11.36 - samples/sec: 2698.32 - lr: 0.000007 - momentum: 0.000000
2023-10-16 18:40:05,675 epoch 9 - iter 232/292 - loss 0.01701978 - time (sec): 12.86 - samples/sec: 2654.89 - lr: 0.000007 - momentum: 0.000000
2023-10-16 18:40:07,426 epoch 9 - iter 261/292 - loss 0.01550812 - time (sec): 14.62 - samples/sec: 2648.98 - lr: 0.000006 - momentum: 0.000000
2023-10-16 18:40:09,246 epoch 9 - iter 290/292 - loss 0.01507845 - time (sec): 16.43 - samples/sec: 2677.62 - lr: 0.000006 - momentum: 0.000000
2023-10-16 18:40:09,380 ----------------------------------------------------------------------------------------------------
2023-10-16 18:40:09,380 EPOCH 9 done: loss 0.0149 - lr: 0.000006
2023-10-16 18:40:10,634 DEV : loss 0.1720294952392578 - f1-score (micro avg) 0.7479
2023-10-16 18:40:10,639 ----------------------------------------------------------------------------------------------------
2023-10-16 18:40:12,109 epoch 10 - iter 29/292 - loss 0.01950142 - time (sec): 1.47 - samples/sec: 2638.32 - lr: 0.000005 - momentum: 0.000000
2023-10-16 18:40:13,665 epoch 10 - iter 58/292 - loss 0.01376562 - time (sec): 3.02 - samples/sec: 2703.94 - lr: 0.000005 - momentum: 0.000000
2023-10-16 18:40:15,361 epoch 10 - iter 87/292 - loss 0.01047050 - time (sec): 4.72 - samples/sec: 2740.54 - lr: 0.000004 - momentum: 0.000000
2023-10-16 18:40:17,260 epoch 10 - iter 116/292 - loss 0.01107990 - time (sec): 6.62 - samples/sec: 2746.99 - lr: 0.000003 - momentum: 0.000000
2023-10-16 18:40:18,822 epoch 10 - iter 145/292 - loss 0.01088382 - time (sec): 8.18 - samples/sec: 2721.81 - lr: 0.000003 - momentum: 0.000000
2023-10-16 18:40:20,596 epoch 10 - iter 174/292 - loss 0.01209993 - time (sec): 9.96 - samples/sec: 2724.55 - lr: 0.000002 - momentum: 0.000000
2023-10-16 18:40:22,121 epoch 10 - iter 203/292 - loss 0.01153913 - time (sec): 11.48 - samples/sec: 2708.05 - lr: 0.000002 - momentum: 0.000000
2023-10-16 18:40:23,805 epoch 10 - iter 232/292 - loss 0.01083310 - time (sec): 13.16 - samples/sec: 2693.51 - lr: 0.000001 - momentum: 0.000000
2023-10-16 18:40:25,547 epoch 10 - iter 261/292 - loss 0.00986534 - time (sec): 14.91 - samples/sec: 2720.24 - lr: 0.000001 - momentum: 0.000000
2023-10-16 18:40:27,096 epoch 10 - iter 290/292 - loss 0.00929650 - time (sec): 16.46 - samples/sec: 2692.69 - lr: 0.000000 - momentum: 0.000000
2023-10-16 18:40:27,177 ----------------------------------------------------------------------------------------------------
2023-10-16 18:40:27,177 EPOCH 10 done: loss 0.0093 - lr: 0.000000
2023-10-16 18:40:28,479 DEV : loss 0.1805955320596695 - f1-score (micro avg) 0.7542
2023-10-16 18:40:28,856 ----------------------------------------------------------------------------------------------------
2023-10-16 18:40:28,858 Loading model from best epoch ...
2023-10-16 18:40:30,628 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
2023-10-16 18:40:33,999
Results:
- F-score (micro) 0.7443
- F-score (macro) 0.6697
- Accuracy 0.6164
By class:
precision recall f1-score support
PER 0.8146 0.8333 0.8239 348
LOC 0.6460 0.7969 0.7136 261
ORG 0.3833 0.4423 0.4107 52
HumanProd 0.6333 0.8636 0.7308 22
micro avg 0.7031 0.7906 0.7443 683
macro avg 0.6193 0.7341 0.6697 683
weighted avg 0.7115 0.7906 0.7473 683
2023-10-16 18:40:34,000 ----------------------------------------------------------------------------------------------------
|