File size: 25,453 Bytes
cdbbfa7 |
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 |
2023-10-19 03:02:32,455 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,456 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(31103, 768)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-11): 12 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=81, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-19 03:02:32,456 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,457 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 03:02:32,457 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,457 Train: 6900 sentences
2023-10-19 03:02:32,457 (train_with_dev=False, train_with_test=False)
2023-10-19 03:02:32,457 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,457 Training Params:
2023-10-19 03:02:32,457 - learning_rate: "3e-05"
2023-10-19 03:02:32,457 - mini_batch_size: "16"
2023-10-19 03:02:32,457 - max_epochs: "10"
2023-10-19 03:02:32,457 - shuffle: "True"
2023-10-19 03:02:32,457 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,457 Plugins:
2023-10-19 03:02:32,457 - TensorboardLogger
2023-10-19 03:02:32,457 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 03:02:32,457 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,457 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 03:02:32,458 - metric: "('micro avg', 'f1-score')"
2023-10-19 03:02:32,458 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,458 Computation:
2023-10-19 03:02:32,458 - compute on device: cuda:0
2023-10-19 03:02:32,458 - embedding storage: none
2023-10-19 03:02:32,458 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,458 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr3e-05-5"
2023-10-19 03:02:32,458 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,458 ----------------------------------------------------------------------------------------------------
2023-10-19 03:02:32,458 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 03:02:45,358 epoch 1 - iter 43/432 - loss 4.68092903 - time (sec): 12.90 - samples/sec: 472.22 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:02:59,668 epoch 1 - iter 86/432 - loss 3.80733117 - time (sec): 27.21 - samples/sec: 458.56 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:03:13,521 epoch 1 - iter 129/432 - loss 3.15933165 - time (sec): 41.06 - samples/sec: 465.39 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:03:26,787 epoch 1 - iter 172/432 - loss 2.80639142 - time (sec): 54.33 - samples/sec: 460.04 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:03:40,465 epoch 1 - iter 215/432 - loss 2.50948460 - time (sec): 68.01 - samples/sec: 458.64 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:03:53,954 epoch 1 - iter 258/432 - loss 2.29011944 - time (sec): 81.50 - samples/sec: 460.98 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:04:07,705 epoch 1 - iter 301/432 - loss 2.09775363 - time (sec): 95.25 - samples/sec: 459.80 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:04:21,038 epoch 1 - iter 344/432 - loss 1.95000051 - time (sec): 108.58 - samples/sec: 459.19 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:04:34,393 epoch 1 - iter 387/432 - loss 1.83143150 - time (sec): 121.93 - samples/sec: 456.61 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:04:48,237 epoch 1 - iter 430/432 - loss 1.71866002 - time (sec): 135.78 - samples/sec: 453.10 - lr: 0.000030 - momentum: 0.000000
2023-10-19 03:04:48,835 ----------------------------------------------------------------------------------------------------
2023-10-19 03:04:48,835 EPOCH 1 done: loss 1.7140 - lr: 0.000030
2023-10-19 03:05:01,077 DEV : loss 0.5552897453308105 - f1-score (micro avg) 0.6622
2023-10-19 03:05:01,101 saving best model
2023-10-19 03:05:01,517 ----------------------------------------------------------------------------------------------------
2023-10-19 03:05:15,028 epoch 2 - iter 43/432 - loss 0.60311222 - time (sec): 13.51 - samples/sec: 435.31 - lr: 0.000030 - momentum: 0.000000
2023-10-19 03:05:28,407 epoch 2 - iter 86/432 - loss 0.57492961 - time (sec): 26.89 - samples/sec: 450.97 - lr: 0.000029 - momentum: 0.000000
2023-10-19 03:05:42,437 epoch 2 - iter 129/432 - loss 0.57047978 - time (sec): 40.92 - samples/sec: 455.93 - lr: 0.000029 - momentum: 0.000000
2023-10-19 03:05:56,220 epoch 2 - iter 172/432 - loss 0.55732391 - time (sec): 54.70 - samples/sec: 450.69 - lr: 0.000029 - momentum: 0.000000
2023-10-19 03:06:10,611 epoch 2 - iter 215/432 - loss 0.53979872 - time (sec): 69.09 - samples/sec: 447.24 - lr: 0.000028 - momentum: 0.000000
2023-10-19 03:06:24,033 epoch 2 - iter 258/432 - loss 0.52406456 - time (sec): 82.51 - samples/sec: 452.59 - lr: 0.000028 - momentum: 0.000000
2023-10-19 03:06:38,941 epoch 2 - iter 301/432 - loss 0.51367307 - time (sec): 97.42 - samples/sec: 444.61 - lr: 0.000028 - momentum: 0.000000
2023-10-19 03:06:53,084 epoch 2 - iter 344/432 - loss 0.49754137 - time (sec): 111.57 - samples/sec: 443.70 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:07:07,204 epoch 2 - iter 387/432 - loss 0.48910598 - time (sec): 125.69 - samples/sec: 439.67 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:07:21,241 epoch 2 - iter 430/432 - loss 0.47410522 - time (sec): 139.72 - samples/sec: 441.12 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:07:21,774 ----------------------------------------------------------------------------------------------------
2023-10-19 03:07:21,774 EPOCH 2 done: loss 0.4748 - lr: 0.000027
2023-10-19 03:07:34,105 DEV : loss 0.3492853343486786 - f1-score (micro avg) 0.778
2023-10-19 03:07:34,129 saving best model
2023-10-19 03:07:35,382 ----------------------------------------------------------------------------------------------------
2023-10-19 03:07:49,725 epoch 3 - iter 43/432 - loss 0.32742202 - time (sec): 14.34 - samples/sec: 440.94 - lr: 0.000026 - momentum: 0.000000
2023-10-19 03:08:03,255 epoch 3 - iter 86/432 - loss 0.31063739 - time (sec): 27.87 - samples/sec: 437.58 - lr: 0.000026 - momentum: 0.000000
2023-10-19 03:08:18,407 epoch 3 - iter 129/432 - loss 0.31037428 - time (sec): 43.02 - samples/sec: 428.23 - lr: 0.000026 - momentum: 0.000000
2023-10-19 03:08:32,878 epoch 3 - iter 172/432 - loss 0.30284596 - time (sec): 57.49 - samples/sec: 425.34 - lr: 0.000025 - momentum: 0.000000
2023-10-19 03:08:47,535 epoch 3 - iter 215/432 - loss 0.29952088 - time (sec): 72.15 - samples/sec: 425.09 - lr: 0.000025 - momentum: 0.000000
2023-10-19 03:09:02,921 epoch 3 - iter 258/432 - loss 0.29399153 - time (sec): 87.54 - samples/sec: 423.60 - lr: 0.000025 - momentum: 0.000000
2023-10-19 03:09:17,555 epoch 3 - iter 301/432 - loss 0.29404747 - time (sec): 102.17 - samples/sec: 423.61 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:09:32,378 epoch 3 - iter 344/432 - loss 0.29589502 - time (sec): 116.99 - samples/sec: 424.08 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:09:46,405 epoch 3 - iter 387/432 - loss 0.29720740 - time (sec): 131.02 - samples/sec: 424.71 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:10:01,246 epoch 3 - iter 430/432 - loss 0.29631246 - time (sec): 145.86 - samples/sec: 422.71 - lr: 0.000023 - momentum: 0.000000
2023-10-19 03:10:01,690 ----------------------------------------------------------------------------------------------------
2023-10-19 03:10:01,690 EPOCH 3 done: loss 0.2959 - lr: 0.000023
2023-10-19 03:10:14,851 DEV : loss 0.3259921371936798 - f1-score (micro avg) 0.7982
2023-10-19 03:10:14,875 saving best model
2023-10-19 03:10:16,119 ----------------------------------------------------------------------------------------------------
2023-10-19 03:10:31,459 epoch 4 - iter 43/432 - loss 0.20672208 - time (sec): 15.34 - samples/sec: 401.20 - lr: 0.000023 - momentum: 0.000000
2023-10-19 03:10:46,531 epoch 4 - iter 86/432 - loss 0.19852246 - time (sec): 30.41 - samples/sec: 418.47 - lr: 0.000023 - momentum: 0.000000
2023-10-19 03:11:00,882 epoch 4 - iter 129/432 - loss 0.19616414 - time (sec): 44.76 - samples/sec: 421.57 - lr: 0.000022 - momentum: 0.000000
2023-10-19 03:11:14,827 epoch 4 - iter 172/432 - loss 0.20627791 - time (sec): 58.71 - samples/sec: 424.33 - lr: 0.000022 - momentum: 0.000000
2023-10-19 03:11:29,748 epoch 4 - iter 215/432 - loss 0.21224683 - time (sec): 73.63 - samples/sec: 421.12 - lr: 0.000022 - momentum: 0.000000
2023-10-19 03:11:43,731 epoch 4 - iter 258/432 - loss 0.21227075 - time (sec): 87.61 - samples/sec: 424.32 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:11:58,975 epoch 4 - iter 301/432 - loss 0.21292796 - time (sec): 102.85 - samples/sec: 419.09 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:12:13,655 epoch 4 - iter 344/432 - loss 0.21307796 - time (sec): 117.54 - samples/sec: 418.07 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:12:29,419 epoch 4 - iter 387/432 - loss 0.21476478 - time (sec): 133.30 - samples/sec: 413.81 - lr: 0.000020 - momentum: 0.000000
2023-10-19 03:12:44,470 epoch 4 - iter 430/432 - loss 0.21820196 - time (sec): 148.35 - samples/sec: 414.61 - lr: 0.000020 - momentum: 0.000000
2023-10-19 03:12:44,864 ----------------------------------------------------------------------------------------------------
2023-10-19 03:12:44,864 EPOCH 4 done: loss 0.2178 - lr: 0.000020
2023-10-19 03:12:58,149 DEV : loss 0.2954443395137787 - f1-score (micro avg) 0.8237
2023-10-19 03:12:58,173 saving best model
2023-10-19 03:12:59,444 ----------------------------------------------------------------------------------------------------
2023-10-19 03:13:15,154 epoch 5 - iter 43/432 - loss 0.15390087 - time (sec): 15.71 - samples/sec: 415.14 - lr: 0.000020 - momentum: 0.000000
2023-10-19 03:13:30,869 epoch 5 - iter 86/432 - loss 0.15550679 - time (sec): 31.42 - samples/sec: 403.88 - lr: 0.000019 - momentum: 0.000000
2023-10-19 03:13:45,378 epoch 5 - iter 129/432 - loss 0.15604865 - time (sec): 45.93 - samples/sec: 402.33 - lr: 0.000019 - momentum: 0.000000
2023-10-19 03:14:00,384 epoch 5 - iter 172/432 - loss 0.15506530 - time (sec): 60.94 - samples/sec: 408.22 - lr: 0.000019 - momentum: 0.000000
2023-10-19 03:14:14,455 epoch 5 - iter 215/432 - loss 0.15758901 - time (sec): 75.01 - samples/sec: 410.23 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:14:29,344 epoch 5 - iter 258/432 - loss 0.15953645 - time (sec): 89.90 - samples/sec: 411.80 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:14:44,219 epoch 5 - iter 301/432 - loss 0.15917566 - time (sec): 104.77 - samples/sec: 409.05 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:14:59,634 epoch 5 - iter 344/432 - loss 0.15850960 - time (sec): 120.19 - samples/sec: 409.33 - lr: 0.000017 - momentum: 0.000000
2023-10-19 03:15:15,342 epoch 5 - iter 387/432 - loss 0.16067848 - time (sec): 135.90 - samples/sec: 407.33 - lr: 0.000017 - momentum: 0.000000
2023-10-19 03:15:29,540 epoch 5 - iter 430/432 - loss 0.16521243 - time (sec): 150.09 - samples/sec: 410.51 - lr: 0.000017 - momentum: 0.000000
2023-10-19 03:15:30,009 ----------------------------------------------------------------------------------------------------
2023-10-19 03:15:30,010 EPOCH 5 done: loss 0.1649 - lr: 0.000017
2023-10-19 03:15:43,137 DEV : loss 0.3015434145927429 - f1-score (micro avg) 0.8299
2023-10-19 03:15:43,162 saving best model
2023-10-19 03:15:44,425 ----------------------------------------------------------------------------------------------------
2023-10-19 03:15:58,770 epoch 6 - iter 43/432 - loss 0.13202038 - time (sec): 14.34 - samples/sec: 417.18 - lr: 0.000016 - momentum: 0.000000
2023-10-19 03:16:13,650 epoch 6 - iter 86/432 - loss 0.12553836 - time (sec): 29.22 - samples/sec: 407.79 - lr: 0.000016 - momentum: 0.000000
2023-10-19 03:16:28,364 epoch 6 - iter 129/432 - loss 0.12939794 - time (sec): 43.94 - samples/sec: 417.91 - lr: 0.000016 - momentum: 0.000000
2023-10-19 03:16:42,571 epoch 6 - iter 172/432 - loss 0.12769753 - time (sec): 58.14 - samples/sec: 425.46 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:16:56,766 epoch 6 - iter 215/432 - loss 0.12873983 - time (sec): 72.34 - samples/sec: 426.63 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:17:11,198 epoch 6 - iter 258/432 - loss 0.13206339 - time (sec): 86.77 - samples/sec: 424.89 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:17:25,555 epoch 6 - iter 301/432 - loss 0.12993628 - time (sec): 101.13 - samples/sec: 422.61 - lr: 0.000014 - momentum: 0.000000
2023-10-19 03:17:38,273 epoch 6 - iter 344/432 - loss 0.13004768 - time (sec): 113.85 - samples/sec: 431.76 - lr: 0.000014 - momentum: 0.000000
2023-10-19 03:17:52,227 epoch 6 - iter 387/432 - loss 0.13032000 - time (sec): 127.80 - samples/sec: 434.94 - lr: 0.000014 - momentum: 0.000000
2023-10-19 03:18:05,986 epoch 6 - iter 430/432 - loss 0.13151672 - time (sec): 141.56 - samples/sec: 435.39 - lr: 0.000013 - momentum: 0.000000
2023-10-19 03:18:06,429 ----------------------------------------------------------------------------------------------------
2023-10-19 03:18:06,429 EPOCH 6 done: loss 0.1313 - lr: 0.000013
2023-10-19 03:18:18,383 DEV : loss 0.3147521913051605 - f1-score (micro avg) 0.837
2023-10-19 03:18:18,407 saving best model
2023-10-19 03:18:19,654 ----------------------------------------------------------------------------------------------------
2023-10-19 03:18:33,965 epoch 7 - iter 43/432 - loss 0.09978456 - time (sec): 14.31 - samples/sec: 439.36 - lr: 0.000013 - momentum: 0.000000
2023-10-19 03:18:47,773 epoch 7 - iter 86/432 - loss 0.10425709 - time (sec): 28.12 - samples/sec: 442.24 - lr: 0.000013 - momentum: 0.000000
2023-10-19 03:19:01,199 epoch 7 - iter 129/432 - loss 0.10081928 - time (sec): 41.54 - samples/sec: 444.14 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:19:15,447 epoch 7 - iter 172/432 - loss 0.10228024 - time (sec): 55.79 - samples/sec: 445.10 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:19:28,556 epoch 7 - iter 215/432 - loss 0.09910047 - time (sec): 68.90 - samples/sec: 447.41 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:19:42,583 epoch 7 - iter 258/432 - loss 0.09892292 - time (sec): 82.93 - samples/sec: 445.88 - lr: 0.000011 - momentum: 0.000000
2023-10-19 03:19:56,325 epoch 7 - iter 301/432 - loss 0.09965975 - time (sec): 96.67 - samples/sec: 450.23 - lr: 0.000011 - momentum: 0.000000
2023-10-19 03:20:09,811 epoch 7 - iter 344/432 - loss 0.10180121 - time (sec): 110.16 - samples/sec: 449.26 - lr: 0.000011 - momentum: 0.000000
2023-10-19 03:20:23,439 epoch 7 - iter 387/432 - loss 0.10327251 - time (sec): 123.78 - samples/sec: 447.78 - lr: 0.000010 - momentum: 0.000000
2023-10-19 03:20:37,405 epoch 7 - iter 430/432 - loss 0.10270499 - time (sec): 137.75 - samples/sec: 448.10 - lr: 0.000010 - momentum: 0.000000
2023-10-19 03:20:38,070 ----------------------------------------------------------------------------------------------------
2023-10-19 03:20:38,070 EPOCH 7 done: loss 0.1030 - lr: 0.000010
2023-10-19 03:20:50,296 DEV : loss 0.3245373070240021 - f1-score (micro avg) 0.8369
2023-10-19 03:20:50,321 ----------------------------------------------------------------------------------------------------
2023-10-19 03:21:03,617 epoch 8 - iter 43/432 - loss 0.08836329 - time (sec): 13.30 - samples/sec: 459.56 - lr: 0.000010 - momentum: 0.000000
2023-10-19 03:21:18,106 epoch 8 - iter 86/432 - loss 0.08588265 - time (sec): 27.78 - samples/sec: 423.45 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:21:32,684 epoch 8 - iter 129/432 - loss 0.08683372 - time (sec): 42.36 - samples/sec: 424.46 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:21:46,306 epoch 8 - iter 172/432 - loss 0.08510177 - time (sec): 55.98 - samples/sec: 440.66 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:21:59,965 epoch 8 - iter 215/432 - loss 0.08335334 - time (sec): 69.64 - samples/sec: 439.41 - lr: 0.000008 - momentum: 0.000000
2023-10-19 03:22:13,850 epoch 8 - iter 258/432 - loss 0.08326947 - time (sec): 83.53 - samples/sec: 439.89 - lr: 0.000008 - momentum: 0.000000
2023-10-19 03:22:28,357 epoch 8 - iter 301/432 - loss 0.08295965 - time (sec): 98.03 - samples/sec: 438.39 - lr: 0.000008 - momentum: 0.000000
2023-10-19 03:22:42,156 epoch 8 - iter 344/432 - loss 0.08364151 - time (sec): 111.83 - samples/sec: 440.99 - lr: 0.000007 - momentum: 0.000000
2023-10-19 03:22:55,572 epoch 8 - iter 387/432 - loss 0.08380031 - time (sec): 125.25 - samples/sec: 443.16 - lr: 0.000007 - momentum: 0.000000
2023-10-19 03:23:09,667 epoch 8 - iter 430/432 - loss 0.08256002 - time (sec): 139.34 - samples/sec: 442.31 - lr: 0.000007 - momentum: 0.000000
2023-10-19 03:23:10,370 ----------------------------------------------------------------------------------------------------
2023-10-19 03:23:10,370 EPOCH 8 done: loss 0.0828 - lr: 0.000007
2023-10-19 03:23:22,392 DEV : loss 0.34586212038993835 - f1-score (micro avg) 0.8435
2023-10-19 03:23:22,416 saving best model
2023-10-19 03:23:24,523 ----------------------------------------------------------------------------------------------------
2023-10-19 03:23:37,690 epoch 9 - iter 43/432 - loss 0.06404456 - time (sec): 13.17 - samples/sec: 467.43 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:23:51,542 epoch 9 - iter 86/432 - loss 0.06912955 - time (sec): 27.02 - samples/sec: 463.82 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:24:04,557 epoch 9 - iter 129/432 - loss 0.06602599 - time (sec): 40.03 - samples/sec: 469.64 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:24:18,441 epoch 9 - iter 172/432 - loss 0.06580031 - time (sec): 53.92 - samples/sec: 468.30 - lr: 0.000005 - momentum: 0.000000
2023-10-19 03:24:32,240 epoch 9 - iter 215/432 - loss 0.06730200 - time (sec): 67.71 - samples/sec: 458.39 - lr: 0.000005 - momentum: 0.000000
2023-10-19 03:24:45,981 epoch 9 - iter 258/432 - loss 0.06853445 - time (sec): 81.46 - samples/sec: 456.87 - lr: 0.000005 - momentum: 0.000000
2023-10-19 03:24:59,976 epoch 9 - iter 301/432 - loss 0.06801088 - time (sec): 95.45 - samples/sec: 454.91 - lr: 0.000004 - momentum: 0.000000
2023-10-19 03:25:13,563 epoch 9 - iter 344/432 - loss 0.06752770 - time (sec): 109.04 - samples/sec: 453.30 - lr: 0.000004 - momentum: 0.000000
2023-10-19 03:25:27,798 epoch 9 - iter 387/432 - loss 0.06815869 - time (sec): 123.27 - samples/sec: 450.85 - lr: 0.000004 - momentum: 0.000000
2023-10-19 03:25:41,524 epoch 9 - iter 430/432 - loss 0.06769484 - time (sec): 137.00 - samples/sec: 449.74 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:25:41,970 ----------------------------------------------------------------------------------------------------
2023-10-19 03:25:41,971 EPOCH 9 done: loss 0.0678 - lr: 0.000003
2023-10-19 03:25:54,505 DEV : loss 0.35387569665908813 - f1-score (micro avg) 0.8449
2023-10-19 03:25:54,530 saving best model
2023-10-19 03:25:55,769 ----------------------------------------------------------------------------------------------------
2023-10-19 03:26:08,762 epoch 10 - iter 43/432 - loss 0.05227225 - time (sec): 12.99 - samples/sec: 462.56 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:26:22,942 epoch 10 - iter 86/432 - loss 0.05341720 - time (sec): 27.17 - samples/sec: 438.15 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:26:35,887 epoch 10 - iter 129/432 - loss 0.05487206 - time (sec): 40.12 - samples/sec: 454.00 - lr: 0.000002 - momentum: 0.000000
2023-10-19 03:26:50,149 epoch 10 - iter 172/432 - loss 0.05596544 - time (sec): 54.38 - samples/sec: 461.20 - lr: 0.000002 - momentum: 0.000000
2023-10-19 03:27:03,985 epoch 10 - iter 215/432 - loss 0.05733517 - time (sec): 68.21 - samples/sec: 458.73 - lr: 0.000002 - momentum: 0.000000
2023-10-19 03:27:17,924 epoch 10 - iter 258/432 - loss 0.05765922 - time (sec): 82.15 - samples/sec: 454.50 - lr: 0.000001 - momentum: 0.000000
2023-10-19 03:27:30,964 epoch 10 - iter 301/432 - loss 0.05769597 - time (sec): 95.19 - samples/sec: 455.32 - lr: 0.000001 - momentum: 0.000000
2023-10-19 03:27:45,282 epoch 10 - iter 344/432 - loss 0.05926565 - time (sec): 109.51 - samples/sec: 453.13 - lr: 0.000001 - momentum: 0.000000
2023-10-19 03:27:59,510 epoch 10 - iter 387/432 - loss 0.05821429 - time (sec): 123.74 - samples/sec: 448.10 - lr: 0.000000 - momentum: 0.000000
2023-10-19 03:28:12,650 epoch 10 - iter 430/432 - loss 0.05761600 - time (sec): 136.88 - samples/sec: 450.35 - lr: 0.000000 - momentum: 0.000000
2023-10-19 03:28:13,196 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:13,196 EPOCH 10 done: loss 0.0576 - lr: 0.000000
2023-10-19 03:28:25,462 DEV : loss 0.3606269955635071 - f1-score (micro avg) 0.841
2023-10-19 03:28:25,916 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:25,917 Loading model from best epoch ...
2023-10-19 03:28:28,137 SequenceTagger predicts: Dictionary with 81 tags: O, S-location-route, B-location-route, E-location-route, I-location-route, S-location-stop, B-location-stop, E-location-stop, I-location-stop, S-trigger, B-trigger, E-trigger, I-trigger, S-organization-company, B-organization-company, E-organization-company, I-organization-company, S-location-city, B-location-city, E-location-city, I-location-city, S-location, B-location, E-location, I-location, S-event-cause, B-event-cause, E-event-cause, I-event-cause, S-location-street, B-location-street, E-location-street, I-location-street, S-time, B-time, E-time, I-time, S-date, B-date, E-date, I-date, S-number, B-number, E-number, I-number, S-duration, B-duration, E-duration, I-duration, S-organization
2023-10-19 03:28:44,997
Results:
- F-score (micro) 0.7571
- F-score (macro) 0.5822
- Accuracy 0.6503
By class:
precision recall f1-score support
trigger 0.6612 0.5342 0.5910 833
location-stop 0.8622 0.8340 0.8478 765
location 0.7932 0.8421 0.8169 665
location-city 0.8075 0.8746 0.8397 566
date 0.8753 0.8376 0.8560 394
location-street 0.9339 0.8782 0.9052 386
time 0.7917 0.8906 0.8382 256
location-route 0.8205 0.6761 0.7413 284
organization-company 0.7867 0.7024 0.7421 252
distance 0.9824 1.0000 0.9911 167
number 0.6776 0.8322 0.7470 149
duration 0.3636 0.3436 0.3533 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.8788 0.4203 0.5686 69
organization 0.5185 0.5000 0.5091 28
person 0.5556 1.0000 0.7143 10
set 0.0000 0.0000 0.0000 0
org-position 0.0000 0.0000 0.0000 1
money 0.0000 0.0000 0.0000 0
micro avg 0.7516 0.7626 0.7571 4988
macro avg 0.5952 0.5877 0.5822 4988
weighted avg 0.7897 0.7626 0.7725 4988
2023-10-19 03:28:44,997 ----------------------------------------------------------------------------------------------------
|