File size: 25,155 Bytes
3f675fe |
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 |
2023-10-06 14:11:25,611 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,612 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 14:11:25,612 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,612 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 14:11:25,612 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,612 Train: 1214 sentences
2023-10-06 14:11:25,612 (train_with_dev=False, train_with_test=False)
2023-10-06 14:11:25,612 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 Training Params:
2023-10-06 14:11:25,613 - learning_rate: "0.00016"
2023-10-06 14:11:25,613 - mini_batch_size: "4"
2023-10-06 14:11:25,613 - max_epochs: "10"
2023-10-06 14:11:25,613 - shuffle: "True"
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 Plugins:
2023-10-06 14:11:25,613 - TensorboardLogger
2023-10-06 14:11:25,613 - LinearScheduler | warmup_fraction: '0.1'
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 Final evaluation on model from best epoch (best-model.pt)
2023-10-06 14:11:25,613 - metric: "('micro avg', 'f1-score')"
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 Computation:
2023-10-06 14:11:25,613 - compute on device: cuda:0
2023-10-06 14:11:25,613 - embedding storage: none
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 Model training base path: "hmbench-ajmc/en-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-4"
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,613 ----------------------------------------------------------------------------------------------------
2023-10-06 14:11:25,614 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-06 14:11:36,883 epoch 1 - iter 30/304 - loss 3.24794717 - time (sec): 11.27 - samples/sec: 271.92 - lr: 0.000015 - momentum: 0.000000
2023-10-06 14:11:48,388 epoch 1 - iter 60/304 - loss 3.23649970 - time (sec): 22.77 - samples/sec: 271.03 - lr: 0.000031 - momentum: 0.000000
2023-10-06 14:11:59,480 epoch 1 - iter 90/304 - loss 3.21188821 - time (sec): 33.86 - samples/sec: 270.37 - lr: 0.000047 - momentum: 0.000000
2023-10-06 14:12:10,887 epoch 1 - iter 120/304 - loss 3.13757647 - time (sec): 45.27 - samples/sec: 270.54 - lr: 0.000063 - momentum: 0.000000
2023-10-06 14:12:22,654 epoch 1 - iter 150/304 - loss 3.02078335 - time (sec): 57.04 - samples/sec: 272.02 - lr: 0.000078 - momentum: 0.000000
2023-10-06 14:12:34,042 epoch 1 - iter 180/304 - loss 2.90736795 - time (sec): 68.43 - samples/sec: 271.43 - lr: 0.000094 - momentum: 0.000000
2023-10-06 14:12:45,083 epoch 1 - iter 210/304 - loss 2.78130427 - time (sec): 79.47 - samples/sec: 270.54 - lr: 0.000110 - momentum: 0.000000
2023-10-06 14:12:56,244 epoch 1 - iter 240/304 - loss 2.64825607 - time (sec): 90.63 - samples/sec: 269.30 - lr: 0.000126 - momentum: 0.000000
2023-10-06 14:13:08,193 epoch 1 - iter 270/304 - loss 2.48837414 - time (sec): 102.58 - samples/sec: 270.25 - lr: 0.000142 - momentum: 0.000000
2023-10-06 14:13:18,910 epoch 1 - iter 300/304 - loss 2.34919296 - time (sec): 113.29 - samples/sec: 269.78 - lr: 0.000157 - momentum: 0.000000
2023-10-06 14:13:20,396 ----------------------------------------------------------------------------------------------------
2023-10-06 14:13:20,397 EPOCH 1 done: loss 2.3323 - lr: 0.000157
2023-10-06 14:13:27,220 DEV : loss 0.8810060620307922 - f1-score (micro avg) 0.0
2023-10-06 14:13:27,227 ----------------------------------------------------------------------------------------------------
2023-10-06 14:13:38,873 epoch 2 - iter 30/304 - loss 0.74122896 - time (sec): 11.65 - samples/sec: 276.51 - lr: 0.000158 - momentum: 0.000000
2023-10-06 14:13:50,109 epoch 2 - iter 60/304 - loss 0.68607239 - time (sec): 22.88 - samples/sec: 272.36 - lr: 0.000157 - momentum: 0.000000
2023-10-06 14:14:01,460 epoch 2 - iter 90/304 - loss 0.66330841 - time (sec): 34.23 - samples/sec: 271.12 - lr: 0.000155 - momentum: 0.000000
2023-10-06 14:14:13,021 epoch 2 - iter 120/304 - loss 0.62361761 - time (sec): 45.79 - samples/sec: 274.36 - lr: 0.000153 - momentum: 0.000000
2023-10-06 14:14:23,948 epoch 2 - iter 150/304 - loss 0.60082612 - time (sec): 56.72 - samples/sec: 273.75 - lr: 0.000151 - momentum: 0.000000
2023-10-06 14:14:35,282 epoch 2 - iter 180/304 - loss 0.56186732 - time (sec): 68.05 - samples/sec: 272.54 - lr: 0.000150 - momentum: 0.000000
2023-10-06 14:14:46,549 epoch 2 - iter 210/304 - loss 0.54139779 - time (sec): 79.32 - samples/sec: 272.38 - lr: 0.000148 - momentum: 0.000000
2023-10-06 14:14:57,495 epoch 2 - iter 240/304 - loss 0.51007846 - time (sec): 90.27 - samples/sec: 272.36 - lr: 0.000146 - momentum: 0.000000
2023-10-06 14:15:09,184 epoch 2 - iter 270/304 - loss 0.49170617 - time (sec): 101.96 - samples/sec: 273.59 - lr: 0.000144 - momentum: 0.000000
2023-10-06 14:15:20,178 epoch 2 - iter 300/304 - loss 0.47259793 - time (sec): 112.95 - samples/sec: 272.11 - lr: 0.000143 - momentum: 0.000000
2023-10-06 14:15:21,353 ----------------------------------------------------------------------------------------------------
2023-10-06 14:15:21,353 EPOCH 2 done: loss 0.4708 - lr: 0.000143
2023-10-06 14:15:28,534 DEV : loss 0.3191007077693939 - f1-score (micro avg) 0.4907
2023-10-06 14:15:28,543 saving best model
2023-10-06 14:15:29,413 ----------------------------------------------------------------------------------------------------
2023-10-06 14:15:40,687 epoch 3 - iter 30/304 - loss 0.22409010 - time (sec): 11.27 - samples/sec: 264.63 - lr: 0.000141 - momentum: 0.000000
2023-10-06 14:15:52,371 epoch 3 - iter 60/304 - loss 0.22786621 - time (sec): 22.96 - samples/sec: 268.94 - lr: 0.000139 - momentum: 0.000000
2023-10-06 14:16:03,169 epoch 3 - iter 90/304 - loss 0.23089277 - time (sec): 33.75 - samples/sec: 263.73 - lr: 0.000137 - momentum: 0.000000
2023-10-06 14:16:14,285 epoch 3 - iter 120/304 - loss 0.23250409 - time (sec): 44.87 - samples/sec: 262.94 - lr: 0.000135 - momentum: 0.000000
2023-10-06 14:16:26,187 epoch 3 - iter 150/304 - loss 0.22008502 - time (sec): 56.77 - samples/sec: 266.63 - lr: 0.000134 - momentum: 0.000000
2023-10-06 14:16:37,381 epoch 3 - iter 180/304 - loss 0.21586374 - time (sec): 67.97 - samples/sec: 265.25 - lr: 0.000132 - momentum: 0.000000
2023-10-06 14:16:49,144 epoch 3 - iter 210/304 - loss 0.20951350 - time (sec): 79.73 - samples/sec: 267.41 - lr: 0.000130 - momentum: 0.000000
2023-10-06 14:17:00,811 epoch 3 - iter 240/304 - loss 0.20749487 - time (sec): 91.40 - samples/sec: 267.39 - lr: 0.000128 - momentum: 0.000000
2023-10-06 14:17:12,634 epoch 3 - iter 270/304 - loss 0.20252725 - time (sec): 103.22 - samples/sec: 267.93 - lr: 0.000127 - momentum: 0.000000
2023-10-06 14:17:23,905 epoch 3 - iter 300/304 - loss 0.19933893 - time (sec): 114.49 - samples/sec: 266.80 - lr: 0.000125 - momentum: 0.000000
2023-10-06 14:17:25,518 ----------------------------------------------------------------------------------------------------
2023-10-06 14:17:25,518 EPOCH 3 done: loss 0.1990 - lr: 0.000125
2023-10-06 14:17:33,399 DEV : loss 0.18546858429908752 - f1-score (micro avg) 0.6987
2023-10-06 14:17:33,407 saving best model
2023-10-06 14:17:37,766 ----------------------------------------------------------------------------------------------------
2023-10-06 14:17:49,248 epoch 4 - iter 30/304 - loss 0.13091282 - time (sec): 11.48 - samples/sec: 256.89 - lr: 0.000123 - momentum: 0.000000
2023-10-06 14:18:01,293 epoch 4 - iter 60/304 - loss 0.12913109 - time (sec): 23.53 - samples/sec: 261.17 - lr: 0.000121 - momentum: 0.000000
2023-10-06 14:18:12,651 epoch 4 - iter 90/304 - loss 0.12301054 - time (sec): 34.88 - samples/sec: 256.29 - lr: 0.000119 - momentum: 0.000000
2023-10-06 14:18:24,503 epoch 4 - iter 120/304 - loss 0.11594677 - time (sec): 46.73 - samples/sec: 254.76 - lr: 0.000118 - momentum: 0.000000
2023-10-06 14:18:36,414 epoch 4 - iter 150/304 - loss 0.11223834 - time (sec): 58.65 - samples/sec: 253.88 - lr: 0.000116 - momentum: 0.000000
2023-10-06 14:18:48,710 epoch 4 - iter 180/304 - loss 0.11360638 - time (sec): 70.94 - samples/sec: 254.05 - lr: 0.000114 - momentum: 0.000000
2023-10-06 14:19:01,112 epoch 4 - iter 210/304 - loss 0.11598109 - time (sec): 83.34 - samples/sec: 255.32 - lr: 0.000112 - momentum: 0.000000
2023-10-06 14:19:13,227 epoch 4 - iter 240/304 - loss 0.11480521 - time (sec): 95.46 - samples/sec: 255.52 - lr: 0.000111 - momentum: 0.000000
2023-10-06 14:19:25,625 epoch 4 - iter 270/304 - loss 0.11435502 - time (sec): 107.86 - samples/sec: 256.28 - lr: 0.000109 - momentum: 0.000000
2023-10-06 14:19:37,641 epoch 4 - iter 300/304 - loss 0.11002677 - time (sec): 119.87 - samples/sec: 256.46 - lr: 0.000107 - momentum: 0.000000
2023-10-06 14:19:38,872 ----------------------------------------------------------------------------------------------------
2023-10-06 14:19:38,873 EPOCH 4 done: loss 0.1096 - lr: 0.000107
2023-10-06 14:19:46,800 DEV : loss 0.1540684998035431 - f1-score (micro avg) 0.8169
2023-10-06 14:19:46,809 saving best model
2023-10-06 14:19:51,173 ----------------------------------------------------------------------------------------------------
2023-10-06 14:20:02,875 epoch 5 - iter 30/304 - loss 0.06569301 - time (sec): 11.70 - samples/sec: 253.60 - lr: 0.000105 - momentum: 0.000000
2023-10-06 14:20:15,213 epoch 5 - iter 60/304 - loss 0.06515493 - time (sec): 24.04 - samples/sec: 260.50 - lr: 0.000103 - momentum: 0.000000
2023-10-06 14:20:27,606 epoch 5 - iter 90/304 - loss 0.06435294 - time (sec): 36.43 - samples/sec: 257.99 - lr: 0.000102 - momentum: 0.000000
2023-10-06 14:20:39,487 epoch 5 - iter 120/304 - loss 0.06345297 - time (sec): 48.31 - samples/sec: 255.22 - lr: 0.000100 - momentum: 0.000000
2023-10-06 14:20:51,426 epoch 5 - iter 150/304 - loss 0.06293608 - time (sec): 60.25 - samples/sec: 254.97 - lr: 0.000098 - momentum: 0.000000
2023-10-06 14:21:04,316 epoch 5 - iter 180/304 - loss 0.06304714 - time (sec): 73.14 - samples/sec: 256.54 - lr: 0.000096 - momentum: 0.000000
2023-10-06 14:21:16,681 epoch 5 - iter 210/304 - loss 0.07005881 - time (sec): 85.51 - samples/sec: 257.33 - lr: 0.000094 - momentum: 0.000000
2023-10-06 14:21:28,657 epoch 5 - iter 240/304 - loss 0.07079656 - time (sec): 97.48 - samples/sec: 255.02 - lr: 0.000093 - momentum: 0.000000
2023-10-06 14:21:40,448 epoch 5 - iter 270/304 - loss 0.06829423 - time (sec): 109.27 - samples/sec: 254.92 - lr: 0.000091 - momentum: 0.000000
2023-10-06 14:21:51,676 epoch 5 - iter 300/304 - loss 0.06782035 - time (sec): 120.50 - samples/sec: 253.91 - lr: 0.000089 - momentum: 0.000000
2023-10-06 14:21:53,203 ----------------------------------------------------------------------------------------------------
2023-10-06 14:21:53,204 EPOCH 5 done: loss 0.0681 - lr: 0.000089
2023-10-06 14:22:01,230 DEV : loss 0.14909522235393524 - f1-score (micro avg) 0.8284
2023-10-06 14:22:01,238 saving best model
2023-10-06 14:22:05,592 ----------------------------------------------------------------------------------------------------
2023-10-06 14:22:17,219 epoch 6 - iter 30/304 - loss 0.02579684 - time (sec): 11.63 - samples/sec: 253.40 - lr: 0.000087 - momentum: 0.000000
2023-10-06 14:22:28,885 epoch 6 - iter 60/304 - loss 0.03871116 - time (sec): 23.29 - samples/sec: 250.65 - lr: 0.000085 - momentum: 0.000000
2023-10-06 14:22:40,696 epoch 6 - iter 90/304 - loss 0.03597576 - time (sec): 35.10 - samples/sec: 249.02 - lr: 0.000084 - momentum: 0.000000
2023-10-06 14:22:52,987 epoch 6 - iter 120/304 - loss 0.04134854 - time (sec): 47.39 - samples/sec: 251.11 - lr: 0.000082 - momentum: 0.000000
2023-10-06 14:23:05,126 epoch 6 - iter 150/304 - loss 0.03971115 - time (sec): 59.53 - samples/sec: 253.00 - lr: 0.000080 - momentum: 0.000000
2023-10-06 14:23:17,267 epoch 6 - iter 180/304 - loss 0.04314250 - time (sec): 71.67 - samples/sec: 253.75 - lr: 0.000078 - momentum: 0.000000
2023-10-06 14:23:29,160 epoch 6 - iter 210/304 - loss 0.04971771 - time (sec): 83.57 - samples/sec: 254.08 - lr: 0.000077 - momentum: 0.000000
2023-10-06 14:23:41,053 epoch 6 - iter 240/304 - loss 0.05075503 - time (sec): 95.46 - samples/sec: 253.45 - lr: 0.000075 - momentum: 0.000000
2023-10-06 14:23:52,975 epoch 6 - iter 270/304 - loss 0.05062134 - time (sec): 107.38 - samples/sec: 253.36 - lr: 0.000073 - momentum: 0.000000
2023-10-06 14:24:05,473 epoch 6 - iter 300/304 - loss 0.04896354 - time (sec): 119.88 - samples/sec: 254.14 - lr: 0.000071 - momentum: 0.000000
2023-10-06 14:24:07,244 ----------------------------------------------------------------------------------------------------
2023-10-06 14:24:07,244 EPOCH 6 done: loss 0.0503 - lr: 0.000071
2023-10-06 14:24:15,275 DEV : loss 0.1544189751148224 - f1-score (micro avg) 0.8257
2023-10-06 14:24:15,282 ----------------------------------------------------------------------------------------------------
2023-10-06 14:24:28,110 epoch 7 - iter 30/304 - loss 0.06052569 - time (sec): 12.83 - samples/sec: 269.91 - lr: 0.000069 - momentum: 0.000000
2023-10-06 14:24:40,058 epoch 7 - iter 60/304 - loss 0.04475238 - time (sec): 24.77 - samples/sec: 259.51 - lr: 0.000068 - momentum: 0.000000
2023-10-06 14:24:51,827 epoch 7 - iter 90/304 - loss 0.04355562 - time (sec): 36.54 - samples/sec: 259.31 - lr: 0.000066 - momentum: 0.000000
2023-10-06 14:25:03,072 epoch 7 - iter 120/304 - loss 0.04393992 - time (sec): 47.79 - samples/sec: 253.95 - lr: 0.000064 - momentum: 0.000000
2023-10-06 14:25:15,495 epoch 7 - iter 150/304 - loss 0.04278608 - time (sec): 60.21 - samples/sec: 254.55 - lr: 0.000062 - momentum: 0.000000
2023-10-06 14:25:27,238 epoch 7 - iter 180/304 - loss 0.03979482 - time (sec): 71.95 - samples/sec: 253.66 - lr: 0.000061 - momentum: 0.000000
2023-10-06 14:25:39,338 epoch 7 - iter 210/304 - loss 0.03687164 - time (sec): 84.05 - samples/sec: 253.43 - lr: 0.000059 - momentum: 0.000000
2023-10-06 14:25:51,070 epoch 7 - iter 240/304 - loss 0.03885836 - time (sec): 95.79 - samples/sec: 253.28 - lr: 0.000057 - momentum: 0.000000
2023-10-06 14:26:03,398 epoch 7 - iter 270/304 - loss 0.03622058 - time (sec): 108.11 - samples/sec: 254.27 - lr: 0.000055 - momentum: 0.000000
2023-10-06 14:26:15,655 epoch 7 - iter 300/304 - loss 0.03868131 - time (sec): 120.37 - samples/sec: 254.71 - lr: 0.000054 - momentum: 0.000000
2023-10-06 14:26:17,064 ----------------------------------------------------------------------------------------------------
2023-10-06 14:26:17,065 EPOCH 7 done: loss 0.0383 - lr: 0.000054
2023-10-06 14:26:25,110 DEV : loss 0.15451328456401825 - f1-score (micro avg) 0.8367
2023-10-06 14:26:25,118 saving best model
2023-10-06 14:26:29,468 ----------------------------------------------------------------------------------------------------
2023-10-06 14:26:41,475 epoch 8 - iter 30/304 - loss 0.02165609 - time (sec): 12.01 - samples/sec: 254.30 - lr: 0.000052 - momentum: 0.000000
2023-10-06 14:26:53,772 epoch 8 - iter 60/304 - loss 0.04272985 - time (sec): 24.30 - samples/sec: 256.60 - lr: 0.000050 - momentum: 0.000000
2023-10-06 14:27:05,779 epoch 8 - iter 90/304 - loss 0.03773130 - time (sec): 36.31 - samples/sec: 255.44 - lr: 0.000048 - momentum: 0.000000
2023-10-06 14:27:18,542 epoch 8 - iter 120/304 - loss 0.03506583 - time (sec): 49.07 - samples/sec: 257.66 - lr: 0.000046 - momentum: 0.000000
2023-10-06 14:27:30,602 epoch 8 - iter 150/304 - loss 0.03570404 - time (sec): 61.13 - samples/sec: 256.42 - lr: 0.000045 - momentum: 0.000000
2023-10-06 14:27:41,936 epoch 8 - iter 180/304 - loss 0.03432633 - time (sec): 72.47 - samples/sec: 254.27 - lr: 0.000043 - momentum: 0.000000
2023-10-06 14:27:53,914 epoch 8 - iter 210/304 - loss 0.03452223 - time (sec): 84.44 - samples/sec: 253.22 - lr: 0.000041 - momentum: 0.000000
2023-10-06 14:28:05,627 epoch 8 - iter 240/304 - loss 0.03310915 - time (sec): 96.16 - samples/sec: 252.85 - lr: 0.000039 - momentum: 0.000000
2023-10-06 14:28:17,751 epoch 8 - iter 270/304 - loss 0.03337918 - time (sec): 108.28 - samples/sec: 253.27 - lr: 0.000038 - momentum: 0.000000
2023-10-06 14:28:30,045 epoch 8 - iter 300/304 - loss 0.03190035 - time (sec): 120.58 - samples/sec: 253.70 - lr: 0.000036 - momentum: 0.000000
2023-10-06 14:28:31,609 ----------------------------------------------------------------------------------------------------
2023-10-06 14:28:31,609 EPOCH 8 done: loss 0.0315 - lr: 0.000036
2023-10-06 14:28:39,657 DEV : loss 0.1636699140071869 - f1-score (micro avg) 0.837
2023-10-06 14:28:39,666 saving best model
2023-10-06 14:28:44,025 ----------------------------------------------------------------------------------------------------
2023-10-06 14:28:56,685 epoch 9 - iter 30/304 - loss 0.01426336 - time (sec): 12.66 - samples/sec: 262.21 - lr: 0.000034 - momentum: 0.000000
2023-10-06 14:29:09,194 epoch 9 - iter 60/304 - loss 0.01439267 - time (sec): 25.17 - samples/sec: 259.14 - lr: 0.000032 - momentum: 0.000000
2023-10-06 14:29:20,744 epoch 9 - iter 90/304 - loss 0.01983298 - time (sec): 36.72 - samples/sec: 253.67 - lr: 0.000030 - momentum: 0.000000
2023-10-06 14:29:33,082 epoch 9 - iter 120/304 - loss 0.01866103 - time (sec): 49.06 - samples/sec: 254.65 - lr: 0.000029 - momentum: 0.000000
2023-10-06 14:29:45,307 epoch 9 - iter 150/304 - loss 0.02460981 - time (sec): 61.28 - samples/sec: 255.99 - lr: 0.000027 - momentum: 0.000000
2023-10-06 14:29:57,380 epoch 9 - iter 180/304 - loss 0.02524037 - time (sec): 73.35 - samples/sec: 255.68 - lr: 0.000025 - momentum: 0.000000
2023-10-06 14:30:09,567 epoch 9 - iter 210/304 - loss 0.02667408 - time (sec): 85.54 - samples/sec: 256.38 - lr: 0.000023 - momentum: 0.000000
2023-10-06 14:30:20,750 epoch 9 - iter 240/304 - loss 0.02742361 - time (sec): 96.72 - samples/sec: 255.42 - lr: 0.000022 - momentum: 0.000000
2023-10-06 14:30:32,314 epoch 9 - iter 270/304 - loss 0.02776823 - time (sec): 108.29 - samples/sec: 256.06 - lr: 0.000020 - momentum: 0.000000
2023-10-06 14:30:43,325 epoch 9 - iter 300/304 - loss 0.02735437 - time (sec): 119.30 - samples/sec: 256.23 - lr: 0.000018 - momentum: 0.000000
2023-10-06 14:30:44,855 ----------------------------------------------------------------------------------------------------
2023-10-06 14:30:44,856 EPOCH 9 done: loss 0.0270 - lr: 0.000018
2023-10-06 14:30:52,100 DEV : loss 0.16385288536548615 - f1-score (micro avg) 0.8431
2023-10-06 14:30:52,108 saving best model
2023-10-06 14:30:53,032 ----------------------------------------------------------------------------------------------------
2023-10-06 14:31:04,431 epoch 10 - iter 30/304 - loss 0.02745366 - time (sec): 11.40 - samples/sec: 262.51 - lr: 0.000016 - momentum: 0.000000
2023-10-06 14:31:15,791 epoch 10 - iter 60/304 - loss 0.02565244 - time (sec): 22.76 - samples/sec: 265.62 - lr: 0.000014 - momentum: 0.000000
2023-10-06 14:31:27,018 epoch 10 - iter 90/304 - loss 0.02200870 - time (sec): 33.98 - samples/sec: 266.83 - lr: 0.000013 - momentum: 0.000000
2023-10-06 14:31:38,453 epoch 10 - iter 120/304 - loss 0.02154119 - time (sec): 45.42 - samples/sec: 264.38 - lr: 0.000011 - momentum: 0.000000
2023-10-06 14:31:49,351 epoch 10 - iter 150/304 - loss 0.01862176 - time (sec): 56.32 - samples/sec: 261.87 - lr: 0.000009 - momentum: 0.000000
2023-10-06 14:32:01,026 epoch 10 - iter 180/304 - loss 0.02338622 - time (sec): 67.99 - samples/sec: 263.48 - lr: 0.000007 - momentum: 0.000000
2023-10-06 14:32:12,148 epoch 10 - iter 210/304 - loss 0.02194682 - time (sec): 79.11 - samples/sec: 264.10 - lr: 0.000006 - momentum: 0.000000
2023-10-06 14:32:23,856 epoch 10 - iter 240/304 - loss 0.02236526 - time (sec): 90.82 - samples/sec: 265.65 - lr: 0.000004 - momentum: 0.000000
2023-10-06 14:32:35,435 epoch 10 - iter 270/304 - loss 0.02102846 - time (sec): 102.40 - samples/sec: 267.80 - lr: 0.000002 - momentum: 0.000000
2023-10-06 14:32:47,064 epoch 10 - iter 300/304 - loss 0.02123298 - time (sec): 114.03 - samples/sec: 268.67 - lr: 0.000000 - momentum: 0.000000
2023-10-06 14:32:48,418 ----------------------------------------------------------------------------------------------------
2023-10-06 14:32:48,418 EPOCH 10 done: loss 0.0224 - lr: 0.000000
2023-10-06 14:32:55,632 DEV : loss 0.16673216223716736 - f1-score (micro avg) 0.841
2023-10-06 14:32:56,519 ----------------------------------------------------------------------------------------------------
2023-10-06 14:32:56,520 Loading model from best epoch ...
2023-10-06 14:33:00,143 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 14:33:06,776
Results:
- F-score (micro) 0.8082
- F-score (macro) 0.6229
- Accuracy 0.6843
By class:
precision recall f1-score support
scope 0.7722 0.8079 0.7896 151
pers 0.7778 0.9479 0.8545 96
work 0.7523 0.8632 0.8039 95
loc 0.6667 0.6667 0.6667 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7674 0.8534 0.8082 348
macro avg 0.5938 0.6571 0.6229 348
weighted avg 0.7607 0.8534 0.8036 348
2023-10-06 14:33:06,776 ----------------------------------------------------------------------------------------------------
|