File size: 24,029 Bytes
3b0326d |
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 |
2023-10-17 09:30:31,178 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,178 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): ElectraModel(
(embeddings): ElectraEmbeddings(
(word_embeddings): Embedding(32001, 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): ElectraEncoder(
(layer): ModuleList(
(0-11): 12 x ElectraLayer(
(attention): ElectraAttention(
(self): ElectraSelfAttention(
(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): ElectraSelfOutput(
(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): ElectraIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): ElectraOutput(
(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)
)
)
)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 Train: 1214 sentences
2023-10-17 09:30:31,179 (train_with_dev=False, train_with_test=False)
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 Training Params:
2023-10-17 09:30:31,179 - learning_rate: "3e-05"
2023-10-17 09:30:31,179 - mini_batch_size: "4"
2023-10-17 09:30:31,179 - max_epochs: "10"
2023-10-17 09:30:31,179 - shuffle: "True"
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 Plugins:
2023-10-17 09:30:31,179 - TensorboardLogger
2023-10-17 09:30:31,179 - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 09:30:31,179 - metric: "('micro avg', 'f1-score')"
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,179 Computation:
2023-10-17 09:30:31,179 - compute on device: cuda:0
2023-10-17 09:30:31,179 - embedding storage: none
2023-10-17 09:30:31,179 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,180 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-17 09:30:31,180 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,180 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:31,180 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 09:30:33,540 epoch 1 - iter 30/304 - loss 3.40341811 - time (sec): 2.36 - samples/sec: 1275.39 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:30:34,870 epoch 1 - iter 60/304 - loss 2.76268533 - time (sec): 3.69 - samples/sec: 1612.88 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:30:36,273 epoch 1 - iter 90/304 - loss 2.09069265 - time (sec): 5.09 - samples/sec: 1844.82 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:30:37,679 epoch 1 - iter 120/304 - loss 1.68530411 - time (sec): 6.50 - samples/sec: 1952.76 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:30:39,073 epoch 1 - iter 150/304 - loss 1.46288557 - time (sec): 7.89 - samples/sec: 1958.76 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:30:40,419 epoch 1 - iter 180/304 - loss 1.28563337 - time (sec): 9.24 - samples/sec: 1977.24 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:30:41,811 epoch 1 - iter 210/304 - loss 1.14935430 - time (sec): 10.63 - samples/sec: 2014.34 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:30:43,137 epoch 1 - iter 240/304 - loss 1.04594044 - time (sec): 11.96 - samples/sec: 2044.92 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:30:44,462 epoch 1 - iter 270/304 - loss 0.95951493 - time (sec): 13.28 - samples/sec: 2067.26 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:30:45,861 epoch 1 - iter 300/304 - loss 0.88553963 - time (sec): 14.68 - samples/sec: 2087.86 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:30:46,032 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:46,032 EPOCH 1 done: loss 0.8781 - lr: 0.000030
2023-10-17 09:30:46,938 DEV : loss 0.1928645819425583 - f1-score (micro avg) 0.6572
2023-10-17 09:30:46,944 saving best model
2023-10-17 09:30:47,324 ----------------------------------------------------------------------------------------------------
2023-10-17 09:30:48,689 epoch 2 - iter 30/304 - loss 0.19033845 - time (sec): 1.36 - samples/sec: 2207.31 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:30:50,068 epoch 2 - iter 60/304 - loss 0.19049934 - time (sec): 2.74 - samples/sec: 2227.36 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:30:51,445 epoch 2 - iter 90/304 - loss 0.17286170 - time (sec): 4.12 - samples/sec: 2237.14 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:30:52,772 epoch 2 - iter 120/304 - loss 0.16185954 - time (sec): 5.45 - samples/sec: 2248.69 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:30:54,086 epoch 2 - iter 150/304 - loss 0.15626809 - time (sec): 6.76 - samples/sec: 2281.43 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:30:55,357 epoch 2 - iter 180/304 - loss 0.15121608 - time (sec): 8.03 - samples/sec: 2280.31 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:30:56,667 epoch 2 - iter 210/304 - loss 0.14604985 - time (sec): 9.34 - samples/sec: 2265.86 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:30:58,020 epoch 2 - iter 240/304 - loss 0.14876228 - time (sec): 10.69 - samples/sec: 2292.74 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:30:59,361 epoch 2 - iter 270/304 - loss 0.14221295 - time (sec): 12.03 - samples/sec: 2305.12 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:31:00,721 epoch 2 - iter 300/304 - loss 0.14474972 - time (sec): 13.39 - samples/sec: 2291.33 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:31:00,892 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:00,892 EPOCH 2 done: loss 0.1438 - lr: 0.000027
2023-10-17 09:31:01,837 DEV : loss 0.14745701849460602 - f1-score (micro avg) 0.8038
2023-10-17 09:31:01,843 saving best model
2023-10-17 09:31:02,338 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:03,654 epoch 3 - iter 30/304 - loss 0.09474617 - time (sec): 1.31 - samples/sec: 2209.40 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:31:05,063 epoch 3 - iter 60/304 - loss 0.08922804 - time (sec): 2.72 - samples/sec: 2157.78 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:31:06,505 epoch 3 - iter 90/304 - loss 0.08927453 - time (sec): 4.17 - samples/sec: 2102.13 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:31:07,910 epoch 3 - iter 120/304 - loss 0.08498659 - time (sec): 5.57 - samples/sec: 2103.13 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:31:09,349 epoch 3 - iter 150/304 - loss 0.07743174 - time (sec): 7.01 - samples/sec: 2159.77 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:31:10,691 epoch 3 - iter 180/304 - loss 0.09126252 - time (sec): 8.35 - samples/sec: 2194.22 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:31:12,047 epoch 3 - iter 210/304 - loss 0.09607426 - time (sec): 9.71 - samples/sec: 2208.73 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:31:13,398 epoch 3 - iter 240/304 - loss 0.09411271 - time (sec): 11.06 - samples/sec: 2213.20 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:31:14,728 epoch 3 - iter 270/304 - loss 0.08853084 - time (sec): 12.39 - samples/sec: 2207.82 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:31:16,067 epoch 3 - iter 300/304 - loss 0.08617369 - time (sec): 13.73 - samples/sec: 2232.98 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:31:16,241 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:16,242 EPOCH 3 done: loss 0.0868 - lr: 0.000023
2023-10-17 09:31:17,177 DEV : loss 0.150361567735672 - f1-score (micro avg) 0.8233
2023-10-17 09:31:17,184 saving best model
2023-10-17 09:31:17,770 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:19,216 epoch 4 - iter 30/304 - loss 0.04765358 - time (sec): 1.44 - samples/sec: 2152.91 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:31:20,604 epoch 4 - iter 60/304 - loss 0.06898020 - time (sec): 2.83 - samples/sec: 2164.59 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:31:21,980 epoch 4 - iter 90/304 - loss 0.06988082 - time (sec): 4.21 - samples/sec: 2134.50 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:31:23,320 epoch 4 - iter 120/304 - loss 0.06829514 - time (sec): 5.55 - samples/sec: 2230.06 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:31:24,661 epoch 4 - iter 150/304 - loss 0.06516852 - time (sec): 6.89 - samples/sec: 2220.38 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:31:26,023 epoch 4 - iter 180/304 - loss 0.06321737 - time (sec): 8.25 - samples/sec: 2206.75 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:31:27,357 epoch 4 - iter 210/304 - loss 0.06440426 - time (sec): 9.59 - samples/sec: 2233.44 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:31:28,782 epoch 4 - iter 240/304 - loss 0.06148461 - time (sec): 11.01 - samples/sec: 2231.14 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:31:30,299 epoch 4 - iter 270/304 - loss 0.06405485 - time (sec): 12.53 - samples/sec: 2207.24 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:31:31,821 epoch 4 - iter 300/304 - loss 0.06259846 - time (sec): 14.05 - samples/sec: 2185.49 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:31:32,021 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:32,022 EPOCH 4 done: loss 0.0626 - lr: 0.000020
2023-10-17 09:31:33,007 DEV : loss 0.19989213347434998 - f1-score (micro avg) 0.8248
2023-10-17 09:31:33,015 saving best model
2023-10-17 09:31:33,506 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:34,851 epoch 5 - iter 30/304 - loss 0.07427175 - time (sec): 1.34 - samples/sec: 2515.11 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:31:36,202 epoch 5 - iter 60/304 - loss 0.05862733 - time (sec): 2.69 - samples/sec: 2355.67 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:31:37,538 epoch 5 - iter 90/304 - loss 0.05988285 - time (sec): 4.03 - samples/sec: 2402.34 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:31:38,865 epoch 5 - iter 120/304 - loss 0.04951363 - time (sec): 5.36 - samples/sec: 2372.69 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:31:40,251 epoch 5 - iter 150/304 - loss 0.04470615 - time (sec): 6.74 - samples/sec: 2340.22 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:31:41,572 epoch 5 - iter 180/304 - loss 0.04611420 - time (sec): 8.06 - samples/sec: 2316.33 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:31:42,887 epoch 5 - iter 210/304 - loss 0.04532396 - time (sec): 9.38 - samples/sec: 2311.70 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:31:44,192 epoch 5 - iter 240/304 - loss 0.04875675 - time (sec): 10.68 - samples/sec: 2287.02 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:31:45,542 epoch 5 - iter 270/304 - loss 0.04694412 - time (sec): 12.03 - samples/sec: 2291.36 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:31:46,970 epoch 5 - iter 300/304 - loss 0.05007069 - time (sec): 13.46 - samples/sec: 2280.60 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:31:47,157 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:47,157 EPOCH 5 done: loss 0.0498 - lr: 0.000017
2023-10-17 09:31:48,120 DEV : loss 0.2023184597492218 - f1-score (micro avg) 0.841
2023-10-17 09:31:48,127 saving best model
2023-10-17 09:31:48,632 ----------------------------------------------------------------------------------------------------
2023-10-17 09:31:50,025 epoch 6 - iter 30/304 - loss 0.04511870 - time (sec): 1.39 - samples/sec: 2230.73 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:31:51,435 epoch 6 - iter 60/304 - loss 0.03883136 - time (sec): 2.80 - samples/sec: 2113.38 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:31:52,772 epoch 6 - iter 90/304 - loss 0.03906137 - time (sec): 4.14 - samples/sec: 2150.93 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:31:54,154 epoch 6 - iter 120/304 - loss 0.03579353 - time (sec): 5.52 - samples/sec: 2162.09 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:31:55,567 epoch 6 - iter 150/304 - loss 0.03494026 - time (sec): 6.93 - samples/sec: 2182.94 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:31:56,932 epoch 6 - iter 180/304 - loss 0.03394086 - time (sec): 8.30 - samples/sec: 2184.06 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:31:58,280 epoch 6 - iter 210/304 - loss 0.03922439 - time (sec): 9.64 - samples/sec: 2209.43 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:31:59,637 epoch 6 - iter 240/304 - loss 0.03719479 - time (sec): 11.00 - samples/sec: 2206.25 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:32:01,032 epoch 6 - iter 270/304 - loss 0.03881903 - time (sec): 12.40 - samples/sec: 2209.13 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:32:02,428 epoch 6 - iter 300/304 - loss 0.03998433 - time (sec): 13.79 - samples/sec: 2222.87 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:32:02,609 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:02,610 EPOCH 6 done: loss 0.0398 - lr: 0.000013
2023-10-17 09:32:03,536 DEV : loss 0.19735880196094513 - f1-score (micro avg) 0.8606
2023-10-17 09:32:03,542 saving best model
2023-10-17 09:32:04,046 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:05,471 epoch 7 - iter 30/304 - loss 0.01823262 - time (sec): 1.42 - samples/sec: 1968.60 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:32:06,844 epoch 7 - iter 60/304 - loss 0.01379847 - time (sec): 2.80 - samples/sec: 2085.82 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:32:08,155 epoch 7 - iter 90/304 - loss 0.01965802 - time (sec): 4.11 - samples/sec: 2171.32 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:32:09,500 epoch 7 - iter 120/304 - loss 0.02037882 - time (sec): 5.45 - samples/sec: 2172.21 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:32:10,830 epoch 7 - iter 150/304 - loss 0.01800502 - time (sec): 6.78 - samples/sec: 2209.27 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:32:12,189 epoch 7 - iter 180/304 - loss 0.01811769 - time (sec): 8.14 - samples/sec: 2211.46 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:32:13,541 epoch 7 - iter 210/304 - loss 0.02066402 - time (sec): 9.49 - samples/sec: 2217.21 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:32:14,893 epoch 7 - iter 240/304 - loss 0.02128125 - time (sec): 10.85 - samples/sec: 2252.69 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:32:16,182 epoch 7 - iter 270/304 - loss 0.02352683 - time (sec): 12.13 - samples/sec: 2285.78 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:32:17,486 epoch 7 - iter 300/304 - loss 0.02762806 - time (sec): 13.44 - samples/sec: 2279.83 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:32:17,667 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:17,668 EPOCH 7 done: loss 0.0278 - lr: 0.000010
2023-10-17 09:32:18,600 DEV : loss 0.22195689380168915 - f1-score (micro avg) 0.8413
2023-10-17 09:32:18,607 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:19,989 epoch 8 - iter 30/304 - loss 0.01263015 - time (sec): 1.38 - samples/sec: 2437.36 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:32:21,353 epoch 8 - iter 60/304 - loss 0.01338996 - time (sec): 2.74 - samples/sec: 2325.69 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:32:22,717 epoch 8 - iter 90/304 - loss 0.02176368 - time (sec): 4.11 - samples/sec: 2311.46 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:32:24,063 epoch 8 - iter 120/304 - loss 0.01886905 - time (sec): 5.45 - samples/sec: 2232.01 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:32:25,422 epoch 8 - iter 150/304 - loss 0.01578714 - time (sec): 6.81 - samples/sec: 2278.52 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:32:26,753 epoch 8 - iter 180/304 - loss 0.01908566 - time (sec): 8.14 - samples/sec: 2262.13 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:32:28,141 epoch 8 - iter 210/304 - loss 0.02325066 - time (sec): 9.53 - samples/sec: 2244.39 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:32:29,540 epoch 8 - iter 240/304 - loss 0.02452136 - time (sec): 10.93 - samples/sec: 2242.79 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:32:30,896 epoch 8 - iter 270/304 - loss 0.02299051 - time (sec): 12.29 - samples/sec: 2247.51 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:32:32,238 epoch 8 - iter 300/304 - loss 0.02348440 - time (sec): 13.63 - samples/sec: 2246.47 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:32:32,419 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:32,419 EPOCH 8 done: loss 0.0232 - lr: 0.000007
2023-10-17 09:32:33,398 DEV : loss 0.2149593085050583 - f1-score (micro avg) 0.8527
2023-10-17 09:32:33,406 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:35,020 epoch 9 - iter 30/304 - loss 0.02915313 - time (sec): 1.61 - samples/sec: 1907.76 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:32:36,612 epoch 9 - iter 60/304 - loss 0.01511731 - time (sec): 3.20 - samples/sec: 1866.16 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:32:38,222 epoch 9 - iter 90/304 - loss 0.01855884 - time (sec): 4.81 - samples/sec: 1903.60 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:32:39,672 epoch 9 - iter 120/304 - loss 0.01614332 - time (sec): 6.26 - samples/sec: 1922.74 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:32:41,136 epoch 9 - iter 150/304 - loss 0.01755943 - time (sec): 7.73 - samples/sec: 1971.62 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:32:42,567 epoch 9 - iter 180/304 - loss 0.01749215 - time (sec): 9.16 - samples/sec: 2003.99 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:32:43,882 epoch 9 - iter 210/304 - loss 0.01545958 - time (sec): 10.47 - samples/sec: 2035.36 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:32:45,181 epoch 9 - iter 240/304 - loss 0.01559802 - time (sec): 11.77 - samples/sec: 2060.93 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:32:46,548 epoch 9 - iter 270/304 - loss 0.01720692 - time (sec): 13.14 - samples/sec: 2087.79 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:32:47,898 epoch 9 - iter 300/304 - loss 0.01840772 - time (sec): 14.49 - samples/sec: 2115.19 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:32:48,066 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:48,066 EPOCH 9 done: loss 0.0182 - lr: 0.000003
2023-10-17 09:32:49,027 DEV : loss 0.21825647354125977 - f1-score (micro avg) 0.8547
2023-10-17 09:32:49,033 ----------------------------------------------------------------------------------------------------
2023-10-17 09:32:50,363 epoch 10 - iter 30/304 - loss 0.00382941 - time (sec): 1.33 - samples/sec: 2212.97 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:32:51,806 epoch 10 - iter 60/304 - loss 0.01280602 - time (sec): 2.77 - samples/sec: 2156.55 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:32:53,180 epoch 10 - iter 90/304 - loss 0.01157864 - time (sec): 4.15 - samples/sec: 2235.64 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:32:54,513 epoch 10 - iter 120/304 - loss 0.01749777 - time (sec): 5.48 - samples/sec: 2225.87 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:32:55,851 epoch 10 - iter 150/304 - loss 0.01594405 - time (sec): 6.82 - samples/sec: 2221.32 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:32:57,231 epoch 10 - iter 180/304 - loss 0.01600590 - time (sec): 8.20 - samples/sec: 2213.10 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:32:58,559 epoch 10 - iter 210/304 - loss 0.01401505 - time (sec): 9.52 - samples/sec: 2242.13 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:32:59,884 epoch 10 - iter 240/304 - loss 0.01299417 - time (sec): 10.85 - samples/sec: 2242.61 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:33:01,211 epoch 10 - iter 270/304 - loss 0.01365368 - time (sec): 12.18 - samples/sec: 2250.29 - lr: 0.000000 - momentum: 0.000000
2023-10-17 09:33:02,541 epoch 10 - iter 300/304 - loss 0.01386075 - time (sec): 13.51 - samples/sec: 2266.65 - lr: 0.000000 - momentum: 0.000000
2023-10-17 09:33:02,721 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:02,721 EPOCH 10 done: loss 0.0143 - lr: 0.000000
2023-10-17 09:33:03,723 DEV : loss 0.21264854073524475 - f1-score (micro avg) 0.8517
2023-10-17 09:33:04,116 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:04,117 Loading model from best epoch ...
2023-10-17 09:33:06,307 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
2023-10-17 09:33:07,013
Results:
- F-score (micro) 0.8156
- F-score (macro) 0.6596
- Accuracy 0.6952
By class:
precision recall f1-score support
scope 0.7312 0.7748 0.7524 151
work 0.7685 0.8737 0.8177 95
pers 0.9184 0.9375 0.9278 96
loc 1.0000 0.6667 0.8000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7935 0.8391 0.8156 348
macro avg 0.6836 0.6505 0.6596 348
weighted avg 0.7891 0.8391 0.8126 348
2023-10-17 09:33:07,014 ----------------------------------------------------------------------------------------------------
|