File size: 25,071 Bytes
c19f791 |
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 |
2023-10-06 09:33:07,210 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,211 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 09:33:07,211 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,212 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /app/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-06 09:33:07,212 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,212 Train: 1214 sentences
2023-10-06 09:33:07,212 (train_with_dev=False, train_with_test=False)
2023-10-06 09:33:07,212 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,212 Training Params:
2023-10-06 09:33:07,212 - learning_rate: "0.00015"
2023-10-06 09:33:07,212 - mini_batch_size: "4"
2023-10-06 09:33:07,212 - max_epochs: "10"
2023-10-06 09:33:07,212 - shuffle: "True"
2023-10-06 09:33:07,212 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,212 Plugins:
2023-10-06 09:33:07,212 - TensorboardLogger
2023-10-06 09:33:07,212 - LinearScheduler | warmup_fraction: '0.1'
2023-10-06 09:33:07,213 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,213 Final evaluation on model from best epoch (best-model.pt)
2023-10-06 09:33:07,213 - metric: "('micro avg', 'f1-score')"
2023-10-06 09:33:07,213 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,213 Computation:
2023-10-06 09:33:07,213 - compute on device: cuda:0
2023-10-06 09:33:07,213 - embedding storage: none
2023-10-06 09:33:07,213 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,213 Model training base path: "hmbench-ajmc/en-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-1"
2023-10-06 09:33:07,213 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,213 ----------------------------------------------------------------------------------------------------
2023-10-06 09:33:07,213 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-06 09:33:19,861 epoch 1 - iter 30/304 - loss 3.22766358 - time (sec): 12.65 - samples/sec: 271.61 - lr: 0.000014 - momentum: 0.000000
2023-10-06 09:33:31,567 epoch 1 - iter 60/304 - loss 3.22012864 - time (sec): 24.35 - samples/sec: 276.84 - lr: 0.000029 - momentum: 0.000000
2023-10-06 09:33:42,884 epoch 1 - iter 90/304 - loss 3.20085054 - time (sec): 35.67 - samples/sec: 273.01 - lr: 0.000044 - momentum: 0.000000
2023-10-06 09:33:54,515 epoch 1 - iter 120/304 - loss 3.14263082 - time (sec): 47.30 - samples/sec: 270.00 - lr: 0.000059 - momentum: 0.000000
2023-10-06 09:34:05,414 epoch 1 - iter 150/304 - loss 3.05331139 - time (sec): 58.20 - samples/sec: 266.99 - lr: 0.000074 - momentum: 0.000000
2023-10-06 09:34:16,292 epoch 1 - iter 180/304 - loss 2.94790558 - time (sec): 69.08 - samples/sec: 263.78 - lr: 0.000088 - momentum: 0.000000
2023-10-06 09:34:27,228 epoch 1 - iter 210/304 - loss 2.82602180 - time (sec): 80.01 - samples/sec: 263.91 - lr: 0.000103 - momentum: 0.000000
2023-10-06 09:34:38,522 epoch 1 - iter 240/304 - loss 2.69128752 - time (sec): 91.31 - samples/sec: 264.00 - lr: 0.000118 - momentum: 0.000000
2023-10-06 09:34:50,143 epoch 1 - iter 270/304 - loss 2.54261090 - time (sec): 102.93 - samples/sec: 264.22 - lr: 0.000133 - momentum: 0.000000
2023-10-06 09:35:02,345 epoch 1 - iter 300/304 - loss 2.37796888 - time (sec): 115.13 - samples/sec: 266.62 - lr: 0.000148 - momentum: 0.000000
2023-10-06 09:35:03,599 ----------------------------------------------------------------------------------------------------
2023-10-06 09:35:03,599 EPOCH 1 done: loss 2.3652 - lr: 0.000148
2023-10-06 09:35:10,578 DEV : loss 0.9551804661750793 - f1-score (micro avg) 0.0
2023-10-06 09:35:10,585 ----------------------------------------------------------------------------------------------------
2023-10-06 09:35:21,807 epoch 2 - iter 30/304 - loss 0.86415668 - time (sec): 11.22 - samples/sec: 273.96 - lr: 0.000148 - momentum: 0.000000
2023-10-06 09:35:32,980 epoch 2 - iter 60/304 - loss 0.79412008 - time (sec): 22.39 - samples/sec: 269.71 - lr: 0.000147 - momentum: 0.000000
2023-10-06 09:35:44,119 epoch 2 - iter 90/304 - loss 0.75532736 - time (sec): 33.53 - samples/sec: 271.17 - lr: 0.000145 - momentum: 0.000000
2023-10-06 09:35:55,846 epoch 2 - iter 120/304 - loss 0.71453981 - time (sec): 45.26 - samples/sec: 277.06 - lr: 0.000143 - momentum: 0.000000
2023-10-06 09:36:06,578 epoch 2 - iter 150/304 - loss 0.67298181 - time (sec): 55.99 - samples/sec: 273.81 - lr: 0.000142 - momentum: 0.000000
2023-10-06 09:36:18,095 epoch 2 - iter 180/304 - loss 0.61760988 - time (sec): 67.51 - samples/sec: 272.95 - lr: 0.000140 - momentum: 0.000000
2023-10-06 09:36:29,144 epoch 2 - iter 210/304 - loss 0.57288512 - time (sec): 78.56 - samples/sec: 271.86 - lr: 0.000139 - momentum: 0.000000
2023-10-06 09:36:40,832 epoch 2 - iter 240/304 - loss 0.54254596 - time (sec): 90.25 - samples/sec: 272.07 - lr: 0.000137 - momentum: 0.000000
2023-10-06 09:36:52,311 epoch 2 - iter 270/304 - loss 0.52576467 - time (sec): 101.72 - samples/sec: 272.27 - lr: 0.000135 - momentum: 0.000000
2023-10-06 09:37:03,212 epoch 2 - iter 300/304 - loss 0.50613131 - time (sec): 112.63 - samples/sec: 272.01 - lr: 0.000134 - momentum: 0.000000
2023-10-06 09:37:04,590 ----------------------------------------------------------------------------------------------------
2023-10-06 09:37:04,591 EPOCH 2 done: loss 0.5027 - lr: 0.000134
2023-10-06 09:37:11,780 DEV : loss 0.336232990026474 - f1-score (micro avg) 0.4566
2023-10-06 09:37:11,786 saving best model
2023-10-06 09:37:12,630 ----------------------------------------------------------------------------------------------------
2023-10-06 09:37:24,235 epoch 3 - iter 30/304 - loss 0.27444457 - time (sec): 11.60 - samples/sec: 275.76 - lr: 0.000132 - momentum: 0.000000
2023-10-06 09:37:35,928 epoch 3 - iter 60/304 - loss 0.24449914 - time (sec): 23.30 - samples/sec: 274.76 - lr: 0.000130 - momentum: 0.000000
2023-10-06 09:37:46,610 epoch 3 - iter 90/304 - loss 0.23302935 - time (sec): 33.98 - samples/sec: 269.99 - lr: 0.000128 - momentum: 0.000000
2023-10-06 09:37:58,323 epoch 3 - iter 120/304 - loss 0.24260854 - time (sec): 45.69 - samples/sec: 272.43 - lr: 0.000127 - momentum: 0.000000
2023-10-06 09:38:09,376 epoch 3 - iter 150/304 - loss 0.23802862 - time (sec): 56.74 - samples/sec: 269.66 - lr: 0.000125 - momentum: 0.000000
2023-10-06 09:38:20,841 epoch 3 - iter 180/304 - loss 0.23624670 - time (sec): 68.21 - samples/sec: 268.46 - lr: 0.000124 - momentum: 0.000000
2023-10-06 09:38:32,446 epoch 3 - iter 210/304 - loss 0.22902235 - time (sec): 79.82 - samples/sec: 268.91 - lr: 0.000122 - momentum: 0.000000
2023-10-06 09:38:44,578 epoch 3 - iter 240/304 - loss 0.22095367 - time (sec): 91.95 - samples/sec: 269.35 - lr: 0.000120 - momentum: 0.000000
2023-10-06 09:38:56,045 epoch 3 - iter 270/304 - loss 0.21731013 - time (sec): 103.41 - samples/sec: 267.61 - lr: 0.000119 - momentum: 0.000000
2023-10-06 09:39:07,381 epoch 3 - iter 300/304 - loss 0.21213132 - time (sec): 114.75 - samples/sec: 266.34 - lr: 0.000117 - momentum: 0.000000
2023-10-06 09:39:08,861 ----------------------------------------------------------------------------------------------------
2023-10-06 09:39:08,861 EPOCH 3 done: loss 0.2102 - lr: 0.000117
2023-10-06 09:39:16,617 DEV : loss 0.1942567229270935 - f1-score (micro avg) 0.684
2023-10-06 09:39:16,624 saving best model
2023-10-06 09:39:20,969 ----------------------------------------------------------------------------------------------------
2023-10-06 09:39:32,511 epoch 4 - iter 30/304 - loss 0.13635077 - time (sec): 11.54 - samples/sec: 263.69 - lr: 0.000115 - momentum: 0.000000
2023-10-06 09:39:44,587 epoch 4 - iter 60/304 - loss 0.14753714 - time (sec): 23.62 - samples/sec: 257.20 - lr: 0.000113 - momentum: 0.000000
2023-10-06 09:39:56,161 epoch 4 - iter 90/304 - loss 0.14352309 - time (sec): 35.19 - samples/sec: 255.70 - lr: 0.000112 - momentum: 0.000000
2023-10-06 09:40:08,129 epoch 4 - iter 120/304 - loss 0.13477672 - time (sec): 47.16 - samples/sec: 255.35 - lr: 0.000110 - momentum: 0.000000
2023-10-06 09:40:21,195 epoch 4 - iter 150/304 - loss 0.13442818 - time (sec): 60.22 - samples/sec: 258.25 - lr: 0.000109 - momentum: 0.000000
2023-10-06 09:40:33,220 epoch 4 - iter 180/304 - loss 0.12831180 - time (sec): 72.25 - samples/sec: 256.75 - lr: 0.000107 - momentum: 0.000000
2023-10-06 09:40:44,736 epoch 4 - iter 210/304 - loss 0.12277323 - time (sec): 83.77 - samples/sec: 256.22 - lr: 0.000105 - momentum: 0.000000
2023-10-06 09:40:57,033 epoch 4 - iter 240/304 - loss 0.11777950 - time (sec): 96.06 - samples/sec: 256.02 - lr: 0.000104 - momentum: 0.000000
2023-10-06 09:41:08,651 epoch 4 - iter 270/304 - loss 0.11516771 - time (sec): 107.68 - samples/sec: 256.26 - lr: 0.000102 - momentum: 0.000000
2023-10-06 09:41:20,678 epoch 4 - iter 300/304 - loss 0.11601501 - time (sec): 119.71 - samples/sec: 256.38 - lr: 0.000100 - momentum: 0.000000
2023-10-06 09:41:21,943 ----------------------------------------------------------------------------------------------------
2023-10-06 09:41:21,944 EPOCH 4 done: loss 0.1155 - lr: 0.000100
2023-10-06 09:41:29,842 DEV : loss 0.14497919380664825 - f1-score (micro avg) 0.8184
2023-10-06 09:41:29,848 saving best model
2023-10-06 09:41:34,770 ----------------------------------------------------------------------------------------------------
2023-10-06 09:41:46,883 epoch 5 - iter 30/304 - loss 0.07533132 - time (sec): 12.11 - samples/sec: 264.53 - lr: 0.000098 - momentum: 0.000000
2023-10-06 09:41:59,065 epoch 5 - iter 60/304 - loss 0.06755720 - time (sec): 24.29 - samples/sec: 258.18 - lr: 0.000097 - momentum: 0.000000
2023-10-06 09:42:10,872 epoch 5 - iter 90/304 - loss 0.07841830 - time (sec): 36.10 - samples/sec: 257.51 - lr: 0.000095 - momentum: 0.000000
2023-10-06 09:42:22,235 epoch 5 - iter 120/304 - loss 0.07172348 - time (sec): 47.46 - samples/sec: 258.53 - lr: 0.000094 - momentum: 0.000000
2023-10-06 09:42:33,384 epoch 5 - iter 150/304 - loss 0.07184241 - time (sec): 58.61 - samples/sec: 255.31 - lr: 0.000092 - momentum: 0.000000
2023-10-06 09:42:46,240 epoch 5 - iter 180/304 - loss 0.07656051 - time (sec): 71.47 - samples/sec: 257.87 - lr: 0.000090 - momentum: 0.000000
2023-10-06 09:42:57,906 epoch 5 - iter 210/304 - loss 0.07829839 - time (sec): 83.13 - samples/sec: 257.09 - lr: 0.000089 - momentum: 0.000000
2023-10-06 09:43:10,505 epoch 5 - iter 240/304 - loss 0.07561320 - time (sec): 95.73 - samples/sec: 257.15 - lr: 0.000087 - momentum: 0.000000
2023-10-06 09:43:22,497 epoch 5 - iter 270/304 - loss 0.07540018 - time (sec): 107.73 - samples/sec: 257.44 - lr: 0.000085 - momentum: 0.000000
2023-10-06 09:43:34,347 epoch 5 - iter 300/304 - loss 0.07275885 - time (sec): 119.58 - samples/sec: 257.18 - lr: 0.000084 - momentum: 0.000000
2023-10-06 09:43:35,554 ----------------------------------------------------------------------------------------------------
2023-10-06 09:43:35,554 EPOCH 5 done: loss 0.0728 - lr: 0.000084
2023-10-06 09:43:43,495 DEV : loss 0.1400863230228424 - f1-score (micro avg) 0.7981
2023-10-06 09:43:43,502 ----------------------------------------------------------------------------------------------------
2023-10-06 09:43:55,497 epoch 6 - iter 30/304 - loss 0.04585316 - time (sec): 11.99 - samples/sec: 259.63 - lr: 0.000082 - momentum: 0.000000
2023-10-06 09:44:06,879 epoch 6 - iter 60/304 - loss 0.06461409 - time (sec): 23.38 - samples/sec: 253.81 - lr: 0.000080 - momentum: 0.000000
2023-10-06 09:44:18,966 epoch 6 - iter 90/304 - loss 0.05834725 - time (sec): 35.46 - samples/sec: 256.47 - lr: 0.000079 - momentum: 0.000000
2023-10-06 09:44:31,065 epoch 6 - iter 120/304 - loss 0.04840357 - time (sec): 47.56 - samples/sec: 256.09 - lr: 0.000077 - momentum: 0.000000
2023-10-06 09:44:43,410 epoch 6 - iter 150/304 - loss 0.05688001 - time (sec): 59.91 - samples/sec: 257.43 - lr: 0.000075 - momentum: 0.000000
2023-10-06 09:44:55,075 epoch 6 - iter 180/304 - loss 0.05438671 - time (sec): 71.57 - samples/sec: 257.81 - lr: 0.000074 - momentum: 0.000000
2023-10-06 09:45:06,970 epoch 6 - iter 210/304 - loss 0.05257578 - time (sec): 83.47 - samples/sec: 256.52 - lr: 0.000072 - momentum: 0.000000
2023-10-06 09:45:19,008 epoch 6 - iter 240/304 - loss 0.05521499 - time (sec): 95.51 - samples/sec: 256.46 - lr: 0.000070 - momentum: 0.000000
2023-10-06 09:45:31,506 epoch 6 - iter 270/304 - loss 0.05493219 - time (sec): 108.00 - samples/sec: 256.53 - lr: 0.000069 - momentum: 0.000000
2023-10-06 09:45:42,977 epoch 6 - iter 300/304 - loss 0.05347444 - time (sec): 119.47 - samples/sec: 255.83 - lr: 0.000067 - momentum: 0.000000
2023-10-06 09:45:44,574 ----------------------------------------------------------------------------------------------------
2023-10-06 09:45:44,574 EPOCH 6 done: loss 0.0537 - lr: 0.000067
2023-10-06 09:45:52,648 DEV : loss 0.14857152104377747 - f1-score (micro avg) 0.823
2023-10-06 09:45:52,656 saving best model
2023-10-06 09:45:56,996 ----------------------------------------------------------------------------------------------------
2023-10-06 09:46:08,578 epoch 7 - iter 30/304 - loss 0.04428307 - time (sec): 11.58 - samples/sec: 243.26 - lr: 0.000065 - momentum: 0.000000
2023-10-06 09:46:20,534 epoch 7 - iter 60/304 - loss 0.05221050 - time (sec): 23.54 - samples/sec: 252.04 - lr: 0.000063 - momentum: 0.000000
2023-10-06 09:46:32,177 epoch 7 - iter 90/304 - loss 0.05961108 - time (sec): 35.18 - samples/sec: 257.88 - lr: 0.000062 - momentum: 0.000000
2023-10-06 09:46:44,071 epoch 7 - iter 120/304 - loss 0.04768490 - time (sec): 47.07 - samples/sec: 263.19 - lr: 0.000060 - momentum: 0.000000
2023-10-06 09:46:55,690 epoch 7 - iter 150/304 - loss 0.04749052 - time (sec): 58.69 - samples/sec: 264.38 - lr: 0.000059 - momentum: 0.000000
2023-10-06 09:47:06,699 epoch 7 - iter 180/304 - loss 0.04432266 - time (sec): 69.70 - samples/sec: 264.99 - lr: 0.000057 - momentum: 0.000000
2023-10-06 09:47:17,366 epoch 7 - iter 210/304 - loss 0.04492047 - time (sec): 80.37 - samples/sec: 265.24 - lr: 0.000055 - momentum: 0.000000
2023-10-06 09:47:29,083 epoch 7 - iter 240/304 - loss 0.04349912 - time (sec): 92.09 - samples/sec: 265.98 - lr: 0.000054 - momentum: 0.000000
2023-10-06 09:47:40,202 epoch 7 - iter 270/304 - loss 0.04444322 - time (sec): 103.20 - samples/sec: 266.32 - lr: 0.000052 - momentum: 0.000000
2023-10-06 09:47:51,727 epoch 7 - iter 300/304 - loss 0.04167686 - time (sec): 114.73 - samples/sec: 267.47 - lr: 0.000050 - momentum: 0.000000
2023-10-06 09:47:53,021 ----------------------------------------------------------------------------------------------------
2023-10-06 09:47:53,021 EPOCH 7 done: loss 0.0426 - lr: 0.000050
2023-10-06 09:48:00,126 DEV : loss 0.15859530866146088 - f1-score (micro avg) 0.8376
2023-10-06 09:48:00,134 saving best model
2023-10-06 09:48:04,493 ----------------------------------------------------------------------------------------------------
2023-10-06 09:48:16,338 epoch 8 - iter 30/304 - loss 0.01337046 - time (sec): 11.84 - samples/sec: 281.50 - lr: 0.000048 - momentum: 0.000000
2023-10-06 09:48:27,675 epoch 8 - iter 60/304 - loss 0.02525395 - time (sec): 23.18 - samples/sec: 278.94 - lr: 0.000047 - momentum: 0.000000
2023-10-06 09:48:38,830 epoch 8 - iter 90/304 - loss 0.02209827 - time (sec): 34.34 - samples/sec: 275.08 - lr: 0.000045 - momentum: 0.000000
2023-10-06 09:48:49,856 epoch 8 - iter 120/304 - loss 0.03001053 - time (sec): 45.36 - samples/sec: 272.50 - lr: 0.000044 - momentum: 0.000000
2023-10-06 09:49:01,008 epoch 8 - iter 150/304 - loss 0.02753470 - time (sec): 56.51 - samples/sec: 271.60 - lr: 0.000042 - momentum: 0.000000
2023-10-06 09:49:12,780 epoch 8 - iter 180/304 - loss 0.03272986 - time (sec): 68.29 - samples/sec: 272.72 - lr: 0.000040 - momentum: 0.000000
2023-10-06 09:49:22,913 epoch 8 - iter 210/304 - loss 0.03349853 - time (sec): 78.42 - samples/sec: 269.93 - lr: 0.000039 - momentum: 0.000000
2023-10-06 09:49:34,471 epoch 8 - iter 240/304 - loss 0.03256324 - time (sec): 89.98 - samples/sec: 270.19 - lr: 0.000037 - momentum: 0.000000
2023-10-06 09:49:45,988 epoch 8 - iter 270/304 - loss 0.03226168 - time (sec): 101.49 - samples/sec: 270.76 - lr: 0.000035 - momentum: 0.000000
2023-10-06 09:49:57,494 epoch 8 - iter 300/304 - loss 0.03460514 - time (sec): 113.00 - samples/sec: 271.13 - lr: 0.000034 - momentum: 0.000000
2023-10-06 09:49:58,898 ----------------------------------------------------------------------------------------------------
2023-10-06 09:49:58,898 EPOCH 8 done: loss 0.0342 - lr: 0.000034
2023-10-06 09:50:06,091 DEV : loss 0.16549013555049896 - f1-score (micro avg) 0.8233
2023-10-06 09:50:06,099 ----------------------------------------------------------------------------------------------------
2023-10-06 09:50:17,416 epoch 9 - iter 30/304 - loss 0.03607490 - time (sec): 11.32 - samples/sec: 270.33 - lr: 0.000032 - momentum: 0.000000
2023-10-06 09:50:28,950 epoch 9 - iter 60/304 - loss 0.03611696 - time (sec): 22.85 - samples/sec: 271.38 - lr: 0.000030 - momentum: 0.000000
2023-10-06 09:50:40,327 epoch 9 - iter 90/304 - loss 0.03683352 - time (sec): 34.23 - samples/sec: 270.37 - lr: 0.000029 - momentum: 0.000000
2023-10-06 09:50:51,690 epoch 9 - iter 120/304 - loss 0.03545349 - time (sec): 45.59 - samples/sec: 272.34 - lr: 0.000027 - momentum: 0.000000
2023-10-06 09:51:02,237 epoch 9 - iter 150/304 - loss 0.03053773 - time (sec): 56.14 - samples/sec: 269.86 - lr: 0.000025 - momentum: 0.000000
2023-10-06 09:51:13,637 epoch 9 - iter 180/304 - loss 0.03153764 - time (sec): 67.54 - samples/sec: 271.24 - lr: 0.000024 - momentum: 0.000000
2023-10-06 09:51:24,593 epoch 9 - iter 210/304 - loss 0.02897687 - time (sec): 78.49 - samples/sec: 271.56 - lr: 0.000022 - momentum: 0.000000
2023-10-06 09:51:36,029 epoch 9 - iter 240/304 - loss 0.02913720 - time (sec): 89.93 - samples/sec: 271.78 - lr: 0.000020 - momentum: 0.000000
2023-10-06 09:51:47,224 epoch 9 - iter 270/304 - loss 0.03177374 - time (sec): 101.12 - samples/sec: 271.57 - lr: 0.000019 - momentum: 0.000000
2023-10-06 09:51:58,879 epoch 9 - iter 300/304 - loss 0.02970036 - time (sec): 112.78 - samples/sec: 271.13 - lr: 0.000017 - momentum: 0.000000
2023-10-06 09:52:00,344 ----------------------------------------------------------------------------------------------------
2023-10-06 09:52:00,344 EPOCH 9 done: loss 0.0293 - lr: 0.000017
2023-10-06 09:52:07,303 DEV : loss 0.16596698760986328 - f1-score (micro avg) 0.8314
2023-10-06 09:52:07,310 ----------------------------------------------------------------------------------------------------
2023-10-06 09:52:18,366 epoch 10 - iter 30/304 - loss 0.06044261 - time (sec): 11.05 - samples/sec: 263.50 - lr: 0.000015 - momentum: 0.000000
2023-10-06 09:52:28,920 epoch 10 - iter 60/304 - loss 0.03666508 - time (sec): 21.61 - samples/sec: 259.58 - lr: 0.000014 - momentum: 0.000000
2023-10-06 09:52:40,817 epoch 10 - iter 90/304 - loss 0.02806714 - time (sec): 33.51 - samples/sec: 266.41 - lr: 0.000012 - momentum: 0.000000
2023-10-06 09:52:52,604 epoch 10 - iter 120/304 - loss 0.02578416 - time (sec): 45.29 - samples/sec: 268.50 - lr: 0.000010 - momentum: 0.000000
2023-10-06 09:53:03,970 epoch 10 - iter 150/304 - loss 0.02219939 - time (sec): 56.66 - samples/sec: 269.24 - lr: 0.000009 - momentum: 0.000000
2023-10-06 09:53:15,393 epoch 10 - iter 180/304 - loss 0.02271526 - time (sec): 68.08 - samples/sec: 270.25 - lr: 0.000007 - momentum: 0.000000
2023-10-06 09:53:27,194 epoch 10 - iter 210/304 - loss 0.02468534 - time (sec): 79.88 - samples/sec: 271.05 - lr: 0.000005 - momentum: 0.000000
2023-10-06 09:53:38,242 epoch 10 - iter 240/304 - loss 0.02324976 - time (sec): 90.93 - samples/sec: 270.79 - lr: 0.000004 - momentum: 0.000000
2023-10-06 09:53:49,359 epoch 10 - iter 270/304 - loss 0.02612149 - time (sec): 102.05 - samples/sec: 271.28 - lr: 0.000002 - momentum: 0.000000
2023-10-06 09:54:00,387 epoch 10 - iter 300/304 - loss 0.02507619 - time (sec): 113.08 - samples/sec: 270.99 - lr: 0.000000 - momentum: 0.000000
2023-10-06 09:54:01,674 ----------------------------------------------------------------------------------------------------
2023-10-06 09:54:01,674 EPOCH 10 done: loss 0.0248 - lr: 0.000000
2023-10-06 09:54:08,593 DEV : loss 0.16923761367797852 - f1-score (micro avg) 0.8304
2023-10-06 09:54:09,441 ----------------------------------------------------------------------------------------------------
2023-10-06 09:54:09,442 Loading model from best epoch ...
2023-10-06 09:54:13,978 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
2023-10-06 09:54:20,511
Results:
- F-score (micro) 0.8066
- F-score (macro) 0.6236
- Accuracy 0.6837
By class:
precision recall f1-score support
scope 0.7516 0.8013 0.7756 151
pers 0.8108 0.9375 0.8696 96
work 0.7642 0.8526 0.8060 95
loc 0.6667 0.6667 0.6667 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7717 0.8448 0.8066 348
macro avg 0.5986 0.6516 0.6236 348
weighted avg 0.7641 0.8448 0.8022 348
2023-10-06 09:54:20,511 ----------------------------------------------------------------------------------------------------
|