File size: 25,038 Bytes
27186af |
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 |
2023-10-08 19:45:24,608 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,609 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()
)"
2023-10-08 19:45:24,609 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,609 MultiCorpus: 966 train + 219 dev + 204 test sentences
- NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /app/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-08 19:45:24,609 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,609 Train: 966 sentences
2023-10-08 19:45:24,610 (train_with_dev=False, train_with_test=False)
2023-10-08 19:45:24,610 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,610 Training Params:
2023-10-08 19:45:24,610 - learning_rate: "0.00016"
2023-10-08 19:45:24,610 - mini_batch_size: "4"
2023-10-08 19:45:24,610 - max_epochs: "10"
2023-10-08 19:45:24,610 - shuffle: "True"
2023-10-08 19:45:24,610 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,610 Plugins:
2023-10-08 19:45:24,610 - TensorboardLogger
2023-10-08 19:45:24,610 - LinearScheduler | warmup_fraction: '0.1'
2023-10-08 19:45:24,610 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,610 Final evaluation on model from best epoch (best-model.pt)
2023-10-08 19:45:24,610 - metric: "('micro avg', 'f1-score')"
2023-10-08 19:45:24,610 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,610 Computation:
2023-10-08 19:45:24,610 - compute on device: cuda:0
2023-10-08 19:45:24,610 - embedding storage: none
2023-10-08 19:45:24,610 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,610 Model training base path: "hmbench-ajmc/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-2"
2023-10-08 19:45:24,611 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,611 ----------------------------------------------------------------------------------------------------
2023-10-08 19:45:24,611 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-08 19:45:34,945 epoch 1 - iter 24/242 - loss 3.22997625 - time (sec): 10.33 - samples/sec: 252.39 - lr: 0.000015 - momentum: 0.000000
2023-10-08 19:45:46,113 epoch 1 - iter 48/242 - loss 3.21892739 - time (sec): 21.50 - samples/sec: 251.61 - lr: 0.000031 - momentum: 0.000000
2023-10-08 19:45:55,869 epoch 1 - iter 72/242 - loss 3.20067097 - time (sec): 31.26 - samples/sec: 247.24 - lr: 0.000047 - momentum: 0.000000
2023-10-08 19:46:05,092 epoch 1 - iter 96/242 - loss 3.16152640 - time (sec): 40.48 - samples/sec: 244.64 - lr: 0.000063 - momentum: 0.000000
2023-10-08 19:46:14,956 epoch 1 - iter 120/242 - loss 3.07831714 - time (sec): 50.34 - samples/sec: 243.72 - lr: 0.000079 - momentum: 0.000000
2023-10-08 19:46:24,682 epoch 1 - iter 144/242 - loss 2.97878770 - time (sec): 60.07 - samples/sec: 242.98 - lr: 0.000095 - momentum: 0.000000
2023-10-08 19:46:34,640 epoch 1 - iter 168/242 - loss 2.86761192 - time (sec): 70.03 - samples/sec: 244.06 - lr: 0.000110 - momentum: 0.000000
2023-10-08 19:46:44,707 epoch 1 - iter 192/242 - loss 2.74954671 - time (sec): 80.10 - samples/sec: 244.87 - lr: 0.000126 - momentum: 0.000000
2023-10-08 19:46:55,158 epoch 1 - iter 216/242 - loss 2.61612478 - time (sec): 90.55 - samples/sec: 246.37 - lr: 0.000142 - momentum: 0.000000
2023-10-08 19:47:04,618 epoch 1 - iter 240/242 - loss 2.50020636 - time (sec): 100.01 - samples/sec: 245.60 - lr: 0.000158 - momentum: 0.000000
2023-10-08 19:47:05,269 ----------------------------------------------------------------------------------------------------
2023-10-08 19:47:05,269 EPOCH 1 done: loss 2.4909 - lr: 0.000158
2023-10-08 19:47:11,567 DEV : loss 1.099568247795105 - f1-score (micro avg) 0.0
2023-10-08 19:47:11,572 ----------------------------------------------------------------------------------------------------
2023-10-08 19:47:21,192 epoch 2 - iter 24/242 - loss 1.04876294 - time (sec): 9.62 - samples/sec: 241.41 - lr: 0.000158 - momentum: 0.000000
2023-10-08 19:47:30,922 epoch 2 - iter 48/242 - loss 0.95343248 - time (sec): 19.35 - samples/sec: 240.74 - lr: 0.000157 - momentum: 0.000000
2023-10-08 19:47:41,284 epoch 2 - iter 72/242 - loss 0.85835044 - time (sec): 29.71 - samples/sec: 243.85 - lr: 0.000155 - momentum: 0.000000
2023-10-08 19:47:51,320 epoch 2 - iter 96/242 - loss 0.80100060 - time (sec): 39.75 - samples/sec: 243.92 - lr: 0.000153 - momentum: 0.000000
2023-10-08 19:48:01,539 epoch 2 - iter 120/242 - loss 0.75007659 - time (sec): 49.97 - samples/sec: 242.91 - lr: 0.000151 - momentum: 0.000000
2023-10-08 19:48:11,611 epoch 2 - iter 144/242 - loss 0.71917788 - time (sec): 60.04 - samples/sec: 244.70 - lr: 0.000150 - momentum: 0.000000
2023-10-08 19:48:21,491 epoch 2 - iter 168/242 - loss 0.69316124 - time (sec): 69.92 - samples/sec: 244.66 - lr: 0.000148 - momentum: 0.000000
2023-10-08 19:48:31,322 epoch 2 - iter 192/242 - loss 0.66261978 - time (sec): 79.75 - samples/sec: 244.76 - lr: 0.000146 - momentum: 0.000000
2023-10-08 19:48:41,037 epoch 2 - iter 216/242 - loss 0.63975858 - time (sec): 89.46 - samples/sec: 243.11 - lr: 0.000144 - momentum: 0.000000
2023-10-08 19:48:51,748 epoch 2 - iter 240/242 - loss 0.60260031 - time (sec): 100.18 - samples/sec: 244.43 - lr: 0.000142 - momentum: 0.000000
2023-10-08 19:48:52,661 ----------------------------------------------------------------------------------------------------
2023-10-08 19:48:52,662 EPOCH 2 done: loss 0.5991 - lr: 0.000142
2023-10-08 19:48:59,164 DEV : loss 0.3767709732055664 - f1-score (micro avg) 0.0884
2023-10-08 19:48:59,170 saving best model
2023-10-08 19:49:00,024 ----------------------------------------------------------------------------------------------------
2023-10-08 19:49:10,356 epoch 3 - iter 24/242 - loss 0.32126961 - time (sec): 10.33 - samples/sec: 258.08 - lr: 0.000141 - momentum: 0.000000
2023-10-08 19:49:21,025 epoch 3 - iter 48/242 - loss 0.33046740 - time (sec): 21.00 - samples/sec: 254.01 - lr: 0.000139 - momentum: 0.000000
2023-10-08 19:49:31,196 epoch 3 - iter 72/242 - loss 0.32398414 - time (sec): 31.17 - samples/sec: 250.05 - lr: 0.000137 - momentum: 0.000000
2023-10-08 19:49:40,745 epoch 3 - iter 96/242 - loss 0.31704962 - time (sec): 40.72 - samples/sec: 245.76 - lr: 0.000135 - momentum: 0.000000
2023-10-08 19:49:50,344 epoch 3 - iter 120/242 - loss 0.30319337 - time (sec): 50.32 - samples/sec: 245.86 - lr: 0.000134 - momentum: 0.000000
2023-10-08 19:49:59,638 epoch 3 - iter 144/242 - loss 0.29975640 - time (sec): 59.61 - samples/sec: 243.54 - lr: 0.000132 - momentum: 0.000000
2023-10-08 19:50:09,993 epoch 3 - iter 168/242 - loss 0.29759959 - time (sec): 69.97 - samples/sec: 243.44 - lr: 0.000130 - momentum: 0.000000
2023-10-08 19:50:21,026 epoch 3 - iter 192/242 - loss 0.28435701 - time (sec): 81.00 - samples/sec: 244.14 - lr: 0.000128 - momentum: 0.000000
2023-10-08 19:50:30,810 epoch 3 - iter 216/242 - loss 0.27994173 - time (sec): 90.78 - samples/sec: 244.22 - lr: 0.000126 - momentum: 0.000000
2023-10-08 19:50:40,820 epoch 3 - iter 240/242 - loss 0.27772976 - time (sec): 100.79 - samples/sec: 244.03 - lr: 0.000125 - momentum: 0.000000
2023-10-08 19:50:41,483 ----------------------------------------------------------------------------------------------------
2023-10-08 19:50:41,483 EPOCH 3 done: loss 0.2782 - lr: 0.000125
2023-10-08 19:50:47,998 DEV : loss 0.232819601893425 - f1-score (micro avg) 0.53
2023-10-08 19:50:48,004 saving best model
2023-10-08 19:50:52,378 ----------------------------------------------------------------------------------------------------
2023-10-08 19:51:03,124 epoch 4 - iter 24/242 - loss 0.15471500 - time (sec): 10.74 - samples/sec: 247.29 - lr: 0.000123 - momentum: 0.000000
2023-10-08 19:51:13,665 epoch 4 - iter 48/242 - loss 0.16110007 - time (sec): 21.29 - samples/sec: 247.77 - lr: 0.000121 - momentum: 0.000000
2023-10-08 19:51:23,232 epoch 4 - iter 72/242 - loss 0.16918778 - time (sec): 30.85 - samples/sec: 245.46 - lr: 0.000119 - momentum: 0.000000
2023-10-08 19:51:32,860 epoch 4 - iter 96/242 - loss 0.17023718 - time (sec): 40.48 - samples/sec: 243.23 - lr: 0.000118 - momentum: 0.000000
2023-10-08 19:51:42,568 epoch 4 - iter 120/242 - loss 0.17776590 - time (sec): 50.19 - samples/sec: 243.44 - lr: 0.000116 - momentum: 0.000000
2023-10-08 19:51:52,610 epoch 4 - iter 144/242 - loss 0.17672138 - time (sec): 60.23 - samples/sec: 245.12 - lr: 0.000114 - momentum: 0.000000
2023-10-08 19:52:02,986 epoch 4 - iter 168/242 - loss 0.17895870 - time (sec): 70.61 - samples/sec: 246.05 - lr: 0.000112 - momentum: 0.000000
2023-10-08 19:52:13,174 epoch 4 - iter 192/242 - loss 0.17606903 - time (sec): 80.79 - samples/sec: 246.28 - lr: 0.000110 - momentum: 0.000000
2023-10-08 19:52:22,742 epoch 4 - iter 216/242 - loss 0.17725752 - time (sec): 90.36 - samples/sec: 244.85 - lr: 0.000109 - momentum: 0.000000
2023-10-08 19:52:33,004 epoch 4 - iter 240/242 - loss 0.17294228 - time (sec): 100.62 - samples/sec: 244.71 - lr: 0.000107 - momentum: 0.000000
2023-10-08 19:52:33,544 ----------------------------------------------------------------------------------------------------
2023-10-08 19:52:33,544 EPOCH 4 done: loss 0.1732 - lr: 0.000107
2023-10-08 19:52:40,051 DEV : loss 0.15743188560009003 - f1-score (micro avg) 0.7975
2023-10-08 19:52:40,057 saving best model
2023-10-08 19:52:44,433 ----------------------------------------------------------------------------------------------------
2023-10-08 19:52:54,068 epoch 5 - iter 24/242 - loss 0.15996377 - time (sec): 9.63 - samples/sec: 240.93 - lr: 0.000105 - momentum: 0.000000
2023-10-08 19:53:04,522 epoch 5 - iter 48/242 - loss 0.14548365 - time (sec): 20.09 - samples/sec: 250.40 - lr: 0.000103 - momentum: 0.000000
2023-10-08 19:53:13,898 epoch 5 - iter 72/242 - loss 0.13218129 - time (sec): 29.46 - samples/sec: 246.51 - lr: 0.000102 - momentum: 0.000000
2023-10-08 19:53:24,449 epoch 5 - iter 96/242 - loss 0.13047575 - time (sec): 40.01 - samples/sec: 248.86 - lr: 0.000100 - momentum: 0.000000
2023-10-08 19:53:34,463 epoch 5 - iter 120/242 - loss 0.12745750 - time (sec): 50.03 - samples/sec: 246.44 - lr: 0.000098 - momentum: 0.000000
2023-10-08 19:53:45,087 epoch 5 - iter 144/242 - loss 0.11817391 - time (sec): 60.65 - samples/sec: 247.36 - lr: 0.000096 - momentum: 0.000000
2023-10-08 19:53:55,271 epoch 5 - iter 168/242 - loss 0.11997625 - time (sec): 70.84 - samples/sec: 246.91 - lr: 0.000094 - momentum: 0.000000
2023-10-08 19:54:05,215 epoch 5 - iter 192/242 - loss 0.11890926 - time (sec): 80.78 - samples/sec: 245.26 - lr: 0.000093 - momentum: 0.000000
2023-10-08 19:54:14,902 epoch 5 - iter 216/242 - loss 0.11924436 - time (sec): 90.47 - samples/sec: 243.77 - lr: 0.000091 - momentum: 0.000000
2023-10-08 19:54:25,441 epoch 5 - iter 240/242 - loss 0.11795489 - time (sec): 101.01 - samples/sec: 243.94 - lr: 0.000089 - momentum: 0.000000
2023-10-08 19:54:25,998 ----------------------------------------------------------------------------------------------------
2023-10-08 19:54:25,998 EPOCH 5 done: loss 0.1178 - lr: 0.000089
2023-10-08 19:54:32,741 DEV : loss 0.12743264436721802 - f1-score (micro avg) 0.8208
2023-10-08 19:54:32,747 saving best model
2023-10-08 19:54:37,104 ----------------------------------------------------------------------------------------------------
2023-10-08 19:54:46,447 epoch 6 - iter 24/242 - loss 0.05946833 - time (sec): 9.34 - samples/sec: 239.14 - lr: 0.000087 - momentum: 0.000000
2023-10-08 19:54:56,509 epoch 6 - iter 48/242 - loss 0.08074757 - time (sec): 19.40 - samples/sec: 240.69 - lr: 0.000086 - momentum: 0.000000
2023-10-08 19:55:06,789 epoch 6 - iter 72/242 - loss 0.08837018 - time (sec): 29.68 - samples/sec: 243.60 - lr: 0.000084 - momentum: 0.000000
2023-10-08 19:55:15,996 epoch 6 - iter 96/242 - loss 0.08681205 - time (sec): 38.89 - samples/sec: 241.35 - lr: 0.000082 - momentum: 0.000000
2023-10-08 19:55:26,498 epoch 6 - iter 120/242 - loss 0.08911376 - time (sec): 49.39 - samples/sec: 242.35 - lr: 0.000080 - momentum: 0.000000
2023-10-08 19:55:36,029 epoch 6 - iter 144/242 - loss 0.08938334 - time (sec): 58.92 - samples/sec: 241.70 - lr: 0.000078 - momentum: 0.000000
2023-10-08 19:55:46,311 epoch 6 - iter 168/242 - loss 0.08788206 - time (sec): 69.21 - samples/sec: 241.98 - lr: 0.000077 - momentum: 0.000000
2023-10-08 19:55:57,250 epoch 6 - iter 192/242 - loss 0.08854715 - time (sec): 80.14 - samples/sec: 243.74 - lr: 0.000075 - momentum: 0.000000
2023-10-08 19:56:07,436 epoch 6 - iter 216/242 - loss 0.08459032 - time (sec): 90.33 - samples/sec: 243.30 - lr: 0.000073 - momentum: 0.000000
2023-10-08 19:56:18,092 epoch 6 - iter 240/242 - loss 0.08333726 - time (sec): 100.99 - samples/sec: 243.73 - lr: 0.000071 - momentum: 0.000000
2023-10-08 19:56:18,712 ----------------------------------------------------------------------------------------------------
2023-10-08 19:56:18,713 EPOCH 6 done: loss 0.0835 - lr: 0.000071
2023-10-08 19:56:25,205 DEV : loss 0.11654166877269745 - f1-score (micro avg) 0.8404
2023-10-08 19:56:25,211 saving best model
2023-10-08 19:56:26,155 ----------------------------------------------------------------------------------------------------
2023-10-08 19:56:36,695 epoch 7 - iter 24/242 - loss 0.06293024 - time (sec): 10.54 - samples/sec: 251.85 - lr: 0.000070 - momentum: 0.000000
2023-10-08 19:56:46,959 epoch 7 - iter 48/242 - loss 0.07168250 - time (sec): 20.80 - samples/sec: 253.91 - lr: 0.000068 - momentum: 0.000000
2023-10-08 19:56:57,446 epoch 7 - iter 72/242 - loss 0.07005661 - time (sec): 31.29 - samples/sec: 251.77 - lr: 0.000066 - momentum: 0.000000
2023-10-08 19:57:07,998 epoch 7 - iter 96/242 - loss 0.06701038 - time (sec): 41.84 - samples/sec: 251.93 - lr: 0.000064 - momentum: 0.000000
2023-10-08 19:57:17,396 epoch 7 - iter 120/242 - loss 0.06522144 - time (sec): 51.24 - samples/sec: 250.59 - lr: 0.000062 - momentum: 0.000000
2023-10-08 19:57:28,080 epoch 7 - iter 144/242 - loss 0.06970900 - time (sec): 61.92 - samples/sec: 251.18 - lr: 0.000061 - momentum: 0.000000
2023-10-08 19:57:38,403 epoch 7 - iter 168/242 - loss 0.06773139 - time (sec): 72.25 - samples/sec: 249.88 - lr: 0.000059 - momentum: 0.000000
2023-10-08 19:57:47,810 epoch 7 - iter 192/242 - loss 0.06432826 - time (sec): 81.65 - samples/sec: 247.36 - lr: 0.000057 - momentum: 0.000000
2023-10-08 19:57:58,023 epoch 7 - iter 216/242 - loss 0.06417272 - time (sec): 91.87 - samples/sec: 246.03 - lr: 0.000055 - momentum: 0.000000
2023-10-08 19:58:07,355 epoch 7 - iter 240/242 - loss 0.06233721 - time (sec): 101.20 - samples/sec: 243.34 - lr: 0.000054 - momentum: 0.000000
2023-10-08 19:58:07,907 ----------------------------------------------------------------------------------------------------
2023-10-08 19:58:07,908 EPOCH 7 done: loss 0.0623 - lr: 0.000054
2023-10-08 19:58:14,365 DEV : loss 0.12197184562683105 - f1-score (micro avg) 0.8253
2023-10-08 19:58:14,371 ----------------------------------------------------------------------------------------------------
2023-10-08 19:58:23,968 epoch 8 - iter 24/242 - loss 0.04913621 - time (sec): 9.60 - samples/sec: 240.84 - lr: 0.000052 - momentum: 0.000000
2023-10-08 19:58:33,485 epoch 8 - iter 48/242 - loss 0.04977968 - time (sec): 19.11 - samples/sec: 242.35 - lr: 0.000050 - momentum: 0.000000
2023-10-08 19:58:43,764 epoch 8 - iter 72/242 - loss 0.05146262 - time (sec): 29.39 - samples/sec: 245.95 - lr: 0.000048 - momentum: 0.000000
2023-10-08 19:58:53,956 epoch 8 - iter 96/242 - loss 0.05064168 - time (sec): 39.58 - samples/sec: 245.78 - lr: 0.000046 - momentum: 0.000000
2023-10-08 19:59:04,411 epoch 8 - iter 120/242 - loss 0.04654593 - time (sec): 50.04 - samples/sec: 245.73 - lr: 0.000045 - momentum: 0.000000
2023-10-08 19:59:13,765 epoch 8 - iter 144/242 - loss 0.05186997 - time (sec): 59.39 - samples/sec: 243.63 - lr: 0.000043 - momentum: 0.000000
2023-10-08 19:59:24,144 epoch 8 - iter 168/242 - loss 0.05262190 - time (sec): 69.77 - samples/sec: 243.31 - lr: 0.000041 - momentum: 0.000000
2023-10-08 19:59:35,045 epoch 8 - iter 192/242 - loss 0.05281831 - time (sec): 80.67 - samples/sec: 244.31 - lr: 0.000039 - momentum: 0.000000
2023-10-08 19:59:45,315 epoch 8 - iter 216/242 - loss 0.05261827 - time (sec): 90.94 - samples/sec: 243.79 - lr: 0.000038 - momentum: 0.000000
2023-10-08 19:59:55,268 epoch 8 - iter 240/242 - loss 0.05007550 - time (sec): 100.90 - samples/sec: 242.92 - lr: 0.000036 - momentum: 0.000000
2023-10-08 19:59:56,094 ----------------------------------------------------------------------------------------------------
2023-10-08 19:59:56,094 EPOCH 8 done: loss 0.0498 - lr: 0.000036
2023-10-08 20:00:02,314 DEV : loss 0.12492693960666656 - f1-score (micro avg) 0.8346
2023-10-08 20:00:02,323 ----------------------------------------------------------------------------------------------------
2023-10-08 20:00:12,018 epoch 9 - iter 24/242 - loss 0.07463564 - time (sec): 9.69 - samples/sec: 249.45 - lr: 0.000034 - momentum: 0.000000
2023-10-08 20:00:21,605 epoch 9 - iter 48/242 - loss 0.05260851 - time (sec): 19.28 - samples/sec: 252.95 - lr: 0.000032 - momentum: 0.000000
2023-10-08 20:00:31,881 epoch 9 - iter 72/242 - loss 0.04459482 - time (sec): 29.56 - samples/sec: 259.61 - lr: 0.000030 - momentum: 0.000000
2023-10-08 20:00:41,439 epoch 9 - iter 96/242 - loss 0.04243585 - time (sec): 39.11 - samples/sec: 259.67 - lr: 0.000029 - momentum: 0.000000
2023-10-08 20:00:50,313 epoch 9 - iter 120/242 - loss 0.04173357 - time (sec): 47.99 - samples/sec: 258.48 - lr: 0.000027 - momentum: 0.000000
2023-10-08 20:00:59,638 epoch 9 - iter 144/242 - loss 0.04074134 - time (sec): 57.31 - samples/sec: 257.97 - lr: 0.000025 - momentum: 0.000000
2023-10-08 20:01:09,189 epoch 9 - iter 168/242 - loss 0.03865436 - time (sec): 66.86 - samples/sec: 257.67 - lr: 0.000023 - momentum: 0.000000
2023-10-08 20:01:18,331 epoch 9 - iter 192/242 - loss 0.03967704 - time (sec): 76.01 - samples/sec: 257.96 - lr: 0.000022 - momentum: 0.000000
2023-10-08 20:01:27,743 epoch 9 - iter 216/242 - loss 0.04177349 - time (sec): 85.42 - samples/sec: 258.52 - lr: 0.000020 - momentum: 0.000000
2023-10-08 20:01:37,368 epoch 9 - iter 240/242 - loss 0.04171713 - time (sec): 95.04 - samples/sec: 259.05 - lr: 0.000018 - momentum: 0.000000
2023-10-08 20:01:37,896 ----------------------------------------------------------------------------------------------------
2023-10-08 20:01:37,896 EPOCH 9 done: loss 0.0415 - lr: 0.000018
2023-10-08 20:01:43,732 DEV : loss 0.13147075474262238 - f1-score (micro avg) 0.8279
2023-10-08 20:01:43,738 ----------------------------------------------------------------------------------------------------
2023-10-08 20:01:53,393 epoch 10 - iter 24/242 - loss 0.03253620 - time (sec): 9.65 - samples/sec: 274.91 - lr: 0.000016 - momentum: 0.000000
2023-10-08 20:02:02,377 epoch 10 - iter 48/242 - loss 0.03156519 - time (sec): 18.64 - samples/sec: 268.33 - lr: 0.000014 - momentum: 0.000000
2023-10-08 20:02:11,235 epoch 10 - iter 72/242 - loss 0.03135636 - time (sec): 27.50 - samples/sec: 265.82 - lr: 0.000013 - momentum: 0.000000
2023-10-08 20:02:20,131 epoch 10 - iter 96/242 - loss 0.03255705 - time (sec): 36.39 - samples/sec: 260.50 - lr: 0.000011 - momentum: 0.000000
2023-10-08 20:02:29,695 epoch 10 - iter 120/242 - loss 0.03206630 - time (sec): 45.96 - samples/sec: 261.75 - lr: 0.000009 - momentum: 0.000000
2023-10-08 20:02:38,449 epoch 10 - iter 144/242 - loss 0.03262375 - time (sec): 54.71 - samples/sec: 260.36 - lr: 0.000007 - momentum: 0.000000
2023-10-08 20:02:47,771 epoch 10 - iter 168/242 - loss 0.03187373 - time (sec): 64.03 - samples/sec: 259.93 - lr: 0.000006 - momentum: 0.000000
2023-10-08 20:02:57,721 epoch 10 - iter 192/242 - loss 0.03284857 - time (sec): 73.98 - samples/sec: 260.79 - lr: 0.000004 - momentum: 0.000000
2023-10-08 20:03:07,720 epoch 10 - iter 216/242 - loss 0.03825284 - time (sec): 83.98 - samples/sec: 262.77 - lr: 0.000002 - momentum: 0.000000
2023-10-08 20:03:17,458 epoch 10 - iter 240/242 - loss 0.03867135 - time (sec): 93.72 - samples/sec: 261.58 - lr: 0.000000 - momentum: 0.000000
2023-10-08 20:03:18,240 ----------------------------------------------------------------------------------------------------
2023-10-08 20:03:18,241 EPOCH 10 done: loss 0.0385 - lr: 0.000000
2023-10-08 20:03:24,206 DEV : loss 0.13405872881412506 - f1-score (micro avg) 0.8365
2023-10-08 20:03:25,084 ----------------------------------------------------------------------------------------------------
2023-10-08 20:03:25,085 Loading model from best epoch ...
2023-10-08 20:03:28,148 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
2023-10-08 20:03:33,831
Results:
- F-score (micro) 0.8114
- F-score (macro) 0.489
- Accuracy 0.717
By class:
precision recall f1-score support
pers 0.8182 0.8417 0.8298 139
scope 0.8310 0.9147 0.8708 129
work 0.6957 0.8000 0.7442 80
loc 0.0000 0.0000 0.0000 9
date 0.0000 0.0000 0.0000 3
micro avg 0.7931 0.8306 0.8114 360
macro avg 0.4690 0.5113 0.4890 360
weighted avg 0.7683 0.8306 0.7978 360
2023-10-08 20:03:33,831 ----------------------------------------------------------------------------------------------------
|