File size: 23,989 Bytes
240ab77 |
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 |
2023-10-13 11:05:24,965 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,966 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(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): 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-13 11:05:24,966 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,966 MultiCorpus: 966 train + 219 dev + 204 test sentences
- NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-13 11:05:24,966 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,966 Train: 966 sentences
2023-10-13 11:05:24,967 (train_with_dev=False, train_with_test=False)
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 Training Params:
2023-10-13 11:05:24,967 - learning_rate: "3e-05"
2023-10-13 11:05:24,967 - mini_batch_size: "4"
2023-10-13 11:05:24,967 - max_epochs: "10"
2023-10-13 11:05:24,967 - shuffle: "True"
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 Plugins:
2023-10-13 11:05:24,967 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 11:05:24,967 - metric: "('micro avg', 'f1-score')"
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 Computation:
2023-10-13 11:05:24,967 - compute on device: cuda:0
2023-10-13 11:05:24,967 - embedding storage: none
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:24,967 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:26,068 epoch 1 - iter 24/242 - loss 3.26045040 - time (sec): 1.10 - samples/sec: 1997.04 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:05:27,168 epoch 1 - iter 48/242 - loss 2.88611384 - time (sec): 2.20 - samples/sec: 2190.45 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:05:28,240 epoch 1 - iter 72/242 - loss 2.29154480 - time (sec): 3.27 - samples/sec: 2204.10 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:05:29,304 epoch 1 - iter 96/242 - loss 1.83341707 - time (sec): 4.34 - samples/sec: 2293.36 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:05:30,397 epoch 1 - iter 120/242 - loss 1.58399035 - time (sec): 5.43 - samples/sec: 2294.08 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:05:31,429 epoch 1 - iter 144/242 - loss 1.41150946 - time (sec): 6.46 - samples/sec: 2255.49 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:05:32,514 epoch 1 - iter 168/242 - loss 1.26653071 - time (sec): 7.55 - samples/sec: 2273.95 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:05:33,561 epoch 1 - iter 192/242 - loss 1.15583293 - time (sec): 8.59 - samples/sec: 2276.18 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:05:34,597 epoch 1 - iter 216/242 - loss 1.07012297 - time (sec): 9.63 - samples/sec: 2269.55 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:05:35,676 epoch 1 - iter 240/242 - loss 0.98086424 - time (sec): 10.71 - samples/sec: 2285.79 - lr: 0.000030 - momentum: 0.000000
2023-10-13 11:05:35,771 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:35,772 EPOCH 1 done: loss 0.9715 - lr: 0.000030
2023-10-13 11:05:36,434 DEV : loss 0.22636541724205017 - f1-score (micro avg) 0.5455
2023-10-13 11:05:36,439 saving best model
2023-10-13 11:05:36,829 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:37,892 epoch 2 - iter 24/242 - loss 0.26044400 - time (sec): 1.06 - samples/sec: 2430.95 - lr: 0.000030 - momentum: 0.000000
2023-10-13 11:05:38,995 epoch 2 - iter 48/242 - loss 0.24138370 - time (sec): 2.16 - samples/sec: 2402.11 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:05:40,099 epoch 2 - iter 72/242 - loss 0.24308040 - time (sec): 3.27 - samples/sec: 2251.75 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:05:41,200 epoch 2 - iter 96/242 - loss 0.23121133 - time (sec): 4.37 - samples/sec: 2271.47 - lr: 0.000029 - momentum: 0.000000
2023-10-13 11:05:42,277 epoch 2 - iter 120/242 - loss 0.21626000 - time (sec): 5.45 - samples/sec: 2249.01 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:05:43,360 epoch 2 - iter 144/242 - loss 0.21173941 - time (sec): 6.53 - samples/sec: 2258.81 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:05:44,467 epoch 2 - iter 168/242 - loss 0.20705356 - time (sec): 7.64 - samples/sec: 2263.16 - lr: 0.000028 - momentum: 0.000000
2023-10-13 11:05:45,543 epoch 2 - iter 192/242 - loss 0.20385589 - time (sec): 8.71 - samples/sec: 2270.21 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:05:46,632 epoch 2 - iter 216/242 - loss 0.19354748 - time (sec): 9.80 - samples/sec: 2272.40 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:05:47,701 epoch 2 - iter 240/242 - loss 0.18924590 - time (sec): 10.87 - samples/sec: 2266.50 - lr: 0.000027 - momentum: 0.000000
2023-10-13 11:05:47,787 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:47,787 EPOCH 2 done: loss 0.1897 - lr: 0.000027
2023-10-13 11:05:48,562 DEV : loss 0.12835250794887543 - f1-score (micro avg) 0.7798
2023-10-13 11:05:48,567 saving best model
2023-10-13 11:05:49,076 ----------------------------------------------------------------------------------------------------
2023-10-13 11:05:50,152 epoch 3 - iter 24/242 - loss 0.11671487 - time (sec): 1.07 - samples/sec: 2298.83 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:05:51,269 epoch 3 - iter 48/242 - loss 0.13534817 - time (sec): 2.19 - samples/sec: 2253.79 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:05:52,356 epoch 3 - iter 72/242 - loss 0.12326417 - time (sec): 3.28 - samples/sec: 2131.83 - lr: 0.000026 - momentum: 0.000000
2023-10-13 11:05:53,448 epoch 3 - iter 96/242 - loss 0.11100839 - time (sec): 4.37 - samples/sec: 2184.35 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:05:54,539 epoch 3 - iter 120/242 - loss 0.13168483 - time (sec): 5.46 - samples/sec: 2217.49 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:05:55,606 epoch 3 - iter 144/242 - loss 0.13061693 - time (sec): 6.53 - samples/sec: 2255.29 - lr: 0.000025 - momentum: 0.000000
2023-10-13 11:05:56,758 epoch 3 - iter 168/242 - loss 0.12146008 - time (sec): 7.68 - samples/sec: 2259.41 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:05:57,846 epoch 3 - iter 192/242 - loss 0.12442545 - time (sec): 8.77 - samples/sec: 2250.68 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:05:58,895 epoch 3 - iter 216/242 - loss 0.11859671 - time (sec): 9.82 - samples/sec: 2233.08 - lr: 0.000024 - momentum: 0.000000
2023-10-13 11:06:00,138 epoch 3 - iter 240/242 - loss 0.11276404 - time (sec): 11.06 - samples/sec: 2215.53 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:06:00,226 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:00,226 EPOCH 3 done: loss 0.1117 - lr: 0.000023
2023-10-13 11:06:00,994 DEV : loss 0.13323190808296204 - f1-score (micro avg) 0.8194
2023-10-13 11:06:00,998 saving best model
2023-10-13 11:06:01,497 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:02,580 epoch 4 - iter 24/242 - loss 0.07762309 - time (sec): 1.08 - samples/sec: 2243.88 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:06:03,674 epoch 4 - iter 48/242 - loss 0.07491095 - time (sec): 2.17 - samples/sec: 2317.40 - lr: 0.000023 - momentum: 0.000000
2023-10-13 11:06:04,732 epoch 4 - iter 72/242 - loss 0.07455367 - time (sec): 3.23 - samples/sec: 2278.61 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:06:05,801 epoch 4 - iter 96/242 - loss 0.07298124 - time (sec): 4.30 - samples/sec: 2281.83 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:06:06,880 epoch 4 - iter 120/242 - loss 0.07436689 - time (sec): 5.38 - samples/sec: 2303.54 - lr: 0.000022 - momentum: 0.000000
2023-10-13 11:06:07,956 epoch 4 - iter 144/242 - loss 0.07580398 - time (sec): 6.45 - samples/sec: 2316.56 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:06:09,007 epoch 4 - iter 168/242 - loss 0.07131010 - time (sec): 7.50 - samples/sec: 2302.79 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:06:10,081 epoch 4 - iter 192/242 - loss 0.07415322 - time (sec): 8.58 - samples/sec: 2275.06 - lr: 0.000021 - momentum: 0.000000
2023-10-13 11:06:11,158 epoch 4 - iter 216/242 - loss 0.07568736 - time (sec): 9.66 - samples/sec: 2269.11 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:06:12,274 epoch 4 - iter 240/242 - loss 0.07358843 - time (sec): 10.77 - samples/sec: 2284.71 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:06:12,366 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:12,367 EPOCH 4 done: loss 0.0733 - lr: 0.000020
2023-10-13 11:06:13,140 DEV : loss 0.15198326110839844 - f1-score (micro avg) 0.8235
2023-10-13 11:06:13,144 saving best model
2023-10-13 11:06:13,640 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:14,721 epoch 5 - iter 24/242 - loss 0.07274525 - time (sec): 1.08 - samples/sec: 2450.06 - lr: 0.000020 - momentum: 0.000000
2023-10-13 11:06:15,798 epoch 5 - iter 48/242 - loss 0.06649204 - time (sec): 2.16 - samples/sec: 2319.17 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:06:16,864 epoch 5 - iter 72/242 - loss 0.05377757 - time (sec): 3.22 - samples/sec: 2256.18 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:06:17,955 epoch 5 - iter 96/242 - loss 0.06363114 - time (sec): 4.31 - samples/sec: 2266.28 - lr: 0.000019 - momentum: 0.000000
2023-10-13 11:06:19,018 epoch 5 - iter 120/242 - loss 0.06437488 - time (sec): 5.38 - samples/sec: 2282.19 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:06:20,080 epoch 5 - iter 144/242 - loss 0.05925376 - time (sec): 6.44 - samples/sec: 2295.61 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:06:21,135 epoch 5 - iter 168/242 - loss 0.05949345 - time (sec): 7.49 - samples/sec: 2327.46 - lr: 0.000018 - momentum: 0.000000
2023-10-13 11:06:22,293 epoch 5 - iter 192/242 - loss 0.05779375 - time (sec): 8.65 - samples/sec: 2295.53 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:06:23,434 epoch 5 - iter 216/242 - loss 0.05891234 - time (sec): 9.79 - samples/sec: 2292.53 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:06:24,504 epoch 5 - iter 240/242 - loss 0.05658195 - time (sec): 10.86 - samples/sec: 2265.63 - lr: 0.000017 - momentum: 0.000000
2023-10-13 11:06:24,592 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:24,592 EPOCH 5 done: loss 0.0566 - lr: 0.000017
2023-10-13 11:06:25,388 DEV : loss 0.1912955939769745 - f1-score (micro avg) 0.8244
2023-10-13 11:06:25,394 saving best model
2023-10-13 11:06:25,910 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:27,018 epoch 6 - iter 24/242 - loss 0.06617410 - time (sec): 1.11 - samples/sec: 2341.85 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:06:28,113 epoch 6 - iter 48/242 - loss 0.05850652 - time (sec): 2.20 - samples/sec: 2312.88 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:06:29,189 epoch 6 - iter 72/242 - loss 0.05073463 - time (sec): 3.28 - samples/sec: 2349.60 - lr: 0.000016 - momentum: 0.000000
2023-10-13 11:06:30,249 epoch 6 - iter 96/242 - loss 0.04505559 - time (sec): 4.34 - samples/sec: 2262.10 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:06:31,358 epoch 6 - iter 120/242 - loss 0.04664781 - time (sec): 5.45 - samples/sec: 2294.26 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:06:32,443 epoch 6 - iter 144/242 - loss 0.04235768 - time (sec): 6.53 - samples/sec: 2284.89 - lr: 0.000015 - momentum: 0.000000
2023-10-13 11:06:33,487 epoch 6 - iter 168/242 - loss 0.04469986 - time (sec): 7.57 - samples/sec: 2252.76 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:06:34,559 epoch 6 - iter 192/242 - loss 0.04069028 - time (sec): 8.65 - samples/sec: 2243.91 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:06:35,638 epoch 6 - iter 216/242 - loss 0.04199094 - time (sec): 9.73 - samples/sec: 2246.12 - lr: 0.000014 - momentum: 0.000000
2023-10-13 11:06:36,707 epoch 6 - iter 240/242 - loss 0.04314476 - time (sec): 10.79 - samples/sec: 2279.24 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:06:36,787 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:36,787 EPOCH 6 done: loss 0.0432 - lr: 0.000013
2023-10-13 11:06:37,614 DEV : loss 0.18537166714668274 - f1-score (micro avg) 0.8366
2023-10-13 11:06:37,619 saving best model
2023-10-13 11:06:38,105 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:39,174 epoch 7 - iter 24/242 - loss 0.01600020 - time (sec): 1.06 - samples/sec: 2410.61 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:06:40,249 epoch 7 - iter 48/242 - loss 0.02047617 - time (sec): 2.13 - samples/sec: 2366.74 - lr: 0.000013 - momentum: 0.000000
2023-10-13 11:06:41,298 epoch 7 - iter 72/242 - loss 0.02035596 - time (sec): 3.18 - samples/sec: 2312.63 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:06:42,362 epoch 7 - iter 96/242 - loss 0.02688458 - time (sec): 4.25 - samples/sec: 2295.53 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:06:43,418 epoch 7 - iter 120/242 - loss 0.03084187 - time (sec): 5.30 - samples/sec: 2306.37 - lr: 0.000012 - momentum: 0.000000
2023-10-13 11:06:44,530 epoch 7 - iter 144/242 - loss 0.02784585 - time (sec): 6.42 - samples/sec: 2310.41 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:06:45,592 epoch 7 - iter 168/242 - loss 0.02810855 - time (sec): 7.48 - samples/sec: 2316.89 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:06:46,663 epoch 7 - iter 192/242 - loss 0.02898516 - time (sec): 8.55 - samples/sec: 2289.84 - lr: 0.000011 - momentum: 0.000000
2023-10-13 11:06:47,755 epoch 7 - iter 216/242 - loss 0.03038159 - time (sec): 9.64 - samples/sec: 2292.36 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:06:48,838 epoch 7 - iter 240/242 - loss 0.02942164 - time (sec): 10.72 - samples/sec: 2287.96 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:06:48,926 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:48,926 EPOCH 7 done: loss 0.0292 - lr: 0.000010
2023-10-13 11:06:49,699 DEV : loss 0.19361057877540588 - f1-score (micro avg) 0.8267
2023-10-13 11:06:49,705 ----------------------------------------------------------------------------------------------------
2023-10-13 11:06:50,807 epoch 8 - iter 24/242 - loss 0.02404239 - time (sec): 1.10 - samples/sec: 2441.79 - lr: 0.000010 - momentum: 0.000000
2023-10-13 11:06:51,860 epoch 8 - iter 48/242 - loss 0.02940480 - time (sec): 2.15 - samples/sec: 2412.74 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:06:52,944 epoch 8 - iter 72/242 - loss 0.02453911 - time (sec): 3.24 - samples/sec: 2378.28 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:06:54,003 epoch 8 - iter 96/242 - loss 0.02656054 - time (sec): 4.30 - samples/sec: 2377.14 - lr: 0.000009 - momentum: 0.000000
2023-10-13 11:06:55,064 epoch 8 - iter 120/242 - loss 0.02321820 - time (sec): 5.36 - samples/sec: 2394.25 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:06:56,131 epoch 8 - iter 144/242 - loss 0.02216193 - time (sec): 6.42 - samples/sec: 2365.89 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:06:57,207 epoch 8 - iter 168/242 - loss 0.02347826 - time (sec): 7.50 - samples/sec: 2330.07 - lr: 0.000008 - momentum: 0.000000
2023-10-13 11:06:58,256 epoch 8 - iter 192/242 - loss 0.02405429 - time (sec): 8.55 - samples/sec: 2317.08 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:06:59,301 epoch 8 - iter 216/242 - loss 0.02396532 - time (sec): 9.60 - samples/sec: 2330.16 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:07:00,352 epoch 8 - iter 240/242 - loss 0.02408148 - time (sec): 10.65 - samples/sec: 2316.55 - lr: 0.000007 - momentum: 0.000000
2023-10-13 11:07:00,434 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:00,434 EPOCH 8 done: loss 0.0240 - lr: 0.000007
2023-10-13 11:07:01,228 DEV : loss 0.20021933317184448 - f1-score (micro avg) 0.8436
2023-10-13 11:07:01,233 saving best model
2023-10-13 11:07:01,700 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:02,768 epoch 9 - iter 24/242 - loss 0.01550654 - time (sec): 1.07 - samples/sec: 2285.05 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:07:03,832 epoch 9 - iter 48/242 - loss 0.02270449 - time (sec): 2.13 - samples/sec: 2390.28 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:07:04,912 epoch 9 - iter 72/242 - loss 0.02250225 - time (sec): 3.21 - samples/sec: 2420.69 - lr: 0.000006 - momentum: 0.000000
2023-10-13 11:07:05,950 epoch 9 - iter 96/242 - loss 0.01864297 - time (sec): 4.25 - samples/sec: 2319.14 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:07:06,989 epoch 9 - iter 120/242 - loss 0.01711462 - time (sec): 5.29 - samples/sec: 2273.59 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:07:08,035 epoch 9 - iter 144/242 - loss 0.01565846 - time (sec): 6.33 - samples/sec: 2289.88 - lr: 0.000005 - momentum: 0.000000
2023-10-13 11:07:09,117 epoch 9 - iter 168/242 - loss 0.01575760 - time (sec): 7.41 - samples/sec: 2321.46 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:07:10,201 epoch 9 - iter 192/242 - loss 0.01432253 - time (sec): 8.50 - samples/sec: 2308.51 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:07:11,232 epoch 9 - iter 216/242 - loss 0.01599132 - time (sec): 9.53 - samples/sec: 2286.85 - lr: 0.000004 - momentum: 0.000000
2023-10-13 11:07:12,331 epoch 9 - iter 240/242 - loss 0.01606926 - time (sec): 10.63 - samples/sec: 2315.03 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:07:12,413 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:12,413 EPOCH 9 done: loss 0.0163 - lr: 0.000003
2023-10-13 11:07:13,169 DEV : loss 0.1932135969400406 - f1-score (micro avg) 0.8416
2023-10-13 11:07:13,174 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:14,212 epoch 10 - iter 24/242 - loss 0.02167304 - time (sec): 1.04 - samples/sec: 2341.97 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:07:15,311 epoch 10 - iter 48/242 - loss 0.01936270 - time (sec): 2.14 - samples/sec: 2426.22 - lr: 0.000003 - momentum: 0.000000
2023-10-13 11:07:16,378 epoch 10 - iter 72/242 - loss 0.01709001 - time (sec): 3.20 - samples/sec: 2323.76 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:07:17,441 epoch 10 - iter 96/242 - loss 0.01646947 - time (sec): 4.27 - samples/sec: 2249.78 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:07:18,532 epoch 10 - iter 120/242 - loss 0.01471660 - time (sec): 5.36 - samples/sec: 2333.19 - lr: 0.000002 - momentum: 0.000000
2023-10-13 11:07:19,616 epoch 10 - iter 144/242 - loss 0.01419476 - time (sec): 6.44 - samples/sec: 2307.73 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:07:20,684 epoch 10 - iter 168/242 - loss 0.01495178 - time (sec): 7.51 - samples/sec: 2288.09 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:07:21,742 epoch 10 - iter 192/242 - loss 0.01644886 - time (sec): 8.57 - samples/sec: 2267.34 - lr: 0.000001 - momentum: 0.000000
2023-10-13 11:07:22,818 epoch 10 - iter 216/242 - loss 0.01509444 - time (sec): 9.64 - samples/sec: 2272.31 - lr: 0.000000 - momentum: 0.000000
2023-10-13 11:07:23,922 epoch 10 - iter 240/242 - loss 0.01457994 - time (sec): 10.75 - samples/sec: 2285.62 - lr: 0.000000 - momentum: 0.000000
2023-10-13 11:07:24,003 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:24,004 EPOCH 10 done: loss 0.0145 - lr: 0.000000
2023-10-13 11:07:24,763 DEV : loss 0.20257213711738586 - f1-score (micro avg) 0.8408
2023-10-13 11:07:25,119 ----------------------------------------------------------------------------------------------------
2023-10-13 11:07:25,121 Loading model from best epoch ...
2023-10-13 11:07:26,541 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-13 11:07:27,369
Results:
- F-score (micro) 0.8295
- F-score (macro) 0.5622
- Accuracy 0.7255
By class:
precision recall f1-score support
pers 0.8414 0.8777 0.8592 139
scope 0.8633 0.9302 0.8955 129
work 0.6977 0.7500 0.7229 80
loc 0.6667 0.2222 0.3333 9
date 0.0000 0.0000 0.0000 3
micro avg 0.8150 0.8444 0.8295 360
macro avg 0.6138 0.5560 0.5622 360
weighted avg 0.8059 0.8444 0.8216 360
2023-10-13 11:07:27,369 ----------------------------------------------------------------------------------------------------
|