File size: 25,190 Bytes
95b954a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
2023-10-06 22:19:57,613 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,615 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): T5LayerNorm()
(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): T5LayerNorm()
(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): T5LayerNorm()
(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): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(final_layer_norm): T5LayerNorm()
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1472, out_features=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-06 22:19:57,615 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,615 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /app/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-06 22:19:57,615 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,615 Train: 1100 sentences
2023-10-06 22:19:57,615 (train_with_dev=False, train_with_test=False)
2023-10-06 22:19:57,615 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,615 Training Params:
2023-10-06 22:19:57,616 - learning_rate: "0.00016"
2023-10-06 22:19:57,616 - mini_batch_size: "4"
2023-10-06 22:19:57,616 - max_epochs: "10"
2023-10-06 22:19:57,616 - shuffle: "True"
2023-10-06 22:19:57,616 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,616 Plugins:
2023-10-06 22:19:57,616 - TensorboardLogger
2023-10-06 22:19:57,616 - LinearScheduler | warmup_fraction: '0.1'
2023-10-06 22:19:57,616 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,616 Final evaluation on model from best epoch (best-model.pt)
2023-10-06 22:19:57,616 - metric: "('micro avg', 'f1-score')"
2023-10-06 22:19:57,616 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,616 Computation:
2023-10-06 22:19:57,616 - compute on device: cuda:0
2023-10-06 22:19:57,616 - embedding storage: none
2023-10-06 22:19:57,617 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,617 Model training base path: "hmbench-ajmc/de-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-2"
2023-10-06 22:19:57,617 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,617 ----------------------------------------------------------------------------------------------------
2023-10-06 22:19:57,617 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-06 22:20:08,003 epoch 1 - iter 27/275 - loss 3.23046973 - time (sec): 10.38 - samples/sec: 207.90 - lr: 0.000015 - momentum: 0.000000
2023-10-06 22:20:19,207 epoch 1 - iter 54/275 - loss 3.22045630 - time (sec): 21.59 - samples/sec: 207.88 - lr: 0.000031 - momentum: 0.000000
2023-10-06 22:20:30,543 epoch 1 - iter 81/275 - loss 3.20278466 - time (sec): 32.92 - samples/sec: 209.54 - lr: 0.000047 - momentum: 0.000000
2023-10-06 22:20:40,870 epoch 1 - iter 108/275 - loss 3.16363759 - time (sec): 43.25 - samples/sec: 205.15 - lr: 0.000062 - momentum: 0.000000
2023-10-06 22:20:52,093 epoch 1 - iter 135/275 - loss 3.07464330 - time (sec): 54.47 - samples/sec: 205.49 - lr: 0.000078 - momentum: 0.000000
2023-10-06 22:21:01,940 epoch 1 - iter 162/275 - loss 2.98484966 - time (sec): 64.32 - samples/sec: 203.73 - lr: 0.000094 - momentum: 0.000000
2023-10-06 22:21:13,053 epoch 1 - iter 189/275 - loss 2.86837180 - time (sec): 75.43 - samples/sec: 205.24 - lr: 0.000109 - momentum: 0.000000
2023-10-06 22:21:23,565 epoch 1 - iter 216/275 - loss 2.75403892 - time (sec): 85.95 - samples/sec: 205.56 - lr: 0.000125 - momentum: 0.000000
2023-10-06 22:21:34,838 epoch 1 - iter 243/275 - loss 2.61332537 - time (sec): 97.22 - samples/sec: 206.98 - lr: 0.000141 - momentum: 0.000000
2023-10-06 22:21:45,272 epoch 1 - iter 270/275 - loss 2.49139408 - time (sec): 107.65 - samples/sec: 207.32 - lr: 0.000157 - momentum: 0.000000
2023-10-06 22:21:47,401 ----------------------------------------------------------------------------------------------------
2023-10-06 22:21:47,402 EPOCH 1 done: loss 2.4654 - lr: 0.000157
2023-10-06 22:21:53,775 DEV : loss 1.122562289237976 - f1-score (micro avg) 0.0
2023-10-06 22:21:53,781 ----------------------------------------------------------------------------------------------------
2023-10-06 22:22:04,252 epoch 2 - iter 27/275 - loss 1.06316421 - time (sec): 10.47 - samples/sec: 209.84 - lr: 0.000158 - momentum: 0.000000
2023-10-06 22:22:15,114 epoch 2 - iter 54/275 - loss 0.99982815 - time (sec): 21.33 - samples/sec: 210.39 - lr: 0.000157 - momentum: 0.000000
2023-10-06 22:22:25,327 epoch 2 - iter 81/275 - loss 0.95642739 - time (sec): 31.54 - samples/sec: 206.41 - lr: 0.000155 - momentum: 0.000000
2023-10-06 22:22:36,243 epoch 2 - iter 108/275 - loss 0.93981903 - time (sec): 42.46 - samples/sec: 206.47 - lr: 0.000153 - momentum: 0.000000
2023-10-06 22:22:47,493 epoch 2 - iter 135/275 - loss 0.87433260 - time (sec): 53.71 - samples/sec: 207.37 - lr: 0.000151 - momentum: 0.000000
2023-10-06 22:22:58,582 epoch 2 - iter 162/275 - loss 0.82965738 - time (sec): 64.80 - samples/sec: 205.66 - lr: 0.000150 - momentum: 0.000000
2023-10-06 22:23:08,837 epoch 2 - iter 189/275 - loss 0.79093517 - time (sec): 75.05 - samples/sec: 204.31 - lr: 0.000148 - momentum: 0.000000
2023-10-06 22:23:19,870 epoch 2 - iter 216/275 - loss 0.74140812 - time (sec): 86.09 - samples/sec: 204.55 - lr: 0.000146 - momentum: 0.000000
2023-10-06 22:23:30,843 epoch 2 - iter 243/275 - loss 0.70765895 - time (sec): 97.06 - samples/sec: 205.88 - lr: 0.000144 - momentum: 0.000000
2023-10-06 22:23:41,422 epoch 2 - iter 270/275 - loss 0.68311458 - time (sec): 107.64 - samples/sec: 206.89 - lr: 0.000143 - momentum: 0.000000
2023-10-06 22:23:43,598 ----------------------------------------------------------------------------------------------------
2023-10-06 22:23:43,598 EPOCH 2 done: loss 0.6774 - lr: 0.000143
2023-10-06 22:23:50,082 DEV : loss 0.40427157282829285 - f1-score (micro avg) 0.4749
2023-10-06 22:23:50,088 saving best model
2023-10-06 22:23:50,952 ----------------------------------------------------------------------------------------------------
2023-10-06 22:24:01,156 epoch 3 - iter 27/275 - loss 0.38574587 - time (sec): 10.20 - samples/sec: 209.75 - lr: 0.000141 - momentum: 0.000000
2023-10-06 22:24:12,561 epoch 3 - iter 54/275 - loss 0.36307024 - time (sec): 21.61 - samples/sec: 212.24 - lr: 0.000139 - momentum: 0.000000
2023-10-06 22:24:23,860 epoch 3 - iter 81/275 - loss 0.36188610 - time (sec): 32.91 - samples/sec: 210.66 - lr: 0.000137 - momentum: 0.000000
2023-10-06 22:24:34,334 epoch 3 - iter 108/275 - loss 0.34404760 - time (sec): 43.38 - samples/sec: 207.15 - lr: 0.000135 - momentum: 0.000000
2023-10-06 22:24:44,676 epoch 3 - iter 135/275 - loss 0.32394867 - time (sec): 53.72 - samples/sec: 205.00 - lr: 0.000134 - momentum: 0.000000
2023-10-06 22:24:56,051 epoch 3 - iter 162/275 - loss 0.32128496 - time (sec): 65.10 - samples/sec: 206.58 - lr: 0.000132 - momentum: 0.000000
2023-10-06 22:25:07,011 epoch 3 - iter 189/275 - loss 0.31666190 - time (sec): 76.06 - samples/sec: 206.99 - lr: 0.000130 - momentum: 0.000000
2023-10-06 22:25:17,509 epoch 3 - iter 216/275 - loss 0.30596676 - time (sec): 86.56 - samples/sec: 205.75 - lr: 0.000128 - momentum: 0.000000
2023-10-06 22:25:28,963 epoch 3 - iter 243/275 - loss 0.29289012 - time (sec): 98.01 - samples/sec: 206.87 - lr: 0.000127 - momentum: 0.000000
2023-10-06 22:25:39,328 epoch 3 - iter 270/275 - loss 0.28836828 - time (sec): 108.38 - samples/sec: 206.99 - lr: 0.000125 - momentum: 0.000000
2023-10-06 22:25:41,093 ----------------------------------------------------------------------------------------------------
2023-10-06 22:25:41,093 EPOCH 3 done: loss 0.2864 - lr: 0.000125
2023-10-06 22:25:47,636 DEV : loss 0.19967962801456451 - f1-score (micro avg) 0.7842
2023-10-06 22:25:47,642 saving best model
2023-10-06 22:25:48,570 ----------------------------------------------------------------------------------------------------
2023-10-06 22:25:59,737 epoch 4 - iter 27/275 - loss 0.18598406 - time (sec): 11.17 - samples/sec: 212.26 - lr: 0.000123 - momentum: 0.000000
2023-10-06 22:26:10,416 epoch 4 - iter 54/275 - loss 0.17351357 - time (sec): 21.84 - samples/sec: 212.41 - lr: 0.000121 - momentum: 0.000000
2023-10-06 22:26:21,077 epoch 4 - iter 81/275 - loss 0.18311547 - time (sec): 32.51 - samples/sec: 212.45 - lr: 0.000119 - momentum: 0.000000
2023-10-06 22:26:32,048 epoch 4 - iter 108/275 - loss 0.17408439 - time (sec): 43.48 - samples/sec: 212.85 - lr: 0.000118 - momentum: 0.000000
2023-10-06 22:26:42,183 epoch 4 - iter 135/275 - loss 0.17031787 - time (sec): 53.61 - samples/sec: 209.79 - lr: 0.000116 - momentum: 0.000000
2023-10-06 22:26:52,816 epoch 4 - iter 162/275 - loss 0.16848434 - time (sec): 64.24 - samples/sec: 208.98 - lr: 0.000114 - momentum: 0.000000
2023-10-06 22:27:03,836 epoch 4 - iter 189/275 - loss 0.16145777 - time (sec): 75.27 - samples/sec: 208.37 - lr: 0.000112 - momentum: 0.000000
2023-10-06 22:27:14,515 epoch 4 - iter 216/275 - loss 0.15556608 - time (sec): 85.94 - samples/sec: 208.44 - lr: 0.000111 - momentum: 0.000000
2023-10-06 22:27:24,940 epoch 4 - iter 243/275 - loss 0.15447509 - time (sec): 96.37 - samples/sec: 208.45 - lr: 0.000109 - momentum: 0.000000
2023-10-06 22:27:36,076 epoch 4 - iter 270/275 - loss 0.15163452 - time (sec): 107.50 - samples/sec: 208.14 - lr: 0.000107 - momentum: 0.000000
2023-10-06 22:27:38,020 ----------------------------------------------------------------------------------------------------
2023-10-06 22:27:38,020 EPOCH 4 done: loss 0.1501 - lr: 0.000107
2023-10-06 22:27:44,585 DEV : loss 0.1390346884727478 - f1-score (micro avg) 0.8291
2023-10-06 22:27:44,590 saving best model
2023-10-06 22:27:45,511 ----------------------------------------------------------------------------------------------------
2023-10-06 22:27:56,779 epoch 5 - iter 27/275 - loss 0.12408828 - time (sec): 11.27 - samples/sec: 223.95 - lr: 0.000105 - momentum: 0.000000
2023-10-06 22:28:07,327 epoch 5 - iter 54/275 - loss 0.11531775 - time (sec): 21.81 - samples/sec: 212.35 - lr: 0.000103 - momentum: 0.000000
2023-10-06 22:28:18,432 epoch 5 - iter 81/275 - loss 0.10327970 - time (sec): 32.92 - samples/sec: 210.97 - lr: 0.000102 - momentum: 0.000000
2023-10-06 22:28:29,135 epoch 5 - iter 108/275 - loss 0.09930425 - time (sec): 43.62 - samples/sec: 209.99 - lr: 0.000100 - momentum: 0.000000
2023-10-06 22:28:39,069 epoch 5 - iter 135/275 - loss 0.09480377 - time (sec): 53.56 - samples/sec: 206.50 - lr: 0.000098 - momentum: 0.000000
2023-10-06 22:28:50,333 epoch 5 - iter 162/275 - loss 0.08876726 - time (sec): 64.82 - samples/sec: 207.54 - lr: 0.000096 - momentum: 0.000000
2023-10-06 22:29:01,744 epoch 5 - iter 189/275 - loss 0.09497833 - time (sec): 76.23 - samples/sec: 208.37 - lr: 0.000095 - momentum: 0.000000
2023-10-06 22:29:12,196 epoch 5 - iter 216/275 - loss 0.09275557 - time (sec): 86.68 - samples/sec: 206.95 - lr: 0.000093 - momentum: 0.000000
2023-10-06 22:29:22,893 epoch 5 - iter 243/275 - loss 0.09396631 - time (sec): 97.38 - samples/sec: 206.35 - lr: 0.000091 - momentum: 0.000000
2023-10-06 22:29:33,633 epoch 5 - iter 270/275 - loss 0.09534730 - time (sec): 108.12 - samples/sec: 206.59 - lr: 0.000089 - momentum: 0.000000
2023-10-06 22:29:35,734 ----------------------------------------------------------------------------------------------------
2023-10-06 22:29:35,734 EPOCH 5 done: loss 0.0944 - lr: 0.000089
2023-10-06 22:29:42,409 DEV : loss 0.12325194478034973 - f1-score (micro avg) 0.8632
2023-10-06 22:29:42,415 saving best model
2023-10-06 22:29:43,340 ----------------------------------------------------------------------------------------------------
2023-10-06 22:29:54,552 epoch 6 - iter 27/275 - loss 0.05850414 - time (sec): 11.21 - samples/sec: 205.26 - lr: 0.000087 - momentum: 0.000000
2023-10-06 22:30:05,979 epoch 6 - iter 54/275 - loss 0.06612571 - time (sec): 22.64 - samples/sec: 208.69 - lr: 0.000086 - momentum: 0.000000
2023-10-06 22:30:17,098 epoch 6 - iter 81/275 - loss 0.06088849 - time (sec): 33.76 - samples/sec: 210.45 - lr: 0.000084 - momentum: 0.000000
2023-10-06 22:30:28,140 epoch 6 - iter 108/275 - loss 0.06707336 - time (sec): 44.80 - samples/sec: 209.99 - lr: 0.000082 - momentum: 0.000000
2023-10-06 22:30:38,494 epoch 6 - iter 135/275 - loss 0.06978029 - time (sec): 55.15 - samples/sec: 209.21 - lr: 0.000080 - momentum: 0.000000
2023-10-06 22:30:48,317 epoch 6 - iter 162/275 - loss 0.07177387 - time (sec): 64.97 - samples/sec: 207.26 - lr: 0.000079 - momentum: 0.000000
2023-10-06 22:30:59,170 epoch 6 - iter 189/275 - loss 0.06989013 - time (sec): 75.83 - samples/sec: 206.96 - lr: 0.000077 - momentum: 0.000000
2023-10-06 22:31:09,796 epoch 6 - iter 216/275 - loss 0.07138482 - time (sec): 86.45 - samples/sec: 206.94 - lr: 0.000075 - momentum: 0.000000
2023-10-06 22:31:20,268 epoch 6 - iter 243/275 - loss 0.07213276 - time (sec): 96.93 - samples/sec: 206.88 - lr: 0.000073 - momentum: 0.000000
2023-10-06 22:31:31,421 epoch 6 - iter 270/275 - loss 0.07074569 - time (sec): 108.08 - samples/sec: 206.66 - lr: 0.000072 - momentum: 0.000000
2023-10-06 22:31:33,525 ----------------------------------------------------------------------------------------------------
2023-10-06 22:31:33,525 EPOCH 6 done: loss 0.0704 - lr: 0.000072
2023-10-06 22:31:40,161 DEV : loss 0.11782091856002808 - f1-score (micro avg) 0.8678
2023-10-06 22:31:40,167 saving best model
2023-10-06 22:31:41,101 ----------------------------------------------------------------------------------------------------
2023-10-06 22:31:52,232 epoch 7 - iter 27/275 - loss 0.03938381 - time (sec): 11.13 - samples/sec: 217.72 - lr: 0.000070 - momentum: 0.000000
2023-10-06 22:32:03,100 epoch 7 - iter 54/275 - loss 0.05396100 - time (sec): 22.00 - samples/sec: 212.80 - lr: 0.000068 - momentum: 0.000000
2023-10-06 22:32:13,461 epoch 7 - iter 81/275 - loss 0.04534983 - time (sec): 32.36 - samples/sec: 207.33 - lr: 0.000066 - momentum: 0.000000
2023-10-06 22:32:24,012 epoch 7 - iter 108/275 - loss 0.04423814 - time (sec): 42.91 - samples/sec: 205.74 - lr: 0.000064 - momentum: 0.000000
2023-10-06 22:32:34,380 epoch 7 - iter 135/275 - loss 0.04611314 - time (sec): 53.28 - samples/sec: 205.40 - lr: 0.000063 - momentum: 0.000000
2023-10-06 22:32:45,931 epoch 7 - iter 162/275 - loss 0.04893617 - time (sec): 64.83 - samples/sec: 206.47 - lr: 0.000061 - momentum: 0.000000
2023-10-06 22:32:56,333 epoch 7 - iter 189/275 - loss 0.05266054 - time (sec): 75.23 - samples/sec: 205.04 - lr: 0.000059 - momentum: 0.000000
2023-10-06 22:33:06,956 epoch 7 - iter 216/275 - loss 0.05442865 - time (sec): 85.85 - samples/sec: 205.12 - lr: 0.000058 - momentum: 0.000000
2023-10-06 22:33:17,494 epoch 7 - iter 243/275 - loss 0.05907969 - time (sec): 96.39 - samples/sec: 205.58 - lr: 0.000056 - momentum: 0.000000
2023-10-06 22:33:28,918 epoch 7 - iter 270/275 - loss 0.05681461 - time (sec): 107.82 - samples/sec: 206.86 - lr: 0.000054 - momentum: 0.000000
2023-10-06 22:33:31,093 ----------------------------------------------------------------------------------------------------
2023-10-06 22:33:31,093 EPOCH 7 done: loss 0.0578 - lr: 0.000054
2023-10-06 22:33:37,713 DEV : loss 0.11987826228141785 - f1-score (micro avg) 0.882
2023-10-06 22:33:37,719 saving best model
2023-10-06 22:33:38,646 ----------------------------------------------------------------------------------------------------
2023-10-06 22:33:49,334 epoch 8 - iter 27/275 - loss 0.03329545 - time (sec): 10.69 - samples/sec: 201.75 - lr: 0.000052 - momentum: 0.000000
2023-10-06 22:33:59,757 epoch 8 - iter 54/275 - loss 0.04592979 - time (sec): 21.11 - samples/sec: 204.50 - lr: 0.000050 - momentum: 0.000000
2023-10-06 22:34:10,984 epoch 8 - iter 81/275 - loss 0.05586859 - time (sec): 32.34 - samples/sec: 207.82 - lr: 0.000048 - momentum: 0.000000
2023-10-06 22:34:22,267 epoch 8 - iter 108/275 - loss 0.05455353 - time (sec): 43.62 - samples/sec: 208.92 - lr: 0.000047 - momentum: 0.000000
2023-10-06 22:34:33,165 epoch 8 - iter 135/275 - loss 0.04841264 - time (sec): 54.52 - samples/sec: 209.27 - lr: 0.000045 - momentum: 0.000000
2023-10-06 22:34:43,597 epoch 8 - iter 162/275 - loss 0.04875369 - time (sec): 64.95 - samples/sec: 208.67 - lr: 0.000043 - momentum: 0.000000
2023-10-06 22:34:54,186 epoch 8 - iter 189/275 - loss 0.04671139 - time (sec): 75.54 - samples/sec: 207.58 - lr: 0.000042 - momentum: 0.000000
2023-10-06 22:35:05,512 epoch 8 - iter 216/275 - loss 0.04691085 - time (sec): 86.86 - samples/sec: 208.67 - lr: 0.000040 - momentum: 0.000000
2023-10-06 22:35:15,731 epoch 8 - iter 243/275 - loss 0.04408575 - time (sec): 97.08 - samples/sec: 206.68 - lr: 0.000038 - momentum: 0.000000
2023-10-06 22:35:26,627 epoch 8 - iter 270/275 - loss 0.04172358 - time (sec): 107.98 - samples/sec: 206.96 - lr: 0.000036 - momentum: 0.000000
2023-10-06 22:35:28,725 ----------------------------------------------------------------------------------------------------
2023-10-06 22:35:28,725 EPOCH 8 done: loss 0.0429 - lr: 0.000036
2023-10-06 22:35:35,343 DEV : loss 0.12027797102928162 - f1-score (micro avg) 0.8854
2023-10-06 22:35:35,349 saving best model
2023-10-06 22:35:36,284 ----------------------------------------------------------------------------------------------------
2023-10-06 22:35:46,952 epoch 9 - iter 27/275 - loss 0.04986711 - time (sec): 10.67 - samples/sec: 215.71 - lr: 0.000034 - momentum: 0.000000
2023-10-06 22:35:58,646 epoch 9 - iter 54/275 - loss 0.03493711 - time (sec): 22.36 - samples/sec: 215.55 - lr: 0.000032 - momentum: 0.000000
2023-10-06 22:36:08,815 epoch 9 - iter 81/275 - loss 0.03697438 - time (sec): 32.53 - samples/sec: 207.97 - lr: 0.000031 - momentum: 0.000000
2023-10-06 22:36:19,397 epoch 9 - iter 108/275 - loss 0.03623976 - time (sec): 43.11 - samples/sec: 206.28 - lr: 0.000029 - momentum: 0.000000
2023-10-06 22:36:30,579 epoch 9 - iter 135/275 - loss 0.03334176 - time (sec): 54.29 - samples/sec: 207.21 - lr: 0.000027 - momentum: 0.000000
2023-10-06 22:36:41,808 epoch 9 - iter 162/275 - loss 0.03063102 - time (sec): 65.52 - samples/sec: 208.74 - lr: 0.000026 - momentum: 0.000000
2023-10-06 22:36:52,183 epoch 9 - iter 189/275 - loss 0.02832208 - time (sec): 75.90 - samples/sec: 207.31 - lr: 0.000024 - momentum: 0.000000
2023-10-06 22:37:02,502 epoch 9 - iter 216/275 - loss 0.03178635 - time (sec): 86.22 - samples/sec: 206.19 - lr: 0.000022 - momentum: 0.000000
2023-10-06 22:37:12,629 epoch 9 - iter 243/275 - loss 0.03567592 - time (sec): 96.34 - samples/sec: 206.17 - lr: 0.000020 - momentum: 0.000000
2023-10-06 22:37:24,066 epoch 9 - iter 270/275 - loss 0.03589895 - time (sec): 107.78 - samples/sec: 206.74 - lr: 0.000019 - momentum: 0.000000
2023-10-06 22:37:26,287 ----------------------------------------------------------------------------------------------------
2023-10-06 22:37:26,287 EPOCH 9 done: loss 0.0402 - lr: 0.000019
2023-10-06 22:37:32,922 DEV : loss 0.12215113639831543 - f1-score (micro avg) 0.8852
2023-10-06 22:37:32,928 ----------------------------------------------------------------------------------------------------
2023-10-06 22:37:43,513 epoch 10 - iter 27/275 - loss 0.03017664 - time (sec): 10.58 - samples/sec: 207.01 - lr: 0.000017 - momentum: 0.000000
2023-10-06 22:37:54,245 epoch 10 - iter 54/275 - loss 0.03648685 - time (sec): 21.32 - samples/sec: 208.34 - lr: 0.000015 - momentum: 0.000000
2023-10-06 22:38:04,499 epoch 10 - iter 81/275 - loss 0.03264491 - time (sec): 31.57 - samples/sec: 204.69 - lr: 0.000013 - momentum: 0.000000
2023-10-06 22:38:15,205 epoch 10 - iter 108/275 - loss 0.03814732 - time (sec): 42.28 - samples/sec: 203.19 - lr: 0.000011 - momentum: 0.000000
2023-10-06 22:38:27,605 epoch 10 - iter 135/275 - loss 0.04002682 - time (sec): 54.68 - samples/sec: 205.45 - lr: 0.000010 - momentum: 0.000000
2023-10-06 22:38:37,681 epoch 10 - iter 162/275 - loss 0.04109835 - time (sec): 64.75 - samples/sec: 205.91 - lr: 0.000008 - momentum: 0.000000
2023-10-06 22:38:48,711 epoch 10 - iter 189/275 - loss 0.03880280 - time (sec): 75.78 - samples/sec: 206.50 - lr: 0.000006 - momentum: 0.000000
2023-10-06 22:38:59,906 epoch 10 - iter 216/275 - loss 0.03568743 - time (sec): 86.98 - samples/sec: 207.39 - lr: 0.000004 - momentum: 0.000000
2023-10-06 22:39:10,843 epoch 10 - iter 243/275 - loss 0.03599762 - time (sec): 97.91 - samples/sec: 207.55 - lr: 0.000003 - momentum: 0.000000
2023-10-06 22:39:21,179 epoch 10 - iter 270/275 - loss 0.03470141 - time (sec): 108.25 - samples/sec: 206.87 - lr: 0.000001 - momentum: 0.000000
2023-10-06 22:39:22,963 ----------------------------------------------------------------------------------------------------
2023-10-06 22:39:22,963 EPOCH 10 done: loss 0.0351 - lr: 0.000001
2023-10-06 22:39:29,572 DEV : loss 0.12222656607627869 - f1-score (micro avg) 0.8913
2023-10-06 22:39:29,578 saving best model
2023-10-06 22:39:31,470 ----------------------------------------------------------------------------------------------------
2023-10-06 22:39:31,472 Loading model from best epoch ...
2023-10-06 22:39:34,130 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
2023-10-06 22:39:41,345
Results:
- F-score (micro) 0.8903
- F-score (macro) 0.7282
- Accuracy 0.8175
By class:
precision recall f1-score support
scope 0.8798 0.9148 0.8969 176
pers 0.9302 0.9375 0.9339 128
work 0.7848 0.8378 0.8105 74
loc 1.0000 1.0000 1.0000 2
object 0.0000 0.0000 0.0000 2
micro avg 0.8779 0.9031 0.8903 382
macro avg 0.7190 0.7380 0.7282 382
weighted avg 0.8743 0.9031 0.8884 382
2023-10-06 22:39:41,346 ----------------------------------------------------------------------------------------------------
|