File size: 23,984 Bytes
b34c186 |
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 |
2023-10-17 09:33:30,241 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 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 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 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 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 Train: 1214 sentences
2023-10-17 09:33:30,242 (train_with_dev=False, train_with_test=False)
2023-10-17 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 Training Params:
2023-10-17 09:33:30,242 - learning_rate: "5e-05"
2023-10-17 09:33:30,242 - mini_batch_size: "4"
2023-10-17 09:33:30,242 - max_epochs: "10"
2023-10-17 09:33:30,242 - shuffle: "True"
2023-10-17 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 Plugins:
2023-10-17 09:33:30,242 - TensorboardLogger
2023-10-17 09:33:30,242 - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 09:33:30,242 - metric: "('micro avg', 'f1-score')"
2023-10-17 09:33:30,242 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,242 Computation:
2023-10-17 09:33:30,242 - compute on device: cuda:0
2023-10-17 09:33:30,243 - embedding storage: none
2023-10-17 09:33:30,243 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,243 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-17 09:33:30,243 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,243 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:30,243 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 09:33:31,606 epoch 1 - iter 30/304 - loss 3.25804981 - time (sec): 1.36 - samples/sec: 2208.37 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:33:32,934 epoch 1 - iter 60/304 - loss 2.36313859 - time (sec): 2.69 - samples/sec: 2211.39 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:33:34,214 epoch 1 - iter 90/304 - loss 1.76687822 - time (sec): 3.97 - samples/sec: 2366.03 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:33:35,519 epoch 1 - iter 120/304 - loss 1.42293198 - time (sec): 5.27 - samples/sec: 2405.55 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:33:36,849 epoch 1 - iter 150/304 - loss 1.23485272 - time (sec): 6.61 - samples/sec: 2340.39 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:33:38,135 epoch 1 - iter 180/304 - loss 1.08832958 - time (sec): 7.89 - samples/sec: 2314.73 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:33:39,417 epoch 1 - iter 210/304 - loss 0.97415434 - time (sec): 9.17 - samples/sec: 2334.11 - lr: 0.000034 - momentum: 0.000000
2023-10-17 09:33:40,697 epoch 1 - iter 240/304 - loss 0.88672066 - time (sec): 10.45 - samples/sec: 2338.93 - lr: 0.000039 - momentum: 0.000000
2023-10-17 09:33:42,059 epoch 1 - iter 270/304 - loss 0.81370723 - time (sec): 11.82 - samples/sec: 2323.70 - lr: 0.000044 - momentum: 0.000000
2023-10-17 09:33:43,448 epoch 1 - iter 300/304 - loss 0.75173915 - time (sec): 13.20 - samples/sec: 2321.25 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:33:43,621 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:43,622 EPOCH 1 done: loss 0.7451 - lr: 0.000049
2023-10-17 09:33:44,523 DEV : loss 0.161675825715065 - f1-score (micro avg) 0.6765
2023-10-17 09:33:44,530 saving best model
2023-10-17 09:33:44,878 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:46,288 epoch 2 - iter 30/304 - loss 0.17926316 - time (sec): 1.41 - samples/sec: 2136.46 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:33:47,632 epoch 2 - iter 60/304 - loss 0.17959788 - time (sec): 2.75 - samples/sec: 2218.15 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:33:48,959 epoch 2 - iter 90/304 - loss 0.15959564 - time (sec): 4.08 - samples/sec: 2258.44 - lr: 0.000048 - momentum: 0.000000
2023-10-17 09:33:50,278 epoch 2 - iter 120/304 - loss 0.14577787 - time (sec): 5.40 - samples/sec: 2268.14 - lr: 0.000048 - momentum: 0.000000
2023-10-17 09:33:51,661 epoch 2 - iter 150/304 - loss 0.14309388 - time (sec): 6.78 - samples/sec: 2273.91 - lr: 0.000047 - momentum: 0.000000
2023-10-17 09:33:52,936 epoch 2 - iter 180/304 - loss 0.13888269 - time (sec): 8.06 - samples/sec: 2272.89 - lr: 0.000047 - momentum: 0.000000
2023-10-17 09:33:54,317 epoch 2 - iter 210/304 - loss 0.13552043 - time (sec): 9.44 - samples/sec: 2242.76 - lr: 0.000046 - momentum: 0.000000
2023-10-17 09:33:55,729 epoch 2 - iter 240/304 - loss 0.13838089 - time (sec): 10.85 - samples/sec: 2259.83 - lr: 0.000046 - momentum: 0.000000
2023-10-17 09:33:57,023 epoch 2 - iter 270/304 - loss 0.13466550 - time (sec): 12.14 - samples/sec: 2284.52 - lr: 0.000045 - momentum: 0.000000
2023-10-17 09:33:58,306 epoch 2 - iter 300/304 - loss 0.13660685 - time (sec): 13.43 - samples/sec: 2285.83 - lr: 0.000045 - momentum: 0.000000
2023-10-17 09:33:58,476 ----------------------------------------------------------------------------------------------------
2023-10-17 09:33:58,477 EPOCH 2 done: loss 0.1357 - lr: 0.000045
2023-10-17 09:33:59,429 DEV : loss 0.13294953107833862 - f1-score (micro avg) 0.8388
2023-10-17 09:33:59,435 saving best model
2023-10-17 09:33:59,862 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:01,217 epoch 3 - iter 30/304 - loss 0.10186564 - time (sec): 1.35 - samples/sec: 2147.02 - lr: 0.000044 - momentum: 0.000000
2023-10-17 09:34:02,552 epoch 3 - iter 60/304 - loss 0.08701531 - time (sec): 2.69 - samples/sec: 2186.79 - lr: 0.000043 - momentum: 0.000000
2023-10-17 09:34:03,883 epoch 3 - iter 90/304 - loss 0.08470113 - time (sec): 4.02 - samples/sec: 2179.19 - lr: 0.000043 - momentum: 0.000000
2023-10-17 09:34:05,289 epoch 3 - iter 120/304 - loss 0.08058118 - time (sec): 5.42 - samples/sec: 2159.74 - lr: 0.000042 - momentum: 0.000000
2023-10-17 09:34:06,696 epoch 3 - iter 150/304 - loss 0.07176557 - time (sec): 6.83 - samples/sec: 2216.09 - lr: 0.000042 - momentum: 0.000000
2023-10-17 09:34:08,075 epoch 3 - iter 180/304 - loss 0.08766980 - time (sec): 8.21 - samples/sec: 2231.73 - lr: 0.000041 - momentum: 0.000000
2023-10-17 09:34:09,455 epoch 3 - iter 210/304 - loss 0.09295201 - time (sec): 9.59 - samples/sec: 2235.65 - lr: 0.000041 - momentum: 0.000000
2023-10-17 09:34:10,749 epoch 3 - iter 240/304 - loss 0.09005317 - time (sec): 10.88 - samples/sec: 2248.59 - lr: 0.000040 - momentum: 0.000000
2023-10-17 09:34:12,027 epoch 3 - iter 270/304 - loss 0.08696873 - time (sec): 12.16 - samples/sec: 2248.96 - lr: 0.000040 - momentum: 0.000000
2023-10-17 09:34:13,349 epoch 3 - iter 300/304 - loss 0.08573648 - time (sec): 13.48 - samples/sec: 2273.37 - lr: 0.000039 - momentum: 0.000000
2023-10-17 09:34:13,530 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:13,531 EPOCH 3 done: loss 0.0855 - lr: 0.000039
2023-10-17 09:34:14,488 DEV : loss 0.18068550527095795 - f1-score (micro avg) 0.8046
2023-10-17 09:34:14,496 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:15,784 epoch 4 - iter 30/304 - loss 0.05019669 - time (sec): 1.29 - samples/sec: 2416.76 - lr: 0.000038 - momentum: 0.000000
2023-10-17 09:34:17,052 epoch 4 - iter 60/304 - loss 0.05952380 - time (sec): 2.55 - samples/sec: 2400.94 - lr: 0.000038 - momentum: 0.000000
2023-10-17 09:34:18,320 epoch 4 - iter 90/304 - loss 0.05936065 - time (sec): 3.82 - samples/sec: 2349.79 - lr: 0.000037 - momentum: 0.000000
2023-10-17 09:34:19,623 epoch 4 - iter 120/304 - loss 0.05864896 - time (sec): 5.13 - samples/sec: 2414.14 - lr: 0.000037 - momentum: 0.000000
2023-10-17 09:34:20,901 epoch 4 - iter 150/304 - loss 0.06134356 - time (sec): 6.40 - samples/sec: 2389.22 - lr: 0.000036 - momentum: 0.000000
2023-10-17 09:34:22,237 epoch 4 - iter 180/304 - loss 0.05914494 - time (sec): 7.74 - samples/sec: 2352.70 - lr: 0.000036 - momentum: 0.000000
2023-10-17 09:34:23,569 epoch 4 - iter 210/304 - loss 0.06076366 - time (sec): 9.07 - samples/sec: 2360.11 - lr: 0.000035 - momentum: 0.000000
2023-10-17 09:34:24,883 epoch 4 - iter 240/304 - loss 0.06044483 - time (sec): 10.39 - samples/sec: 2365.35 - lr: 0.000035 - momentum: 0.000000
2023-10-17 09:34:26,193 epoch 4 - iter 270/304 - loss 0.06275507 - time (sec): 11.70 - samples/sec: 2364.46 - lr: 0.000034 - momentum: 0.000000
2023-10-17 09:34:27,536 epoch 4 - iter 300/304 - loss 0.06152975 - time (sec): 13.04 - samples/sec: 2355.11 - lr: 0.000033 - momentum: 0.000000
2023-10-17 09:34:27,723 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:27,723 EPOCH 4 done: loss 0.0620 - lr: 0.000033
2023-10-17 09:34:28,672 DEV : loss 0.175832137465477 - f1-score (micro avg) 0.8293
2023-10-17 09:34:28,678 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:30,056 epoch 5 - iter 30/304 - loss 0.06038916 - time (sec): 1.38 - samples/sec: 2451.93 - lr: 0.000033 - momentum: 0.000000
2023-10-17 09:34:31,498 epoch 5 - iter 60/304 - loss 0.05371355 - time (sec): 2.82 - samples/sec: 2251.01 - lr: 0.000032 - momentum: 0.000000
2023-10-17 09:34:32,830 epoch 5 - iter 90/304 - loss 0.05116334 - time (sec): 4.15 - samples/sec: 2332.16 - lr: 0.000032 - momentum: 0.000000
2023-10-17 09:34:34,173 epoch 5 - iter 120/304 - loss 0.04426179 - time (sec): 5.49 - samples/sec: 2313.46 - lr: 0.000031 - momentum: 0.000000
2023-10-17 09:34:35,527 epoch 5 - iter 150/304 - loss 0.04033000 - time (sec): 6.85 - samples/sec: 2304.34 - lr: 0.000031 - momentum: 0.000000
2023-10-17 09:34:36,853 epoch 5 - iter 180/304 - loss 0.04201480 - time (sec): 8.17 - samples/sec: 2285.13 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:34:38,187 epoch 5 - iter 210/304 - loss 0.04071244 - time (sec): 9.51 - samples/sec: 2280.43 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:34:39,501 epoch 5 - iter 240/304 - loss 0.04523655 - time (sec): 10.82 - samples/sec: 2257.81 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:34:40,785 epoch 5 - iter 270/304 - loss 0.04313341 - time (sec): 12.11 - samples/sec: 2277.61 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:34:42,094 epoch 5 - iter 300/304 - loss 0.04659600 - time (sec): 13.42 - samples/sec: 2288.60 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:34:42,256 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:42,256 EPOCH 5 done: loss 0.0462 - lr: 0.000028
2023-10-17 09:34:43,227 DEV : loss 0.19779552519321442 - f1-score (micro avg) 0.8475
2023-10-17 09:34:43,234 saving best model
2023-10-17 09:34:43,689 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:45,101 epoch 6 - iter 30/304 - loss 0.05143267 - time (sec): 1.40 - samples/sec: 2210.38 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:34:46,425 epoch 6 - iter 60/304 - loss 0.03537847 - time (sec): 2.73 - samples/sec: 2170.17 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:34:47,769 epoch 6 - iter 90/304 - loss 0.03156355 - time (sec): 4.07 - samples/sec: 2186.19 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:34:49,120 epoch 6 - iter 120/304 - loss 0.02614683 - time (sec): 5.42 - samples/sec: 2201.33 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:34:50,493 epoch 6 - iter 150/304 - loss 0.02570856 - time (sec): 6.79 - samples/sec: 2227.33 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:34:51,827 epoch 6 - iter 180/304 - loss 0.02466593 - time (sec): 8.13 - samples/sec: 2229.40 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:34:53,204 epoch 6 - iter 210/304 - loss 0.02965446 - time (sec): 9.51 - samples/sec: 2241.84 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:34:54,541 epoch 6 - iter 240/304 - loss 0.02712866 - time (sec): 10.84 - samples/sec: 2238.86 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:34:55,890 epoch 6 - iter 270/304 - loss 0.02982859 - time (sec): 12.19 - samples/sec: 2246.57 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:34:57,245 epoch 6 - iter 300/304 - loss 0.03308022 - time (sec): 13.55 - samples/sec: 2263.29 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:34:57,420 ----------------------------------------------------------------------------------------------------
2023-10-17 09:34:57,421 EPOCH 6 done: loss 0.0330 - lr: 0.000022
2023-10-17 09:34:58,543 DEV : loss 0.18329085409641266 - f1-score (micro avg) 0.8568
2023-10-17 09:34:58,550 saving best model
2023-10-17 09:34:59,058 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:00,421 epoch 7 - iter 30/304 - loss 0.00903014 - time (sec): 1.36 - samples/sec: 2058.42 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:35:01,810 epoch 7 - iter 60/304 - loss 0.01054061 - time (sec): 2.75 - samples/sec: 2120.91 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:35:03,185 epoch 7 - iter 90/304 - loss 0.01510108 - time (sec): 4.13 - samples/sec: 2161.56 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:35:04,616 epoch 7 - iter 120/304 - loss 0.01565376 - time (sec): 5.56 - samples/sec: 2131.48 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:35:06,050 epoch 7 - iter 150/304 - loss 0.01317230 - time (sec): 6.99 - samples/sec: 2143.38 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:35:07,407 epoch 7 - iter 180/304 - loss 0.01320453 - time (sec): 8.35 - samples/sec: 2156.66 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:35:08,703 epoch 7 - iter 210/304 - loss 0.01596236 - time (sec): 9.64 - samples/sec: 2182.73 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:35:10,013 epoch 7 - iter 240/304 - loss 0.01593314 - time (sec): 10.95 - samples/sec: 2230.29 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:35:11,362 epoch 7 - iter 270/304 - loss 0.01798677 - time (sec): 12.30 - samples/sec: 2254.56 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:35:12,771 epoch 7 - iter 300/304 - loss 0.02095176 - time (sec): 13.71 - samples/sec: 2234.42 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:35:12,969 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:12,970 EPOCH 7 done: loss 0.0211 - lr: 0.000017
2023-10-17 09:35:13,928 DEV : loss 0.2318311482667923 - f1-score (micro avg) 0.8571
2023-10-17 09:35:13,935 saving best model
2023-10-17 09:35:14,386 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:15,821 epoch 8 - iter 30/304 - loss 0.00640611 - time (sec): 1.43 - samples/sec: 2346.78 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:35:17,274 epoch 8 - iter 60/304 - loss 0.00420715 - time (sec): 2.89 - samples/sec: 2210.37 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:35:18,674 epoch 8 - iter 90/304 - loss 0.01207152 - time (sec): 4.29 - samples/sec: 2215.29 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:35:20,025 epoch 8 - iter 120/304 - loss 0.01364647 - time (sec): 5.64 - samples/sec: 2159.32 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:35:21,393 epoch 8 - iter 150/304 - loss 0.01137201 - time (sec): 7.01 - samples/sec: 2216.12 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:35:22,749 epoch 8 - iter 180/304 - loss 0.01119804 - time (sec): 8.36 - samples/sec: 2203.40 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:35:24,097 epoch 8 - iter 210/304 - loss 0.01460673 - time (sec): 9.71 - samples/sec: 2203.24 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:35:25,448 epoch 8 - iter 240/304 - loss 0.01538458 - time (sec): 11.06 - samples/sec: 2216.67 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:35:26,821 epoch 8 - iter 270/304 - loss 0.01486285 - time (sec): 12.43 - samples/sec: 2220.99 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:35:28,153 epoch 8 - iter 300/304 - loss 0.01592791 - time (sec): 13.77 - samples/sec: 2224.23 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:35:28,323 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:28,324 EPOCH 8 done: loss 0.0157 - lr: 0.000011
2023-10-17 09:35:29,276 DEV : loss 0.21787002682685852 - f1-score (micro avg) 0.8561
2023-10-17 09:35:29,283 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:30,696 epoch 9 - iter 30/304 - loss 0.01042886 - time (sec): 1.41 - samples/sec: 2178.98 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:35:32,023 epoch 9 - iter 60/304 - loss 0.00538462 - time (sec): 2.74 - samples/sec: 2184.25 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:35:33,344 epoch 9 - iter 90/304 - loss 0.01550286 - time (sec): 4.06 - samples/sec: 2257.11 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:35:34,676 epoch 9 - iter 120/304 - loss 0.01188775 - time (sec): 5.39 - samples/sec: 2234.21 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:35:36,048 epoch 9 - iter 150/304 - loss 0.01119042 - time (sec): 6.76 - samples/sec: 2252.88 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:35:37,409 epoch 9 - iter 180/304 - loss 0.01085870 - time (sec): 8.12 - samples/sec: 2259.30 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:35:38,748 epoch 9 - iter 210/304 - loss 0.00941338 - time (sec): 9.46 - samples/sec: 2252.93 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:35:40,069 epoch 9 - iter 240/304 - loss 0.00912920 - time (sec): 10.78 - samples/sec: 2249.94 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:35:41,405 epoch 9 - iter 270/304 - loss 0.01006905 - time (sec): 12.12 - samples/sec: 2263.51 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:35:42,742 epoch 9 - iter 300/304 - loss 0.01164740 - time (sec): 13.46 - samples/sec: 2277.54 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:35:42,913 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:42,914 EPOCH 9 done: loss 0.0115 - lr: 0.000006
2023-10-17 09:35:43,887 DEV : loss 0.22361968457698822 - f1-score (micro avg) 0.8551
2023-10-17 09:35:43,895 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:45,259 epoch 10 - iter 30/304 - loss 0.00155770 - time (sec): 1.36 - samples/sec: 2158.68 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:35:46,575 epoch 10 - iter 60/304 - loss 0.00990788 - time (sec): 2.68 - samples/sec: 2231.22 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:35:47,906 epoch 10 - iter 90/304 - loss 0.00933886 - time (sec): 4.01 - samples/sec: 2311.59 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:35:49,363 epoch 10 - iter 120/304 - loss 0.01043367 - time (sec): 5.47 - samples/sec: 2231.01 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:35:50,741 epoch 10 - iter 150/304 - loss 0.00896913 - time (sec): 6.84 - samples/sec: 2212.05 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:35:52,078 epoch 10 - iter 180/304 - loss 0.00836120 - time (sec): 8.18 - samples/sec: 2217.08 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:35:53,436 epoch 10 - iter 210/304 - loss 0.00726658 - time (sec): 9.54 - samples/sec: 2238.68 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:35:54,774 epoch 10 - iter 240/304 - loss 0.00677716 - time (sec): 10.88 - samples/sec: 2236.89 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:35:56,181 epoch 10 - iter 270/304 - loss 0.00720824 - time (sec): 12.28 - samples/sec: 2230.52 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:35:57,552 epoch 10 - iter 300/304 - loss 0.00782340 - time (sec): 13.66 - samples/sec: 2241.83 - lr: 0.000000 - momentum: 0.000000
2023-10-17 09:35:57,727 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:57,727 EPOCH 10 done: loss 0.0079 - lr: 0.000000
2023-10-17 09:35:58,665 DEV : loss 0.2244568020105362 - f1-score (micro avg) 0.8565
2023-10-17 09:35:59,046 ----------------------------------------------------------------------------------------------------
2023-10-17 09:35:59,047 Loading model from best epoch ...
2023-10-17 09:36:00,460 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 09:36:01,338
Results:
- F-score (micro) 0.8268
- F-score (macro) 0.605
- Accuracy 0.7133
By class:
precision recall f1-score support
scope 0.7610 0.8013 0.7806 151
pers 0.8750 0.9479 0.9100 96
work 0.7981 0.8737 0.8342 95
loc 1.0000 0.3333 0.5000 3
date 0.0000 0.0000 0.0000 3
micro avg 0.8043 0.8506 0.8268 348
macro avg 0.6868 0.5913 0.6050 348
weighted avg 0.7981 0.8506 0.8218 348
2023-10-17 09:36:01,338 ----------------------------------------------------------------------------------------------------
|