File size: 24,138 Bytes
00de2c0 |
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 |
2023-10-18 16:14:19,586 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,586 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 16:14:19,586 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,586 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-18 16:14:19,586 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,586 Train: 1214 sentences
2023-10-18 16:14:19,586 (train_with_dev=False, train_with_test=False)
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Training Params:
2023-10-18 16:14:19,587 - learning_rate: "3e-05"
2023-10-18 16:14:19,587 - mini_batch_size: "8"
2023-10-18 16:14:19,587 - max_epochs: "10"
2023-10-18 16:14:19,587 - shuffle: "True"
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Plugins:
2023-10-18 16:14:19,587 - TensorboardLogger
2023-10-18 16:14:19,587 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 16:14:19,587 - metric: "('micro avg', 'f1-score')"
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Computation:
2023-10-18 16:14:19,587 - compute on device: cuda:0
2023-10-18 16:14:19,587 - embedding storage: none
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Model training base path: "hmbench-ajmc/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:19,587 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 16:14:19,950 epoch 1 - iter 15/152 - loss 3.70740706 - time (sec): 0.36 - samples/sec: 7989.31 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:14:20,276 epoch 1 - iter 30/152 - loss 3.70891912 - time (sec): 0.69 - samples/sec: 8657.50 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:14:20,606 epoch 1 - iter 45/152 - loss 3.64714283 - time (sec): 1.02 - samples/sec: 8773.49 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:14:20,941 epoch 1 - iter 60/152 - loss 3.59271918 - time (sec): 1.35 - samples/sec: 8885.18 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:14:21,274 epoch 1 - iter 75/152 - loss 3.50024596 - time (sec): 1.69 - samples/sec: 9061.70 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:14:21,603 epoch 1 - iter 90/152 - loss 3.36782693 - time (sec): 2.02 - samples/sec: 9183.48 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:14:21,945 epoch 1 - iter 105/152 - loss 3.20758430 - time (sec): 2.36 - samples/sec: 9187.99 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:14:22,269 epoch 1 - iter 120/152 - loss 3.05292876 - time (sec): 2.68 - samples/sec: 9155.76 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:14:22,618 epoch 1 - iter 135/152 - loss 2.89385963 - time (sec): 3.03 - samples/sec: 9062.92 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:14:22,951 epoch 1 - iter 150/152 - loss 2.72722874 - time (sec): 3.36 - samples/sec: 9116.95 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:14:22,994 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:22,994 EPOCH 1 done: loss 2.7120 - lr: 0.000029
2023-10-18 16:14:23,322 DEV : loss 0.8151066899299622 - f1-score (micro avg) 0.0
2023-10-18 16:14:23,327 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:23,664 epoch 2 - iter 15/152 - loss 1.04272481 - time (sec): 0.34 - samples/sec: 9259.11 - lr: 0.000030 - momentum: 0.000000
2023-10-18 16:14:23,990 epoch 2 - iter 30/152 - loss 0.95691556 - time (sec): 0.66 - samples/sec: 9084.69 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:14:24,315 epoch 2 - iter 45/152 - loss 0.91316865 - time (sec): 0.99 - samples/sec: 9371.74 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:14:24,651 epoch 2 - iter 60/152 - loss 0.91248910 - time (sec): 1.32 - samples/sec: 9303.44 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:14:24,985 epoch 2 - iter 75/152 - loss 0.89845409 - time (sec): 1.66 - samples/sec: 9311.66 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:14:25,300 epoch 2 - iter 90/152 - loss 0.88716995 - time (sec): 1.97 - samples/sec: 9533.46 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:14:25,637 epoch 2 - iter 105/152 - loss 0.84976950 - time (sec): 2.31 - samples/sec: 9466.16 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:14:25,972 epoch 2 - iter 120/152 - loss 0.83046703 - time (sec): 2.64 - samples/sec: 9250.73 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:14:26,291 epoch 2 - iter 135/152 - loss 0.82753683 - time (sec): 2.96 - samples/sec: 9285.14 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:14:26,613 epoch 2 - iter 150/152 - loss 0.81527989 - time (sec): 3.29 - samples/sec: 9323.40 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:14:26,657 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:26,657 EPOCH 2 done: loss 0.8136 - lr: 0.000027
2023-10-18 16:14:27,152 DEV : loss 0.6542724370956421 - f1-score (micro avg) 0.0
2023-10-18 16:14:27,157 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:27,480 epoch 3 - iter 15/152 - loss 0.66380491 - time (sec): 0.32 - samples/sec: 9317.53 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:14:27,817 epoch 3 - iter 30/152 - loss 0.71312012 - time (sec): 0.66 - samples/sec: 9379.54 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:14:28,136 epoch 3 - iter 45/152 - loss 0.66878033 - time (sec): 0.98 - samples/sec: 9304.53 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:14:28,489 epoch 3 - iter 60/152 - loss 0.67676228 - time (sec): 1.33 - samples/sec: 9301.62 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:14:28,842 epoch 3 - iter 75/152 - loss 0.66316423 - time (sec): 1.68 - samples/sec: 9339.81 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:14:29,200 epoch 3 - iter 90/152 - loss 0.65454872 - time (sec): 2.04 - samples/sec: 9173.50 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:14:29,545 epoch 3 - iter 105/152 - loss 0.63681589 - time (sec): 2.39 - samples/sec: 9124.69 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:14:29,899 epoch 3 - iter 120/152 - loss 0.62456123 - time (sec): 2.74 - samples/sec: 9031.75 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:14:30,257 epoch 3 - iter 135/152 - loss 0.60695594 - time (sec): 3.10 - samples/sec: 9009.89 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:14:30,585 epoch 3 - iter 150/152 - loss 0.60126758 - time (sec): 3.43 - samples/sec: 8934.86 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:14:30,626 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:30,627 EPOCH 3 done: loss 0.5995 - lr: 0.000023
2023-10-18 16:14:31,122 DEV : loss 0.47917139530181885 - f1-score (micro avg) 0.0041
2023-10-18 16:14:31,127 saving best model
2023-10-18 16:14:31,160 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:31,487 epoch 4 - iter 15/152 - loss 0.55870288 - time (sec): 0.33 - samples/sec: 10231.76 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:14:31,805 epoch 4 - iter 30/152 - loss 0.59119756 - time (sec): 0.64 - samples/sec: 9546.87 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:14:32,286 epoch 4 - iter 45/152 - loss 0.53257898 - time (sec): 1.12 - samples/sec: 8394.70 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:14:32,616 epoch 4 - iter 60/152 - loss 0.53039907 - time (sec): 1.46 - samples/sec: 8428.69 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:14:32,958 epoch 4 - iter 75/152 - loss 0.53955919 - time (sec): 1.80 - samples/sec: 8640.88 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:14:33,290 epoch 4 - iter 90/152 - loss 0.51870706 - time (sec): 2.13 - samples/sec: 8760.09 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:14:33,607 epoch 4 - iter 105/152 - loss 0.50971416 - time (sec): 2.45 - samples/sec: 8968.46 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:14:33,942 epoch 4 - iter 120/152 - loss 0.50708301 - time (sec): 2.78 - samples/sec: 8988.34 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:14:34,257 epoch 4 - iter 135/152 - loss 0.50197658 - time (sec): 3.10 - samples/sec: 8963.27 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:14:34,580 epoch 4 - iter 150/152 - loss 0.49393271 - time (sec): 3.42 - samples/sec: 8961.06 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:14:34,628 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:34,629 EPOCH 4 done: loss 0.4940 - lr: 0.000020
2023-10-18 16:14:35,141 DEV : loss 0.3989596664905548 - f1-score (micro avg) 0.245
2023-10-18 16:14:35,147 saving best model
2023-10-18 16:14:35,193 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:35,520 epoch 5 - iter 15/152 - loss 0.46136293 - time (sec): 0.33 - samples/sec: 9427.18 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:14:35,882 epoch 5 - iter 30/152 - loss 0.47353895 - time (sec): 0.69 - samples/sec: 9220.21 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:14:36,219 epoch 5 - iter 45/152 - loss 0.48635178 - time (sec): 1.03 - samples/sec: 9575.75 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:14:36,532 epoch 5 - iter 60/152 - loss 0.46696894 - time (sec): 1.34 - samples/sec: 9650.20 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:14:36,857 epoch 5 - iter 75/152 - loss 0.44269793 - time (sec): 1.66 - samples/sec: 9544.65 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:14:37,185 epoch 5 - iter 90/152 - loss 0.45211746 - time (sec): 1.99 - samples/sec: 9421.92 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:14:37,521 epoch 5 - iter 105/152 - loss 0.44843539 - time (sec): 2.33 - samples/sec: 9392.83 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:14:37,875 epoch 5 - iter 120/152 - loss 0.44558332 - time (sec): 2.68 - samples/sec: 9223.79 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:14:38,226 epoch 5 - iter 135/152 - loss 0.43892253 - time (sec): 3.03 - samples/sec: 9087.19 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:14:38,584 epoch 5 - iter 150/152 - loss 0.43735788 - time (sec): 3.39 - samples/sec: 9025.35 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:14:38,627 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:38,627 EPOCH 5 done: loss 0.4350 - lr: 0.000017
2023-10-18 16:14:39,137 DEV : loss 0.37336358428001404 - f1-score (micro avg) 0.3385
2023-10-18 16:14:39,142 saving best model
2023-10-18 16:14:39,177 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:39,525 epoch 6 - iter 15/152 - loss 0.38909019 - time (sec): 0.35 - samples/sec: 8400.17 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:14:39,875 epoch 6 - iter 30/152 - loss 0.40703602 - time (sec): 0.70 - samples/sec: 8398.89 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:14:40,201 epoch 6 - iter 45/152 - loss 0.41827443 - time (sec): 1.02 - samples/sec: 8718.18 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:14:40,528 epoch 6 - iter 60/152 - loss 0.40297375 - time (sec): 1.35 - samples/sec: 8841.87 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:14:40,860 epoch 6 - iter 75/152 - loss 0.41614379 - time (sec): 1.68 - samples/sec: 9079.98 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:14:41,194 epoch 6 - iter 90/152 - loss 0.42604386 - time (sec): 2.02 - samples/sec: 9144.37 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:14:41,530 epoch 6 - iter 105/152 - loss 0.41944796 - time (sec): 2.35 - samples/sec: 9068.61 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:14:41,850 epoch 6 - iter 120/152 - loss 0.41276481 - time (sec): 2.67 - samples/sec: 9046.06 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:14:42,208 epoch 6 - iter 135/152 - loss 0.40953834 - time (sec): 3.03 - samples/sec: 9057.84 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:14:42,539 epoch 6 - iter 150/152 - loss 0.40883256 - time (sec): 3.36 - samples/sec: 9126.22 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:14:42,576 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:42,576 EPOCH 6 done: loss 0.4106 - lr: 0.000013
2023-10-18 16:14:43,090 DEV : loss 0.3582286834716797 - f1-score (micro avg) 0.3661
2023-10-18 16:14:43,095 saving best model
2023-10-18 16:14:43,128 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:43,489 epoch 7 - iter 15/152 - loss 0.36878538 - time (sec): 0.36 - samples/sec: 8297.34 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:14:43,844 epoch 7 - iter 30/152 - loss 0.37324167 - time (sec): 0.72 - samples/sec: 8516.14 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:14:44,161 epoch 7 - iter 45/152 - loss 0.39895662 - time (sec): 1.03 - samples/sec: 8596.00 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:14:44,508 epoch 7 - iter 60/152 - loss 0.38077778 - time (sec): 1.38 - samples/sec: 8568.20 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:14:44,860 epoch 7 - iter 75/152 - loss 0.37998547 - time (sec): 1.73 - samples/sec: 8621.10 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:14:45,217 epoch 7 - iter 90/152 - loss 0.37443302 - time (sec): 2.09 - samples/sec: 8701.48 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:14:45,550 epoch 7 - iter 105/152 - loss 0.36700582 - time (sec): 2.42 - samples/sec: 8829.17 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:14:45,873 epoch 7 - iter 120/152 - loss 0.37341692 - time (sec): 2.74 - samples/sec: 8864.26 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:14:46,195 epoch 7 - iter 135/152 - loss 0.37635494 - time (sec): 3.07 - samples/sec: 8949.42 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:14:46,522 epoch 7 - iter 150/152 - loss 0.38600423 - time (sec): 3.39 - samples/sec: 9020.34 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:14:46,566 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:46,566 EPOCH 7 done: loss 0.3840 - lr: 0.000010
2023-10-18 16:14:47,084 DEV : loss 0.34290459752082825 - f1-score (micro avg) 0.3953
2023-10-18 16:14:47,089 saving best model
2023-10-18 16:14:47,122 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:47,470 epoch 8 - iter 15/152 - loss 0.46128735 - time (sec): 0.35 - samples/sec: 9163.93 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:14:47,786 epoch 8 - iter 30/152 - loss 0.41739483 - time (sec): 0.66 - samples/sec: 9663.44 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:14:48,109 epoch 8 - iter 45/152 - loss 0.36445950 - time (sec): 0.99 - samples/sec: 9623.26 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:14:48,431 epoch 8 - iter 60/152 - loss 0.36194631 - time (sec): 1.31 - samples/sec: 9343.92 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:14:48,752 epoch 8 - iter 75/152 - loss 0.35672477 - time (sec): 1.63 - samples/sec: 9396.72 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:14:49,074 epoch 8 - iter 90/152 - loss 0.35745362 - time (sec): 1.95 - samples/sec: 9388.06 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:14:49,418 epoch 8 - iter 105/152 - loss 0.35927087 - time (sec): 2.30 - samples/sec: 9365.21 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:14:49,768 epoch 8 - iter 120/152 - loss 0.35874584 - time (sec): 2.65 - samples/sec: 9281.51 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:14:50,099 epoch 8 - iter 135/152 - loss 0.36692959 - time (sec): 2.98 - samples/sec: 9253.37 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:14:50,445 epoch 8 - iter 150/152 - loss 0.36907541 - time (sec): 3.32 - samples/sec: 9211.67 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:14:50,490 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:50,490 EPOCH 8 done: loss 0.3703 - lr: 0.000007
2023-10-18 16:14:51,007 DEV : loss 0.3377641439437866 - f1-score (micro avg) 0.3968
2023-10-18 16:14:51,013 saving best model
2023-10-18 16:14:51,045 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:51,382 epoch 9 - iter 15/152 - loss 0.36902711 - time (sec): 0.34 - samples/sec: 9605.47 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:14:51,694 epoch 9 - iter 30/152 - loss 0.36172452 - time (sec): 0.65 - samples/sec: 9401.82 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:14:52,022 epoch 9 - iter 45/152 - loss 0.36103385 - time (sec): 0.98 - samples/sec: 9248.33 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:14:52,342 epoch 9 - iter 60/152 - loss 0.36296944 - time (sec): 1.30 - samples/sec: 9338.97 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:14:52,664 epoch 9 - iter 75/152 - loss 0.35951793 - time (sec): 1.62 - samples/sec: 9304.75 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:14:52,990 epoch 9 - iter 90/152 - loss 0.35382745 - time (sec): 1.94 - samples/sec: 9276.69 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:14:53,324 epoch 9 - iter 105/152 - loss 0.35352197 - time (sec): 2.28 - samples/sec: 9196.41 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:14:53,678 epoch 9 - iter 120/152 - loss 0.35354054 - time (sec): 2.63 - samples/sec: 9264.16 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:14:54,009 epoch 9 - iter 135/152 - loss 0.35497994 - time (sec): 2.96 - samples/sec: 9298.85 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:14:54,344 epoch 9 - iter 150/152 - loss 0.35835628 - time (sec): 3.30 - samples/sec: 9285.09 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:14:54,388 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:54,388 EPOCH 9 done: loss 0.3582 - lr: 0.000004
2023-10-18 16:14:54,923 DEV : loss 0.32884225249290466 - f1-score (micro avg) 0.4068
2023-10-18 16:14:54,929 saving best model
2023-10-18 16:14:54,961 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:55,293 epoch 10 - iter 15/152 - loss 0.33695965 - time (sec): 0.33 - samples/sec: 9035.58 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:14:55,642 epoch 10 - iter 30/152 - loss 0.35601442 - time (sec): 0.68 - samples/sec: 8904.69 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:14:55,990 epoch 10 - iter 45/152 - loss 0.35541243 - time (sec): 1.03 - samples/sec: 8716.71 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:14:56,335 epoch 10 - iter 60/152 - loss 0.35564157 - time (sec): 1.37 - samples/sec: 8687.94 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:14:56,666 epoch 10 - iter 75/152 - loss 0.35549319 - time (sec): 1.71 - samples/sec: 8899.60 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:14:57,002 epoch 10 - iter 90/152 - loss 0.35639063 - time (sec): 2.04 - samples/sec: 8972.96 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:14:57,320 epoch 10 - iter 105/152 - loss 0.35591624 - time (sec): 2.36 - samples/sec: 9034.10 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:14:57,657 epoch 10 - iter 120/152 - loss 0.35145120 - time (sec): 2.70 - samples/sec: 9030.47 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:14:58,008 epoch 10 - iter 135/152 - loss 0.35301827 - time (sec): 3.05 - samples/sec: 8972.59 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:14:58,366 epoch 10 - iter 150/152 - loss 0.36004132 - time (sec): 3.40 - samples/sec: 8953.55 - lr: 0.000000 - momentum: 0.000000
2023-10-18 16:14:58,410 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:58,410 EPOCH 10 done: loss 0.3603 - lr: 0.000000
2023-10-18 16:14:58,927 DEV : loss 0.3272362947463989 - f1-score (micro avg) 0.4073
2023-10-18 16:14:58,932 saving best model
2023-10-18 16:14:58,992 ----------------------------------------------------------------------------------------------------
2023-10-18 16:14:58,993 Loading model from best epoch ...
2023-10-18 16:14:59,079 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
2023-10-18 16:14:59,570
Results:
- F-score (micro) 0.4629
- F-score (macro) 0.2828
- Accuracy 0.3074
By class:
precision recall f1-score support
scope 0.4393 0.5033 0.4691 151
work 0.3194 0.4842 0.3849 95
pers 0.5385 0.5833 0.5600 96
loc 0.0000 0.0000 0.0000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.4228 0.5115 0.4629 348
macro avg 0.2594 0.3142 0.2828 348
weighted avg 0.4264 0.5115 0.4631 348
2023-10-18 16:14:59,570 ----------------------------------------------------------------------------------------------------
|