File size: 24,158 Bytes
b576412 |
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 14:33:33,455 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,456 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 14:33:33,456 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,456 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 14:33:33,456 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,456 Train: 1100 sentences
2023-10-18 14:33:33,456 (train_with_dev=False, train_with_test=False)
2023-10-18 14:33:33,456 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,456 Training Params:
2023-10-18 14:33:33,456 - learning_rate: "3e-05"
2023-10-18 14:33:33,456 - mini_batch_size: "4"
2023-10-18 14:33:33,456 - max_epochs: "10"
2023-10-18 14:33:33,457 - shuffle: "True"
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 Plugins:
2023-10-18 14:33:33,457 - TensorboardLogger
2023-10-18 14:33:33,457 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 14:33:33,457 - metric: "('micro avg', 'f1-score')"
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 Computation:
2023-10-18 14:33:33,457 - compute on device: cuda:0
2023-10-18 14:33:33,457 - embedding storage: none
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 Model training base path: "hmbench-ajmc/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:33,457 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 14:33:34,901 epoch 1 - iter 27/275 - loss 3.95807539 - time (sec): 1.44 - samples/sec: 1696.55 - lr: 0.000003 - momentum: 0.000000
2023-10-18 14:33:35,335 epoch 1 - iter 54/275 - loss 4.02684268 - time (sec): 1.88 - samples/sec: 2500.12 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:33:35,764 epoch 1 - iter 81/275 - loss 3.93498797 - time (sec): 2.31 - samples/sec: 2931.71 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:33:36,175 epoch 1 - iter 108/275 - loss 3.82505787 - time (sec): 2.72 - samples/sec: 3244.87 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:33:36,591 epoch 1 - iter 135/275 - loss 3.62952957 - time (sec): 3.13 - samples/sec: 3618.88 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:33:37,001 epoch 1 - iter 162/275 - loss 3.41964347 - time (sec): 3.54 - samples/sec: 3831.26 - lr: 0.000018 - momentum: 0.000000
2023-10-18 14:33:37,399 epoch 1 - iter 189/275 - loss 3.22624157 - time (sec): 3.94 - samples/sec: 4001.92 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:33:37,800 epoch 1 - iter 216/275 - loss 3.00227363 - time (sec): 4.34 - samples/sec: 4182.55 - lr: 0.000023 - momentum: 0.000000
2023-10-18 14:33:38,209 epoch 1 - iter 243/275 - loss 2.81798890 - time (sec): 4.75 - samples/sec: 4237.42 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:33:38,605 epoch 1 - iter 270/275 - loss 2.66322507 - time (sec): 5.15 - samples/sec: 4342.81 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:33:38,682 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:38,682 EPOCH 1 done: loss 2.6324 - lr: 0.000029
2023-10-18 14:33:38,943 DEV : loss 0.8727257251739502 - f1-score (micro avg) 0.0
2023-10-18 14:33:38,947 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:39,348 epoch 2 - iter 27/275 - loss 0.95414304 - time (sec): 0.40 - samples/sec: 6156.96 - lr: 0.000030 - momentum: 0.000000
2023-10-18 14:33:39,760 epoch 2 - iter 54/275 - loss 1.00539324 - time (sec): 0.81 - samples/sec: 5799.67 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:33:40,168 epoch 2 - iter 81/275 - loss 1.03670034 - time (sec): 1.22 - samples/sec: 5747.24 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:33:40,578 epoch 2 - iter 108/275 - loss 1.01175848 - time (sec): 1.63 - samples/sec: 5675.91 - lr: 0.000029 - momentum: 0.000000
2023-10-18 14:33:40,990 epoch 2 - iter 135/275 - loss 1.00671150 - time (sec): 2.04 - samples/sec: 5516.96 - lr: 0.000028 - momentum: 0.000000
2023-10-18 14:33:41,395 epoch 2 - iter 162/275 - loss 0.97791266 - time (sec): 2.45 - samples/sec: 5565.61 - lr: 0.000028 - momentum: 0.000000
2023-10-18 14:33:41,806 epoch 2 - iter 189/275 - loss 0.95352470 - time (sec): 2.86 - samples/sec: 5565.32 - lr: 0.000028 - momentum: 0.000000
2023-10-18 14:33:42,205 epoch 2 - iter 216/275 - loss 0.93400324 - time (sec): 3.26 - samples/sec: 5490.92 - lr: 0.000027 - momentum: 0.000000
2023-10-18 14:33:42,618 epoch 2 - iter 243/275 - loss 0.90908336 - time (sec): 3.67 - samples/sec: 5528.79 - lr: 0.000027 - momentum: 0.000000
2023-10-18 14:33:43,013 epoch 2 - iter 270/275 - loss 0.89179470 - time (sec): 4.07 - samples/sec: 5493.60 - lr: 0.000027 - momentum: 0.000000
2023-10-18 14:33:43,086 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:43,086 EPOCH 2 done: loss 0.8891 - lr: 0.000027
2023-10-18 14:33:43,458 DEV : loss 0.690082848072052 - f1-score (micro avg) 0.0
2023-10-18 14:33:43,465 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:43,868 epoch 3 - iter 27/275 - loss 0.79786830 - time (sec): 0.40 - samples/sec: 5628.57 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:33:44,271 epoch 3 - iter 54/275 - loss 0.73841948 - time (sec): 0.81 - samples/sec: 5612.54 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:33:44,684 epoch 3 - iter 81/275 - loss 0.76137491 - time (sec): 1.22 - samples/sec: 5654.41 - lr: 0.000026 - momentum: 0.000000
2023-10-18 14:33:45,222 epoch 3 - iter 108/275 - loss 0.72902040 - time (sec): 1.76 - samples/sec: 5272.71 - lr: 0.000025 - momentum: 0.000000
2023-10-18 14:33:45,637 epoch 3 - iter 135/275 - loss 0.73347067 - time (sec): 2.17 - samples/sec: 5275.39 - lr: 0.000025 - momentum: 0.000000
2023-10-18 14:33:46,032 epoch 3 - iter 162/275 - loss 0.71535696 - time (sec): 2.57 - samples/sec: 5337.01 - lr: 0.000025 - momentum: 0.000000
2023-10-18 14:33:46,451 epoch 3 - iter 189/275 - loss 0.70609375 - time (sec): 2.99 - samples/sec: 5330.98 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:33:46,863 epoch 3 - iter 216/275 - loss 0.70424713 - time (sec): 3.40 - samples/sec: 5323.43 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:33:47,271 epoch 3 - iter 243/275 - loss 0.70311682 - time (sec): 3.81 - samples/sec: 5323.86 - lr: 0.000024 - momentum: 0.000000
2023-10-18 14:33:47,675 epoch 3 - iter 270/275 - loss 0.70164780 - time (sec): 4.21 - samples/sec: 5333.31 - lr: 0.000023 - momentum: 0.000000
2023-10-18 14:33:47,745 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:47,746 EPOCH 3 done: loss 0.6995 - lr: 0.000023
2023-10-18 14:33:48,107 DEV : loss 0.5440794825553894 - f1-score (micro avg) 0.1311
2023-10-18 14:33:48,111 saving best model
2023-10-18 14:33:48,147 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:48,544 epoch 4 - iter 27/275 - loss 0.68168972 - time (sec): 0.40 - samples/sec: 5570.72 - lr: 0.000023 - momentum: 0.000000
2023-10-18 14:33:48,938 epoch 4 - iter 54/275 - loss 0.64810506 - time (sec): 0.79 - samples/sec: 5518.00 - lr: 0.000023 - momentum: 0.000000
2023-10-18 14:33:49,349 epoch 4 - iter 81/275 - loss 0.61425076 - time (sec): 1.20 - samples/sec: 5321.55 - lr: 0.000022 - momentum: 0.000000
2023-10-18 14:33:49,753 epoch 4 - iter 108/275 - loss 0.63426737 - time (sec): 1.61 - samples/sec: 5357.68 - lr: 0.000022 - momentum: 0.000000
2023-10-18 14:33:50,162 epoch 4 - iter 135/275 - loss 0.61651865 - time (sec): 2.01 - samples/sec: 5551.61 - lr: 0.000022 - momentum: 0.000000
2023-10-18 14:33:50,569 epoch 4 - iter 162/275 - loss 0.60018412 - time (sec): 2.42 - samples/sec: 5531.42 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:33:50,985 epoch 4 - iter 189/275 - loss 0.59771216 - time (sec): 2.84 - samples/sec: 5518.53 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:33:51,401 epoch 4 - iter 216/275 - loss 0.58918031 - time (sec): 3.25 - samples/sec: 5523.57 - lr: 0.000021 - momentum: 0.000000
2023-10-18 14:33:51,811 epoch 4 - iter 243/275 - loss 0.58391359 - time (sec): 3.66 - samples/sec: 5518.71 - lr: 0.000020 - momentum: 0.000000
2023-10-18 14:33:52,214 epoch 4 - iter 270/275 - loss 0.57886356 - time (sec): 4.07 - samples/sec: 5491.47 - lr: 0.000020 - momentum: 0.000000
2023-10-18 14:33:52,293 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:52,293 EPOCH 4 done: loss 0.5788 - lr: 0.000020
2023-10-18 14:33:52,651 DEV : loss 0.446980744600296 - f1-score (micro avg) 0.3195
2023-10-18 14:33:52,655 saving best model
2023-10-18 14:33:52,692 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:53,118 epoch 5 - iter 27/275 - loss 0.47038975 - time (sec): 0.42 - samples/sec: 6169.87 - lr: 0.000020 - momentum: 0.000000
2023-10-18 14:33:53,533 epoch 5 - iter 54/275 - loss 0.49156303 - time (sec): 0.84 - samples/sec: 5549.68 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:33:53,934 epoch 5 - iter 81/275 - loss 0.50829332 - time (sec): 1.24 - samples/sec: 5562.38 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:33:54,345 epoch 5 - iter 108/275 - loss 0.51783415 - time (sec): 1.65 - samples/sec: 5661.14 - lr: 0.000019 - momentum: 0.000000
2023-10-18 14:33:54,754 epoch 5 - iter 135/275 - loss 0.52054288 - time (sec): 2.06 - samples/sec: 5532.59 - lr: 0.000018 - momentum: 0.000000
2023-10-18 14:33:55,152 epoch 5 - iter 162/275 - loss 0.52045580 - time (sec): 2.46 - samples/sec: 5529.64 - lr: 0.000018 - momentum: 0.000000
2023-10-18 14:33:55,550 epoch 5 - iter 189/275 - loss 0.52141928 - time (sec): 2.86 - samples/sec: 5513.83 - lr: 0.000018 - momentum: 0.000000
2023-10-18 14:33:55,986 epoch 5 - iter 216/275 - loss 0.52400933 - time (sec): 3.29 - samples/sec: 5438.15 - lr: 0.000017 - momentum: 0.000000
2023-10-18 14:33:56,388 epoch 5 - iter 243/275 - loss 0.51808409 - time (sec): 3.69 - samples/sec: 5417.92 - lr: 0.000017 - momentum: 0.000000
2023-10-18 14:33:56,801 epoch 5 - iter 270/275 - loss 0.51933400 - time (sec): 4.11 - samples/sec: 5446.28 - lr: 0.000017 - momentum: 0.000000
2023-10-18 14:33:56,874 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:56,874 EPOCH 5 done: loss 0.5164 - lr: 0.000017
2023-10-18 14:33:57,240 DEV : loss 0.3829083740711212 - f1-score (micro avg) 0.4412
2023-10-18 14:33:57,244 saving best model
2023-10-18 14:33:57,280 ----------------------------------------------------------------------------------------------------
2023-10-18 14:33:57,671 epoch 6 - iter 27/275 - loss 0.60568622 - time (sec): 0.39 - samples/sec: 5055.69 - lr: 0.000016 - momentum: 0.000000
2023-10-18 14:33:58,062 epoch 6 - iter 54/275 - loss 0.51501565 - time (sec): 0.78 - samples/sec: 5417.32 - lr: 0.000016 - momentum: 0.000000
2023-10-18 14:33:58,466 epoch 6 - iter 81/275 - loss 0.52007717 - time (sec): 1.19 - samples/sec: 5542.45 - lr: 0.000016 - momentum: 0.000000
2023-10-18 14:33:58,875 epoch 6 - iter 108/275 - loss 0.50831316 - time (sec): 1.59 - samples/sec: 5541.06 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:33:59,277 epoch 6 - iter 135/275 - loss 0.48824914 - time (sec): 2.00 - samples/sec: 5482.41 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:33:59,688 epoch 6 - iter 162/275 - loss 0.48448898 - time (sec): 2.41 - samples/sec: 5579.49 - lr: 0.000015 - momentum: 0.000000
2023-10-18 14:34:00,104 epoch 6 - iter 189/275 - loss 0.47906986 - time (sec): 2.82 - samples/sec: 5542.73 - lr: 0.000014 - momentum: 0.000000
2023-10-18 14:34:00,518 epoch 6 - iter 216/275 - loss 0.47103482 - time (sec): 3.24 - samples/sec: 5512.00 - lr: 0.000014 - momentum: 0.000000
2023-10-18 14:34:00,925 epoch 6 - iter 243/275 - loss 0.47641128 - time (sec): 3.64 - samples/sec: 5565.64 - lr: 0.000014 - momentum: 0.000000
2023-10-18 14:34:01,335 epoch 6 - iter 270/275 - loss 0.47212454 - time (sec): 4.05 - samples/sec: 5528.51 - lr: 0.000013 - momentum: 0.000000
2023-10-18 14:34:01,411 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:01,411 EPOCH 6 done: loss 0.4711 - lr: 0.000013
2023-10-18 14:34:01,779 DEV : loss 0.35361379384994507 - f1-score (micro avg) 0.5
2023-10-18 14:34:01,783 saving best model
2023-10-18 14:34:01,818 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:02,230 epoch 7 - iter 27/275 - loss 0.51653193 - time (sec): 0.41 - samples/sec: 5057.55 - lr: 0.000013 - momentum: 0.000000
2023-10-18 14:34:02,649 epoch 7 - iter 54/275 - loss 0.47829517 - time (sec): 0.83 - samples/sec: 5139.10 - lr: 0.000013 - momentum: 0.000000
2023-10-18 14:34:03,056 epoch 7 - iter 81/275 - loss 0.47507434 - time (sec): 1.24 - samples/sec: 5124.10 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:34:03,467 epoch 7 - iter 108/275 - loss 0.46524549 - time (sec): 1.65 - samples/sec: 5065.57 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:34:03,840 epoch 7 - iter 135/275 - loss 0.45425778 - time (sec): 2.02 - samples/sec: 5284.03 - lr: 0.000012 - momentum: 0.000000
2023-10-18 14:34:04,214 epoch 7 - iter 162/275 - loss 0.44426560 - time (sec): 2.40 - samples/sec: 5469.89 - lr: 0.000011 - momentum: 0.000000
2023-10-18 14:34:04,589 epoch 7 - iter 189/275 - loss 0.45075310 - time (sec): 2.77 - samples/sec: 5577.78 - lr: 0.000011 - momentum: 0.000000
2023-10-18 14:34:04,963 epoch 7 - iter 216/275 - loss 0.44430239 - time (sec): 3.14 - samples/sec: 5653.18 - lr: 0.000011 - momentum: 0.000000
2023-10-18 14:34:05,336 epoch 7 - iter 243/275 - loss 0.43835253 - time (sec): 3.52 - samples/sec: 5736.85 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:34:05,707 epoch 7 - iter 270/275 - loss 0.44103139 - time (sec): 3.89 - samples/sec: 5772.09 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:34:05,774 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:05,774 EPOCH 7 done: loss 0.4392 - lr: 0.000010
2023-10-18 14:34:06,139 DEV : loss 0.3377951979637146 - f1-score (micro avg) 0.5332
2023-10-18 14:34:06,143 saving best model
2023-10-18 14:34:06,177 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:06,542 epoch 8 - iter 27/275 - loss 0.46120490 - time (sec): 0.36 - samples/sec: 6245.19 - lr: 0.000010 - momentum: 0.000000
2023-10-18 14:34:06,916 epoch 8 - iter 54/275 - loss 0.43711143 - time (sec): 0.74 - samples/sec: 5782.83 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:34:07,322 epoch 8 - iter 81/275 - loss 0.42993624 - time (sec): 1.14 - samples/sec: 5625.05 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:34:07,747 epoch 8 - iter 108/275 - loss 0.43798123 - time (sec): 1.57 - samples/sec: 5618.59 - lr: 0.000009 - momentum: 0.000000
2023-10-18 14:34:08,155 epoch 8 - iter 135/275 - loss 0.41689337 - time (sec): 1.98 - samples/sec: 5691.67 - lr: 0.000008 - momentum: 0.000000
2023-10-18 14:34:08,558 epoch 8 - iter 162/275 - loss 0.40611288 - time (sec): 2.38 - samples/sec: 5626.24 - lr: 0.000008 - momentum: 0.000000
2023-10-18 14:34:08,978 epoch 8 - iter 189/275 - loss 0.41126376 - time (sec): 2.80 - samples/sec: 5564.85 - lr: 0.000008 - momentum: 0.000000
2023-10-18 14:34:09,372 epoch 8 - iter 216/275 - loss 0.41874573 - time (sec): 3.19 - samples/sec: 5530.94 - lr: 0.000007 - momentum: 0.000000
2023-10-18 14:34:09,785 epoch 8 - iter 243/275 - loss 0.42031093 - time (sec): 3.61 - samples/sec: 5527.18 - lr: 0.000007 - momentum: 0.000000
2023-10-18 14:34:10,200 epoch 8 - iter 270/275 - loss 0.41959777 - time (sec): 4.02 - samples/sec: 5558.55 - lr: 0.000007 - momentum: 0.000000
2023-10-18 14:34:10,283 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:10,284 EPOCH 8 done: loss 0.4179 - lr: 0.000007
2023-10-18 14:34:10,653 DEV : loss 0.3256723880767822 - f1-score (micro avg) 0.5433
2023-10-18 14:34:10,657 saving best model
2023-10-18 14:34:10,693 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:11,121 epoch 9 - iter 27/275 - loss 0.40590119 - time (sec): 0.43 - samples/sec: 5380.00 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:34:11,522 epoch 9 - iter 54/275 - loss 0.41779296 - time (sec): 0.83 - samples/sec: 5553.98 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:34:11,937 epoch 9 - iter 81/275 - loss 0.41452508 - time (sec): 1.24 - samples/sec: 5468.20 - lr: 0.000006 - momentum: 0.000000
2023-10-18 14:34:12,330 epoch 9 - iter 108/275 - loss 0.43171475 - time (sec): 1.64 - samples/sec: 5435.80 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:34:12,730 epoch 9 - iter 135/275 - loss 0.44049718 - time (sec): 2.04 - samples/sec: 5420.83 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:34:13,137 epoch 9 - iter 162/275 - loss 0.43920082 - time (sec): 2.44 - samples/sec: 5429.86 - lr: 0.000005 - momentum: 0.000000
2023-10-18 14:34:13,545 epoch 9 - iter 189/275 - loss 0.42865859 - time (sec): 2.85 - samples/sec: 5430.42 - lr: 0.000004 - momentum: 0.000000
2023-10-18 14:34:13,961 epoch 9 - iter 216/275 - loss 0.42145289 - time (sec): 3.27 - samples/sec: 5461.56 - lr: 0.000004 - momentum: 0.000000
2023-10-18 14:34:14,364 epoch 9 - iter 243/275 - loss 0.42176964 - time (sec): 3.67 - samples/sec: 5563.73 - lr: 0.000004 - momentum: 0.000000
2023-10-18 14:34:14,763 epoch 9 - iter 270/275 - loss 0.41965621 - time (sec): 4.07 - samples/sec: 5493.05 - lr: 0.000003 - momentum: 0.000000
2023-10-18 14:34:14,840 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:14,841 EPOCH 9 done: loss 0.4216 - lr: 0.000003
2023-10-18 14:34:15,212 DEV : loss 0.320939838886261 - f1-score (micro avg) 0.5464
2023-10-18 14:34:15,216 saving best model
2023-10-18 14:34:15,250 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:15,638 epoch 10 - iter 27/275 - loss 0.35279704 - time (sec): 0.39 - samples/sec: 5775.64 - lr: 0.000003 - momentum: 0.000000
2023-10-18 14:34:16,040 epoch 10 - iter 54/275 - loss 0.39298011 - time (sec): 0.79 - samples/sec: 5759.75 - lr: 0.000003 - momentum: 0.000000
2023-10-18 14:34:16,440 epoch 10 - iter 81/275 - loss 0.40468269 - time (sec): 1.19 - samples/sec: 5509.45 - lr: 0.000002 - momentum: 0.000000
2023-10-18 14:34:16,854 epoch 10 - iter 108/275 - loss 0.39740579 - time (sec): 1.60 - samples/sec: 5443.48 - lr: 0.000002 - momentum: 0.000000
2023-10-18 14:34:17,257 epoch 10 - iter 135/275 - loss 0.40381656 - time (sec): 2.01 - samples/sec: 5498.53 - lr: 0.000002 - momentum: 0.000000
2023-10-18 14:34:17,655 epoch 10 - iter 162/275 - loss 0.41005123 - time (sec): 2.40 - samples/sec: 5561.44 - lr: 0.000001 - momentum: 0.000000
2023-10-18 14:34:18,067 epoch 10 - iter 189/275 - loss 0.42288410 - time (sec): 2.82 - samples/sec: 5606.36 - lr: 0.000001 - momentum: 0.000000
2023-10-18 14:34:18,477 epoch 10 - iter 216/275 - loss 0.41179863 - time (sec): 3.23 - samples/sec: 5613.41 - lr: 0.000001 - momentum: 0.000000
2023-10-18 14:34:18,883 epoch 10 - iter 243/275 - loss 0.40928966 - time (sec): 3.63 - samples/sec: 5552.26 - lr: 0.000000 - momentum: 0.000000
2023-10-18 14:34:19,287 epoch 10 - iter 270/275 - loss 0.40508631 - time (sec): 4.04 - samples/sec: 5543.71 - lr: 0.000000 - momentum: 0.000000
2023-10-18 14:34:19,371 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:19,371 EPOCH 10 done: loss 0.4038 - lr: 0.000000
2023-10-18 14:34:19,737 DEV : loss 0.3195188045501709 - f1-score (micro avg) 0.5483
2023-10-18 14:34:19,741 saving best model
2023-10-18 14:34:19,802 ----------------------------------------------------------------------------------------------------
2023-10-18 14:34:19,803 Loading model from best epoch ...
2023-10-18 14:34:19,882 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 14:34:20,162
Results:
- F-score (micro) 0.587
- F-score (macro) 0.3506
- Accuracy 0.4269
By class:
precision recall f1-score support
scope 0.5707 0.5966 0.5833 176
pers 0.8452 0.5547 0.6698 128
work 0.4651 0.5405 0.5000 74
object 0.0000 0.0000 0.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.6102 0.5654 0.5870 382
macro avg 0.3762 0.3384 0.3506 382
weighted avg 0.6362 0.5654 0.5901 382
2023-10-18 14:34:20,162 ----------------------------------------------------------------------------------------------------
|