File size: 25,292 Bytes
c053319 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 |
2023-10-11 12:17:47,458 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,460 Model: "SequenceTagger(
(embeddings): ByT5Embeddings(
(model): T5EncoderModel(
(shared): Embedding(384, 1472)
(encoder): T5Stack(
(embed_tokens): Embedding(384, 1472)
(block): ModuleList(
(0): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
(relative_attention_bias): Embedding(32, 6)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(1-11): 11 x T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1472, out_features=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-11 12:17:47,460 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,461 MultiCorpus: 1085 train + 148 dev + 364 test sentences
- NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
2023-10-11 12:17:47,461 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,461 Train: 1085 sentences
2023-10-11 12:17:47,461 (train_with_dev=False, train_with_test=False)
2023-10-11 12:17:47,461 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,461 Training Params:
2023-10-11 12:17:47,461 - learning_rate: "0.00016"
2023-10-11 12:17:47,461 - mini_batch_size: "4"
2023-10-11 12:17:47,461 - max_epochs: "10"
2023-10-11 12:17:47,461 - shuffle: "True"
2023-10-11 12:17:47,461 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,461 Plugins:
2023-10-11 12:17:47,461 - TensorboardLogger
2023-10-11 12:17:47,462 - LinearScheduler | warmup_fraction: '0.1'
2023-10-11 12:17:47,462 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,462 Final evaluation on model from best epoch (best-model.pt)
2023-10-11 12:17:47,462 - metric: "('micro avg', 'f1-score')"
2023-10-11 12:17:47,462 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,462 Computation:
2023-10-11 12:17:47,462 - compute on device: cuda:0
2023-10-11 12:17:47,462 - embedding storage: none
2023-10-11 12:17:47,462 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,462 Model training base path: "hmbench-newseye/sv-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-4"
2023-10-11 12:17:47,462 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,462 ----------------------------------------------------------------------------------------------------
2023-10-11 12:17:47,462 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-11 12:17:57,185 epoch 1 - iter 27/272 - loss 2.83784856 - time (sec): 9.72 - samples/sec: 573.53 - lr: 0.000015 - momentum: 0.000000
2023-10-11 12:18:07,237 epoch 1 - iter 54/272 - loss 2.83077250 - time (sec): 19.77 - samples/sec: 575.99 - lr: 0.000031 - momentum: 0.000000
2023-10-11 12:18:16,704 epoch 1 - iter 81/272 - loss 2.80770322 - time (sec): 29.24 - samples/sec: 570.04 - lr: 0.000047 - momentum: 0.000000
2023-10-11 12:18:25,982 epoch 1 - iter 108/272 - loss 2.75243362 - time (sec): 38.52 - samples/sec: 565.04 - lr: 0.000063 - momentum: 0.000000
2023-10-11 12:18:34,945 epoch 1 - iter 135/272 - loss 2.67455773 - time (sec): 47.48 - samples/sec: 554.80 - lr: 0.000079 - momentum: 0.000000
2023-10-11 12:18:43,921 epoch 1 - iter 162/272 - loss 2.57823913 - time (sec): 56.46 - samples/sec: 550.87 - lr: 0.000095 - momentum: 0.000000
2023-10-11 12:18:52,759 epoch 1 - iter 189/272 - loss 2.47103511 - time (sec): 65.29 - samples/sec: 548.01 - lr: 0.000111 - momentum: 0.000000
2023-10-11 12:19:02,746 epoch 1 - iter 216/272 - loss 2.34565635 - time (sec): 75.28 - samples/sec: 551.99 - lr: 0.000126 - momentum: 0.000000
2023-10-11 12:19:11,733 epoch 1 - iter 243/272 - loss 2.22212358 - time (sec): 84.27 - samples/sec: 552.05 - lr: 0.000142 - momentum: 0.000000
2023-10-11 12:19:20,836 epoch 1 - iter 270/272 - loss 2.09514760 - time (sec): 93.37 - samples/sec: 553.28 - lr: 0.000158 - momentum: 0.000000
2023-10-11 12:19:21,365 ----------------------------------------------------------------------------------------------------
2023-10-11 12:19:21,365 EPOCH 1 done: loss 2.0875 - lr: 0.000158
2023-10-11 12:19:26,097 DEV : loss 0.7258709073066711 - f1-score (micro avg) 0.0
2023-10-11 12:19:26,106 ----------------------------------------------------------------------------------------------------
2023-10-11 12:19:35,428 epoch 2 - iter 27/272 - loss 0.70983607 - time (sec): 9.32 - samples/sec: 573.84 - lr: 0.000158 - momentum: 0.000000
2023-10-11 12:19:44,149 epoch 2 - iter 54/272 - loss 0.68848670 - time (sec): 18.04 - samples/sec: 560.06 - lr: 0.000157 - momentum: 0.000000
2023-10-11 12:19:52,270 epoch 2 - iter 81/272 - loss 0.66075679 - time (sec): 26.16 - samples/sec: 534.87 - lr: 0.000155 - momentum: 0.000000
2023-10-11 12:20:02,359 epoch 2 - iter 108/272 - loss 0.60795335 - time (sec): 36.25 - samples/sec: 557.87 - lr: 0.000153 - momentum: 0.000000
2023-10-11 12:20:11,747 epoch 2 - iter 135/272 - loss 0.58284167 - time (sec): 45.64 - samples/sec: 552.89 - lr: 0.000151 - momentum: 0.000000
2023-10-11 12:20:21,743 epoch 2 - iter 162/272 - loss 0.53477008 - time (sec): 55.63 - samples/sec: 558.84 - lr: 0.000149 - momentum: 0.000000
2023-10-11 12:20:30,560 epoch 2 - iter 189/272 - loss 0.51131648 - time (sec): 64.45 - samples/sec: 549.06 - lr: 0.000148 - momentum: 0.000000
2023-10-11 12:20:39,933 epoch 2 - iter 216/272 - loss 0.48449409 - time (sec): 73.83 - samples/sec: 547.01 - lr: 0.000146 - momentum: 0.000000
2023-10-11 12:20:49,031 epoch 2 - iter 243/272 - loss 0.47029300 - time (sec): 82.92 - samples/sec: 544.63 - lr: 0.000144 - momentum: 0.000000
2023-10-11 12:20:59,571 epoch 2 - iter 270/272 - loss 0.45240623 - time (sec): 93.46 - samples/sec: 554.23 - lr: 0.000142 - momentum: 0.000000
2023-10-11 12:20:59,996 ----------------------------------------------------------------------------------------------------
2023-10-11 12:20:59,996 EPOCH 2 done: loss 0.4521 - lr: 0.000142
2023-10-11 12:21:05,525 DEV : loss 0.27614670991897583 - f1-score (micro avg) 0.3235
2023-10-11 12:21:05,534 saving best model
2023-10-11 12:21:06,411 ----------------------------------------------------------------------------------------------------
2023-10-11 12:21:15,715 epoch 3 - iter 27/272 - loss 0.23309089 - time (sec): 9.30 - samples/sec: 548.35 - lr: 0.000141 - momentum: 0.000000
2023-10-11 12:21:25,472 epoch 3 - iter 54/272 - loss 0.27485890 - time (sec): 19.06 - samples/sec: 567.71 - lr: 0.000139 - momentum: 0.000000
2023-10-11 12:21:34,737 epoch 3 - iter 81/272 - loss 0.27012296 - time (sec): 28.32 - samples/sec: 569.76 - lr: 0.000137 - momentum: 0.000000
2023-10-11 12:21:43,893 epoch 3 - iter 108/272 - loss 0.26806557 - time (sec): 37.48 - samples/sec: 560.35 - lr: 0.000135 - momentum: 0.000000
2023-10-11 12:21:53,166 epoch 3 - iter 135/272 - loss 0.26644863 - time (sec): 46.75 - samples/sec: 560.30 - lr: 0.000133 - momentum: 0.000000
2023-10-11 12:22:02,417 epoch 3 - iter 162/272 - loss 0.27294415 - time (sec): 56.00 - samples/sec: 559.74 - lr: 0.000132 - momentum: 0.000000
2023-10-11 12:22:12,036 epoch 3 - iter 189/272 - loss 0.26862119 - time (sec): 65.62 - samples/sec: 563.37 - lr: 0.000130 - momentum: 0.000000
2023-10-11 12:22:21,344 epoch 3 - iter 216/272 - loss 0.26282089 - time (sec): 74.93 - samples/sec: 559.23 - lr: 0.000128 - momentum: 0.000000
2023-10-11 12:22:30,546 epoch 3 - iter 243/272 - loss 0.26662864 - time (sec): 84.13 - samples/sec: 556.68 - lr: 0.000126 - momentum: 0.000000
2023-10-11 12:22:39,525 epoch 3 - iter 270/272 - loss 0.26058992 - time (sec): 93.11 - samples/sec: 554.85 - lr: 0.000125 - momentum: 0.000000
2023-10-11 12:22:40,069 ----------------------------------------------------------------------------------------------------
2023-10-11 12:22:40,069 EPOCH 3 done: loss 0.2592 - lr: 0.000125
2023-10-11 12:22:45,596 DEV : loss 0.19185124337673187 - f1-score (micro avg) 0.5766
2023-10-11 12:22:45,604 saving best model
2023-10-11 12:22:48,091 ----------------------------------------------------------------------------------------------------
2023-10-11 12:22:57,047 epoch 4 - iter 27/272 - loss 0.17559727 - time (sec): 8.95 - samples/sec: 544.28 - lr: 0.000123 - momentum: 0.000000
2023-10-11 12:23:06,445 epoch 4 - iter 54/272 - loss 0.14763057 - time (sec): 18.35 - samples/sec: 564.09 - lr: 0.000121 - momentum: 0.000000
2023-10-11 12:23:16,156 epoch 4 - iter 81/272 - loss 0.16759112 - time (sec): 28.06 - samples/sec: 578.45 - lr: 0.000119 - momentum: 0.000000
2023-10-11 12:23:25,501 epoch 4 - iter 108/272 - loss 0.16355731 - time (sec): 37.41 - samples/sec: 574.32 - lr: 0.000117 - momentum: 0.000000
2023-10-11 12:23:35,043 epoch 4 - iter 135/272 - loss 0.15538460 - time (sec): 46.95 - samples/sec: 575.87 - lr: 0.000116 - momentum: 0.000000
2023-10-11 12:23:43,666 epoch 4 - iter 162/272 - loss 0.15731211 - time (sec): 55.57 - samples/sec: 567.27 - lr: 0.000114 - momentum: 0.000000
2023-10-11 12:23:53,322 epoch 4 - iter 189/272 - loss 0.15895911 - time (sec): 65.23 - samples/sec: 569.26 - lr: 0.000112 - momentum: 0.000000
2023-10-11 12:24:02,161 epoch 4 - iter 216/272 - loss 0.15623754 - time (sec): 74.07 - samples/sec: 564.59 - lr: 0.000110 - momentum: 0.000000
2023-10-11 12:24:10,962 epoch 4 - iter 243/272 - loss 0.15352344 - time (sec): 82.87 - samples/sec: 560.85 - lr: 0.000109 - momentum: 0.000000
2023-10-11 12:24:20,498 epoch 4 - iter 270/272 - loss 0.15512637 - time (sec): 92.40 - samples/sec: 560.35 - lr: 0.000107 - momentum: 0.000000
2023-10-11 12:24:20,943 ----------------------------------------------------------------------------------------------------
2023-10-11 12:24:20,943 EPOCH 4 done: loss 0.1547 - lr: 0.000107
2023-10-11 12:24:26,384 DEV : loss 0.15080419182777405 - f1-score (micro avg) 0.6617
2023-10-11 12:24:26,392 saving best model
2023-10-11 12:24:28,921 ----------------------------------------------------------------------------------------------------
2023-10-11 12:24:38,560 epoch 5 - iter 27/272 - loss 0.11298860 - time (sec): 9.63 - samples/sec: 581.63 - lr: 0.000105 - momentum: 0.000000
2023-10-11 12:24:47,611 epoch 5 - iter 54/272 - loss 0.11828460 - time (sec): 18.69 - samples/sec: 562.67 - lr: 0.000103 - momentum: 0.000000
2023-10-11 12:24:57,149 epoch 5 - iter 81/272 - loss 0.12324494 - time (sec): 28.22 - samples/sec: 576.89 - lr: 0.000101 - momentum: 0.000000
2023-10-11 12:25:06,969 epoch 5 - iter 108/272 - loss 0.11225919 - time (sec): 38.04 - samples/sec: 581.49 - lr: 0.000100 - momentum: 0.000000
2023-10-11 12:25:15,898 epoch 5 - iter 135/272 - loss 0.10889944 - time (sec): 46.97 - samples/sec: 577.04 - lr: 0.000098 - momentum: 0.000000
2023-10-11 12:25:24,717 epoch 5 - iter 162/272 - loss 0.10759412 - time (sec): 55.79 - samples/sec: 569.39 - lr: 0.000096 - momentum: 0.000000
2023-10-11 12:25:33,490 epoch 5 - iter 189/272 - loss 0.10450328 - time (sec): 64.56 - samples/sec: 563.78 - lr: 0.000094 - momentum: 0.000000
2023-10-11 12:25:42,652 epoch 5 - iter 216/272 - loss 0.10251942 - time (sec): 73.73 - samples/sec: 564.22 - lr: 0.000093 - momentum: 0.000000
2023-10-11 12:25:51,924 epoch 5 - iter 243/272 - loss 0.10536311 - time (sec): 83.00 - samples/sec: 564.83 - lr: 0.000091 - momentum: 0.000000
2023-10-11 12:26:00,818 epoch 5 - iter 270/272 - loss 0.10201182 - time (sec): 91.89 - samples/sec: 561.89 - lr: 0.000089 - momentum: 0.000000
2023-10-11 12:26:01,388 ----------------------------------------------------------------------------------------------------
2023-10-11 12:26:01,388 EPOCH 5 done: loss 0.1023 - lr: 0.000089
2023-10-11 12:26:06,848 DEV : loss 0.1377904713153839 - f1-score (micro avg) 0.6462
2023-10-11 12:26:06,856 ----------------------------------------------------------------------------------------------------
2023-10-11 12:26:16,012 epoch 6 - iter 27/272 - loss 0.06858667 - time (sec): 9.15 - samples/sec: 560.28 - lr: 0.000087 - momentum: 0.000000
2023-10-11 12:26:25,347 epoch 6 - iter 54/272 - loss 0.07270870 - time (sec): 18.49 - samples/sec: 552.38 - lr: 0.000085 - momentum: 0.000000
2023-10-11 12:26:35,819 epoch 6 - iter 81/272 - loss 0.07138524 - time (sec): 28.96 - samples/sec: 571.95 - lr: 0.000084 - momentum: 0.000000
2023-10-11 12:26:44,751 epoch 6 - iter 108/272 - loss 0.07082171 - time (sec): 37.89 - samples/sec: 558.81 - lr: 0.000082 - momentum: 0.000000
2023-10-11 12:26:53,646 epoch 6 - iter 135/272 - loss 0.06942375 - time (sec): 46.79 - samples/sec: 554.10 - lr: 0.000080 - momentum: 0.000000
2023-10-11 12:27:02,878 epoch 6 - iter 162/272 - loss 0.06931374 - time (sec): 56.02 - samples/sec: 555.19 - lr: 0.000078 - momentum: 0.000000
2023-10-11 12:27:11,743 epoch 6 - iter 189/272 - loss 0.07471804 - time (sec): 64.89 - samples/sec: 551.02 - lr: 0.000077 - momentum: 0.000000
2023-10-11 12:27:21,147 epoch 6 - iter 216/272 - loss 0.07358616 - time (sec): 74.29 - samples/sec: 551.36 - lr: 0.000075 - momentum: 0.000000
2023-10-11 12:27:31,007 epoch 6 - iter 243/272 - loss 0.07385375 - time (sec): 84.15 - samples/sec: 554.53 - lr: 0.000073 - momentum: 0.000000
2023-10-11 12:27:40,226 epoch 6 - iter 270/272 - loss 0.07393521 - time (sec): 93.37 - samples/sec: 554.54 - lr: 0.000071 - momentum: 0.000000
2023-10-11 12:27:40,629 ----------------------------------------------------------------------------------------------------
2023-10-11 12:27:40,630 EPOCH 6 done: loss 0.0737 - lr: 0.000071
2023-10-11 12:27:46,135 DEV : loss 0.13831757009029388 - f1-score (micro avg) 0.7681
2023-10-11 12:27:46,142 saving best model
2023-10-11 12:27:48,649 ----------------------------------------------------------------------------------------------------
2023-10-11 12:27:57,510 epoch 7 - iter 27/272 - loss 0.05129014 - time (sec): 8.86 - samples/sec: 549.17 - lr: 0.000069 - momentum: 0.000000
2023-10-11 12:28:06,049 epoch 7 - iter 54/272 - loss 0.06171732 - time (sec): 17.40 - samples/sec: 535.80 - lr: 0.000068 - momentum: 0.000000
2023-10-11 12:28:14,620 epoch 7 - iter 81/272 - loss 0.05770185 - time (sec): 25.97 - samples/sec: 533.83 - lr: 0.000066 - momentum: 0.000000
2023-10-11 12:28:23,980 epoch 7 - iter 108/272 - loss 0.05578072 - time (sec): 35.33 - samples/sec: 540.64 - lr: 0.000064 - momentum: 0.000000
2023-10-11 12:28:33,686 epoch 7 - iter 135/272 - loss 0.05183090 - time (sec): 45.03 - samples/sec: 548.95 - lr: 0.000062 - momentum: 0.000000
2023-10-11 12:28:43,514 epoch 7 - iter 162/272 - loss 0.05034293 - time (sec): 54.86 - samples/sec: 556.20 - lr: 0.000061 - momentum: 0.000000
2023-10-11 12:28:52,842 epoch 7 - iter 189/272 - loss 0.05522158 - time (sec): 64.19 - samples/sec: 553.57 - lr: 0.000059 - momentum: 0.000000
2023-10-11 12:29:01,292 epoch 7 - iter 216/272 - loss 0.05317533 - time (sec): 72.64 - samples/sec: 547.22 - lr: 0.000057 - momentum: 0.000000
2023-10-11 12:29:11,075 epoch 7 - iter 243/272 - loss 0.05369366 - time (sec): 82.42 - samples/sec: 554.67 - lr: 0.000055 - momentum: 0.000000
2023-10-11 12:29:21,164 epoch 7 - iter 270/272 - loss 0.05345304 - time (sec): 92.51 - samples/sec: 560.18 - lr: 0.000054 - momentum: 0.000000
2023-10-11 12:29:21,547 ----------------------------------------------------------------------------------------------------
2023-10-11 12:29:21,548 EPOCH 7 done: loss 0.0535 - lr: 0.000054
2023-10-11 12:29:27,021 DEV : loss 0.14701178669929504 - f1-score (micro avg) 0.7956
2023-10-11 12:29:27,029 saving best model
2023-10-11 12:29:29,508 ----------------------------------------------------------------------------------------------------
2023-10-11 12:29:38,586 epoch 8 - iter 27/272 - loss 0.02662217 - time (sec): 9.07 - samples/sec: 567.16 - lr: 0.000052 - momentum: 0.000000
2023-10-11 12:29:48,267 epoch 8 - iter 54/272 - loss 0.04238572 - time (sec): 18.76 - samples/sec: 584.96 - lr: 0.000050 - momentum: 0.000000
2023-10-11 12:29:57,482 epoch 8 - iter 81/272 - loss 0.04066595 - time (sec): 27.97 - samples/sec: 578.41 - lr: 0.000048 - momentum: 0.000000
2023-10-11 12:30:06,552 epoch 8 - iter 108/272 - loss 0.03956566 - time (sec): 37.04 - samples/sec: 565.28 - lr: 0.000046 - momentum: 0.000000
2023-10-11 12:30:16,114 epoch 8 - iter 135/272 - loss 0.03767651 - time (sec): 46.60 - samples/sec: 567.35 - lr: 0.000045 - momentum: 0.000000
2023-10-11 12:30:26,166 epoch 8 - iter 162/272 - loss 0.04051798 - time (sec): 56.65 - samples/sec: 577.03 - lr: 0.000043 - momentum: 0.000000
2023-10-11 12:30:34,685 epoch 8 - iter 189/272 - loss 0.04409632 - time (sec): 65.17 - samples/sec: 565.84 - lr: 0.000041 - momentum: 0.000000
2023-10-11 12:30:44,286 epoch 8 - iter 216/272 - loss 0.04433015 - time (sec): 74.77 - samples/sec: 566.86 - lr: 0.000039 - momentum: 0.000000
2023-10-11 12:30:53,159 epoch 8 - iter 243/272 - loss 0.04347717 - time (sec): 83.65 - samples/sec: 563.86 - lr: 0.000038 - momentum: 0.000000
2023-10-11 12:31:02,010 epoch 8 - iter 270/272 - loss 0.04284592 - time (sec): 92.50 - samples/sec: 559.27 - lr: 0.000036 - momentum: 0.000000
2023-10-11 12:31:02,455 ----------------------------------------------------------------------------------------------------
2023-10-11 12:31:02,455 EPOCH 8 done: loss 0.0426 - lr: 0.000036
2023-10-11 12:31:07,906 DEV : loss 0.14679642021656036 - f1-score (micro avg) 0.8015
2023-10-11 12:31:07,914 saving best model
2023-10-11 12:31:10,409 ----------------------------------------------------------------------------------------------------
2023-10-11 12:31:19,316 epoch 9 - iter 27/272 - loss 0.03044480 - time (sec): 8.90 - samples/sec: 549.94 - lr: 0.000034 - momentum: 0.000000
2023-10-11 12:31:27,617 epoch 9 - iter 54/272 - loss 0.04315447 - time (sec): 17.20 - samples/sec: 538.76 - lr: 0.000032 - momentum: 0.000000
2023-10-11 12:31:36,320 epoch 9 - iter 81/272 - loss 0.03877733 - time (sec): 25.91 - samples/sec: 540.85 - lr: 0.000030 - momentum: 0.000000
2023-10-11 12:31:45,762 epoch 9 - iter 108/272 - loss 0.03541826 - time (sec): 35.35 - samples/sec: 553.43 - lr: 0.000029 - momentum: 0.000000
2023-10-11 12:31:55,099 epoch 9 - iter 135/272 - loss 0.03420976 - time (sec): 44.69 - samples/sec: 559.43 - lr: 0.000027 - momentum: 0.000000
2023-10-11 12:32:04,049 epoch 9 - iter 162/272 - loss 0.03216315 - time (sec): 53.64 - samples/sec: 558.43 - lr: 0.000025 - momentum: 0.000000
2023-10-11 12:32:13,330 epoch 9 - iter 189/272 - loss 0.03081178 - time (sec): 62.92 - samples/sec: 558.94 - lr: 0.000023 - momentum: 0.000000
2023-10-11 12:32:23,043 epoch 9 - iter 216/272 - loss 0.03134856 - time (sec): 72.63 - samples/sec: 564.70 - lr: 0.000022 - momentum: 0.000000
2023-10-11 12:32:32,028 epoch 9 - iter 243/272 - loss 0.03443496 - time (sec): 81.61 - samples/sec: 562.97 - lr: 0.000020 - momentum: 0.000000
2023-10-11 12:32:41,604 epoch 9 - iter 270/272 - loss 0.03386938 - time (sec): 91.19 - samples/sec: 567.00 - lr: 0.000018 - momentum: 0.000000
2023-10-11 12:32:42,083 ----------------------------------------------------------------------------------------------------
2023-10-11 12:32:42,083 EPOCH 9 done: loss 0.0337 - lr: 0.000018
2023-10-11 12:32:47,749 DEV : loss 0.149958074092865 - f1-score (micro avg) 0.8096
2023-10-11 12:32:47,757 saving best model
2023-10-11 12:32:50,259 ----------------------------------------------------------------------------------------------------
2023-10-11 12:32:59,526 epoch 10 - iter 27/272 - loss 0.03830851 - time (sec): 9.26 - samples/sec: 576.23 - lr: 0.000016 - momentum: 0.000000
2023-10-11 12:33:08,503 epoch 10 - iter 54/272 - loss 0.03546184 - time (sec): 18.24 - samples/sec: 571.99 - lr: 0.000014 - momentum: 0.000000
2023-10-11 12:33:17,103 epoch 10 - iter 81/272 - loss 0.03145260 - time (sec): 26.84 - samples/sec: 562.54 - lr: 0.000013 - momentum: 0.000000
2023-10-11 12:33:26,206 epoch 10 - iter 108/272 - loss 0.03259123 - time (sec): 35.94 - samples/sec: 557.04 - lr: 0.000011 - momentum: 0.000000
2023-10-11 12:33:36,463 epoch 10 - iter 135/272 - loss 0.02974927 - time (sec): 46.20 - samples/sec: 570.11 - lr: 0.000009 - momentum: 0.000000
2023-10-11 12:33:45,171 epoch 10 - iter 162/272 - loss 0.02889802 - time (sec): 54.91 - samples/sec: 558.86 - lr: 0.000007 - momentum: 0.000000
2023-10-11 12:33:54,983 epoch 10 - iter 189/272 - loss 0.02806859 - time (sec): 64.72 - samples/sec: 559.46 - lr: 0.000005 - momentum: 0.000000
2023-10-11 12:34:04,346 epoch 10 - iter 216/272 - loss 0.02816137 - time (sec): 74.08 - samples/sec: 557.21 - lr: 0.000004 - momentum: 0.000000
2023-10-11 12:34:13,684 epoch 10 - iter 243/272 - loss 0.02889036 - time (sec): 83.42 - samples/sec: 558.00 - lr: 0.000002 - momentum: 0.000000
2023-10-11 12:34:23,246 epoch 10 - iter 270/272 - loss 0.02974897 - time (sec): 92.98 - samples/sec: 556.61 - lr: 0.000000 - momentum: 0.000000
2023-10-11 12:34:23,713 ----------------------------------------------------------------------------------------------------
2023-10-11 12:34:23,713 EPOCH 10 done: loss 0.0297 - lr: 0.000000
2023-10-11 12:34:29,409 DEV : loss 0.15252262353897095 - f1-score (micro avg) 0.8051
2023-10-11 12:34:30,254 ----------------------------------------------------------------------------------------------------
2023-10-11 12:34:30,256 Loading model from best epoch ...
2023-10-11 12:34:34,051 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-11 12:34:46,395
Results:
- F-score (micro) 0.7562
- F-score (macro) 0.6778
- Accuracy 0.6276
By class:
precision recall f1-score support
LOC 0.7437 0.8558 0.7958 312
PER 0.7287 0.8654 0.7912 208
ORG 0.3793 0.4000 0.3894 55
HumanProd 0.6667 0.8182 0.7347 22
micro avg 0.7048 0.8157 0.7562 597
macro avg 0.6296 0.7348 0.6778 597
weighted avg 0.7021 0.8157 0.7545 597
2023-10-11 12:34:46,395 ----------------------------------------------------------------------------------------------------
|