File size: 25,041 Bytes
75f863a |
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 |
2023-10-06 21:40:48,284 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,285 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 21:40:48,285 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,285 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 21:40:48,286 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,286 Train: 1100 sentences
2023-10-06 21:40:48,286 (train_with_dev=False, train_with_test=False)
2023-10-06 21:40:48,286 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,286 Training Params:
2023-10-06 21:40:48,286 - learning_rate: "0.00016"
2023-10-06 21:40:48,286 - mini_batch_size: "8"
2023-10-06 21:40:48,286 - max_epochs: "10"
2023-10-06 21:40:48,286 - shuffle: "True"
2023-10-06 21:40:48,286 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,286 Plugins:
2023-10-06 21:40:48,286 - TensorboardLogger
2023-10-06 21:40:48,286 - LinearScheduler | warmup_fraction: '0.1'
2023-10-06 21:40:48,286 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,286 Final evaluation on model from best epoch (best-model.pt)
2023-10-06 21:40:48,286 - metric: "('micro avg', 'f1-score')"
2023-10-06 21:40:48,286 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,286 Computation:
2023-10-06 21:40:48,286 - compute on device: cuda:0
2023-10-06 21:40:48,287 - embedding storage: none
2023-10-06 21:40:48,287 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,287 Model training base path: "hmbench-ajmc/de-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1"
2023-10-06 21:40:48,287 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,287 ----------------------------------------------------------------------------------------------------
2023-10-06 21:40:48,287 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-06 21:40:57,559 epoch 1 - iter 13/138 - loss 3.22932241 - time (sec): 9.27 - samples/sec: 230.62 - lr: 0.000014 - momentum: 0.000000
2023-10-06 21:41:07,327 epoch 1 - iter 26/138 - loss 3.22496377 - time (sec): 19.04 - samples/sec: 224.28 - lr: 0.000029 - momentum: 0.000000
2023-10-06 21:41:16,428 epoch 1 - iter 39/138 - loss 3.21594068 - time (sec): 28.14 - samples/sec: 219.65 - lr: 0.000044 - momentum: 0.000000
2023-10-06 21:41:25,744 epoch 1 - iter 52/138 - loss 3.20171907 - time (sec): 37.46 - samples/sec: 218.47 - lr: 0.000059 - momentum: 0.000000
2023-10-06 21:41:36,624 epoch 1 - iter 65/138 - loss 3.16881497 - time (sec): 48.34 - samples/sec: 221.68 - lr: 0.000074 - momentum: 0.000000
2023-10-06 21:41:46,773 epoch 1 - iter 78/138 - loss 3.11163081 - time (sec): 58.48 - samples/sec: 223.37 - lr: 0.000089 - momentum: 0.000000
2023-10-06 21:41:56,659 epoch 1 - iter 91/138 - loss 3.04972079 - time (sec): 68.37 - samples/sec: 223.09 - lr: 0.000104 - momentum: 0.000000
2023-10-06 21:42:06,249 epoch 1 - iter 104/138 - loss 2.97412228 - time (sec): 77.96 - samples/sec: 223.07 - lr: 0.000119 - momentum: 0.000000
2023-10-06 21:42:16,033 epoch 1 - iter 117/138 - loss 2.89301074 - time (sec): 87.74 - samples/sec: 223.03 - lr: 0.000134 - momentum: 0.000000
2023-10-06 21:42:25,040 epoch 1 - iter 130/138 - loss 2.82504112 - time (sec): 96.75 - samples/sec: 222.68 - lr: 0.000150 - momentum: 0.000000
2023-10-06 21:42:30,771 ----------------------------------------------------------------------------------------------------
2023-10-06 21:42:30,772 EPOCH 1 done: loss 2.7769 - lr: 0.000150
2023-10-06 21:42:37,535 DEV : loss 1.7709752321243286 - f1-score (micro avg) 0.0
2023-10-06 21:42:37,541 ----------------------------------------------------------------------------------------------------
2023-10-06 21:42:47,080 epoch 2 - iter 13/138 - loss 1.70465968 - time (sec): 9.54 - samples/sec: 224.57 - lr: 0.000158 - momentum: 0.000000
2023-10-06 21:42:57,077 epoch 2 - iter 26/138 - loss 1.57513086 - time (sec): 19.53 - samples/sec: 222.02 - lr: 0.000157 - momentum: 0.000000
2023-10-06 21:43:06,413 epoch 2 - iter 39/138 - loss 1.51682688 - time (sec): 28.87 - samples/sec: 221.16 - lr: 0.000155 - momentum: 0.000000
2023-10-06 21:43:15,371 epoch 2 - iter 52/138 - loss 1.43139706 - time (sec): 37.83 - samples/sec: 217.53 - lr: 0.000153 - momentum: 0.000000
2023-10-06 21:43:24,766 epoch 2 - iter 65/138 - loss 1.35600385 - time (sec): 47.22 - samples/sec: 217.26 - lr: 0.000152 - momentum: 0.000000
2023-10-06 21:43:34,661 epoch 2 - iter 78/138 - loss 1.29510452 - time (sec): 57.12 - samples/sec: 217.62 - lr: 0.000150 - momentum: 0.000000
2023-10-06 21:43:44,696 epoch 2 - iter 91/138 - loss 1.23627642 - time (sec): 67.15 - samples/sec: 219.26 - lr: 0.000148 - momentum: 0.000000
2023-10-06 21:43:54,956 epoch 2 - iter 104/138 - loss 1.18744407 - time (sec): 77.41 - samples/sec: 220.17 - lr: 0.000147 - momentum: 0.000000
2023-10-06 21:44:04,455 epoch 2 - iter 117/138 - loss 1.15075822 - time (sec): 86.91 - samples/sec: 220.82 - lr: 0.000145 - momentum: 0.000000
2023-10-06 21:44:14,750 epoch 2 - iter 130/138 - loss 1.11339905 - time (sec): 97.21 - samples/sec: 222.22 - lr: 0.000143 - momentum: 0.000000
2023-10-06 21:44:20,016 ----------------------------------------------------------------------------------------------------
2023-10-06 21:44:20,016 EPOCH 2 done: loss 1.0983 - lr: 0.000143
2023-10-06 21:44:26,738 DEV : loss 0.7268592715263367 - f1-score (micro avg) 0.0
2023-10-06 21:44:26,744 ----------------------------------------------------------------------------------------------------
2023-10-06 21:44:36,396 epoch 3 - iter 13/138 - loss 0.70907147 - time (sec): 9.65 - samples/sec: 223.08 - lr: 0.000141 - momentum: 0.000000
2023-10-06 21:44:46,642 epoch 3 - iter 26/138 - loss 0.64621440 - time (sec): 19.90 - samples/sec: 226.52 - lr: 0.000139 - momentum: 0.000000
2023-10-06 21:44:56,414 epoch 3 - iter 39/138 - loss 0.63420933 - time (sec): 29.67 - samples/sec: 226.60 - lr: 0.000137 - momentum: 0.000000
2023-10-06 21:45:06,826 epoch 3 - iter 52/138 - loss 0.61482481 - time (sec): 40.08 - samples/sec: 227.07 - lr: 0.000136 - momentum: 0.000000
2023-10-06 21:45:15,817 epoch 3 - iter 65/138 - loss 0.60997011 - time (sec): 49.07 - samples/sec: 226.14 - lr: 0.000134 - momentum: 0.000000
2023-10-06 21:45:26,124 epoch 3 - iter 78/138 - loss 0.59932463 - time (sec): 59.38 - samples/sec: 226.83 - lr: 0.000132 - momentum: 0.000000
2023-10-06 21:45:35,137 epoch 3 - iter 91/138 - loss 0.58378814 - time (sec): 68.39 - samples/sec: 224.50 - lr: 0.000131 - momentum: 0.000000
2023-10-06 21:45:44,232 epoch 3 - iter 104/138 - loss 0.56431660 - time (sec): 77.49 - samples/sec: 223.01 - lr: 0.000129 - momentum: 0.000000
2023-10-06 21:45:53,869 epoch 3 - iter 117/138 - loss 0.54913062 - time (sec): 87.12 - samples/sec: 222.36 - lr: 0.000127 - momentum: 0.000000
2023-10-06 21:46:03,803 epoch 3 - iter 130/138 - loss 0.52734165 - time (sec): 97.06 - samples/sec: 222.20 - lr: 0.000126 - momentum: 0.000000
2023-10-06 21:46:09,423 ----------------------------------------------------------------------------------------------------
2023-10-06 21:46:09,423 EPOCH 3 done: loss 0.5189 - lr: 0.000126
2023-10-06 21:46:16,125 DEV : loss 0.38523873686790466 - f1-score (micro avg) 0.489
2023-10-06 21:46:16,131 saving best model
2023-10-06 21:46:17,033 ----------------------------------------------------------------------------------------------------
2023-10-06 21:46:27,861 epoch 4 - iter 13/138 - loss 0.32840705 - time (sec): 10.83 - samples/sec: 229.53 - lr: 0.000123 - momentum: 0.000000
2023-10-06 21:46:37,706 epoch 4 - iter 26/138 - loss 0.31706666 - time (sec): 20.67 - samples/sec: 224.32 - lr: 0.000121 - momentum: 0.000000
2023-10-06 21:46:46,686 epoch 4 - iter 39/138 - loss 0.32419045 - time (sec): 29.65 - samples/sec: 219.45 - lr: 0.000120 - momentum: 0.000000
2023-10-06 21:46:56,167 epoch 4 - iter 52/138 - loss 0.32908592 - time (sec): 39.13 - samples/sec: 221.28 - lr: 0.000118 - momentum: 0.000000
2023-10-06 21:47:05,997 epoch 4 - iter 65/138 - loss 0.32326386 - time (sec): 48.96 - samples/sec: 221.68 - lr: 0.000116 - momentum: 0.000000
2023-10-06 21:47:16,087 epoch 4 - iter 78/138 - loss 0.32849866 - time (sec): 59.05 - samples/sec: 222.94 - lr: 0.000115 - momentum: 0.000000
2023-10-06 21:47:25,799 epoch 4 - iter 91/138 - loss 0.31853506 - time (sec): 68.76 - samples/sec: 222.11 - lr: 0.000113 - momentum: 0.000000
2023-10-06 21:47:35,244 epoch 4 - iter 104/138 - loss 0.31529818 - time (sec): 78.21 - samples/sec: 221.90 - lr: 0.000111 - momentum: 0.000000
2023-10-06 21:47:44,556 epoch 4 - iter 117/138 - loss 0.31233610 - time (sec): 87.52 - samples/sec: 222.39 - lr: 0.000110 - momentum: 0.000000
2023-10-06 21:47:53,872 epoch 4 - iter 130/138 - loss 0.30543028 - time (sec): 96.84 - samples/sec: 221.67 - lr: 0.000108 - momentum: 0.000000
2023-10-06 21:47:59,648 ----------------------------------------------------------------------------------------------------
2023-10-06 21:47:59,649 EPOCH 4 done: loss 0.3000 - lr: 0.000108
2023-10-06 21:48:06,361 DEV : loss 0.24843597412109375 - f1-score (micro avg) 0.6997
2023-10-06 21:48:06,367 saving best model
2023-10-06 21:48:07,281 ----------------------------------------------------------------------------------------------------
2023-10-06 21:48:17,052 epoch 5 - iter 13/138 - loss 0.23847167 - time (sec): 9.77 - samples/sec: 216.80 - lr: 0.000105 - momentum: 0.000000
2023-10-06 21:48:26,728 epoch 5 - iter 26/138 - loss 0.24511983 - time (sec): 19.45 - samples/sec: 218.92 - lr: 0.000104 - momentum: 0.000000
2023-10-06 21:48:36,023 epoch 5 - iter 39/138 - loss 0.24670887 - time (sec): 28.74 - samples/sec: 219.24 - lr: 0.000102 - momentum: 0.000000
2023-10-06 21:48:46,778 epoch 5 - iter 52/138 - loss 0.23014874 - time (sec): 39.49 - samples/sec: 223.98 - lr: 0.000100 - momentum: 0.000000
2023-10-06 21:48:56,955 epoch 5 - iter 65/138 - loss 0.22490150 - time (sec): 49.67 - samples/sec: 224.11 - lr: 0.000099 - momentum: 0.000000
2023-10-06 21:49:06,877 epoch 5 - iter 78/138 - loss 0.21726106 - time (sec): 59.59 - samples/sec: 223.18 - lr: 0.000097 - momentum: 0.000000
2023-10-06 21:49:17,317 epoch 5 - iter 91/138 - loss 0.20425902 - time (sec): 70.03 - samples/sec: 222.68 - lr: 0.000095 - momentum: 0.000000
2023-10-06 21:49:26,535 epoch 5 - iter 104/138 - loss 0.19921248 - time (sec): 79.25 - samples/sec: 223.20 - lr: 0.000094 - momentum: 0.000000
2023-10-06 21:49:35,724 epoch 5 - iter 117/138 - loss 0.19801591 - time (sec): 88.44 - samples/sec: 222.34 - lr: 0.000092 - momentum: 0.000000
2023-10-06 21:49:44,843 epoch 5 - iter 130/138 - loss 0.19298194 - time (sec): 97.56 - samples/sec: 222.42 - lr: 0.000090 - momentum: 0.000000
2023-10-06 21:49:49,977 ----------------------------------------------------------------------------------------------------
2023-10-06 21:49:49,978 EPOCH 5 done: loss 0.1936 - lr: 0.000090
2023-10-06 21:49:56,718 DEV : loss 0.174832284450531 - f1-score (micro avg) 0.8195
2023-10-06 21:49:56,724 saving best model
2023-10-06 21:49:57,626 ----------------------------------------------------------------------------------------------------
2023-10-06 21:50:07,606 epoch 6 - iter 13/138 - loss 0.16131818 - time (sec): 9.98 - samples/sec: 227.71 - lr: 0.000088 - momentum: 0.000000
2023-10-06 21:50:16,783 epoch 6 - iter 26/138 - loss 0.15133612 - time (sec): 19.15 - samples/sec: 222.61 - lr: 0.000086 - momentum: 0.000000
2023-10-06 21:50:26,529 epoch 6 - iter 39/138 - loss 0.14751188 - time (sec): 28.90 - samples/sec: 224.42 - lr: 0.000084 - momentum: 0.000000
2023-10-06 21:50:36,588 epoch 6 - iter 52/138 - loss 0.14004272 - time (sec): 38.96 - samples/sec: 222.56 - lr: 0.000083 - momentum: 0.000000
2023-10-06 21:50:46,407 epoch 6 - iter 65/138 - loss 0.13322328 - time (sec): 48.78 - samples/sec: 222.35 - lr: 0.000081 - momentum: 0.000000
2023-10-06 21:50:56,197 epoch 6 - iter 78/138 - loss 0.12399005 - time (sec): 58.57 - samples/sec: 221.69 - lr: 0.000079 - momentum: 0.000000
2023-10-06 21:51:06,185 epoch 6 - iter 91/138 - loss 0.13276856 - time (sec): 68.56 - samples/sec: 223.70 - lr: 0.000077 - momentum: 0.000000
2023-10-06 21:51:15,657 epoch 6 - iter 104/138 - loss 0.13175238 - time (sec): 78.03 - samples/sec: 224.01 - lr: 0.000076 - momentum: 0.000000
2023-10-06 21:51:25,316 epoch 6 - iter 117/138 - loss 0.12953164 - time (sec): 87.69 - samples/sec: 223.29 - lr: 0.000074 - momentum: 0.000000
2023-10-06 21:51:34,559 epoch 6 - iter 130/138 - loss 0.12830343 - time (sec): 96.93 - samples/sec: 223.10 - lr: 0.000072 - momentum: 0.000000
2023-10-06 21:51:40,136 ----------------------------------------------------------------------------------------------------
2023-10-06 21:51:40,137 EPOCH 6 done: loss 0.1278 - lr: 0.000072
2023-10-06 21:51:46,829 DEV : loss 0.1418776512145996 - f1-score (micro avg) 0.8502
2023-10-06 21:51:46,835 saving best model
2023-10-06 21:51:47,751 ----------------------------------------------------------------------------------------------------
2023-10-06 21:51:56,984 epoch 7 - iter 13/138 - loss 0.09202341 - time (sec): 9.23 - samples/sec: 216.86 - lr: 0.000070 - momentum: 0.000000
2023-10-06 21:52:06,248 epoch 7 - iter 26/138 - loss 0.08962437 - time (sec): 18.50 - samples/sec: 213.72 - lr: 0.000068 - momentum: 0.000000
2023-10-06 21:52:15,978 epoch 7 - iter 39/138 - loss 0.10050212 - time (sec): 28.23 - samples/sec: 217.22 - lr: 0.000066 - momentum: 0.000000
2023-10-06 21:52:25,953 epoch 7 - iter 52/138 - loss 0.08973982 - time (sec): 38.20 - samples/sec: 221.41 - lr: 0.000065 - momentum: 0.000000
2023-10-06 21:52:36,149 epoch 7 - iter 65/138 - loss 0.08788279 - time (sec): 48.40 - samples/sec: 222.91 - lr: 0.000063 - momentum: 0.000000
2023-10-06 21:52:45,504 epoch 7 - iter 78/138 - loss 0.09283149 - time (sec): 57.75 - samples/sec: 221.05 - lr: 0.000061 - momentum: 0.000000
2023-10-06 21:52:55,369 epoch 7 - iter 91/138 - loss 0.09156409 - time (sec): 67.62 - samples/sec: 220.85 - lr: 0.000060 - momentum: 0.000000
2023-10-06 21:53:05,592 epoch 7 - iter 104/138 - loss 0.08895562 - time (sec): 77.84 - samples/sec: 222.67 - lr: 0.000058 - momentum: 0.000000
2023-10-06 21:53:15,214 epoch 7 - iter 117/138 - loss 0.08941310 - time (sec): 87.46 - samples/sec: 223.02 - lr: 0.000056 - momentum: 0.000000
2023-10-06 21:53:24,914 epoch 7 - iter 130/138 - loss 0.09673186 - time (sec): 97.16 - samples/sec: 223.19 - lr: 0.000055 - momentum: 0.000000
2023-10-06 21:53:30,238 ----------------------------------------------------------------------------------------------------
2023-10-06 21:53:30,238 EPOCH 7 done: loss 0.0949 - lr: 0.000055
2023-10-06 21:53:36,915 DEV : loss 0.12556645274162292 - f1-score (micro avg) 0.8589
2023-10-06 21:53:36,921 saving best model
2023-10-06 21:53:37,851 ----------------------------------------------------------------------------------------------------
2023-10-06 21:53:46,858 epoch 8 - iter 13/138 - loss 0.07149320 - time (sec): 9.01 - samples/sec: 208.42 - lr: 0.000052 - momentum: 0.000000
2023-10-06 21:53:56,170 epoch 8 - iter 26/138 - loss 0.09203937 - time (sec): 18.32 - samples/sec: 219.57 - lr: 0.000050 - momentum: 0.000000
2023-10-06 21:54:05,229 epoch 8 - iter 39/138 - loss 0.08711760 - time (sec): 27.38 - samples/sec: 219.31 - lr: 0.000049 - momentum: 0.000000
2023-10-06 21:54:15,492 epoch 8 - iter 52/138 - loss 0.08100056 - time (sec): 37.64 - samples/sec: 223.09 - lr: 0.000047 - momentum: 0.000000
2023-10-06 21:54:24,878 epoch 8 - iter 65/138 - loss 0.08426377 - time (sec): 47.03 - samples/sec: 220.58 - lr: 0.000045 - momentum: 0.000000
2023-10-06 21:54:35,039 epoch 8 - iter 78/138 - loss 0.08500926 - time (sec): 57.19 - samples/sec: 221.35 - lr: 0.000044 - momentum: 0.000000
2023-10-06 21:54:44,080 epoch 8 - iter 91/138 - loss 0.08055090 - time (sec): 66.23 - samples/sec: 221.41 - lr: 0.000042 - momentum: 0.000000
2023-10-06 21:54:54,543 epoch 8 - iter 104/138 - loss 0.07418720 - time (sec): 76.69 - samples/sec: 222.26 - lr: 0.000040 - momentum: 0.000000
2023-10-06 21:55:04,243 epoch 8 - iter 117/138 - loss 0.07711477 - time (sec): 86.39 - samples/sec: 222.77 - lr: 0.000039 - momentum: 0.000000
2023-10-06 21:55:14,378 epoch 8 - iter 130/138 - loss 0.07679258 - time (sec): 96.53 - samples/sec: 223.16 - lr: 0.000037 - momentum: 0.000000
2023-10-06 21:55:19,925 ----------------------------------------------------------------------------------------------------
2023-10-06 21:55:19,925 EPOCH 8 done: loss 0.0748 - lr: 0.000037
2023-10-06 21:55:26,567 DEV : loss 0.12296636402606964 - f1-score (micro avg) 0.8554
2023-10-06 21:55:26,573 ----------------------------------------------------------------------------------------------------
2023-10-06 21:55:36,064 epoch 9 - iter 13/138 - loss 0.08957227 - time (sec): 9.49 - samples/sec: 218.99 - lr: 0.000034 - momentum: 0.000000
2023-10-06 21:55:45,358 epoch 9 - iter 26/138 - loss 0.08908673 - time (sec): 18.78 - samples/sec: 221.26 - lr: 0.000033 - momentum: 0.000000
2023-10-06 21:55:54,919 epoch 9 - iter 39/138 - loss 0.08531472 - time (sec): 28.34 - samples/sec: 220.78 - lr: 0.000031 - momentum: 0.000000
2023-10-06 21:56:04,767 epoch 9 - iter 52/138 - loss 0.08120974 - time (sec): 38.19 - samples/sec: 221.25 - lr: 0.000029 - momentum: 0.000000
2023-10-06 21:56:14,503 epoch 9 - iter 65/138 - loss 0.08248220 - time (sec): 47.93 - samples/sec: 221.23 - lr: 0.000028 - momentum: 0.000000
2023-10-06 21:56:24,005 epoch 9 - iter 78/138 - loss 0.08099284 - time (sec): 57.43 - samples/sec: 222.62 - lr: 0.000026 - momentum: 0.000000
2023-10-06 21:56:34,944 epoch 9 - iter 91/138 - loss 0.07394146 - time (sec): 68.37 - samples/sec: 223.61 - lr: 0.000024 - momentum: 0.000000
2023-10-06 21:56:44,292 epoch 9 - iter 104/138 - loss 0.07115356 - time (sec): 77.72 - samples/sec: 222.87 - lr: 0.000023 - momentum: 0.000000
2023-10-06 21:56:53,548 epoch 9 - iter 117/138 - loss 0.06724952 - time (sec): 86.97 - samples/sec: 222.18 - lr: 0.000021 - momentum: 0.000000
2023-10-06 21:57:03,367 epoch 9 - iter 130/138 - loss 0.06453547 - time (sec): 96.79 - samples/sec: 222.79 - lr: 0.000019 - momentum: 0.000000
2023-10-06 21:57:08,812 ----------------------------------------------------------------------------------------------------
2023-10-06 21:57:08,813 EPOCH 9 done: loss 0.0652 - lr: 0.000019
2023-10-06 21:57:15,461 DEV : loss 0.11786513775587082 - f1-score (micro avg) 0.8575
2023-10-06 21:57:15,467 ----------------------------------------------------------------------------------------------------
2023-10-06 21:57:25,317 epoch 10 - iter 13/138 - loss 0.10447337 - time (sec): 9.85 - samples/sec: 221.66 - lr: 0.000017 - momentum: 0.000000
2023-10-06 21:57:34,946 epoch 10 - iter 26/138 - loss 0.08395709 - time (sec): 19.48 - samples/sec: 221.59 - lr: 0.000015 - momentum: 0.000000
2023-10-06 21:57:44,037 epoch 10 - iter 39/138 - loss 0.07476411 - time (sec): 28.57 - samples/sec: 220.35 - lr: 0.000013 - momentum: 0.000000
2023-10-06 21:57:54,257 epoch 10 - iter 52/138 - loss 0.07381145 - time (sec): 38.79 - samples/sec: 223.37 - lr: 0.000012 - momentum: 0.000000
2023-10-06 21:58:03,637 epoch 10 - iter 65/138 - loss 0.06455602 - time (sec): 48.17 - samples/sec: 221.54 - lr: 0.000010 - momentum: 0.000000
2023-10-06 21:58:13,312 epoch 10 - iter 78/138 - loss 0.06474742 - time (sec): 57.84 - samples/sec: 221.77 - lr: 0.000008 - momentum: 0.000000
2023-10-06 21:58:22,926 epoch 10 - iter 91/138 - loss 0.06013250 - time (sec): 67.46 - samples/sec: 220.99 - lr: 0.000007 - momentum: 0.000000
2023-10-06 21:58:32,039 epoch 10 - iter 104/138 - loss 0.06197331 - time (sec): 76.57 - samples/sec: 221.11 - lr: 0.000005 - momentum: 0.000000
2023-10-06 21:58:42,259 epoch 10 - iter 117/138 - loss 0.06140372 - time (sec): 86.79 - samples/sec: 222.49 - lr: 0.000003 - momentum: 0.000000
2023-10-06 21:58:51,604 epoch 10 - iter 130/138 - loss 0.06060334 - time (sec): 96.14 - samples/sec: 222.74 - lr: 0.000002 - momentum: 0.000000
2023-10-06 21:58:57,560 ----------------------------------------------------------------------------------------------------
2023-10-06 21:58:57,560 EPOCH 10 done: loss 0.0608 - lr: 0.000002
2023-10-06 21:59:04,228 DEV : loss 0.1174774318933487 - f1-score (micro avg) 0.8602
2023-10-06 21:59:04,234 saving best model
2023-10-06 21:59:06,124 ----------------------------------------------------------------------------------------------------
2023-10-06 21:59:06,126 Loading model from best epoch ...
2023-10-06 21:59:08,826 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 21:59:16,032
Results:
- F-score (micro) 0.8828
- F-score (macro) 0.5272
- Accuracy 0.8129
By class:
precision recall f1-score support
scope 0.8827 0.8977 0.8901 176
pers 0.8955 0.9375 0.9160 128
work 0.8356 0.8243 0.8299 74
object 0.0000 0.0000 0.0000 2
loc 0.0000 0.0000 0.0000 2
micro avg 0.8782 0.8874 0.8828 382
macro avg 0.5228 0.5319 0.5272 382
weighted avg 0.8686 0.8874 0.8778 382
2023-10-06 21:59:16,032 ----------------------------------------------------------------------------------------------------
|