File size: 24,027 Bytes
3fcb9a6 |
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 |
2023-10-19 23:59:35,156 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 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=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 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
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 Train: 1166 sentences
2023-10-19 23:59:35,157 (train_with_dev=False, train_with_test=False)
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 Training Params:
2023-10-19 23:59:35,157 - learning_rate: "3e-05"
2023-10-19 23:59:35,157 - mini_batch_size: "8"
2023-10-19 23:59:35,157 - max_epochs: "10"
2023-10-19 23:59:35,157 - shuffle: "True"
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 Plugins:
2023-10-19 23:59:35,157 - TensorboardLogger
2023-10-19 23:59:35,157 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 23:59:35,157 - metric: "('micro avg', 'f1-score')"
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,157 Computation:
2023-10-19 23:59:35,157 - compute on device: cuda:0
2023-10-19 23:59:35,157 - embedding storage: none
2023-10-19 23:59:35,157 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,158 Model training base path: "hmbench-newseye/fi-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-19 23:59:35,158 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,158 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:35,158 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 23:59:35,476 epoch 1 - iter 14/146 - loss 3.18295949 - time (sec): 0.32 - samples/sec: 12068.60 - lr: 0.000003 - momentum: 0.000000
2023-10-19 23:59:35,779 epoch 1 - iter 28/146 - loss 3.18089286 - time (sec): 0.62 - samples/sec: 12118.44 - lr: 0.000006 - momentum: 0.000000
2023-10-19 23:59:36,085 epoch 1 - iter 42/146 - loss 3.14660440 - time (sec): 0.93 - samples/sec: 12242.69 - lr: 0.000008 - momentum: 0.000000
2023-10-19 23:59:36,432 epoch 1 - iter 56/146 - loss 3.13843486 - time (sec): 1.27 - samples/sec: 12087.70 - lr: 0.000011 - momentum: 0.000000
2023-10-19 23:59:36,809 epoch 1 - iter 70/146 - loss 3.02837731 - time (sec): 1.65 - samples/sec: 12115.45 - lr: 0.000014 - momentum: 0.000000
2023-10-19 23:59:37,161 epoch 1 - iter 84/146 - loss 2.92849125 - time (sec): 2.00 - samples/sec: 11960.64 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:59:37,521 epoch 1 - iter 98/146 - loss 2.78120716 - time (sec): 2.36 - samples/sec: 12020.12 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:59:37,894 epoch 1 - iter 112/146 - loss 2.62445154 - time (sec): 2.74 - samples/sec: 12187.09 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:59:38,265 epoch 1 - iter 126/146 - loss 2.48234548 - time (sec): 3.11 - samples/sec: 12084.25 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:38,653 epoch 1 - iter 140/146 - loss 2.32927838 - time (sec): 3.49 - samples/sec: 12165.04 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:59:38,809 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:38,809 EPOCH 1 done: loss 2.2660 - lr: 0.000029
2023-10-19 23:59:39,074 DEV : loss 0.5118019580841064 - f1-score (micro avg) 0.0
2023-10-19 23:59:39,078 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:39,463 epoch 2 - iter 14/146 - loss 1.25242238 - time (sec): 0.38 - samples/sec: 12421.92 - lr: 0.000030 - momentum: 0.000000
2023-10-19 23:59:39,839 epoch 2 - iter 28/146 - loss 1.07356757 - time (sec): 0.76 - samples/sec: 12143.27 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:59:40,197 epoch 2 - iter 42/146 - loss 0.95455788 - time (sec): 1.12 - samples/sec: 11891.73 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:59:40,545 epoch 2 - iter 56/146 - loss 0.91349265 - time (sec): 1.47 - samples/sec: 11596.85 - lr: 0.000029 - momentum: 0.000000
2023-10-19 23:59:40,917 epoch 2 - iter 70/146 - loss 0.86781807 - time (sec): 1.84 - samples/sec: 11466.12 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:59:41,263 epoch 2 - iter 84/146 - loss 0.83753148 - time (sec): 2.19 - samples/sec: 11414.05 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:59:41,614 epoch 2 - iter 98/146 - loss 0.81276469 - time (sec): 2.54 - samples/sec: 11316.83 - lr: 0.000028 - momentum: 0.000000
2023-10-19 23:59:42,009 epoch 2 - iter 112/146 - loss 0.78058945 - time (sec): 2.93 - samples/sec: 11521.19 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:59:42,400 epoch 2 - iter 126/146 - loss 0.75445669 - time (sec): 3.32 - samples/sec: 11782.39 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:59:42,759 epoch 2 - iter 140/146 - loss 0.76111334 - time (sec): 3.68 - samples/sec: 11642.35 - lr: 0.000027 - momentum: 0.000000
2023-10-19 23:59:42,893 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:42,893 EPOCH 2 done: loss 0.7533 - lr: 0.000027
2023-10-19 23:59:43,532 DEV : loss 0.4549146592617035 - f1-score (micro avg) 0.0
2023-10-19 23:59:43,535 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:43,881 epoch 3 - iter 14/146 - loss 0.52019195 - time (sec): 0.35 - samples/sec: 11650.89 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:44,397 epoch 3 - iter 28/146 - loss 0.55554037 - time (sec): 0.86 - samples/sec: 9948.50 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:44,750 epoch 3 - iter 42/146 - loss 0.60565982 - time (sec): 1.21 - samples/sec: 10668.62 - lr: 0.000026 - momentum: 0.000000
2023-10-19 23:59:45,138 epoch 3 - iter 56/146 - loss 0.68493437 - time (sec): 1.60 - samples/sec: 10873.09 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:59:45,503 epoch 3 - iter 70/146 - loss 0.67322012 - time (sec): 1.97 - samples/sec: 10774.08 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:59:45,907 epoch 3 - iter 84/146 - loss 0.66209201 - time (sec): 2.37 - samples/sec: 11106.25 - lr: 0.000025 - momentum: 0.000000
2023-10-19 23:59:46,247 epoch 3 - iter 98/146 - loss 0.65709488 - time (sec): 2.71 - samples/sec: 11125.35 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:59:46,605 epoch 3 - iter 112/146 - loss 0.63909005 - time (sec): 3.07 - samples/sec: 11234.49 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:59:46,952 epoch 3 - iter 126/146 - loss 0.62972925 - time (sec): 3.42 - samples/sec: 11133.50 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:59:47,321 epoch 3 - iter 140/146 - loss 0.61992130 - time (sec): 3.79 - samples/sec: 11290.42 - lr: 0.000024 - momentum: 0.000000
2023-10-19 23:59:47,477 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:47,478 EPOCH 3 done: loss 0.6170 - lr: 0.000024
2023-10-19 23:59:48,116 DEV : loss 0.3993528187274933 - f1-score (micro avg) 0.0
2023-10-19 23:59:48,120 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:48,473 epoch 4 - iter 14/146 - loss 0.49195585 - time (sec): 0.35 - samples/sec: 10485.17 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:59:48,847 epoch 4 - iter 28/146 - loss 0.52096420 - time (sec): 0.73 - samples/sec: 10514.36 - lr: 0.000023 - momentum: 0.000000
2023-10-19 23:59:49,211 epoch 4 - iter 42/146 - loss 0.50110568 - time (sec): 1.09 - samples/sec: 11336.25 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:59:49,583 epoch 4 - iter 56/146 - loss 0.51380249 - time (sec): 1.46 - samples/sec: 11278.82 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:59:49,934 epoch 4 - iter 70/146 - loss 0.51458773 - time (sec): 1.81 - samples/sec: 11324.99 - lr: 0.000022 - momentum: 0.000000
2023-10-19 23:59:50,283 epoch 4 - iter 84/146 - loss 0.51597388 - time (sec): 2.16 - samples/sec: 11327.14 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:50,662 epoch 4 - iter 98/146 - loss 0.55252997 - time (sec): 2.54 - samples/sec: 11496.30 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:51,031 epoch 4 - iter 112/146 - loss 0.53615248 - time (sec): 2.91 - samples/sec: 11591.09 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:51,392 epoch 4 - iter 126/146 - loss 0.53462161 - time (sec): 3.27 - samples/sec: 11526.68 - lr: 0.000021 - momentum: 0.000000
2023-10-19 23:59:51,766 epoch 4 - iter 140/146 - loss 0.53229005 - time (sec): 3.65 - samples/sec: 11638.70 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:59:51,922 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:51,923 EPOCH 4 done: loss 0.5321 - lr: 0.000020
2023-10-19 23:59:52,563 DEV : loss 0.35903558135032654 - f1-score (micro avg) 0.0
2023-10-19 23:59:52,567 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:52,950 epoch 5 - iter 14/146 - loss 0.48076598 - time (sec): 0.38 - samples/sec: 13506.37 - lr: 0.000020 - momentum: 0.000000
2023-10-19 23:59:53,338 epoch 5 - iter 28/146 - loss 0.56335970 - time (sec): 0.77 - samples/sec: 12416.48 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:59:53,693 epoch 5 - iter 42/146 - loss 0.53527449 - time (sec): 1.13 - samples/sec: 11906.75 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:59:54,053 epoch 5 - iter 56/146 - loss 0.52682013 - time (sec): 1.48 - samples/sec: 11577.85 - lr: 0.000019 - momentum: 0.000000
2023-10-19 23:59:54,452 epoch 5 - iter 70/146 - loss 0.51918424 - time (sec): 1.88 - samples/sec: 11681.15 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:54,817 epoch 5 - iter 84/146 - loss 0.50445202 - time (sec): 2.25 - samples/sec: 11688.31 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:55,176 epoch 5 - iter 98/146 - loss 0.50158859 - time (sec): 2.61 - samples/sec: 11454.05 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:55,540 epoch 5 - iter 112/146 - loss 0.50004276 - time (sec): 2.97 - samples/sec: 11596.90 - lr: 0.000018 - momentum: 0.000000
2023-10-19 23:59:55,879 epoch 5 - iter 126/146 - loss 0.51064784 - time (sec): 3.31 - samples/sec: 11503.43 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:59:56,276 epoch 5 - iter 140/146 - loss 0.49969320 - time (sec): 3.71 - samples/sec: 11598.76 - lr: 0.000017 - momentum: 0.000000
2023-10-19 23:59:56,428 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:56,428 EPOCH 5 done: loss 0.4946 - lr: 0.000017
2023-10-19 23:59:57,062 DEV : loss 0.34515950083732605 - f1-score (micro avg) 0.0081
2023-10-19 23:59:57,066 saving best model
2023-10-19 23:59:57,093 ----------------------------------------------------------------------------------------------------
2023-10-19 23:59:57,478 epoch 6 - iter 14/146 - loss 0.50665335 - time (sec): 0.38 - samples/sec: 11411.49 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:59:57,841 epoch 6 - iter 28/146 - loss 0.46417149 - time (sec): 0.75 - samples/sec: 10997.53 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:59:58,217 epoch 6 - iter 42/146 - loss 0.47608930 - time (sec): 1.12 - samples/sec: 10911.57 - lr: 0.000016 - momentum: 0.000000
2023-10-19 23:59:58,582 epoch 6 - iter 56/146 - loss 0.48079412 - time (sec): 1.49 - samples/sec: 11158.65 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:59:58,951 epoch 6 - iter 70/146 - loss 0.46065126 - time (sec): 1.86 - samples/sec: 11488.54 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:59:59,328 epoch 6 - iter 84/146 - loss 0.44948389 - time (sec): 2.23 - samples/sec: 11435.45 - lr: 0.000015 - momentum: 0.000000
2023-10-19 23:59:59,718 epoch 6 - iter 98/146 - loss 0.44371072 - time (sec): 2.62 - samples/sec: 11532.27 - lr: 0.000015 - momentum: 0.000000
2023-10-20 00:00:00,073 epoch 6 - iter 112/146 - loss 0.44471092 - time (sec): 2.98 - samples/sec: 11667.98 - lr: 0.000014 - momentum: 0.000000
2023-10-20 00:00:00,428 epoch 6 - iter 126/146 - loss 0.44516141 - time (sec): 3.33 - samples/sec: 11597.63 - lr: 0.000014 - momentum: 0.000000
2023-10-20 00:00:00,799 epoch 6 - iter 140/146 - loss 0.45814073 - time (sec): 3.71 - samples/sec: 11613.79 - lr: 0.000014 - momentum: 0.000000
2023-10-20 00:00:00,948 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:00,948 EPOCH 6 done: loss 0.4585 - lr: 0.000014
2023-10-20 00:00:01,595 DEV : loss 0.34095141291618347 - f1-score (micro avg) 0.0154
2023-10-20 00:00:01,600 saving best model
2023-10-20 00:00:01,642 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:02,017 epoch 7 - iter 14/146 - loss 0.37536862 - time (sec): 0.37 - samples/sec: 14301.95 - lr: 0.000013 - momentum: 0.000000
2023-10-20 00:00:02,380 epoch 7 - iter 28/146 - loss 0.43351013 - time (sec): 0.74 - samples/sec: 12252.57 - lr: 0.000013 - momentum: 0.000000
2023-10-20 00:00:02,752 epoch 7 - iter 42/146 - loss 0.45088688 - time (sec): 1.11 - samples/sec: 11466.86 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:00:03,117 epoch 7 - iter 56/146 - loss 0.42924375 - time (sec): 1.47 - samples/sec: 11822.14 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:00:03,427 epoch 7 - iter 70/146 - loss 0.43297036 - time (sec): 1.78 - samples/sec: 11809.32 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:00:03,696 epoch 7 - iter 84/146 - loss 0.43010334 - time (sec): 2.05 - samples/sec: 12083.12 - lr: 0.000012 - momentum: 0.000000
2023-10-20 00:00:04,108 epoch 7 - iter 98/146 - loss 0.44555768 - time (sec): 2.47 - samples/sec: 12339.04 - lr: 0.000011 - momentum: 0.000000
2023-10-20 00:00:04,448 epoch 7 - iter 112/146 - loss 0.44808496 - time (sec): 2.81 - samples/sec: 12301.85 - lr: 0.000011 - momentum: 0.000000
2023-10-20 00:00:04,967 epoch 7 - iter 126/146 - loss 0.45269904 - time (sec): 3.32 - samples/sec: 11712.90 - lr: 0.000011 - momentum: 0.000000
2023-10-20 00:00:05,313 epoch 7 - iter 140/146 - loss 0.44901216 - time (sec): 3.67 - samples/sec: 11580.63 - lr: 0.000010 - momentum: 0.000000
2023-10-20 00:00:05,473 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:05,473 EPOCH 7 done: loss 0.4437 - lr: 0.000010
2023-10-20 00:00:06,110 DEV : loss 0.32878896594047546 - f1-score (micro avg) 0.0495
2023-10-20 00:00:06,114 saving best model
2023-10-20 00:00:06,158 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:06,534 epoch 8 - iter 14/146 - loss 0.39681875 - time (sec): 0.38 - samples/sec: 11339.31 - lr: 0.000010 - momentum: 0.000000
2023-10-20 00:00:06,942 epoch 8 - iter 28/146 - loss 0.41183417 - time (sec): 0.78 - samples/sec: 11136.80 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:00:07,341 epoch 8 - iter 42/146 - loss 0.37624176 - time (sec): 1.18 - samples/sec: 12052.62 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:00:07,687 epoch 8 - iter 56/146 - loss 0.40502606 - time (sec): 1.53 - samples/sec: 11829.40 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:00:08,032 epoch 8 - iter 70/146 - loss 0.40968586 - time (sec): 1.87 - samples/sec: 11413.53 - lr: 0.000009 - momentum: 0.000000
2023-10-20 00:00:08,402 epoch 8 - iter 84/146 - loss 0.41848763 - time (sec): 2.24 - samples/sec: 11259.67 - lr: 0.000008 - momentum: 0.000000
2023-10-20 00:00:08,753 epoch 8 - iter 98/146 - loss 0.42305015 - time (sec): 2.59 - samples/sec: 11220.23 - lr: 0.000008 - momentum: 0.000000
2023-10-20 00:00:09,114 epoch 8 - iter 112/146 - loss 0.42016543 - time (sec): 2.96 - samples/sec: 11178.15 - lr: 0.000008 - momentum: 0.000000
2023-10-20 00:00:09,488 epoch 8 - iter 126/146 - loss 0.42102476 - time (sec): 3.33 - samples/sec: 11191.99 - lr: 0.000007 - momentum: 0.000000
2023-10-20 00:00:09,901 epoch 8 - iter 140/146 - loss 0.43500062 - time (sec): 3.74 - samples/sec: 11474.44 - lr: 0.000007 - momentum: 0.000000
2023-10-20 00:00:10,065 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:10,065 EPOCH 8 done: loss 0.4372 - lr: 0.000007
2023-10-20 00:00:10,698 DEV : loss 0.3299644887447357 - f1-score (micro avg) 0.0741
2023-10-20 00:00:10,702 saving best model
2023-10-20 00:00:10,737 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:11,089 epoch 9 - iter 14/146 - loss 0.43566357 - time (sec): 0.35 - samples/sec: 11233.15 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:00:11,458 epoch 9 - iter 28/146 - loss 0.40848825 - time (sec): 0.72 - samples/sec: 11203.25 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:00:11,837 epoch 9 - iter 42/146 - loss 0.40732076 - time (sec): 1.10 - samples/sec: 11414.38 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:00:12,194 epoch 9 - iter 56/146 - loss 0.39577925 - time (sec): 1.46 - samples/sec: 11311.79 - lr: 0.000006 - momentum: 0.000000
2023-10-20 00:00:12,528 epoch 9 - iter 70/146 - loss 0.40666537 - time (sec): 1.79 - samples/sec: 11346.74 - lr: 0.000005 - momentum: 0.000000
2023-10-20 00:00:12,891 epoch 9 - iter 84/146 - loss 0.41239649 - time (sec): 2.15 - samples/sec: 11391.10 - lr: 0.000005 - momentum: 0.000000
2023-10-20 00:00:13,234 epoch 9 - iter 98/146 - loss 0.41115755 - time (sec): 2.50 - samples/sec: 11527.62 - lr: 0.000005 - momentum: 0.000000
2023-10-20 00:00:13,627 epoch 9 - iter 112/146 - loss 0.40314181 - time (sec): 2.89 - samples/sec: 11627.06 - lr: 0.000004 - momentum: 0.000000
2023-10-20 00:00:14,025 epoch 9 - iter 126/146 - loss 0.42051838 - time (sec): 3.29 - samples/sec: 11689.03 - lr: 0.000004 - momentum: 0.000000
2023-10-20 00:00:14,386 epoch 9 - iter 140/146 - loss 0.42508445 - time (sec): 3.65 - samples/sec: 11694.75 - lr: 0.000004 - momentum: 0.000000
2023-10-20 00:00:14,537 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:14,537 EPOCH 9 done: loss 0.4241 - lr: 0.000004
2023-10-20 00:00:15,175 DEV : loss 0.32740116119384766 - f1-score (micro avg) 0.0936
2023-10-20 00:00:15,179 saving best model
2023-10-20 00:00:15,213 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:15,569 epoch 10 - iter 14/146 - loss 0.38655630 - time (sec): 0.35 - samples/sec: 13761.43 - lr: 0.000003 - momentum: 0.000000
2023-10-20 00:00:15,986 epoch 10 - iter 28/146 - loss 0.41125034 - time (sec): 0.77 - samples/sec: 13487.87 - lr: 0.000003 - momentum: 0.000000
2023-10-20 00:00:16,338 epoch 10 - iter 42/146 - loss 0.42992884 - time (sec): 1.12 - samples/sec: 12256.74 - lr: 0.000003 - momentum: 0.000000
2023-10-20 00:00:16,705 epoch 10 - iter 56/146 - loss 0.41655376 - time (sec): 1.49 - samples/sec: 12220.10 - lr: 0.000002 - momentum: 0.000000
2023-10-20 00:00:17,068 epoch 10 - iter 70/146 - loss 0.42169088 - time (sec): 1.85 - samples/sec: 11762.54 - lr: 0.000002 - momentum: 0.000000
2023-10-20 00:00:17,434 epoch 10 - iter 84/146 - loss 0.41552101 - time (sec): 2.22 - samples/sec: 11605.28 - lr: 0.000002 - momentum: 0.000000
2023-10-20 00:00:17,786 epoch 10 - iter 98/146 - loss 0.41674133 - time (sec): 2.57 - samples/sec: 11569.70 - lr: 0.000001 - momentum: 0.000000
2023-10-20 00:00:18,145 epoch 10 - iter 112/146 - loss 0.42416179 - time (sec): 2.93 - samples/sec: 11546.08 - lr: 0.000001 - momentum: 0.000000
2023-10-20 00:00:18,512 epoch 10 - iter 126/146 - loss 0.42713975 - time (sec): 3.30 - samples/sec: 11437.32 - lr: 0.000001 - momentum: 0.000000
2023-10-20 00:00:18,886 epoch 10 - iter 140/146 - loss 0.42392021 - time (sec): 3.67 - samples/sec: 11405.36 - lr: 0.000000 - momentum: 0.000000
2023-10-20 00:00:19,064 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:19,064 EPOCH 10 done: loss 0.4288 - lr: 0.000000
2023-10-20 00:00:19,699 DEV : loss 0.32682910561561584 - f1-score (micro avg) 0.1056
2023-10-20 00:00:19,702 saving best model
2023-10-20 00:00:19,763 ----------------------------------------------------------------------------------------------------
2023-10-20 00:00:19,763 Loading model from best epoch ...
2023-10-20 00:00:19,838 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
2023-10-20 00:00:20,720
Results:
- F-score (micro) 0.1894
- F-score (macro) 0.0812
- Accuracy 0.1071
By class:
precision recall f1-score support
PER 0.2813 0.2644 0.2726 348
LOC 0.1739 0.0307 0.0521 261
ORG 0.0000 0.0000 0.0000 52
HumanProd 0.0000 0.0000 0.0000 22
micro avg 0.2681 0.1464 0.1894 683
macro avg 0.1138 0.0738 0.0812 683
weighted avg 0.2098 0.1464 0.1588 683
2023-10-20 00:00:20,720 ----------------------------------------------------------------------------------------------------
|