File size: 25,460 Bytes
24cbc73 |
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 03:28:58,589 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,590 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 03:28:58,590 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,590 Corpus: 6900 train + 1576 dev + 1833 test sentences
2023-10-19 03:28:58,591 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,591 Train: 6900 sentences
2023-10-19 03:28:58,591 (train_with_dev=False, train_with_test=False)
2023-10-19 03:28:58,591 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,591 Training Params:
2023-10-19 03:28:58,591 - learning_rate: "5e-05"
2023-10-19 03:28:58,591 - mini_batch_size: "16"
2023-10-19 03:28:58,591 - max_epochs: "10"
2023-10-19 03:28:58,591 - shuffle: "True"
2023-10-19 03:28:58,591 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,591 Plugins:
2023-10-19 03:28:58,591 - TensorboardLogger
2023-10-19 03:28:58,591 - LinearScheduler | warmup_fraction: '0.1'
2023-10-19 03:28:58,591 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,591 Final evaluation on model from best epoch (best-model.pt)
2023-10-19 03:28:58,591 - metric: "('micro avg', 'f1-score')"
2023-10-19 03:28:58,591 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,591 Computation:
2023-10-19 03:28:58,592 - compute on device: cuda:0
2023-10-19 03:28:58,592 - embedding storage: none
2023-10-19 03:28:58,592 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,592 Model training base path: "autotrain-flair-mobie-gbert_base-bs16-e10-lr5e-05-5"
2023-10-19 03:28:58,592 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,592 ----------------------------------------------------------------------------------------------------
2023-10-19 03:28:58,592 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-19 03:29:11,756 epoch 1 - iter 43/432 - loss 4.47089142 - time (sec): 13.16 - samples/sec: 462.75 - lr: 0.000005 - momentum: 0.000000
2023-10-19 03:29:26,354 epoch 1 - iter 86/432 - loss 3.40687789 - time (sec): 27.76 - samples/sec: 449.44 - lr: 0.000010 - momentum: 0.000000
2023-10-19 03:29:40,695 epoch 1 - iter 129/432 - loss 2.81984328 - time (sec): 42.10 - samples/sec: 453.89 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:29:54,625 epoch 1 - iter 172/432 - loss 2.48664817 - time (sec): 56.03 - samples/sec: 446.05 - lr: 0.000020 - momentum: 0.000000
2023-10-19 03:30:09,101 epoch 1 - iter 215/432 - loss 2.20938885 - time (sec): 70.51 - samples/sec: 442.36 - lr: 0.000025 - momentum: 0.000000
2023-10-19 03:30:23,495 epoch 1 - iter 258/432 - loss 2.00682608 - time (sec): 84.90 - samples/sec: 442.49 - lr: 0.000030 - momentum: 0.000000
2023-10-19 03:30:38,275 epoch 1 - iter 301/432 - loss 1.83000069 - time (sec): 99.68 - samples/sec: 439.34 - lr: 0.000035 - momentum: 0.000000
2023-10-19 03:30:52,684 epoch 1 - iter 344/432 - loss 1.69649278 - time (sec): 114.09 - samples/sec: 437.00 - lr: 0.000040 - momentum: 0.000000
2023-10-19 03:31:07,161 epoch 1 - iter 387/432 - loss 1.59029602 - time (sec): 128.57 - samples/sec: 433.05 - lr: 0.000045 - momentum: 0.000000
2023-10-19 03:31:22,191 epoch 1 - iter 430/432 - loss 1.48899645 - time (sec): 143.60 - samples/sec: 428.42 - lr: 0.000050 - momentum: 0.000000
2023-10-19 03:31:22,823 ----------------------------------------------------------------------------------------------------
2023-10-19 03:31:22,823 EPOCH 1 done: loss 1.4847 - lr: 0.000050
2023-10-19 03:31:35,250 DEV : loss 0.46572113037109375 - f1-score (micro avg) 0.7239
2023-10-19 03:31:35,274 saving best model
2023-10-19 03:31:35,705 ----------------------------------------------------------------------------------------------------
2023-10-19 03:31:49,420 epoch 2 - iter 43/432 - loss 0.47787826 - time (sec): 13.71 - samples/sec: 428.87 - lr: 0.000049 - momentum: 0.000000
2023-10-19 03:32:02,986 epoch 2 - iter 86/432 - loss 0.46422594 - time (sec): 27.28 - samples/sec: 444.51 - lr: 0.000049 - momentum: 0.000000
2023-10-19 03:32:17,113 epoch 2 - iter 129/432 - loss 0.47090059 - time (sec): 41.41 - samples/sec: 450.56 - lr: 0.000048 - momentum: 0.000000
2023-10-19 03:32:30,939 epoch 2 - iter 172/432 - loss 0.46448888 - time (sec): 55.23 - samples/sec: 446.35 - lr: 0.000048 - momentum: 0.000000
2023-10-19 03:32:45,263 epoch 2 - iter 215/432 - loss 0.45313238 - time (sec): 69.56 - samples/sec: 444.26 - lr: 0.000047 - momentum: 0.000000
2023-10-19 03:32:58,608 epoch 2 - iter 258/432 - loss 0.44160239 - time (sec): 82.90 - samples/sec: 450.48 - lr: 0.000047 - momentum: 0.000000
2023-10-19 03:33:13,377 epoch 2 - iter 301/432 - loss 0.43407568 - time (sec): 97.67 - samples/sec: 443.48 - lr: 0.000046 - momentum: 0.000000
2023-10-19 03:33:27,360 epoch 2 - iter 344/432 - loss 0.42190457 - time (sec): 111.65 - samples/sec: 443.35 - lr: 0.000046 - momentum: 0.000000
2023-10-19 03:33:41,325 epoch 2 - iter 387/432 - loss 0.41622439 - time (sec): 125.62 - samples/sec: 439.91 - lr: 0.000045 - momentum: 0.000000
2023-10-19 03:33:55,134 epoch 2 - iter 430/432 - loss 0.40436365 - time (sec): 139.43 - samples/sec: 442.06 - lr: 0.000044 - momentum: 0.000000
2023-10-19 03:33:55,654 ----------------------------------------------------------------------------------------------------
2023-10-19 03:33:55,654 EPOCH 2 done: loss 0.4050 - lr: 0.000044
2023-10-19 03:34:08,178 DEV : loss 0.3259238302707672 - f1-score (micro avg) 0.7826
2023-10-19 03:34:08,202 saving best model
2023-10-19 03:34:09,461 ----------------------------------------------------------------------------------------------------
2023-10-19 03:34:23,428 epoch 3 - iter 43/432 - loss 0.28190490 - time (sec): 13.97 - samples/sec: 452.84 - lr: 0.000044 - momentum: 0.000000
2023-10-19 03:34:36,562 epoch 3 - iter 86/432 - loss 0.26687223 - time (sec): 27.10 - samples/sec: 450.04 - lr: 0.000043 - momentum: 0.000000
2023-10-19 03:34:51,195 epoch 3 - iter 129/432 - loss 0.26449528 - time (sec): 41.73 - samples/sec: 441.48 - lr: 0.000043 - momentum: 0.000000
2023-10-19 03:35:05,122 epoch 3 - iter 172/432 - loss 0.25665322 - time (sec): 55.66 - samples/sec: 439.37 - lr: 0.000042 - momentum: 0.000000
2023-10-19 03:35:19,292 epoch 3 - iter 215/432 - loss 0.25287570 - time (sec): 69.83 - samples/sec: 439.23 - lr: 0.000042 - momentum: 0.000000
2023-10-19 03:35:34,052 epoch 3 - iter 258/432 - loss 0.24910280 - time (sec): 84.59 - samples/sec: 438.36 - lr: 0.000041 - momentum: 0.000000
2023-10-19 03:35:48,084 epoch 3 - iter 301/432 - loss 0.25157812 - time (sec): 98.62 - samples/sec: 438.86 - lr: 0.000041 - momentum: 0.000000
2023-10-19 03:36:02,258 epoch 3 - iter 344/432 - loss 0.25377885 - time (sec): 112.80 - samples/sec: 439.87 - lr: 0.000040 - momentum: 0.000000
2023-10-19 03:36:15,813 epoch 3 - iter 387/432 - loss 0.25537236 - time (sec): 126.35 - samples/sec: 440.41 - lr: 0.000039 - momentum: 0.000000
2023-10-19 03:36:30,192 epoch 3 - iter 430/432 - loss 0.25493575 - time (sec): 140.73 - samples/sec: 438.13 - lr: 0.000039 - momentum: 0.000000
2023-10-19 03:36:30,621 ----------------------------------------------------------------------------------------------------
2023-10-19 03:36:30,621 EPOCH 3 done: loss 0.2546 - lr: 0.000039
2023-10-19 03:36:42,948 DEV : loss 0.3176376521587372 - f1-score (micro avg) 0.8099
2023-10-19 03:36:42,972 saving best model
2023-10-19 03:36:44,252 ----------------------------------------------------------------------------------------------------
2023-10-19 03:36:58,581 epoch 4 - iter 43/432 - loss 0.16639809 - time (sec): 14.33 - samples/sec: 429.53 - lr: 0.000038 - momentum: 0.000000
2023-10-19 03:37:12,557 epoch 4 - iter 86/432 - loss 0.16046383 - time (sec): 28.30 - samples/sec: 449.63 - lr: 0.000038 - momentum: 0.000000
2023-10-19 03:37:25,777 epoch 4 - iter 129/432 - loss 0.16293076 - time (sec): 41.52 - samples/sec: 454.44 - lr: 0.000037 - momentum: 0.000000
2023-10-19 03:37:38,639 epoch 4 - iter 172/432 - loss 0.17169823 - time (sec): 54.39 - samples/sec: 458.05 - lr: 0.000037 - momentum: 0.000000
2023-10-19 03:37:52,354 epoch 4 - iter 215/432 - loss 0.17568654 - time (sec): 68.10 - samples/sec: 455.30 - lr: 0.000036 - momentum: 0.000000
2023-10-19 03:38:05,210 epoch 4 - iter 258/432 - loss 0.17539204 - time (sec): 80.96 - samples/sec: 459.20 - lr: 0.000036 - momentum: 0.000000
2023-10-19 03:38:19,129 epoch 4 - iter 301/432 - loss 0.17616913 - time (sec): 94.88 - samples/sec: 454.33 - lr: 0.000035 - momentum: 0.000000
2023-10-19 03:38:32,506 epoch 4 - iter 344/432 - loss 0.17582288 - time (sec): 108.25 - samples/sec: 453.92 - lr: 0.000034 - momentum: 0.000000
2023-10-19 03:38:46,863 epoch 4 - iter 387/432 - loss 0.17865856 - time (sec): 122.61 - samples/sec: 449.89 - lr: 0.000034 - momentum: 0.000000
2023-10-19 03:39:00,675 epoch 4 - iter 430/432 - loss 0.18280202 - time (sec): 136.42 - samples/sec: 450.86 - lr: 0.000033 - momentum: 0.000000
2023-10-19 03:39:01,048 ----------------------------------------------------------------------------------------------------
2023-10-19 03:39:01,048 EPOCH 4 done: loss 0.1824 - lr: 0.000033
2023-10-19 03:39:12,966 DEV : loss 0.29886704683303833 - f1-score (micro avg) 0.8234
2023-10-19 03:39:12,991 saving best model
2023-10-19 03:39:14,266 ----------------------------------------------------------------------------------------------------
2023-10-19 03:39:28,400 epoch 5 - iter 43/432 - loss 0.11682448 - time (sec): 14.13 - samples/sec: 461.41 - lr: 0.000033 - momentum: 0.000000
2023-10-19 03:39:42,804 epoch 5 - iter 86/432 - loss 0.12275492 - time (sec): 28.54 - samples/sec: 444.72 - lr: 0.000032 - momentum: 0.000000
2023-10-19 03:39:56,165 epoch 5 - iter 129/432 - loss 0.12609206 - time (sec): 41.90 - samples/sec: 441.07 - lr: 0.000032 - momentum: 0.000000
2023-10-19 03:40:09,952 epoch 5 - iter 172/432 - loss 0.12711545 - time (sec): 55.69 - samples/sec: 446.73 - lr: 0.000031 - momentum: 0.000000
2023-10-19 03:40:22,923 epoch 5 - iter 215/432 - loss 0.12886348 - time (sec): 68.66 - samples/sec: 448.19 - lr: 0.000031 - momentum: 0.000000
2023-10-19 03:40:36,641 epoch 5 - iter 258/432 - loss 0.12845048 - time (sec): 82.37 - samples/sec: 449.42 - lr: 0.000030 - momentum: 0.000000
2023-10-19 03:40:50,351 epoch 5 - iter 301/432 - loss 0.12913153 - time (sec): 96.08 - samples/sec: 446.05 - lr: 0.000029 - momentum: 0.000000
2023-10-19 03:41:04,628 epoch 5 - iter 344/432 - loss 0.12936027 - time (sec): 110.36 - samples/sec: 445.78 - lr: 0.000029 - momentum: 0.000000
2023-10-19 03:41:19,188 epoch 5 - iter 387/432 - loss 0.13265379 - time (sec): 124.92 - samples/sec: 443.12 - lr: 0.000028 - momentum: 0.000000
2023-10-19 03:41:32,431 epoch 5 - iter 430/432 - loss 0.13736553 - time (sec): 138.16 - samples/sec: 445.95 - lr: 0.000028 - momentum: 0.000000
2023-10-19 03:41:32,872 ----------------------------------------------------------------------------------------------------
2023-10-19 03:41:32,872 EPOCH 5 done: loss 0.1372 - lr: 0.000028
2023-10-19 03:41:44,920 DEV : loss 0.3204568028450012 - f1-score (micro avg) 0.8314
2023-10-19 03:41:44,948 saving best model
2023-10-19 03:41:46,214 ----------------------------------------------------------------------------------------------------
2023-10-19 03:41:59,586 epoch 6 - iter 43/432 - loss 0.09314269 - time (sec): 13.37 - samples/sec: 447.56 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:42:13,450 epoch 6 - iter 86/432 - loss 0.09075584 - time (sec): 27.23 - samples/sec: 437.57 - lr: 0.000027 - momentum: 0.000000
2023-10-19 03:42:27,171 epoch 6 - iter 129/432 - loss 0.09591164 - time (sec): 40.95 - samples/sec: 448.35 - lr: 0.000026 - momentum: 0.000000
2023-10-19 03:42:40,635 epoch 6 - iter 172/432 - loss 0.09597865 - time (sec): 54.42 - samples/sec: 454.58 - lr: 0.000026 - momentum: 0.000000
2023-10-19 03:42:54,660 epoch 6 - iter 215/432 - loss 0.09909182 - time (sec): 68.44 - samples/sec: 450.91 - lr: 0.000025 - momentum: 0.000000
2023-10-19 03:43:09,178 epoch 6 - iter 258/432 - loss 0.10174570 - time (sec): 82.96 - samples/sec: 444.40 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:43:23,824 epoch 6 - iter 301/432 - loss 0.10046164 - time (sec): 97.61 - samples/sec: 437.85 - lr: 0.000024 - momentum: 0.000000
2023-10-19 03:43:36,945 epoch 6 - iter 344/432 - loss 0.10000466 - time (sec): 110.73 - samples/sec: 443.92 - lr: 0.000023 - momentum: 0.000000
2023-10-19 03:43:51,453 epoch 6 - iter 387/432 - loss 0.10122306 - time (sec): 125.24 - samples/sec: 443.84 - lr: 0.000023 - momentum: 0.000000
2023-10-19 03:44:05,912 epoch 6 - iter 430/432 - loss 0.10223935 - time (sec): 139.70 - samples/sec: 441.20 - lr: 0.000022 - momentum: 0.000000
2023-10-19 03:44:06,379 ----------------------------------------------------------------------------------------------------
2023-10-19 03:44:06,380 EPOCH 6 done: loss 0.1020 - lr: 0.000022
2023-10-19 03:44:19,759 DEV : loss 0.33529824018478394 - f1-score (micro avg) 0.8401
2023-10-19 03:44:19,784 saving best model
2023-10-19 03:44:21,049 ----------------------------------------------------------------------------------------------------
2023-10-19 03:44:36,276 epoch 7 - iter 43/432 - loss 0.07203442 - time (sec): 15.23 - samples/sec: 412.93 - lr: 0.000022 - momentum: 0.000000
2023-10-19 03:44:51,038 epoch 7 - iter 86/432 - loss 0.07103726 - time (sec): 29.99 - samples/sec: 414.67 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:45:05,416 epoch 7 - iter 129/432 - loss 0.06899312 - time (sec): 44.37 - samples/sec: 415.88 - lr: 0.000021 - momentum: 0.000000
2023-10-19 03:45:20,795 epoch 7 - iter 172/432 - loss 0.07194985 - time (sec): 59.75 - samples/sec: 415.65 - lr: 0.000020 - momentum: 0.000000
2023-10-19 03:45:34,874 epoch 7 - iter 215/432 - loss 0.07052196 - time (sec): 73.82 - samples/sec: 417.57 - lr: 0.000019 - momentum: 0.000000
2023-10-19 03:45:49,995 epoch 7 - iter 258/432 - loss 0.07040585 - time (sec): 88.94 - samples/sec: 415.72 - lr: 0.000019 - momentum: 0.000000
2023-10-19 03:46:04,708 epoch 7 - iter 301/432 - loss 0.07018022 - time (sec): 103.66 - samples/sec: 419.87 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:46:19,073 epoch 7 - iter 344/432 - loss 0.07150833 - time (sec): 118.02 - samples/sec: 419.32 - lr: 0.000018 - momentum: 0.000000
2023-10-19 03:46:33,525 epoch 7 - iter 387/432 - loss 0.07349951 - time (sec): 132.47 - samples/sec: 418.40 - lr: 0.000017 - momentum: 0.000000
2023-10-19 03:46:48,302 epoch 7 - iter 430/432 - loss 0.07369037 - time (sec): 147.25 - samples/sec: 419.18 - lr: 0.000017 - momentum: 0.000000
2023-10-19 03:46:49,000 ----------------------------------------------------------------------------------------------------
2023-10-19 03:46:49,000 EPOCH 7 done: loss 0.0738 - lr: 0.000017
2023-10-19 03:47:01,924 DEV : loss 0.34933581948280334 - f1-score (micro avg) 0.8467
2023-10-19 03:47:01,948 saving best model
2023-10-19 03:47:03,222 ----------------------------------------------------------------------------------------------------
2023-10-19 03:47:17,090 epoch 8 - iter 43/432 - loss 0.05716144 - time (sec): 13.87 - samples/sec: 440.63 - lr: 0.000016 - momentum: 0.000000
2023-10-19 03:47:32,144 epoch 8 - iter 86/432 - loss 0.05847175 - time (sec): 28.92 - samples/sec: 406.80 - lr: 0.000016 - momentum: 0.000000
2023-10-19 03:47:47,486 epoch 8 - iter 129/432 - loss 0.05964240 - time (sec): 44.26 - samples/sec: 406.24 - lr: 0.000015 - momentum: 0.000000
2023-10-19 03:48:01,911 epoch 8 - iter 172/432 - loss 0.05753793 - time (sec): 58.69 - samples/sec: 420.36 - lr: 0.000014 - momentum: 0.000000
2023-10-19 03:48:16,435 epoch 8 - iter 215/432 - loss 0.05591410 - time (sec): 73.21 - samples/sec: 417.99 - lr: 0.000014 - momentum: 0.000000
2023-10-19 03:48:31,234 epoch 8 - iter 258/432 - loss 0.05596529 - time (sec): 88.01 - samples/sec: 417.49 - lr: 0.000013 - momentum: 0.000000
2023-10-19 03:48:46,757 epoch 8 - iter 301/432 - loss 0.05651818 - time (sec): 103.53 - samples/sec: 415.10 - lr: 0.000013 - momentum: 0.000000
2023-10-19 03:49:01,544 epoch 8 - iter 344/432 - loss 0.05762473 - time (sec): 118.32 - samples/sec: 416.82 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:49:15,864 epoch 8 - iter 387/432 - loss 0.05808607 - time (sec): 132.64 - samples/sec: 418.46 - lr: 0.000012 - momentum: 0.000000
2023-10-19 03:49:31,049 epoch 8 - iter 430/432 - loss 0.05758731 - time (sec): 147.83 - samples/sec: 416.94 - lr: 0.000011 - momentum: 0.000000
2023-10-19 03:49:31,826 ----------------------------------------------------------------------------------------------------
2023-10-19 03:49:31,826 EPOCH 8 done: loss 0.0578 - lr: 0.000011
2023-10-19 03:49:44,970 DEV : loss 0.38339680433273315 - f1-score (micro avg) 0.8393
2023-10-19 03:49:44,995 ----------------------------------------------------------------------------------------------------
2023-10-19 03:49:59,204 epoch 9 - iter 43/432 - loss 0.03477718 - time (sec): 14.21 - samples/sec: 433.13 - lr: 0.000011 - momentum: 0.000000
2023-10-19 03:50:14,060 epoch 9 - iter 86/432 - loss 0.03916332 - time (sec): 29.06 - samples/sec: 431.15 - lr: 0.000010 - momentum: 0.000000
2023-10-19 03:50:27,952 epoch 9 - iter 129/432 - loss 0.03614330 - time (sec): 42.96 - samples/sec: 437.68 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:50:42,814 epoch 9 - iter 172/432 - loss 0.03823699 - time (sec): 57.82 - samples/sec: 436.70 - lr: 0.000009 - momentum: 0.000000
2023-10-19 03:50:57,585 epoch 9 - iter 215/432 - loss 0.03949486 - time (sec): 72.59 - samples/sec: 427.62 - lr: 0.000008 - momentum: 0.000000
2023-10-19 03:51:12,290 epoch 9 - iter 258/432 - loss 0.04255173 - time (sec): 87.29 - samples/sec: 426.32 - lr: 0.000008 - momentum: 0.000000
2023-10-19 03:51:27,273 epoch 9 - iter 301/432 - loss 0.04281995 - time (sec): 102.28 - samples/sec: 424.55 - lr: 0.000007 - momentum: 0.000000
2023-10-19 03:51:41,879 epoch 9 - iter 344/432 - loss 0.04288552 - time (sec): 116.88 - samples/sec: 422.87 - lr: 0.000007 - momentum: 0.000000
2023-10-19 03:51:57,269 epoch 9 - iter 387/432 - loss 0.04340112 - time (sec): 132.27 - samples/sec: 420.18 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:52:12,096 epoch 9 - iter 430/432 - loss 0.04288897 - time (sec): 147.10 - samples/sec: 418.86 - lr: 0.000006 - momentum: 0.000000
2023-10-19 03:52:12,574 ----------------------------------------------------------------------------------------------------
2023-10-19 03:52:12,574 EPOCH 9 done: loss 0.0429 - lr: 0.000006
2023-10-19 03:52:25,616 DEV : loss 0.4035045802593231 - f1-score (micro avg) 0.8476
2023-10-19 03:52:25,641 saving best model
2023-10-19 03:52:27,667 ----------------------------------------------------------------------------------------------------
2023-10-19 03:52:41,579 epoch 10 - iter 43/432 - loss 0.02320239 - time (sec): 13.91 - samples/sec: 431.98 - lr: 0.000005 - momentum: 0.000000
2023-10-19 03:52:56,667 epoch 10 - iter 86/432 - loss 0.02686951 - time (sec): 29.00 - samples/sec: 410.53 - lr: 0.000004 - momentum: 0.000000
2023-10-19 03:53:10,356 epoch 10 - iter 129/432 - loss 0.02767008 - time (sec): 42.69 - samples/sec: 426.65 - lr: 0.000004 - momentum: 0.000000
2023-10-19 03:53:25,523 epoch 10 - iter 172/432 - loss 0.02995656 - time (sec): 57.85 - samples/sec: 433.48 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:53:40,267 epoch 10 - iter 215/432 - loss 0.03134205 - time (sec): 72.60 - samples/sec: 431.03 - lr: 0.000003 - momentum: 0.000000
2023-10-19 03:53:55,194 epoch 10 - iter 258/432 - loss 0.03131445 - time (sec): 87.53 - samples/sec: 426.60 - lr: 0.000002 - momentum: 0.000000
2023-10-19 03:54:08,818 epoch 10 - iter 301/432 - loss 0.03184536 - time (sec): 101.15 - samples/sec: 428.50 - lr: 0.000002 - momentum: 0.000000
2023-10-19 03:54:23,364 epoch 10 - iter 344/432 - loss 0.03434134 - time (sec): 115.70 - samples/sec: 428.91 - lr: 0.000001 - momentum: 0.000000
2023-10-19 03:54:37,614 epoch 10 - iter 387/432 - loss 0.03405121 - time (sec): 129.95 - samples/sec: 426.70 - lr: 0.000001 - momentum: 0.000000
2023-10-19 03:54:50,631 epoch 10 - iter 430/432 - loss 0.03334862 - time (sec): 142.96 - samples/sec: 431.18 - lr: 0.000000 - momentum: 0.000000
2023-10-19 03:54:51,170 ----------------------------------------------------------------------------------------------------
2023-10-19 03:54:51,170 EPOCH 10 done: loss 0.0333 - lr: 0.000000
2023-10-19 03:55:03,307 DEV : loss 0.41629332304000854 - f1-score (micro avg) 0.8463
2023-10-19 03:55:03,786 ----------------------------------------------------------------------------------------------------
2023-10-19 03:55:03,787 Loading model from best epoch ...
2023-10-19 03:55:06,502 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 03:55:22,259
Results:
- F-score (micro) 0.7689
- F-score (macro) 0.5855
- Accuracy 0.6696
By class:
precision recall f1-score support
location-stop 0.8735 0.8392 0.8560 765
trigger 0.7202 0.5654 0.6335 833
location 0.7834 0.8376 0.8096 665
location-city 0.8197 0.8834 0.8503 566
date 0.8877 0.8426 0.8646 394
location-street 0.9356 0.8653 0.8991 386
time 0.7944 0.8906 0.8398 256
location-route 0.8525 0.7324 0.7879 284
organization-company 0.8191 0.6468 0.7228 252
distance 1.0000 0.9940 0.9970 167
number 0.6932 0.8188 0.7508 149
duration 0.3533 0.3252 0.3387 163
event-cause 0.0000 0.0000 0.0000 0
disaster-type 0.8649 0.4638 0.6038 69
organization 0.5714 0.5714 0.5714 28
person 0.4500 0.9000 0.6000 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 0.7694 0.7684 0.7689 4988
macro avg 0.6010 0.5882 0.5855 4988
weighted avg 0.8067 0.7684 0.7835 4988
2023-10-19 03:55:22,259 ----------------------------------------------------------------------------------------------------
|