File size: 24,214 Bytes
128ab49 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 |
2023-10-18 14:43:30,985 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(32001, 128)
(position_embeddings): Embedding(512, 128)
(token_type_embeddings): Embedding(2, 128)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-1): 2 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=128, out_features=128, bias=True)
(key): Linear(in_features=128, out_features=128, bias=True)
(value): Linear(in_features=128, out_features=128, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=128, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=128, out_features=512, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=512, out_features=128, bias=True)
(LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=128, out_features=128, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=128, out_features=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 Train: 1100 sentences
2023-10-18 14:43:30,986 (train_with_dev=False, train_with_test=False)
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 Training Params:
2023-10-18 14:43:30,986 - learning_rate: "5e-05"
2023-10-18 14:43:30,986 - mini_batch_size: "4"
2023-10-18 14:43:30,986 - max_epochs: "10"
2023-10-18 14:43:30,986 - shuffle: "True"
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 Plugins:
2023-10-18 14:43:30,986 - TensorboardLogger
2023-10-18 14:43:30,986 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,986 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 14:43:30,986 - metric: "('micro avg', 'f1-score')"
2023-10-18 14:43:30,986 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,987 Computation:
2023-10-18 14:43:30,987 - compute on device: cuda:0
2023-10-18 14:43:30,987 - embedding storage: none
2023-10-18 14:43:30,987 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,987 Model training base path: "hmbench-ajmc/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
2023-10-18 14:43:30,987 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,987 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:30,987 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 14:43:31,391 epoch 1 - iter 27/275 - loss 4.03243994 - time (sec): 0.40 - samples/sec: 4913.90 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:43:31,799 epoch 1 - iter 54/275 - loss 3.94570068 - time (sec): 0.81 - samples/sec: 5336.44 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:43:32,203 epoch 1 - iter 81/275 - loss 3.78668884 - time (sec): 1.22 - samples/sec: 5284.72 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:43:32,640 epoch 1 - iter 108/275 - loss 3.54407889 - time (sec): 1.65 - samples/sec: 5346.64 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:43:33,050 epoch 1 - iter 135/275 - loss 3.32952951 - time (sec): 2.06 - samples/sec: 5377.45 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:43:33,459 epoch 1 - iter 162/275 - loss 3.07492688 - time (sec): 2.47 - samples/sec: 5437.85 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:43:33,863 epoch 1 - iter 189/275 - loss 2.82838245 - time (sec): 2.88 - samples/sec: 5460.46 - lr: 0.000034 - momentum: 0.000000
2023-10-18 14:43:34,274 epoch 1 - iter 216/275 - loss 2.58190842 - time (sec): 3.29 - samples/sec: 5557.78 - lr: 0.000039 - momentum: 0.000000
2023-10-18 14:43:34,662 epoch 1 - iter 243/275 - loss 2.42149492 - time (sec): 3.67 - samples/sec: 5509.32 - lr: 0.000044 - momentum: 0.000000
2023-10-18 14:43:35,064 epoch 1 - iter 270/275 - loss 2.28777710 - time (sec): 4.08 - samples/sec: 5502.28 - lr: 0.000049 - momentum: 0.000000
2023-10-18 14:43:35,135 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:35,135 EPOCH 1 done: loss 2.2647 - lr: 0.000049
2023-10-18 14:43:35,389 DEV : loss 0.8980287313461304 - f1-score (micro avg) 0.0
2023-10-18 14:43:35,394 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:35,861 epoch 2 - iter 27/275 - loss 0.78134023 - time (sec): 0.47 - samples/sec: 5452.93 - lr: 0.000049 - momentum: 0.000000
2023-10-18 14:43:36,290 epoch 2 - iter 54/275 - loss 0.81836184 - time (sec): 0.89 - samples/sec: 5236.01 - lr: 0.000049 - momentum: 0.000000
2023-10-18 14:43:36,691 epoch 2 - iter 81/275 - loss 0.86443923 - time (sec): 1.30 - samples/sec: 5364.83 - lr: 0.000048 - momentum: 0.000000
2023-10-18 14:43:37,099 epoch 2 - iter 108/275 - loss 0.88101045 - time (sec): 1.70 - samples/sec: 5208.15 - lr: 0.000048 - momentum: 0.000000
2023-10-18 14:43:37,496 epoch 2 - iter 135/275 - loss 0.85790201 - time (sec): 2.10 - samples/sec: 5227.88 - lr: 0.000047 - momentum: 0.000000
2023-10-18 14:43:37,906 epoch 2 - iter 162/275 - loss 0.83927798 - time (sec): 2.51 - samples/sec: 5311.25 - lr: 0.000047 - momentum: 0.000000
2023-10-18 14:43:38,301 epoch 2 - iter 189/275 - loss 0.83267514 - time (sec): 2.91 - samples/sec: 5255.59 - lr: 0.000046 - momentum: 0.000000
2023-10-18 14:43:38,715 epoch 2 - iter 216/275 - loss 0.82029440 - time (sec): 3.32 - samples/sec: 5332.04 - lr: 0.000046 - momentum: 0.000000
2023-10-18 14:43:39,123 epoch 2 - iter 243/275 - loss 0.80751106 - time (sec): 3.73 - samples/sec: 5387.77 - lr: 0.000045 - momentum: 0.000000
2023-10-18 14:43:39,540 epoch 2 - iter 270/275 - loss 0.78403155 - time (sec): 4.14 - samples/sec: 5409.28 - lr: 0.000045 - momentum: 0.000000
2023-10-18 14:43:39,615 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:39,615 EPOCH 2 done: loss 0.7873 - lr: 0.000045
2023-10-18 14:43:39,977 DEV : loss 0.5882683396339417 - f1-score (micro avg) 0.1087
2023-10-18 14:43:39,983 saving best model
2023-10-18 14:43:40,015 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:40,418 epoch 3 - iter 27/275 - loss 0.69388767 - time (sec): 0.40 - samples/sec: 5755.49 - lr: 0.000044 - momentum: 0.000000
2023-10-18 14:43:40,819 epoch 3 - iter 54/275 - loss 0.69342049 - time (sec): 0.80 - samples/sec: 5998.04 - lr: 0.000043 - momentum: 0.000000
2023-10-18 14:43:41,240 epoch 3 - iter 81/275 - loss 0.64883093 - time (sec): 1.22 - samples/sec: 5789.52 - lr: 0.000043 - momentum: 0.000000
2023-10-18 14:43:41,648 epoch 3 - iter 108/275 - loss 0.61664166 - time (sec): 1.63 - samples/sec: 5743.95 - lr: 0.000042 - momentum: 0.000000
2023-10-18 14:43:42,064 epoch 3 - iter 135/275 - loss 0.60668920 - time (sec): 2.05 - samples/sec: 5671.59 - lr: 0.000042 - momentum: 0.000000
2023-10-18 14:43:42,469 epoch 3 - iter 162/275 - loss 0.58595365 - time (sec): 2.45 - samples/sec: 5607.56 - lr: 0.000041 - momentum: 0.000000
2023-10-18 14:43:42,880 epoch 3 - iter 189/275 - loss 0.58057106 - time (sec): 2.86 - samples/sec: 5533.10 - lr: 0.000041 - momentum: 0.000000
2023-10-18 14:43:43,289 epoch 3 - iter 216/275 - loss 0.57689387 - time (sec): 3.27 - samples/sec: 5527.63 - lr: 0.000040 - momentum: 0.000000
2023-10-18 14:43:43,714 epoch 3 - iter 243/275 - loss 0.57041795 - time (sec): 3.70 - samples/sec: 5516.54 - lr: 0.000040 - momentum: 0.000000
2023-10-18 14:43:44,128 epoch 3 - iter 270/275 - loss 0.57443584 - time (sec): 4.11 - samples/sec: 5454.11 - lr: 0.000039 - momentum: 0.000000
2023-10-18 14:43:44,205 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:44,205 EPOCH 3 done: loss 0.5706 - lr: 0.000039
2023-10-18 14:43:44,711 DEV : loss 0.40124934911727905 - f1-score (micro avg) 0.4511
2023-10-18 14:43:44,715 saving best model
2023-10-18 14:43:44,748 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:45,143 epoch 4 - iter 27/275 - loss 0.50055148 - time (sec): 0.39 - samples/sec: 5265.23 - lr: 0.000038 - momentum: 0.000000
2023-10-18 14:43:45,528 epoch 4 - iter 54/275 - loss 0.51970347 - time (sec): 0.78 - samples/sec: 5258.61 - lr: 0.000038 - momentum: 0.000000
2023-10-18 14:43:45,928 epoch 4 - iter 81/275 - loss 0.51732211 - time (sec): 1.18 - samples/sec: 5367.27 - lr: 0.000037 - momentum: 0.000000
2023-10-18 14:43:46,329 epoch 4 - iter 108/275 - loss 0.50755962 - time (sec): 1.58 - samples/sec: 5437.72 - lr: 0.000037 - momentum: 0.000000
2023-10-18 14:43:46,729 epoch 4 - iter 135/275 - loss 0.49628465 - time (sec): 1.98 - samples/sec: 5464.38 - lr: 0.000036 - momentum: 0.000000
2023-10-18 14:43:47,140 epoch 4 - iter 162/275 - loss 0.50076582 - time (sec): 2.39 - samples/sec: 5510.00 - lr: 0.000036 - momentum: 0.000000
2023-10-18 14:43:47,548 epoch 4 - iter 189/275 - loss 0.49510928 - time (sec): 2.80 - samples/sec: 5495.77 - lr: 0.000035 - momentum: 0.000000
2023-10-18 14:43:47,960 epoch 4 - iter 216/275 - loss 0.48738228 - time (sec): 3.21 - samples/sec: 5541.93 - lr: 0.000035 - momentum: 0.000000
2023-10-18 14:43:48,372 epoch 4 - iter 243/275 - loss 0.47576913 - time (sec): 3.62 - samples/sec: 5580.11 - lr: 0.000034 - momentum: 0.000000
2023-10-18 14:43:48,776 epoch 4 - iter 270/275 - loss 0.46872942 - time (sec): 4.03 - samples/sec: 5552.67 - lr: 0.000034 - momentum: 0.000000
2023-10-18 14:43:48,850 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:48,851 EPOCH 4 done: loss 0.4626 - lr: 0.000034
2023-10-18 14:43:49,220 DEV : loss 0.35367265343666077 - f1-score (micro avg) 0.5377
2023-10-18 14:43:49,224 saving best model
2023-10-18 14:43:49,259 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:49,669 epoch 5 - iter 27/275 - loss 0.43738549 - time (sec): 0.41 - samples/sec: 5917.56 - lr: 0.000033 - momentum: 0.000000
2023-10-18 14:43:50,082 epoch 5 - iter 54/275 - loss 0.39799114 - time (sec): 0.82 - samples/sec: 5796.05 - lr: 0.000032 - momentum: 0.000000
2023-10-18 14:43:50,487 epoch 5 - iter 81/275 - loss 0.39027648 - time (sec): 1.23 - samples/sec: 5653.57 - lr: 0.000032 - momentum: 0.000000
2023-10-18 14:43:50,890 epoch 5 - iter 108/275 - loss 0.40245857 - time (sec): 1.63 - samples/sec: 5667.85 - lr: 0.000031 - momentum: 0.000000
2023-10-18 14:43:51,307 epoch 5 - iter 135/275 - loss 0.39711821 - time (sec): 2.05 - samples/sec: 5615.86 - lr: 0.000031 - momentum: 0.000000
2023-10-18 14:43:51,717 epoch 5 - iter 162/275 - loss 0.40331691 - time (sec): 2.46 - samples/sec: 5526.32 - lr: 0.000030 - momentum: 0.000000
2023-10-18 14:43:52,119 epoch 5 - iter 189/275 - loss 0.41216604 - time (sec): 2.86 - samples/sec: 5580.31 - lr: 0.000030 - momentum: 0.000000
2023-10-18 14:43:52,518 epoch 5 - iter 216/275 - loss 0.40997604 - time (sec): 3.26 - samples/sec: 5523.34 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:43:52,920 epoch 5 - iter 243/275 - loss 0.40419920 - time (sec): 3.66 - samples/sec: 5461.61 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:43:53,330 epoch 5 - iter 270/275 - loss 0.40169560 - time (sec): 4.07 - samples/sec: 5492.40 - lr: 0.000028 - momentum: 0.000000
2023-10-18 14:43:53,407 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:53,407 EPOCH 5 done: loss 0.4014 - lr: 0.000028
2023-10-18 14:43:53,776 DEV : loss 0.30840688943862915 - f1-score (micro avg) 0.5665
2023-10-18 14:43:53,780 saving best model
2023-10-18 14:43:53,813 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:54,210 epoch 6 - iter 27/275 - loss 0.35894930 - time (sec): 0.40 - samples/sec: 5284.38 - lr: 0.000027 - momentum: 0.000000
2023-10-18 14:43:54,614 epoch 6 - iter 54/275 - loss 0.35477863 - time (sec): 0.80 - samples/sec: 5249.74 - lr: 0.000027 - momentum: 0.000000
2023-10-18 14:43:55,013 epoch 6 - iter 81/275 - loss 0.35568652 - time (sec): 1.20 - samples/sec: 5126.14 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:43:55,433 epoch 6 - iter 108/275 - loss 0.36290326 - time (sec): 1.62 - samples/sec: 5281.63 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:43:55,838 epoch 6 - iter 135/275 - loss 0.36415148 - time (sec): 2.02 - samples/sec: 5343.64 - lr: 0.000025 - momentum: 0.000000
2023-10-18 14:43:56,260 epoch 6 - iter 162/275 - loss 0.36307390 - time (sec): 2.45 - samples/sec: 5431.13 - lr: 0.000025 - momentum: 0.000000
2023-10-18 14:43:56,663 epoch 6 - iter 189/275 - loss 0.35302182 - time (sec): 2.85 - samples/sec: 5450.89 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:43:57,066 epoch 6 - iter 216/275 - loss 0.36076859 - time (sec): 3.25 - samples/sec: 5391.34 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:43:57,461 epoch 6 - iter 243/275 - loss 0.37265096 - time (sec): 3.65 - samples/sec: 5409.18 - lr: 0.000023 - momentum: 0.000000
2023-10-18 14:43:57,882 epoch 6 - iter 270/275 - loss 0.36682205 - time (sec): 4.07 - samples/sec: 5476.10 - lr: 0.000022 - momentum: 0.000000
2023-10-18 14:43:57,960 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:57,960 EPOCH 6 done: loss 0.3661 - lr: 0.000022
2023-10-18 14:43:58,329 DEV : loss 0.29626935720443726 - f1-score (micro avg) 0.5761
2023-10-18 14:43:58,334 saving best model
2023-10-18 14:43:58,367 ----------------------------------------------------------------------------------------------------
2023-10-18 14:43:58,769 epoch 7 - iter 27/275 - loss 0.41248552 - time (sec): 0.40 - samples/sec: 4765.46 - lr: 0.000022 - momentum: 0.000000
2023-10-18 14:43:59,174 epoch 7 - iter 54/275 - loss 0.37364688 - time (sec): 0.81 - samples/sec: 5248.47 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:43:59,591 epoch 7 - iter 81/275 - loss 0.34262108 - time (sec): 1.22 - samples/sec: 5527.43 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:43:59,997 epoch 7 - iter 108/275 - loss 0.34718865 - time (sec): 1.63 - samples/sec: 5545.54 - lr: 0.000020 - momentum: 0.000000
2023-10-18 14:44:00,393 epoch 7 - iter 135/275 - loss 0.35484492 - time (sec): 2.03 - samples/sec: 5487.81 - lr: 0.000020 - momentum: 0.000000
2023-10-18 14:44:00,814 epoch 7 - iter 162/275 - loss 0.35510658 - time (sec): 2.45 - samples/sec: 5413.03 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:44:01,233 epoch 7 - iter 189/275 - loss 0.35175496 - time (sec): 2.87 - samples/sec: 5474.12 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:44:01,639 epoch 7 - iter 216/275 - loss 0.35075373 - time (sec): 3.27 - samples/sec: 5448.81 - lr: 0.000018 - momentum: 0.000000
2023-10-18 14:44:02,053 epoch 7 - iter 243/275 - loss 0.34856969 - time (sec): 3.69 - samples/sec: 5489.67 - lr: 0.000017 - momentum: 0.000000
2023-10-18 14:44:02,462 epoch 7 - iter 270/275 - loss 0.34730130 - time (sec): 4.09 - samples/sec: 5468.14 - lr: 0.000017 - momentum: 0.000000
2023-10-18 14:44:02,539 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:02,539 EPOCH 7 done: loss 0.3465 - lr: 0.000017
2023-10-18 14:44:02,911 DEV : loss 0.27915582060813904 - f1-score (micro avg) 0.5926
2023-10-18 14:44:02,915 saving best model
2023-10-18 14:44:02,949 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:03,364 epoch 8 - iter 27/275 - loss 0.35848511 - time (sec): 0.41 - samples/sec: 5845.18 - lr: 0.000016 - momentum: 0.000000
2023-10-18 14:44:03,779 epoch 8 - iter 54/275 - loss 0.34775339 - time (sec): 0.83 - samples/sec: 5720.37 - lr: 0.000016 - momentum: 0.000000
2023-10-18 14:44:04,189 epoch 8 - iter 81/275 - loss 0.35859633 - time (sec): 1.24 - samples/sec: 5795.77 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:44:04,602 epoch 8 - iter 108/275 - loss 0.34543374 - time (sec): 1.65 - samples/sec: 5635.89 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:44:05,007 epoch 8 - iter 135/275 - loss 0.34767511 - time (sec): 2.06 - samples/sec: 5582.96 - lr: 0.000014 - momentum: 0.000000
2023-10-18 14:44:05,415 epoch 8 - iter 162/275 - loss 0.33705009 - time (sec): 2.47 - samples/sec: 5485.67 - lr: 0.000014 - momentum: 0.000000
2023-10-18 14:44:05,809 epoch 8 - iter 189/275 - loss 0.33645892 - time (sec): 2.86 - samples/sec: 5460.05 - lr: 0.000013 - momentum: 0.000000
2023-10-18 14:44:06,217 epoch 8 - iter 216/275 - loss 0.33479643 - time (sec): 3.27 - samples/sec: 5450.33 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:44:06,629 epoch 8 - iter 243/275 - loss 0.32980765 - time (sec): 3.68 - samples/sec: 5459.35 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:44:07,047 epoch 8 - iter 270/275 - loss 0.32263767 - time (sec): 4.10 - samples/sec: 5466.73 - lr: 0.000011 - momentum: 0.000000
2023-10-18 14:44:07,126 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:07,126 EPOCH 8 done: loss 0.3219 - lr: 0.000011
2023-10-18 14:44:07,495 DEV : loss 0.2702096104621887 - f1-score (micro avg) 0.5993
2023-10-18 14:44:07,499 saving best model
2023-10-18 14:44:07,532 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:07,940 epoch 9 - iter 27/275 - loss 0.34018936 - time (sec): 0.41 - samples/sec: 5450.01 - lr: 0.000011 - momentum: 0.000000
2023-10-18 14:44:08,343 epoch 9 - iter 54/275 - loss 0.31793969 - time (sec): 0.81 - samples/sec: 5405.90 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:44:08,750 epoch 9 - iter 81/275 - loss 0.31206053 - time (sec): 1.22 - samples/sec: 5313.60 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:44:09,159 epoch 9 - iter 108/275 - loss 0.31170653 - time (sec): 1.63 - samples/sec: 5239.50 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:44:09,567 epoch 9 - iter 135/275 - loss 0.31614410 - time (sec): 2.03 - samples/sec: 5181.67 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:44:09,974 epoch 9 - iter 162/275 - loss 0.31441368 - time (sec): 2.44 - samples/sec: 5242.22 - lr: 0.000008 - momentum: 0.000000
2023-10-18 14:44:10,383 epoch 9 - iter 189/275 - loss 0.32431431 - time (sec): 2.85 - samples/sec: 5336.02 - lr: 0.000007 - momentum: 0.000000
2023-10-18 14:44:10,802 epoch 9 - iter 216/275 - loss 0.31466197 - time (sec): 3.27 - samples/sec: 5362.79 - lr: 0.000007 - momentum: 0.000000
2023-10-18 14:44:11,235 epoch 9 - iter 243/275 - loss 0.31529849 - time (sec): 3.70 - samples/sec: 5439.49 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:44:11,651 epoch 9 - iter 270/275 - loss 0.31350265 - time (sec): 4.12 - samples/sec: 5436.90 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:44:11,726 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:11,726 EPOCH 9 done: loss 0.3157 - lr: 0.000006
2023-10-18 14:44:12,103 DEV : loss 0.2669928967952728 - f1-score (micro avg) 0.6061
2023-10-18 14:44:12,108 saving best model
2023-10-18 14:44:12,146 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:12,559 epoch 10 - iter 27/275 - loss 0.33483529 - time (sec): 0.41 - samples/sec: 5345.07 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:44:12,965 epoch 10 - iter 54/275 - loss 0.32748772 - time (sec): 0.82 - samples/sec: 5641.30 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:44:13,369 epoch 10 - iter 81/275 - loss 0.35425091 - time (sec): 1.22 - samples/sec: 5676.62 - lr: 0.000004 - momentum: 0.000000
2023-10-18 14:44:13,761 epoch 10 - iter 108/275 - loss 0.32724076 - time (sec): 1.61 - samples/sec: 5580.81 - lr: 0.000004 - momentum: 0.000000
2023-10-18 14:44:14,161 epoch 10 - iter 135/275 - loss 0.33067401 - time (sec): 2.01 - samples/sec: 5741.54 - lr: 0.000003 - momentum: 0.000000
2023-10-18 14:44:14,580 epoch 10 - iter 162/275 - loss 0.32389891 - time (sec): 2.43 - samples/sec: 5632.88 - lr: 0.000002 - momentum: 0.000000
2023-10-18 14:44:14,991 epoch 10 - iter 189/275 - loss 0.32167552 - time (sec): 2.84 - samples/sec: 5561.38 - lr: 0.000002 - momentum: 0.000000
2023-10-18 14:44:15,395 epoch 10 - iter 216/275 - loss 0.31850865 - time (sec): 3.25 - samples/sec: 5541.60 - lr: 0.000001 - momentum: 0.000000
2023-10-18 14:44:15,790 epoch 10 - iter 243/275 - loss 0.31510525 - time (sec): 3.64 - samples/sec: 5537.47 - lr: 0.000001 - momentum: 0.000000
2023-10-18 14:44:16,197 epoch 10 - iter 270/275 - loss 0.31451221 - time (sec): 4.05 - samples/sec: 5521.62 - lr: 0.000000 - momentum: 0.000000
2023-10-18 14:44:16,275 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:16,275 EPOCH 10 done: loss 0.3132 - lr: 0.000000
2023-10-18 14:44:16,654 DEV : loss 0.2650297284126282 - f1-score (micro avg) 0.6087
2023-10-18 14:44:16,658 saving best model
2023-10-18 14:44:16,727 ----------------------------------------------------------------------------------------------------
2023-10-18 14:44:16,727 Loading model from best epoch ...
2023-10-18 14:44:16,804 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-18 14:44:17,094
Results:
- F-score (micro) 0.6632
- F-score (macro) 0.3933
- Accuracy 0.5029
By class:
precision recall f1-score support
scope 0.6237 0.6591 0.6409 176
pers 0.8750 0.7656 0.8167 128
work 0.4526 0.5811 0.5089 74
object 0.0000 0.0000 0.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.6539 0.6728 0.6632 382
macro avg 0.3903 0.4012 0.3933 382
weighted avg 0.6682 0.6728 0.6675 382
2023-10-18 14:44:17,094 ----------------------------------------------------------------------------------------------------
|