File size: 23,732 Bytes
c4522f9 |
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 |
2023-10-14 00:11:30,961 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,962 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=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-14 00:11:30,962 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,962 MultiCorpus: 7936 train + 992 dev + 992 test sentences
- NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Train: 7936 sentences
2023-10-14 00:11:30,963 (train_with_dev=False, train_with_test=False)
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Training Params:
2023-10-14 00:11:30,963 - learning_rate: "3e-05"
2023-10-14 00:11:30,963 - mini_batch_size: "8"
2023-10-14 00:11:30,963 - max_epochs: "10"
2023-10-14 00:11:30,963 - shuffle: "True"
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Plugins:
2023-10-14 00:11:30,963 - LinearScheduler | warmup_fraction: '0.1'
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Final evaluation on model from best epoch (best-model.pt)
2023-10-14 00:11:30,963 - metric: "('micro avg', 'f1-score')"
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Computation:
2023-10-14 00:11:30,963 - compute on device: cuda:0
2023-10-14 00:11:30,963 - embedding storage: none
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:30,963 ----------------------------------------------------------------------------------------------------
2023-10-14 00:11:36,677 epoch 1 - iter 99/992 - loss 2.16888144 - time (sec): 5.71 - samples/sec: 2851.21 - lr: 0.000003 - momentum: 0.000000
2023-10-14 00:11:42,673 epoch 1 - iter 198/992 - loss 1.30775263 - time (sec): 11.71 - samples/sec: 2765.68 - lr: 0.000006 - momentum: 0.000000
2023-10-14 00:11:48,333 epoch 1 - iter 297/992 - loss 0.97103134 - time (sec): 17.37 - samples/sec: 2773.68 - lr: 0.000009 - momentum: 0.000000
2023-10-14 00:11:54,110 epoch 1 - iter 396/992 - loss 0.78162493 - time (sec): 23.15 - samples/sec: 2788.71 - lr: 0.000012 - momentum: 0.000000
2023-10-14 00:12:00,171 epoch 1 - iter 495/992 - loss 0.65918233 - time (sec): 29.21 - samples/sec: 2785.29 - lr: 0.000015 - momentum: 0.000000
2023-10-14 00:12:06,385 epoch 1 - iter 594/992 - loss 0.56584426 - time (sec): 35.42 - samples/sec: 2806.86 - lr: 0.000018 - momentum: 0.000000
2023-10-14 00:12:12,145 epoch 1 - iter 693/992 - loss 0.50932720 - time (sec): 41.18 - samples/sec: 2803.88 - lr: 0.000021 - momentum: 0.000000
2023-10-14 00:12:17,924 epoch 1 - iter 792/992 - loss 0.46331013 - time (sec): 46.96 - samples/sec: 2807.39 - lr: 0.000024 - momentum: 0.000000
2023-10-14 00:12:23,883 epoch 1 - iter 891/992 - loss 0.42855665 - time (sec): 52.92 - samples/sec: 2786.75 - lr: 0.000027 - momentum: 0.000000
2023-10-14 00:12:29,901 epoch 1 - iter 990/992 - loss 0.40009945 - time (sec): 58.94 - samples/sec: 2776.32 - lr: 0.000030 - momentum: 0.000000
2023-10-14 00:12:30,030 ----------------------------------------------------------------------------------------------------
2023-10-14 00:12:30,030 EPOCH 1 done: loss 0.3997 - lr: 0.000030
2023-10-14 00:12:33,137 DEV : loss 0.10478747636079788 - f1-score (micro avg) 0.6927
2023-10-14 00:12:33,157 saving best model
2023-10-14 00:12:33,553 ----------------------------------------------------------------------------------------------------
2023-10-14 00:12:39,339 epoch 2 - iter 99/992 - loss 0.10978478 - time (sec): 5.78 - samples/sec: 2768.41 - lr: 0.000030 - momentum: 0.000000
2023-10-14 00:12:45,165 epoch 2 - iter 198/992 - loss 0.10476447 - time (sec): 11.61 - samples/sec: 2801.81 - lr: 0.000029 - momentum: 0.000000
2023-10-14 00:12:51,147 epoch 2 - iter 297/992 - loss 0.11044910 - time (sec): 17.59 - samples/sec: 2782.40 - lr: 0.000029 - momentum: 0.000000
2023-10-14 00:12:57,135 epoch 2 - iter 396/992 - loss 0.10965807 - time (sec): 23.58 - samples/sec: 2776.96 - lr: 0.000029 - momentum: 0.000000
2023-10-14 00:13:02,983 epoch 2 - iter 495/992 - loss 0.10888826 - time (sec): 29.43 - samples/sec: 2783.86 - lr: 0.000028 - momentum: 0.000000
2023-10-14 00:13:08,856 epoch 2 - iter 594/992 - loss 0.10608504 - time (sec): 35.30 - samples/sec: 2790.49 - lr: 0.000028 - momentum: 0.000000
2023-10-14 00:13:14,595 epoch 2 - iter 693/992 - loss 0.10585318 - time (sec): 41.04 - samples/sec: 2797.08 - lr: 0.000028 - momentum: 0.000000
2023-10-14 00:13:20,316 epoch 2 - iter 792/992 - loss 0.10509565 - time (sec): 46.76 - samples/sec: 2800.79 - lr: 0.000027 - momentum: 0.000000
2023-10-14 00:13:26,191 epoch 2 - iter 891/992 - loss 0.10264619 - time (sec): 52.64 - samples/sec: 2804.00 - lr: 0.000027 - momentum: 0.000000
2023-10-14 00:13:31,994 epoch 2 - iter 990/992 - loss 0.10053276 - time (sec): 58.44 - samples/sec: 2801.72 - lr: 0.000027 - momentum: 0.000000
2023-10-14 00:13:32,111 ----------------------------------------------------------------------------------------------------
2023-10-14 00:13:32,111 EPOCH 2 done: loss 0.1006 - lr: 0.000027
2023-10-14 00:13:35,929 DEV : loss 0.09312836080789566 - f1-score (micro avg) 0.7333
2023-10-14 00:13:35,949 saving best model
2023-10-14 00:13:36,462 ----------------------------------------------------------------------------------------------------
2023-10-14 00:13:42,202 epoch 3 - iter 99/992 - loss 0.07010417 - time (sec): 5.73 - samples/sec: 2791.40 - lr: 0.000026 - momentum: 0.000000
2023-10-14 00:13:48,040 epoch 3 - iter 198/992 - loss 0.07383171 - time (sec): 11.57 - samples/sec: 2756.00 - lr: 0.000026 - momentum: 0.000000
2023-10-14 00:13:54,070 epoch 3 - iter 297/992 - loss 0.07242296 - time (sec): 17.60 - samples/sec: 2773.20 - lr: 0.000026 - momentum: 0.000000
2023-10-14 00:14:00,119 epoch 3 - iter 396/992 - loss 0.07090486 - time (sec): 23.65 - samples/sec: 2789.63 - lr: 0.000025 - momentum: 0.000000
2023-10-14 00:14:05,834 epoch 3 - iter 495/992 - loss 0.07184703 - time (sec): 29.37 - samples/sec: 2798.87 - lr: 0.000025 - momentum: 0.000000
2023-10-14 00:14:11,540 epoch 3 - iter 594/992 - loss 0.07267068 - time (sec): 35.07 - samples/sec: 2795.08 - lr: 0.000025 - momentum: 0.000000
2023-10-14 00:14:17,249 epoch 3 - iter 693/992 - loss 0.07128641 - time (sec): 40.78 - samples/sec: 2802.20 - lr: 0.000024 - momentum: 0.000000
2023-10-14 00:14:23,545 epoch 3 - iter 792/992 - loss 0.06989991 - time (sec): 47.08 - samples/sec: 2785.56 - lr: 0.000024 - momentum: 0.000000
2023-10-14 00:14:29,379 epoch 3 - iter 891/992 - loss 0.06907457 - time (sec): 52.91 - samples/sec: 2787.11 - lr: 0.000024 - momentum: 0.000000
2023-10-14 00:14:35,168 epoch 3 - iter 990/992 - loss 0.06875863 - time (sec): 58.70 - samples/sec: 2790.50 - lr: 0.000023 - momentum: 0.000000
2023-10-14 00:14:35,276 ----------------------------------------------------------------------------------------------------
2023-10-14 00:14:35,276 EPOCH 3 done: loss 0.0689 - lr: 0.000023
2023-10-14 00:14:38,661 DEV : loss 0.10794839262962341 - f1-score (micro avg) 0.7621
2023-10-14 00:14:38,682 saving best model
2023-10-14 00:14:39,146 ----------------------------------------------------------------------------------------------------
2023-10-14 00:14:44,907 epoch 4 - iter 99/992 - loss 0.05337231 - time (sec): 5.76 - samples/sec: 2764.08 - lr: 0.000023 - momentum: 0.000000
2023-10-14 00:14:50,927 epoch 4 - iter 198/992 - loss 0.05465630 - time (sec): 11.78 - samples/sec: 2778.52 - lr: 0.000023 - momentum: 0.000000
2023-10-14 00:14:56,532 epoch 4 - iter 297/992 - loss 0.05188037 - time (sec): 17.38 - samples/sec: 2746.41 - lr: 0.000022 - momentum: 0.000000
2023-10-14 00:15:02,501 epoch 4 - iter 396/992 - loss 0.04937150 - time (sec): 23.35 - samples/sec: 2756.34 - lr: 0.000022 - momentum: 0.000000
2023-10-14 00:15:08,435 epoch 4 - iter 495/992 - loss 0.04928861 - time (sec): 29.29 - samples/sec: 2764.20 - lr: 0.000022 - momentum: 0.000000
2023-10-14 00:15:14,444 epoch 4 - iter 594/992 - loss 0.05163498 - time (sec): 35.30 - samples/sec: 2772.33 - lr: 0.000021 - momentum: 0.000000
2023-10-14 00:15:20,289 epoch 4 - iter 693/992 - loss 0.05124858 - time (sec): 41.14 - samples/sec: 2769.38 - lr: 0.000021 - momentum: 0.000000
2023-10-14 00:15:26,014 epoch 4 - iter 792/992 - loss 0.05078560 - time (sec): 46.87 - samples/sec: 2769.19 - lr: 0.000021 - momentum: 0.000000
2023-10-14 00:15:31,880 epoch 4 - iter 891/992 - loss 0.05119365 - time (sec): 52.73 - samples/sec: 2775.78 - lr: 0.000020 - momentum: 0.000000
2023-10-14 00:15:38,047 epoch 4 - iter 990/992 - loss 0.05007817 - time (sec): 58.90 - samples/sec: 2779.27 - lr: 0.000020 - momentum: 0.000000
2023-10-14 00:15:38,173 ----------------------------------------------------------------------------------------------------
2023-10-14 00:15:38,173 EPOCH 4 done: loss 0.0501 - lr: 0.000020
2023-10-14 00:15:41,595 DEV : loss 0.1288062185049057 - f1-score (micro avg) 0.7515
2023-10-14 00:15:41,617 ----------------------------------------------------------------------------------------------------
2023-10-14 00:15:48,036 epoch 5 - iter 99/992 - loss 0.03956437 - time (sec): 6.42 - samples/sec: 2515.57 - lr: 0.000020 - momentum: 0.000000
2023-10-14 00:15:53,966 epoch 5 - iter 198/992 - loss 0.04134074 - time (sec): 12.35 - samples/sec: 2659.88 - lr: 0.000019 - momentum: 0.000000
2023-10-14 00:15:59,898 epoch 5 - iter 297/992 - loss 0.03664301 - time (sec): 18.28 - samples/sec: 2733.19 - lr: 0.000019 - momentum: 0.000000
2023-10-14 00:16:05,516 epoch 5 - iter 396/992 - loss 0.03655408 - time (sec): 23.90 - samples/sec: 2747.72 - lr: 0.000019 - momentum: 0.000000
2023-10-14 00:16:11,231 epoch 5 - iter 495/992 - loss 0.03738088 - time (sec): 29.61 - samples/sec: 2751.25 - lr: 0.000018 - momentum: 0.000000
2023-10-14 00:16:17,186 epoch 5 - iter 594/992 - loss 0.03701123 - time (sec): 35.57 - samples/sec: 2758.52 - lr: 0.000018 - momentum: 0.000000
2023-10-14 00:16:23,114 epoch 5 - iter 693/992 - loss 0.03771113 - time (sec): 41.50 - samples/sec: 2769.18 - lr: 0.000018 - momentum: 0.000000
2023-10-14 00:16:29,178 epoch 5 - iter 792/992 - loss 0.03792863 - time (sec): 47.56 - samples/sec: 2777.70 - lr: 0.000017 - momentum: 0.000000
2023-10-14 00:16:34,887 epoch 5 - iter 891/992 - loss 0.03729411 - time (sec): 53.27 - samples/sec: 2777.67 - lr: 0.000017 - momentum: 0.000000
2023-10-14 00:16:40,563 epoch 5 - iter 990/992 - loss 0.03803926 - time (sec): 58.94 - samples/sec: 2775.12 - lr: 0.000017 - momentum: 0.000000
2023-10-14 00:16:40,692 ----------------------------------------------------------------------------------------------------
2023-10-14 00:16:40,692 EPOCH 5 done: loss 0.0380 - lr: 0.000017
2023-10-14 00:16:44,223 DEV : loss 0.15828128159046173 - f1-score (micro avg) 0.7449
2023-10-14 00:16:44,247 ----------------------------------------------------------------------------------------------------
2023-10-14 00:16:50,655 epoch 6 - iter 99/992 - loss 0.02650741 - time (sec): 6.41 - samples/sec: 2724.73 - lr: 0.000016 - momentum: 0.000000
2023-10-14 00:16:56,568 epoch 6 - iter 198/992 - loss 0.02855856 - time (sec): 12.32 - samples/sec: 2700.12 - lr: 0.000016 - momentum: 0.000000
2023-10-14 00:17:02,403 epoch 6 - iter 297/992 - loss 0.02827081 - time (sec): 18.15 - samples/sec: 2690.41 - lr: 0.000016 - momentum: 0.000000
2023-10-14 00:17:08,357 epoch 6 - iter 396/992 - loss 0.02948653 - time (sec): 24.11 - samples/sec: 2710.97 - lr: 0.000015 - momentum: 0.000000
2023-10-14 00:17:14,052 epoch 6 - iter 495/992 - loss 0.02954967 - time (sec): 29.80 - samples/sec: 2722.51 - lr: 0.000015 - momentum: 0.000000
2023-10-14 00:17:19,690 epoch 6 - iter 594/992 - loss 0.02941991 - time (sec): 35.44 - samples/sec: 2738.41 - lr: 0.000015 - momentum: 0.000000
2023-10-14 00:17:25,780 epoch 6 - iter 693/992 - loss 0.02883939 - time (sec): 41.53 - samples/sec: 2748.31 - lr: 0.000014 - momentum: 0.000000
2023-10-14 00:17:31,687 epoch 6 - iter 792/992 - loss 0.02966393 - time (sec): 47.44 - samples/sec: 2750.43 - lr: 0.000014 - momentum: 0.000000
2023-10-14 00:17:37,543 epoch 6 - iter 891/992 - loss 0.03020474 - time (sec): 53.29 - samples/sec: 2759.23 - lr: 0.000014 - momentum: 0.000000
2023-10-14 00:17:43,521 epoch 6 - iter 990/992 - loss 0.03041067 - time (sec): 59.27 - samples/sec: 2762.40 - lr: 0.000013 - momentum: 0.000000
2023-10-14 00:17:43,631 ----------------------------------------------------------------------------------------------------
2023-10-14 00:17:43,631 EPOCH 6 done: loss 0.0304 - lr: 0.000013
2023-10-14 00:17:47,078 DEV : loss 0.17794281244277954 - f1-score (micro avg) 0.7561
2023-10-14 00:17:47,099 ----------------------------------------------------------------------------------------------------
2023-10-14 00:17:53,451 epoch 7 - iter 99/992 - loss 0.01788615 - time (sec): 6.35 - samples/sec: 2633.95 - lr: 0.000013 - momentum: 0.000000
2023-10-14 00:17:59,328 epoch 7 - iter 198/992 - loss 0.01786951 - time (sec): 12.23 - samples/sec: 2710.07 - lr: 0.000013 - momentum: 0.000000
2023-10-14 00:18:05,363 epoch 7 - iter 297/992 - loss 0.01689469 - time (sec): 18.26 - samples/sec: 2726.74 - lr: 0.000012 - momentum: 0.000000
2023-10-14 00:18:10,955 epoch 7 - iter 396/992 - loss 0.01790618 - time (sec): 23.85 - samples/sec: 2728.73 - lr: 0.000012 - momentum: 0.000000
2023-10-14 00:18:16,903 epoch 7 - iter 495/992 - loss 0.02065770 - time (sec): 29.80 - samples/sec: 2752.54 - lr: 0.000012 - momentum: 0.000000
2023-10-14 00:18:22,478 epoch 7 - iter 594/992 - loss 0.02009396 - time (sec): 35.38 - samples/sec: 2772.49 - lr: 0.000011 - momentum: 0.000000
2023-10-14 00:18:28,300 epoch 7 - iter 693/992 - loss 0.01954440 - time (sec): 41.20 - samples/sec: 2768.82 - lr: 0.000011 - momentum: 0.000000
2023-10-14 00:18:34,153 epoch 7 - iter 792/992 - loss 0.02049321 - time (sec): 47.05 - samples/sec: 2768.46 - lr: 0.000011 - momentum: 0.000000
2023-10-14 00:18:40,247 epoch 7 - iter 891/992 - loss 0.02112247 - time (sec): 53.15 - samples/sec: 2763.57 - lr: 0.000010 - momentum: 0.000000
2023-10-14 00:18:46,278 epoch 7 - iter 990/992 - loss 0.02172067 - time (sec): 59.18 - samples/sec: 2767.03 - lr: 0.000010 - momentum: 0.000000
2023-10-14 00:18:46,396 ----------------------------------------------------------------------------------------------------
2023-10-14 00:18:46,397 EPOCH 7 done: loss 0.0217 - lr: 0.000010
2023-10-14 00:18:49,841 DEV : loss 0.2032385766506195 - f1-score (micro avg) 0.7611
2023-10-14 00:18:49,862 ----------------------------------------------------------------------------------------------------
2023-10-14 00:18:56,047 epoch 8 - iter 99/992 - loss 0.02018754 - time (sec): 6.18 - samples/sec: 2756.01 - lr: 0.000010 - momentum: 0.000000
2023-10-14 00:19:01,853 epoch 8 - iter 198/992 - loss 0.02020446 - time (sec): 11.99 - samples/sec: 2781.75 - lr: 0.000009 - momentum: 0.000000
2023-10-14 00:19:07,865 epoch 8 - iter 297/992 - loss 0.01858499 - time (sec): 18.00 - samples/sec: 2803.77 - lr: 0.000009 - momentum: 0.000000
2023-10-14 00:19:13,546 epoch 8 - iter 396/992 - loss 0.01820929 - time (sec): 23.68 - samples/sec: 2818.80 - lr: 0.000009 - momentum: 0.000000
2023-10-14 00:19:19,159 epoch 8 - iter 495/992 - loss 0.01766479 - time (sec): 29.30 - samples/sec: 2801.97 - lr: 0.000008 - momentum: 0.000000
2023-10-14 00:19:25,097 epoch 8 - iter 594/992 - loss 0.01862023 - time (sec): 35.23 - samples/sec: 2794.09 - lr: 0.000008 - momentum: 0.000000
2023-10-14 00:19:30,908 epoch 8 - iter 693/992 - loss 0.01845761 - time (sec): 41.05 - samples/sec: 2797.91 - lr: 0.000008 - momentum: 0.000000
2023-10-14 00:19:36,976 epoch 8 - iter 792/992 - loss 0.01775140 - time (sec): 47.11 - samples/sec: 2790.08 - lr: 0.000007 - momentum: 0.000000
2023-10-14 00:19:42,981 epoch 8 - iter 891/992 - loss 0.01742615 - time (sec): 53.12 - samples/sec: 2788.32 - lr: 0.000007 - momentum: 0.000000
2023-10-14 00:19:48,628 epoch 8 - iter 990/992 - loss 0.01748644 - time (sec): 58.77 - samples/sec: 2784.70 - lr: 0.000007 - momentum: 0.000000
2023-10-14 00:19:48,745 ----------------------------------------------------------------------------------------------------
2023-10-14 00:19:48,745 EPOCH 8 done: loss 0.0174 - lr: 0.000007
2023-10-14 00:19:52,565 DEV : loss 0.21129660308361053 - f1-score (micro avg) 0.754
2023-10-14 00:19:52,586 ----------------------------------------------------------------------------------------------------
2023-10-14 00:19:58,233 epoch 9 - iter 99/992 - loss 0.01582445 - time (sec): 5.65 - samples/sec: 2818.03 - lr: 0.000006 - momentum: 0.000000
2023-10-14 00:20:04,200 epoch 9 - iter 198/992 - loss 0.01645995 - time (sec): 11.61 - samples/sec: 2778.98 - lr: 0.000006 - momentum: 0.000000
2023-10-14 00:20:10,220 epoch 9 - iter 297/992 - loss 0.01506388 - time (sec): 17.63 - samples/sec: 2801.59 - lr: 0.000006 - momentum: 0.000000
2023-10-14 00:20:16,226 epoch 9 - iter 396/992 - loss 0.01438323 - time (sec): 23.64 - samples/sec: 2789.87 - lr: 0.000005 - momentum: 0.000000
2023-10-14 00:20:22,248 epoch 9 - iter 495/992 - loss 0.01331515 - time (sec): 29.66 - samples/sec: 2767.81 - lr: 0.000005 - momentum: 0.000000
2023-10-14 00:20:28,138 epoch 9 - iter 594/992 - loss 0.01331908 - time (sec): 35.55 - samples/sec: 2771.62 - lr: 0.000005 - momentum: 0.000000
2023-10-14 00:20:33,994 epoch 9 - iter 693/992 - loss 0.01304711 - time (sec): 41.41 - samples/sec: 2765.58 - lr: 0.000004 - momentum: 0.000000
2023-10-14 00:20:39,654 epoch 9 - iter 792/992 - loss 0.01359041 - time (sec): 47.07 - samples/sec: 2781.33 - lr: 0.000004 - momentum: 0.000000
2023-10-14 00:20:45,656 epoch 9 - iter 891/992 - loss 0.01300277 - time (sec): 53.07 - samples/sec: 2769.11 - lr: 0.000004 - momentum: 0.000000
2023-10-14 00:20:51,582 epoch 9 - iter 990/992 - loss 0.01274266 - time (sec): 58.99 - samples/sec: 2773.76 - lr: 0.000003 - momentum: 0.000000
2023-10-14 00:20:51,708 ----------------------------------------------------------------------------------------------------
2023-10-14 00:20:51,708 EPOCH 9 done: loss 0.0127 - lr: 0.000003
2023-10-14 00:20:55,153 DEV : loss 0.2239181101322174 - f1-score (micro avg) 0.7628
2023-10-14 00:20:55,174 saving best model
2023-10-14 00:20:55,710 ----------------------------------------------------------------------------------------------------
2023-10-14 00:21:02,160 epoch 10 - iter 99/992 - loss 0.01038855 - time (sec): 6.45 - samples/sec: 2660.63 - lr: 0.000003 - momentum: 0.000000
2023-10-14 00:21:07,910 epoch 10 - iter 198/992 - loss 0.00863248 - time (sec): 12.20 - samples/sec: 2721.99 - lr: 0.000003 - momentum: 0.000000
2023-10-14 00:21:13,805 epoch 10 - iter 297/992 - loss 0.00888013 - time (sec): 18.09 - samples/sec: 2752.19 - lr: 0.000002 - momentum: 0.000000
2023-10-14 00:21:19,853 epoch 10 - iter 396/992 - loss 0.00922199 - time (sec): 24.14 - samples/sec: 2764.40 - lr: 0.000002 - momentum: 0.000000
2023-10-14 00:21:25,836 epoch 10 - iter 495/992 - loss 0.00894249 - time (sec): 30.12 - samples/sec: 2789.05 - lr: 0.000002 - momentum: 0.000000
2023-10-14 00:21:31,545 epoch 10 - iter 594/992 - loss 0.00915085 - time (sec): 35.83 - samples/sec: 2792.86 - lr: 0.000001 - momentum: 0.000000
2023-10-14 00:21:37,055 epoch 10 - iter 693/992 - loss 0.00962406 - time (sec): 41.34 - samples/sec: 2793.08 - lr: 0.000001 - momentum: 0.000000
2023-10-14 00:21:42,693 epoch 10 - iter 792/992 - loss 0.00971077 - time (sec): 46.98 - samples/sec: 2786.25 - lr: 0.000001 - momentum: 0.000000
2023-10-14 00:21:48,490 epoch 10 - iter 891/992 - loss 0.00941827 - time (sec): 52.78 - samples/sec: 2782.46 - lr: 0.000000 - momentum: 0.000000
2023-10-14 00:21:54,375 epoch 10 - iter 990/992 - loss 0.00906870 - time (sec): 58.66 - samples/sec: 2790.27 - lr: 0.000000 - momentum: 0.000000
2023-10-14 00:21:54,482 ----------------------------------------------------------------------------------------------------
2023-10-14 00:21:54,482 EPOCH 10 done: loss 0.0091 - lr: 0.000000
2023-10-14 00:21:58,105 DEV : loss 0.23203293979167938 - f1-score (micro avg) 0.7581
2023-10-14 00:21:58,572 ----------------------------------------------------------------------------------------------------
2023-10-14 00:21:58,574 Loading model from best epoch ...
2023-10-14 00:22:00,398 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-14 00:22:03,335
Results:
- F-score (micro) 0.7764
- F-score (macro) 0.692
- Accuracy 0.656
By class:
precision recall f1-score support
LOC 0.8143 0.8504 0.8320 655
PER 0.7244 0.8251 0.7715 223
ORG 0.5091 0.4409 0.4726 127
micro avg 0.7605 0.7930 0.7764 1005
macro avg 0.6826 0.7055 0.6920 1005
weighted avg 0.7558 0.7930 0.7731 1005
2023-10-14 00:22:03,335 ----------------------------------------------------------------------------------------------------
|