File size: 23,965 Bytes
0a3c939 |
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 |
2023-10-14 08:01:57,233 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,234 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 08:01:57,234 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 MultiCorpus: 5777 train + 722 dev + 723 test sentences
- NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Train: 5777 sentences
2023-10-14 08:01:57,235 (train_with_dev=False, train_with_test=False)
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Training Params:
2023-10-14 08:01:57,235 - learning_rate: "3e-05"
2023-10-14 08:01:57,235 - mini_batch_size: "4"
2023-10-14 08:01:57,235 - max_epochs: "10"
2023-10-14 08:01:57,235 - shuffle: "True"
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Plugins:
2023-10-14 08:01:57,235 - LinearScheduler | warmup_fraction: '0.1'
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Final evaluation on model from best epoch (best-model.pt)
2023-10-14 08:01:57,235 - metric: "('micro avg', 'f1-score')"
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Computation:
2023-10-14 08:01:57,235 - compute on device: cuda:0
2023-10-14 08:01:57,235 - embedding storage: none
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:01:57,235 ----------------------------------------------------------------------------------------------------
2023-10-14 08:02:05,605 epoch 1 - iter 144/1445 - loss 1.98365673 - time (sec): 8.37 - samples/sec: 2024.95 - lr: 0.000003 - momentum: 0.000000
2023-10-14 08:02:12,644 epoch 1 - iter 288/1445 - loss 1.12353678 - time (sec): 15.41 - samples/sec: 2193.16 - lr: 0.000006 - momentum: 0.000000
2023-10-14 08:02:19,943 epoch 1 - iter 432/1445 - loss 0.80002002 - time (sec): 22.71 - samples/sec: 2300.53 - lr: 0.000009 - momentum: 0.000000
2023-10-14 08:02:27,153 epoch 1 - iter 576/1445 - loss 0.64820380 - time (sec): 29.92 - samples/sec: 2334.66 - lr: 0.000012 - momentum: 0.000000
2023-10-14 08:02:34,153 epoch 1 - iter 720/1445 - loss 0.55704517 - time (sec): 36.92 - samples/sec: 2349.72 - lr: 0.000015 - momentum: 0.000000
2023-10-14 08:02:41,087 epoch 1 - iter 864/1445 - loss 0.50191366 - time (sec): 43.85 - samples/sec: 2331.26 - lr: 0.000018 - momentum: 0.000000
2023-10-14 08:02:48,174 epoch 1 - iter 1008/1445 - loss 0.45051786 - time (sec): 50.94 - samples/sec: 2371.87 - lr: 0.000021 - momentum: 0.000000
2023-10-14 08:02:55,702 epoch 1 - iter 1152/1445 - loss 0.41254886 - time (sec): 58.47 - samples/sec: 2374.94 - lr: 0.000024 - momentum: 0.000000
2023-10-14 08:03:02,970 epoch 1 - iter 1296/1445 - loss 0.38359668 - time (sec): 65.73 - samples/sec: 2386.92 - lr: 0.000027 - momentum: 0.000000
2023-10-14 08:03:10,330 epoch 1 - iter 1440/1445 - loss 0.35707304 - time (sec): 73.09 - samples/sec: 2401.86 - lr: 0.000030 - momentum: 0.000000
2023-10-14 08:03:10,587 ----------------------------------------------------------------------------------------------------
2023-10-14 08:03:10,587 EPOCH 1 done: loss 0.3561 - lr: 0.000030
2023-10-14 08:03:13,488 DEV : loss 0.15405000746250153 - f1-score (micro avg) 0.5446
2023-10-14 08:03:13,502 saving best model
2023-10-14 08:03:13,875 ----------------------------------------------------------------------------------------------------
2023-10-14 08:03:21,212 epoch 2 - iter 144/1445 - loss 0.14057591 - time (sec): 7.34 - samples/sec: 2367.01 - lr: 0.000030 - momentum: 0.000000
2023-10-14 08:03:28,665 epoch 2 - iter 288/1445 - loss 0.13227084 - time (sec): 14.79 - samples/sec: 2328.11 - lr: 0.000029 - momentum: 0.000000
2023-10-14 08:03:36,066 epoch 2 - iter 432/1445 - loss 0.13180492 - time (sec): 22.19 - samples/sec: 2347.30 - lr: 0.000029 - momentum: 0.000000
2023-10-14 08:03:43,233 epoch 2 - iter 576/1445 - loss 0.12555163 - time (sec): 29.36 - samples/sec: 2360.57 - lr: 0.000029 - momentum: 0.000000
2023-10-14 08:03:50,688 epoch 2 - iter 720/1445 - loss 0.12318631 - time (sec): 36.81 - samples/sec: 2381.45 - lr: 0.000028 - momentum: 0.000000
2023-10-14 08:03:57,836 epoch 2 - iter 864/1445 - loss 0.12027431 - time (sec): 43.96 - samples/sec: 2382.69 - lr: 0.000028 - momentum: 0.000000
2023-10-14 08:04:05,205 epoch 2 - iter 1008/1445 - loss 0.12246549 - time (sec): 51.33 - samples/sec: 2391.19 - lr: 0.000028 - momentum: 0.000000
2023-10-14 08:04:12,194 epoch 2 - iter 1152/1445 - loss 0.11929573 - time (sec): 58.32 - samples/sec: 2377.13 - lr: 0.000027 - momentum: 0.000000
2023-10-14 08:04:19,819 epoch 2 - iter 1296/1445 - loss 0.11665455 - time (sec): 65.94 - samples/sec: 2393.24 - lr: 0.000027 - momentum: 0.000000
2023-10-14 08:04:27,010 epoch 2 - iter 1440/1445 - loss 0.11480563 - time (sec): 73.13 - samples/sec: 2401.85 - lr: 0.000027 - momentum: 0.000000
2023-10-14 08:04:27,254 ----------------------------------------------------------------------------------------------------
2023-10-14 08:04:27,254 EPOCH 2 done: loss 0.1148 - lr: 0.000027
2023-10-14 08:04:31,083 DEV : loss 0.1282866895198822 - f1-score (micro avg) 0.7047
2023-10-14 08:04:31,097 saving best model
2023-10-14 08:04:31,626 ----------------------------------------------------------------------------------------------------
2023-10-14 08:04:38,949 epoch 3 - iter 144/1445 - loss 0.08251436 - time (sec): 7.32 - samples/sec: 2420.04 - lr: 0.000026 - momentum: 0.000000
2023-10-14 08:04:46,376 epoch 3 - iter 288/1445 - loss 0.07784727 - time (sec): 14.75 - samples/sec: 2411.42 - lr: 0.000026 - momentum: 0.000000
2023-10-14 08:04:53,664 epoch 3 - iter 432/1445 - loss 0.07783536 - time (sec): 22.04 - samples/sec: 2414.24 - lr: 0.000026 - momentum: 0.000000
2023-10-14 08:05:00,965 epoch 3 - iter 576/1445 - loss 0.07514099 - time (sec): 29.34 - samples/sec: 2414.20 - lr: 0.000025 - momentum: 0.000000
2023-10-14 08:05:08,267 epoch 3 - iter 720/1445 - loss 0.07581881 - time (sec): 36.64 - samples/sec: 2416.46 - lr: 0.000025 - momentum: 0.000000
2023-10-14 08:05:15,292 epoch 3 - iter 864/1445 - loss 0.07472479 - time (sec): 43.66 - samples/sec: 2430.01 - lr: 0.000025 - momentum: 0.000000
2023-10-14 08:05:22,640 epoch 3 - iter 1008/1445 - loss 0.07638855 - time (sec): 51.01 - samples/sec: 2411.58 - lr: 0.000024 - momentum: 0.000000
2023-10-14 08:05:29,996 epoch 3 - iter 1152/1445 - loss 0.07480564 - time (sec): 58.37 - samples/sec: 2419.81 - lr: 0.000024 - momentum: 0.000000
2023-10-14 08:05:37,136 epoch 3 - iter 1296/1445 - loss 0.07451773 - time (sec): 65.51 - samples/sec: 2425.62 - lr: 0.000024 - momentum: 0.000000
2023-10-14 08:05:44,547 epoch 3 - iter 1440/1445 - loss 0.07377630 - time (sec): 72.92 - samples/sec: 2410.74 - lr: 0.000023 - momentum: 0.000000
2023-10-14 08:05:44,765 ----------------------------------------------------------------------------------------------------
2023-10-14 08:05:44,765 EPOCH 3 done: loss 0.0738 - lr: 0.000023
2023-10-14 08:05:48,189 DEV : loss 0.10148890316486359 - f1-score (micro avg) 0.79
2023-10-14 08:05:48,203 saving best model
2023-10-14 08:05:48,718 ----------------------------------------------------------------------------------------------------
2023-10-14 08:05:56,573 epoch 4 - iter 144/1445 - loss 0.04469757 - time (sec): 7.85 - samples/sec: 2296.48 - lr: 0.000023 - momentum: 0.000000
2023-10-14 08:06:03,927 epoch 4 - iter 288/1445 - loss 0.04147054 - time (sec): 15.21 - samples/sec: 2407.13 - lr: 0.000023 - momentum: 0.000000
2023-10-14 08:06:11,043 epoch 4 - iter 432/1445 - loss 0.04588436 - time (sec): 22.32 - samples/sec: 2382.90 - lr: 0.000022 - momentum: 0.000000
2023-10-14 08:06:18,317 epoch 4 - iter 576/1445 - loss 0.04687950 - time (sec): 29.60 - samples/sec: 2408.53 - lr: 0.000022 - momentum: 0.000000
2023-10-14 08:06:25,425 epoch 4 - iter 720/1445 - loss 0.05047665 - time (sec): 36.71 - samples/sec: 2414.44 - lr: 0.000022 - momentum: 0.000000
2023-10-14 08:06:32,454 epoch 4 - iter 864/1445 - loss 0.05060324 - time (sec): 43.73 - samples/sec: 2406.39 - lr: 0.000021 - momentum: 0.000000
2023-10-14 08:06:39,525 epoch 4 - iter 1008/1445 - loss 0.04884015 - time (sec): 50.81 - samples/sec: 2400.36 - lr: 0.000021 - momentum: 0.000000
2023-10-14 08:06:46,972 epoch 4 - iter 1152/1445 - loss 0.04928212 - time (sec): 58.25 - samples/sec: 2411.64 - lr: 0.000021 - momentum: 0.000000
2023-10-14 08:06:54,267 epoch 4 - iter 1296/1445 - loss 0.05041401 - time (sec): 65.55 - samples/sec: 2399.42 - lr: 0.000020 - momentum: 0.000000
2023-10-14 08:07:01,642 epoch 4 - iter 1440/1445 - loss 0.05090107 - time (sec): 72.92 - samples/sec: 2409.83 - lr: 0.000020 - momentum: 0.000000
2023-10-14 08:07:01,879 ----------------------------------------------------------------------------------------------------
2023-10-14 08:07:01,879 EPOCH 4 done: loss 0.0513 - lr: 0.000020
2023-10-14 08:07:05,346 DEV : loss 0.12521180510520935 - f1-score (micro avg) 0.7713
2023-10-14 08:07:05,361 ----------------------------------------------------------------------------------------------------
2023-10-14 08:07:12,830 epoch 5 - iter 144/1445 - loss 0.03689043 - time (sec): 7.47 - samples/sec: 2376.83 - lr: 0.000020 - momentum: 0.000000
2023-10-14 08:07:20,377 epoch 5 - iter 288/1445 - loss 0.04141324 - time (sec): 15.02 - samples/sec: 2371.46 - lr: 0.000019 - momentum: 0.000000
2023-10-14 08:07:27,312 epoch 5 - iter 432/1445 - loss 0.03820414 - time (sec): 21.95 - samples/sec: 2390.95 - lr: 0.000019 - momentum: 0.000000
2023-10-14 08:07:34,526 epoch 5 - iter 576/1445 - loss 0.03805636 - time (sec): 29.16 - samples/sec: 2397.87 - lr: 0.000019 - momentum: 0.000000
2023-10-14 08:07:41,652 epoch 5 - iter 720/1445 - loss 0.03728520 - time (sec): 36.29 - samples/sec: 2415.63 - lr: 0.000018 - momentum: 0.000000
2023-10-14 08:07:49,124 epoch 5 - iter 864/1445 - loss 0.03609096 - time (sec): 43.76 - samples/sec: 2419.45 - lr: 0.000018 - momentum: 0.000000
2023-10-14 08:07:56,226 epoch 5 - iter 1008/1445 - loss 0.03551319 - time (sec): 50.86 - samples/sec: 2412.87 - lr: 0.000018 - momentum: 0.000000
2023-10-14 08:08:03,611 epoch 5 - iter 1152/1445 - loss 0.03524412 - time (sec): 58.25 - samples/sec: 2413.61 - lr: 0.000017 - momentum: 0.000000
2023-10-14 08:08:11,110 epoch 5 - iter 1296/1445 - loss 0.03695923 - time (sec): 65.75 - samples/sec: 2410.80 - lr: 0.000017 - momentum: 0.000000
2023-10-14 08:08:18,082 epoch 5 - iter 1440/1445 - loss 0.03728152 - time (sec): 72.72 - samples/sec: 2413.40 - lr: 0.000017 - momentum: 0.000000
2023-10-14 08:08:18,376 ----------------------------------------------------------------------------------------------------
2023-10-14 08:08:18,376 EPOCH 5 done: loss 0.0372 - lr: 0.000017
2023-10-14 08:08:22,161 DEV : loss 0.17038105428218842 - f1-score (micro avg) 0.7608
2023-10-14 08:08:22,176 ----------------------------------------------------------------------------------------------------
2023-10-14 08:08:29,368 epoch 6 - iter 144/1445 - loss 0.02545181 - time (sec): 7.19 - samples/sec: 2500.25 - lr: 0.000016 - momentum: 0.000000
2023-10-14 08:08:36,614 epoch 6 - iter 288/1445 - loss 0.02562755 - time (sec): 14.44 - samples/sec: 2504.38 - lr: 0.000016 - momentum: 0.000000
2023-10-14 08:08:43,778 epoch 6 - iter 432/1445 - loss 0.02526942 - time (sec): 21.60 - samples/sec: 2499.22 - lr: 0.000016 - momentum: 0.000000
2023-10-14 08:08:51,447 epoch 6 - iter 576/1445 - loss 0.02775801 - time (sec): 29.27 - samples/sec: 2455.98 - lr: 0.000015 - momentum: 0.000000
2023-10-14 08:08:58,506 epoch 6 - iter 720/1445 - loss 0.02706181 - time (sec): 36.33 - samples/sec: 2439.93 - lr: 0.000015 - momentum: 0.000000
2023-10-14 08:09:05,788 epoch 6 - iter 864/1445 - loss 0.02599246 - time (sec): 43.61 - samples/sec: 2421.51 - lr: 0.000015 - momentum: 0.000000
2023-10-14 08:09:13,141 epoch 6 - iter 1008/1445 - loss 0.02794849 - time (sec): 50.96 - samples/sec: 2420.40 - lr: 0.000014 - momentum: 0.000000
2023-10-14 08:09:20,518 epoch 6 - iter 1152/1445 - loss 0.02869252 - time (sec): 58.34 - samples/sec: 2428.10 - lr: 0.000014 - momentum: 0.000000
2023-10-14 08:09:27,666 epoch 6 - iter 1296/1445 - loss 0.02856538 - time (sec): 65.49 - samples/sec: 2417.95 - lr: 0.000014 - momentum: 0.000000
2023-10-14 08:09:34,870 epoch 6 - iter 1440/1445 - loss 0.02820532 - time (sec): 72.69 - samples/sec: 2416.69 - lr: 0.000013 - momentum: 0.000000
2023-10-14 08:09:35,113 ----------------------------------------------------------------------------------------------------
2023-10-14 08:09:35,113 EPOCH 6 done: loss 0.0282 - lr: 0.000013
2023-10-14 08:09:38,563 DEV : loss 0.1647178679704666 - f1-score (micro avg) 0.7804
2023-10-14 08:09:38,579 ----------------------------------------------------------------------------------------------------
2023-10-14 08:09:45,895 epoch 7 - iter 144/1445 - loss 0.01300211 - time (sec): 7.31 - samples/sec: 2379.65 - lr: 0.000013 - momentum: 0.000000
2023-10-14 08:09:53,075 epoch 7 - iter 288/1445 - loss 0.01696728 - time (sec): 14.50 - samples/sec: 2354.75 - lr: 0.000013 - momentum: 0.000000
2023-10-14 08:10:00,712 epoch 7 - iter 432/1445 - loss 0.01849889 - time (sec): 22.13 - samples/sec: 2370.41 - lr: 0.000012 - momentum: 0.000000
2023-10-14 08:10:07,982 epoch 7 - iter 576/1445 - loss 0.01797361 - time (sec): 29.40 - samples/sec: 2398.07 - lr: 0.000012 - momentum: 0.000000
2023-10-14 08:10:15,199 epoch 7 - iter 720/1445 - loss 0.01798847 - time (sec): 36.62 - samples/sec: 2403.56 - lr: 0.000012 - momentum: 0.000000
2023-10-14 08:10:22,580 epoch 7 - iter 864/1445 - loss 0.01952435 - time (sec): 44.00 - samples/sec: 2420.08 - lr: 0.000011 - momentum: 0.000000
2023-10-14 08:10:29,751 epoch 7 - iter 1008/1445 - loss 0.01984725 - time (sec): 51.17 - samples/sec: 2407.97 - lr: 0.000011 - momentum: 0.000000
2023-10-14 08:10:37,085 epoch 7 - iter 1152/1445 - loss 0.01930156 - time (sec): 58.51 - samples/sec: 2417.50 - lr: 0.000011 - momentum: 0.000000
2023-10-14 08:10:44,067 epoch 7 - iter 1296/1445 - loss 0.01973561 - time (sec): 65.49 - samples/sec: 2413.04 - lr: 0.000010 - momentum: 0.000000
2023-10-14 08:10:51,271 epoch 7 - iter 1440/1445 - loss 0.01980517 - time (sec): 72.69 - samples/sec: 2417.01 - lr: 0.000010 - momentum: 0.000000
2023-10-14 08:10:51,497 ----------------------------------------------------------------------------------------------------
2023-10-14 08:10:51,497 EPOCH 7 done: loss 0.0198 - lr: 0.000010
2023-10-14 08:10:54,970 DEV : loss 0.1839003711938858 - f1-score (micro avg) 0.7965
2023-10-14 08:10:54,986 saving best model
2023-10-14 08:10:55,568 ----------------------------------------------------------------------------------------------------
2023-10-14 08:11:02,709 epoch 8 - iter 144/1445 - loss 0.01405551 - time (sec): 7.14 - samples/sec: 2442.76 - lr: 0.000010 - momentum: 0.000000
2023-10-14 08:11:10,323 epoch 8 - iter 288/1445 - loss 0.01175523 - time (sec): 14.75 - samples/sec: 2391.64 - lr: 0.000009 - momentum: 0.000000
2023-10-14 08:11:17,600 epoch 8 - iter 432/1445 - loss 0.01129704 - time (sec): 22.03 - samples/sec: 2402.18 - lr: 0.000009 - momentum: 0.000000
2023-10-14 08:11:25,174 epoch 8 - iter 576/1445 - loss 0.01292683 - time (sec): 29.60 - samples/sec: 2370.48 - lr: 0.000009 - momentum: 0.000000
2023-10-14 08:11:32,582 epoch 8 - iter 720/1445 - loss 0.01230325 - time (sec): 37.01 - samples/sec: 2406.86 - lr: 0.000008 - momentum: 0.000000
2023-10-14 08:11:39,737 epoch 8 - iter 864/1445 - loss 0.01183301 - time (sec): 44.17 - samples/sec: 2397.89 - lr: 0.000008 - momentum: 0.000000
2023-10-14 08:11:46,776 epoch 8 - iter 1008/1445 - loss 0.01208905 - time (sec): 51.21 - samples/sec: 2412.73 - lr: 0.000008 - momentum: 0.000000
2023-10-14 08:11:53,875 epoch 8 - iter 1152/1445 - loss 0.01318623 - time (sec): 58.31 - samples/sec: 2403.05 - lr: 0.000007 - momentum: 0.000000
2023-10-14 08:12:01,512 epoch 8 - iter 1296/1445 - loss 0.01358646 - time (sec): 65.94 - samples/sec: 2402.71 - lr: 0.000007 - momentum: 0.000000
2023-10-14 08:12:08,839 epoch 8 - iter 1440/1445 - loss 0.01334733 - time (sec): 73.27 - samples/sec: 2400.15 - lr: 0.000007 - momentum: 0.000000
2023-10-14 08:12:09,064 ----------------------------------------------------------------------------------------------------
2023-10-14 08:12:09,064 EPOCH 8 done: loss 0.0133 - lr: 0.000007
2023-10-14 08:12:12,861 DEV : loss 0.18413744866847992 - f1-score (micro avg) 0.7987
2023-10-14 08:12:12,876 saving best model
2023-10-14 08:12:13,455 ----------------------------------------------------------------------------------------------------
2023-10-14 08:12:20,659 epoch 9 - iter 144/1445 - loss 0.01146554 - time (sec): 7.20 - samples/sec: 2530.75 - lr: 0.000006 - momentum: 0.000000
2023-10-14 08:12:28,224 epoch 9 - iter 288/1445 - loss 0.01300968 - time (sec): 14.77 - samples/sec: 2489.92 - lr: 0.000006 - momentum: 0.000000
2023-10-14 08:12:35,547 epoch 9 - iter 432/1445 - loss 0.01004910 - time (sec): 22.09 - samples/sec: 2531.98 - lr: 0.000006 - momentum: 0.000000
2023-10-14 08:12:42,577 epoch 9 - iter 576/1445 - loss 0.00980441 - time (sec): 29.12 - samples/sec: 2477.06 - lr: 0.000005 - momentum: 0.000000
2023-10-14 08:12:50,040 epoch 9 - iter 720/1445 - loss 0.00958906 - time (sec): 36.58 - samples/sec: 2482.19 - lr: 0.000005 - momentum: 0.000000
2023-10-14 08:12:56,931 epoch 9 - iter 864/1445 - loss 0.00931059 - time (sec): 43.47 - samples/sec: 2463.93 - lr: 0.000005 - momentum: 0.000000
2023-10-14 08:13:04,320 epoch 9 - iter 1008/1445 - loss 0.00931590 - time (sec): 50.86 - samples/sec: 2440.57 - lr: 0.000004 - momentum: 0.000000
2023-10-14 08:13:11,276 epoch 9 - iter 1152/1445 - loss 0.00917441 - time (sec): 57.82 - samples/sec: 2423.84 - lr: 0.000004 - momentum: 0.000000
2023-10-14 08:13:18,525 epoch 9 - iter 1296/1445 - loss 0.00925497 - time (sec): 65.07 - samples/sec: 2420.64 - lr: 0.000004 - momentum: 0.000000
2023-10-14 08:13:25,900 epoch 9 - iter 1440/1445 - loss 0.00952078 - time (sec): 72.44 - samples/sec: 2424.96 - lr: 0.000003 - momentum: 0.000000
2023-10-14 08:13:26,131 ----------------------------------------------------------------------------------------------------
2023-10-14 08:13:26,131 EPOCH 9 done: loss 0.0095 - lr: 0.000003
2023-10-14 08:13:29,573 DEV : loss 0.186563640832901 - f1-score (micro avg) 0.8039
2023-10-14 08:13:29,588 saving best model
2023-10-14 08:13:30,149 ----------------------------------------------------------------------------------------------------
2023-10-14 08:13:37,534 epoch 10 - iter 144/1445 - loss 0.00663741 - time (sec): 7.38 - samples/sec: 2488.81 - lr: 0.000003 - momentum: 0.000000
2023-10-14 08:13:45,111 epoch 10 - iter 288/1445 - loss 0.00559908 - time (sec): 14.96 - samples/sec: 2318.32 - lr: 0.000003 - momentum: 0.000000
2023-10-14 08:13:52,608 epoch 10 - iter 432/1445 - loss 0.00730824 - time (sec): 22.46 - samples/sec: 2344.28 - lr: 0.000002 - momentum: 0.000000
2023-10-14 08:14:00,148 epoch 10 - iter 576/1445 - loss 0.00695631 - time (sec): 30.00 - samples/sec: 2363.90 - lr: 0.000002 - momentum: 0.000000
2023-10-14 08:14:07,251 epoch 10 - iter 720/1445 - loss 0.00719157 - time (sec): 37.10 - samples/sec: 2367.92 - lr: 0.000002 - momentum: 0.000000
2023-10-14 08:14:14,804 epoch 10 - iter 864/1445 - loss 0.00696365 - time (sec): 44.65 - samples/sec: 2398.27 - lr: 0.000001 - momentum: 0.000000
2023-10-14 08:14:21,883 epoch 10 - iter 1008/1445 - loss 0.00688362 - time (sec): 51.73 - samples/sec: 2399.15 - lr: 0.000001 - momentum: 0.000000
2023-10-14 08:14:29,091 epoch 10 - iter 1152/1445 - loss 0.00665468 - time (sec): 58.94 - samples/sec: 2394.67 - lr: 0.000001 - momentum: 0.000000
2023-10-14 08:14:36,092 epoch 10 - iter 1296/1445 - loss 0.00650502 - time (sec): 65.94 - samples/sec: 2393.15 - lr: 0.000000 - momentum: 0.000000
2023-10-14 08:14:43,476 epoch 10 - iter 1440/1445 - loss 0.00627816 - time (sec): 73.33 - samples/sec: 2398.42 - lr: 0.000000 - momentum: 0.000000
2023-10-14 08:14:43,689 ----------------------------------------------------------------------------------------------------
2023-10-14 08:14:43,689 EPOCH 10 done: loss 0.0063 - lr: 0.000000
2023-10-14 08:14:47,154 DEV : loss 0.20616155862808228 - f1-score (micro avg) 0.8002
2023-10-14 08:14:47,596 ----------------------------------------------------------------------------------------------------
2023-10-14 08:14:47,597 Loading model from best epoch ...
2023-10-14 08:14:49,401 SequenceTagger predicts: Dictionary with 13 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
2023-10-14 08:14:52,528
Results:
- F-score (micro) 0.8004
- F-score (macro) 0.6926
- Accuracy 0.6828
By class:
precision recall f1-score support
PER 0.8282 0.8299 0.8290 482
LOC 0.8786 0.7904 0.8322 458
ORG 0.4000 0.4348 0.4167 69
micro avg 0.8165 0.7849 0.8004 1009
macro avg 0.7023 0.6850 0.6926 1009
weighted avg 0.8218 0.7849 0.8023 1009
2023-10-14 08:14:52,528 ----------------------------------------------------------------------------------------------------
|