2023-10-17 15:20:20,697 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,699 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=21, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 15:20:20,699 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,699 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator 2023-10-17 15:20:20,699 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,699 Train: 3575 sentences 2023-10-17 15:20:20,699 (train_with_dev=False, train_with_test=False) 2023-10-17 15:20:20,699 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,699 Training Params: 2023-10-17 15:20:20,700 - learning_rate: "5e-05" 2023-10-17 15:20:20,700 - mini_batch_size: "8" 2023-10-17 15:20:20,700 - max_epochs: "10" 2023-10-17 15:20:20,700 - shuffle: "True" 2023-10-17 15:20:20,700 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,700 Plugins: 2023-10-17 15:20:20,700 - TensorboardLogger 2023-10-17 15:20:20,700 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 15:20:20,700 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,700 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 15:20:20,700 - metric: "('micro avg', 'f1-score')" 2023-10-17 15:20:20,700 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,700 Computation: 2023-10-17 15:20:20,700 - compute on device: cuda:0 2023-10-17 15:20:20,700 - embedding storage: none 2023-10-17 15:20:20,701 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,701 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" 2023-10-17 15:20:20,701 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,701 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:20:20,701 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 15:20:25,296 epoch 1 - iter 44/447 - loss 3.29322406 - time (sec): 4.59 - samples/sec: 1935.59 - lr: 0.000005 - momentum: 0.000000 2023-10-17 15:20:29,526 epoch 1 - iter 88/447 - loss 2.20404796 - time (sec): 8.82 - samples/sec: 1932.03 - lr: 0.000010 - momentum: 0.000000 2023-10-17 15:20:33,812 epoch 1 - iter 132/447 - loss 1.66693701 - time (sec): 13.11 - samples/sec: 1943.12 - lr: 0.000015 - momentum: 0.000000 2023-10-17 15:20:37,841 epoch 1 - iter 176/447 - loss 1.34300581 - time (sec): 17.14 - samples/sec: 2013.07 - lr: 0.000020 - momentum: 0.000000 2023-10-17 15:20:42,001 epoch 1 - iter 220/447 - loss 1.13494006 - time (sec): 21.30 - samples/sec: 2034.17 - lr: 0.000024 - momentum: 0.000000 2023-10-17 15:20:46,118 epoch 1 - iter 264/447 - loss 0.99498347 - time (sec): 25.42 - samples/sec: 2037.60 - lr: 0.000029 - momentum: 0.000000 2023-10-17 15:20:50,011 epoch 1 - iter 308/447 - loss 0.90014844 - time (sec): 29.31 - samples/sec: 2045.24 - lr: 0.000034 - momentum: 0.000000 2023-10-17 15:20:54,208 epoch 1 - iter 352/447 - loss 0.82692832 - time (sec): 33.51 - samples/sec: 2030.01 - lr: 0.000039 - momentum: 0.000000 2023-10-17 15:20:58,668 epoch 1 - iter 396/447 - loss 0.75333912 - time (sec): 37.97 - samples/sec: 2037.44 - lr: 0.000044 - momentum: 0.000000 2023-10-17 15:21:02,777 epoch 1 - iter 440/447 - loss 0.70068186 - time (sec): 42.07 - samples/sec: 2029.61 - lr: 0.000049 - momentum: 0.000000 2023-10-17 15:21:03,549 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:21:03,549 EPOCH 1 done: loss 0.6939 - lr: 0.000049 2023-10-17 15:21:10,111 DEV : loss 0.1627715528011322 - f1-score (micro avg) 0.6637 2023-10-17 15:21:10,167 saving best model 2023-10-17 15:21:10,755 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:21:14,984 epoch 2 - iter 44/447 - loss 0.18574466 - time (sec): 4.23 - samples/sec: 2020.81 - lr: 0.000049 - momentum: 0.000000 2023-10-17 15:21:18,869 epoch 2 - iter 88/447 - loss 0.17587291 - time (sec): 8.11 - samples/sec: 2043.93 - lr: 0.000049 - momentum: 0.000000 2023-10-17 15:21:22,901 epoch 2 - iter 132/447 - loss 0.18074319 - time (sec): 12.14 - samples/sec: 2045.51 - lr: 0.000048 - momentum: 0.000000 2023-10-17 15:21:27,252 epoch 2 - iter 176/447 - loss 0.16716021 - time (sec): 16.49 - samples/sec: 2035.17 - lr: 0.000048 - momentum: 0.000000 2023-10-17 15:21:31,318 epoch 2 - iter 220/447 - loss 0.16088597 - time (sec): 20.56 - samples/sec: 2037.01 - lr: 0.000047 - momentum: 0.000000 2023-10-17 15:21:35,411 epoch 2 - iter 264/447 - loss 0.15627115 - time (sec): 24.65 - samples/sec: 2064.17 - lr: 0.000047 - momentum: 0.000000 2023-10-17 15:21:39,518 epoch 2 - iter 308/447 - loss 0.15212403 - time (sec): 28.76 - samples/sec: 2071.36 - lr: 0.000046 - momentum: 0.000000 2023-10-17 15:21:43,871 epoch 2 - iter 352/447 - loss 0.14647911 - time (sec): 33.11 - samples/sec: 2068.26 - lr: 0.000046 - momentum: 0.000000 2023-10-17 15:21:47,774 epoch 2 - iter 396/447 - loss 0.14381048 - time (sec): 37.02 - samples/sec: 2063.23 - lr: 0.000045 - momentum: 0.000000 2023-10-17 15:21:52,104 epoch 2 - iter 440/447 - loss 0.13930114 - time (sec): 41.35 - samples/sec: 2061.40 - lr: 0.000045 - momentum: 0.000000 2023-10-17 15:21:52,733 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:21:52,733 EPOCH 2 done: loss 0.1388 - lr: 0.000045 2023-10-17 15:22:03,664 DEV : loss 0.13203084468841553 - f1-score (micro avg) 0.7453 2023-10-17 15:22:03,719 saving best model 2023-10-17 15:22:04,360 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:22:08,773 epoch 3 - iter 44/447 - loss 0.07462311 - time (sec): 4.41 - samples/sec: 2144.45 - lr: 0.000044 - momentum: 0.000000 2023-10-17 15:22:12,960 epoch 3 - iter 88/447 - loss 0.07763574 - time (sec): 8.60 - samples/sec: 2161.08 - lr: 0.000043 - momentum: 0.000000 2023-10-17 15:22:16,914 epoch 3 - iter 132/447 - loss 0.07588462 - time (sec): 12.55 - samples/sec: 2119.86 - lr: 0.000043 - momentum: 0.000000 2023-10-17 15:22:20,965 epoch 3 - iter 176/447 - loss 0.07957562 - time (sec): 16.60 - samples/sec: 2065.06 - lr: 0.000042 - momentum: 0.000000 2023-10-17 15:22:24,832 epoch 3 - iter 220/447 - loss 0.07641351 - time (sec): 20.47 - samples/sec: 2080.13 - lr: 0.000042 - momentum: 0.000000 2023-10-17 15:22:28,692 epoch 3 - iter 264/447 - loss 0.07516708 - time (sec): 24.33 - samples/sec: 2077.44 - lr: 0.000041 - momentum: 0.000000 2023-10-17 15:22:32,638 epoch 3 - iter 308/447 - loss 0.07530165 - time (sec): 28.28 - samples/sec: 2075.02 - lr: 0.000041 - momentum: 0.000000 2023-10-17 15:22:36,871 epoch 3 - iter 352/447 - loss 0.07665390 - time (sec): 32.51 - samples/sec: 2087.45 - lr: 0.000040 - momentum: 0.000000 2023-10-17 15:22:40,961 epoch 3 - iter 396/447 - loss 0.07644784 - time (sec): 36.60 - samples/sec: 2091.93 - lr: 0.000040 - momentum: 0.000000 2023-10-17 15:22:45,586 epoch 3 - iter 440/447 - loss 0.07596108 - time (sec): 41.22 - samples/sec: 2072.90 - lr: 0.000039 - momentum: 0.000000 2023-10-17 15:22:46,244 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:22:46,244 EPOCH 3 done: loss 0.0779 - lr: 0.000039 2023-10-17 15:22:57,932 DEV : loss 0.15669210255146027 - f1-score (micro avg) 0.7361 2023-10-17 15:22:57,990 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:23:01,950 epoch 4 - iter 44/447 - loss 0.11113508 - time (sec): 3.96 - samples/sec: 2079.82 - lr: 0.000038 - momentum: 0.000000 2023-10-17 15:23:06,160 epoch 4 - iter 88/447 - loss 0.07727697 - time (sec): 8.17 - samples/sec: 2009.83 - lr: 0.000038 - momentum: 0.000000 2023-10-17 15:23:10,270 epoch 4 - iter 132/447 - loss 0.07094192 - time (sec): 12.28 - samples/sec: 1949.87 - lr: 0.000037 - momentum: 0.000000 2023-10-17 15:23:14,604 epoch 4 - iter 176/447 - loss 0.06225710 - time (sec): 16.61 - samples/sec: 1963.87 - lr: 0.000037 - momentum: 0.000000 2023-10-17 15:23:19,493 epoch 4 - iter 220/447 - loss 0.06035341 - time (sec): 21.50 - samples/sec: 1996.90 - lr: 0.000036 - momentum: 0.000000 2023-10-17 15:23:23,666 epoch 4 - iter 264/447 - loss 0.05722586 - time (sec): 25.67 - samples/sec: 1995.76 - lr: 0.000036 - momentum: 0.000000 2023-10-17 15:23:27,927 epoch 4 - iter 308/447 - loss 0.05924836 - time (sec): 29.93 - samples/sec: 1999.94 - lr: 0.000035 - momentum: 0.000000 2023-10-17 15:23:32,357 epoch 4 - iter 352/447 - loss 0.05871739 - time (sec): 34.36 - samples/sec: 1997.60 - lr: 0.000035 - momentum: 0.000000 2023-10-17 15:23:36,757 epoch 4 - iter 396/447 - loss 0.05849539 - time (sec): 38.77 - samples/sec: 1987.97 - lr: 0.000034 - momentum: 0.000000 2023-10-17 15:23:40,809 epoch 4 - iter 440/447 - loss 0.05804840 - time (sec): 42.82 - samples/sec: 1989.71 - lr: 0.000033 - momentum: 0.000000 2023-10-17 15:23:41,474 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:23:41,474 EPOCH 4 done: loss 0.0579 - lr: 0.000033 2023-10-17 15:23:52,260 DEV : loss 0.15689311921596527 - f1-score (micro avg) 0.7574 2023-10-17 15:23:52,319 saving best model 2023-10-17 15:23:54,139 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:23:58,437 epoch 5 - iter 44/447 - loss 0.03896987 - time (sec): 4.29 - samples/sec: 2061.67 - lr: 0.000033 - momentum: 0.000000 2023-10-17 15:24:02,519 epoch 5 - iter 88/447 - loss 0.04068401 - time (sec): 8.38 - samples/sec: 2066.50 - lr: 0.000032 - momentum: 0.000000 2023-10-17 15:24:06,827 epoch 5 - iter 132/447 - loss 0.03466089 - time (sec): 12.68 - samples/sec: 2079.00 - lr: 0.000032 - momentum: 0.000000 2023-10-17 15:24:10,950 epoch 5 - iter 176/447 - loss 0.03234991 - time (sec): 16.81 - samples/sec: 2029.72 - lr: 0.000031 - momentum: 0.000000 2023-10-17 15:24:15,467 epoch 5 - iter 220/447 - loss 0.03486824 - time (sec): 21.32 - samples/sec: 2031.61 - lr: 0.000031 - momentum: 0.000000 2023-10-17 15:24:19,494 epoch 5 - iter 264/447 - loss 0.03514322 - time (sec): 25.35 - samples/sec: 2028.49 - lr: 0.000030 - momentum: 0.000000 2023-10-17 15:24:23,617 epoch 5 - iter 308/447 - loss 0.03414630 - time (sec): 29.47 - samples/sec: 2030.22 - lr: 0.000030 - momentum: 0.000000 2023-10-17 15:24:27,949 epoch 5 - iter 352/447 - loss 0.03379714 - time (sec): 33.81 - samples/sec: 2023.06 - lr: 0.000029 - momentum: 0.000000 2023-10-17 15:24:32,314 epoch 5 - iter 396/447 - loss 0.03258252 - time (sec): 38.17 - samples/sec: 2009.56 - lr: 0.000028 - momentum: 0.000000 2023-10-17 15:24:37,011 epoch 5 - iter 440/447 - loss 0.03419784 - time (sec): 42.87 - samples/sec: 1992.60 - lr: 0.000028 - momentum: 0.000000 2023-10-17 15:24:37,701 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:24:37,702 EPOCH 5 done: loss 0.0342 - lr: 0.000028 2023-10-17 15:24:48,404 DEV : loss 0.19426260888576508 - f1-score (micro avg) 0.7695 2023-10-17 15:24:48,467 saving best model 2023-10-17 15:24:49,151 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:24:53,549 epoch 6 - iter 44/447 - loss 0.01163168 - time (sec): 4.40 - samples/sec: 1887.17 - lr: 0.000027 - momentum: 0.000000 2023-10-17 15:24:58,088 epoch 6 - iter 88/447 - loss 0.01528518 - time (sec): 8.94 - samples/sec: 1878.66 - lr: 0.000027 - momentum: 0.000000 2023-10-17 15:25:02,258 epoch 6 - iter 132/447 - loss 0.01991735 - time (sec): 13.10 - samples/sec: 1941.94 - lr: 0.000026 - momentum: 0.000000 2023-10-17 15:25:06,592 epoch 6 - iter 176/447 - loss 0.02065023 - time (sec): 17.44 - samples/sec: 1960.45 - lr: 0.000026 - momentum: 0.000000 2023-10-17 15:25:10,877 epoch 6 - iter 220/447 - loss 0.01950593 - time (sec): 21.72 - samples/sec: 1980.94 - lr: 0.000025 - momentum: 0.000000 2023-10-17 15:25:14,822 epoch 6 - iter 264/447 - loss 0.01844720 - time (sec): 25.67 - samples/sec: 1977.88 - lr: 0.000025 - momentum: 0.000000 2023-10-17 15:25:19,281 epoch 6 - iter 308/447 - loss 0.01859815 - time (sec): 30.13 - samples/sec: 2007.45 - lr: 0.000024 - momentum: 0.000000 2023-10-17 15:25:23,292 epoch 6 - iter 352/447 - loss 0.01870907 - time (sec): 34.14 - samples/sec: 2019.09 - lr: 0.000023 - momentum: 0.000000 2023-10-17 15:25:27,828 epoch 6 - iter 396/447 - loss 0.01881535 - time (sec): 38.68 - samples/sec: 2000.02 - lr: 0.000023 - momentum: 0.000000 2023-10-17 15:25:31,845 epoch 6 - iter 440/447 - loss 0.01872424 - time (sec): 42.69 - samples/sec: 1997.24 - lr: 0.000022 - momentum: 0.000000 2023-10-17 15:25:32,465 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:25:32,466 EPOCH 6 done: loss 0.0187 - lr: 0.000022 2023-10-17 15:25:43,025 DEV : loss 0.19804143905639648 - f1-score (micro avg) 0.771 2023-10-17 15:25:43,090 saving best model 2023-10-17 15:25:44,546 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:25:49,064 epoch 7 - iter 44/447 - loss 0.01406927 - time (sec): 4.51 - samples/sec: 2113.97 - lr: 0.000022 - momentum: 0.000000 2023-10-17 15:25:53,177 epoch 7 - iter 88/447 - loss 0.01378757 - time (sec): 8.63 - samples/sec: 2067.06 - lr: 0.000021 - momentum: 0.000000 2023-10-17 15:25:57,437 epoch 7 - iter 132/447 - loss 0.01246763 - time (sec): 12.88 - samples/sec: 2063.50 - lr: 0.000021 - momentum: 0.000000 2023-10-17 15:26:01,968 epoch 7 - iter 176/447 - loss 0.01393283 - time (sec): 17.42 - samples/sec: 2068.23 - lr: 0.000020 - momentum: 0.000000 2023-10-17 15:26:05,992 epoch 7 - iter 220/447 - loss 0.01344518 - time (sec): 21.44 - samples/sec: 2076.84 - lr: 0.000020 - momentum: 0.000000 2023-10-17 15:26:10,031 epoch 7 - iter 264/447 - loss 0.01257828 - time (sec): 25.48 - samples/sec: 2061.24 - lr: 0.000019 - momentum: 0.000000 2023-10-17 15:26:14,132 epoch 7 - iter 308/447 - loss 0.01318801 - time (sec): 29.58 - samples/sec: 2051.47 - lr: 0.000018 - momentum: 0.000000 2023-10-17 15:26:18,294 epoch 7 - iter 352/447 - loss 0.01344369 - time (sec): 33.74 - samples/sec: 2051.06 - lr: 0.000018 - momentum: 0.000000 2023-10-17 15:26:22,814 epoch 7 - iter 396/447 - loss 0.01372082 - time (sec): 38.26 - samples/sec: 2025.99 - lr: 0.000017 - momentum: 0.000000 2023-10-17 15:26:27,255 epoch 7 - iter 440/447 - loss 0.01396394 - time (sec): 42.70 - samples/sec: 1996.18 - lr: 0.000017 - momentum: 0.000000 2023-10-17 15:26:27,962 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:26:27,963 EPOCH 7 done: loss 0.0139 - lr: 0.000017 2023-10-17 15:26:38,984 DEV : loss 0.22845597565174103 - f1-score (micro avg) 0.8003 2023-10-17 15:26:39,038 saving best model 2023-10-17 15:26:40,462 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:26:44,896 epoch 8 - iter 44/447 - loss 0.00921936 - time (sec): 4.43 - samples/sec: 1841.71 - lr: 0.000016 - momentum: 0.000000 2023-10-17 15:26:49,151 epoch 8 - iter 88/447 - loss 0.00912078 - time (sec): 8.68 - samples/sec: 1880.14 - lr: 0.000016 - momentum: 0.000000 2023-10-17 15:26:53,847 epoch 8 - iter 132/447 - loss 0.01106636 - time (sec): 13.38 - samples/sec: 1809.62 - lr: 0.000015 - momentum: 0.000000 2023-10-17 15:26:58,466 epoch 8 - iter 176/447 - loss 0.01077249 - time (sec): 18.00 - samples/sec: 1830.19 - lr: 0.000015 - momentum: 0.000000 2023-10-17 15:27:02,928 epoch 8 - iter 220/447 - loss 0.00985768 - time (sec): 22.46 - samples/sec: 1859.16 - lr: 0.000014 - momentum: 0.000000 2023-10-17 15:27:07,409 epoch 8 - iter 264/447 - loss 0.00933209 - time (sec): 26.94 - samples/sec: 1856.19 - lr: 0.000013 - momentum: 0.000000 2023-10-17 15:27:11,913 epoch 8 - iter 308/447 - loss 0.00948564 - time (sec): 31.45 - samples/sec: 1848.78 - lr: 0.000013 - momentum: 0.000000 2023-10-17 15:27:16,212 epoch 8 - iter 352/447 - loss 0.00988733 - time (sec): 35.75 - samples/sec: 1856.93 - lr: 0.000012 - momentum: 0.000000 2023-10-17 15:27:20,656 epoch 8 - iter 396/447 - loss 0.00993039 - time (sec): 40.19 - samples/sec: 1886.26 - lr: 0.000012 - momentum: 0.000000 2023-10-17 15:27:25,141 epoch 8 - iter 440/447 - loss 0.00960367 - time (sec): 44.67 - samples/sec: 1907.98 - lr: 0.000011 - momentum: 0.000000 2023-10-17 15:27:25,768 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:27:25,769 EPOCH 8 done: loss 0.0095 - lr: 0.000011 2023-10-17 15:27:37,592 DEV : loss 0.21943919360637665 - f1-score (micro avg) 0.7933 2023-10-17 15:27:37,660 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:27:41,957 epoch 9 - iter 44/447 - loss 0.00566894 - time (sec): 4.30 - samples/sec: 1769.19 - lr: 0.000011 - momentum: 0.000000 2023-10-17 15:27:45,995 epoch 9 - iter 88/447 - loss 0.00637583 - time (sec): 8.33 - samples/sec: 1919.87 - lr: 0.000010 - momentum: 0.000000 2023-10-17 15:27:50,104 epoch 9 - iter 132/447 - loss 0.00607137 - time (sec): 12.44 - samples/sec: 1954.16 - lr: 0.000010 - momentum: 0.000000 2023-10-17 15:27:54,416 epoch 9 - iter 176/447 - loss 0.00515606 - time (sec): 16.75 - samples/sec: 1948.74 - lr: 0.000009 - momentum: 0.000000 2023-10-17 15:28:00,031 epoch 9 - iter 220/447 - loss 0.00413243 - time (sec): 22.37 - samples/sec: 1922.67 - lr: 0.000008 - momentum: 0.000000 2023-10-17 15:28:04,550 epoch 9 - iter 264/447 - loss 0.00424171 - time (sec): 26.89 - samples/sec: 1929.66 - lr: 0.000008 - momentum: 0.000000 2023-10-17 15:28:09,004 epoch 9 - iter 308/447 - loss 0.00528104 - time (sec): 31.34 - samples/sec: 1914.50 - lr: 0.000007 - momentum: 0.000000 2023-10-17 15:28:13,713 epoch 9 - iter 352/447 - loss 0.00636826 - time (sec): 36.05 - samples/sec: 1888.42 - lr: 0.000007 - momentum: 0.000000 2023-10-17 15:28:18,158 epoch 9 - iter 396/447 - loss 0.00660453 - time (sec): 40.50 - samples/sec: 1892.15 - lr: 0.000006 - momentum: 0.000000 2023-10-17 15:28:22,745 epoch 9 - iter 440/447 - loss 0.00609731 - time (sec): 45.08 - samples/sec: 1883.24 - lr: 0.000006 - momentum: 0.000000 2023-10-17 15:28:23,448 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:28:23,449 EPOCH 9 done: loss 0.0060 - lr: 0.000006 2023-10-17 15:28:34,773 DEV : loss 0.24061691761016846 - f1-score (micro avg) 0.7905 2023-10-17 15:28:34,835 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:28:39,324 epoch 10 - iter 44/447 - loss 0.00465839 - time (sec): 4.49 - samples/sec: 1899.47 - lr: 0.000005 - momentum: 0.000000 2023-10-17 15:28:43,753 epoch 10 - iter 88/447 - loss 0.00384135 - time (sec): 8.92 - samples/sec: 1850.06 - lr: 0.000005 - momentum: 0.000000 2023-10-17 15:28:48,498 epoch 10 - iter 132/447 - loss 0.00456888 - time (sec): 13.66 - samples/sec: 1924.22 - lr: 0.000004 - momentum: 0.000000 2023-10-17 15:28:52,819 epoch 10 - iter 176/447 - loss 0.00488622 - time (sec): 17.98 - samples/sec: 1899.89 - lr: 0.000003 - momentum: 0.000000 2023-10-17 15:28:57,213 epoch 10 - iter 220/447 - loss 0.00398089 - time (sec): 22.38 - samples/sec: 1920.45 - lr: 0.000003 - momentum: 0.000000 2023-10-17 15:29:01,484 epoch 10 - iter 264/447 - loss 0.00334650 - time (sec): 26.65 - samples/sec: 1942.12 - lr: 0.000002 - momentum: 0.000000 2023-10-17 15:29:05,562 epoch 10 - iter 308/447 - loss 0.00323001 - time (sec): 30.72 - samples/sec: 1952.19 - lr: 0.000002 - momentum: 0.000000 2023-10-17 15:29:09,820 epoch 10 - iter 352/447 - loss 0.00363184 - time (sec): 34.98 - samples/sec: 1967.59 - lr: 0.000001 - momentum: 0.000000 2023-10-17 15:29:13,771 epoch 10 - iter 396/447 - loss 0.00344856 - time (sec): 38.93 - samples/sec: 1965.60 - lr: 0.000001 - momentum: 0.000000 2023-10-17 15:29:18,176 epoch 10 - iter 440/447 - loss 0.00328569 - time (sec): 43.34 - samples/sec: 1969.55 - lr: 0.000000 - momentum: 0.000000 2023-10-17 15:29:18,816 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:29:18,816 EPOCH 10 done: loss 0.0032 - lr: 0.000000 2023-10-17 15:29:29,893 DEV : loss 0.23245255649089813 - f1-score (micro avg) 0.8025 2023-10-17 15:29:29,948 saving best model 2023-10-17 15:29:32,004 ---------------------------------------------------------------------------------------------------- 2023-10-17 15:29:32,006 Loading model from best epoch ... 2023-10-17 15:29:35,209 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time 2023-10-17 15:29:41,022 Results: - F-score (micro) 0.762 - F-score (macro) 0.6737 - Accuracy 0.6314 By class: precision recall f1-score support loc 0.8550 0.8607 0.8579 596 pers 0.6850 0.7838 0.7311 333 org 0.5431 0.4773 0.5081 132 prod 0.6071 0.5152 0.5574 66 time 0.7143 0.7143 0.7143 49 micro avg 0.7537 0.7704 0.7620 1176 macro avg 0.6809 0.6702 0.6737 1176 weighted avg 0.7521 0.7704 0.7599 1176 2023-10-17 15:29:41,023 ----------------------------------------------------------------------------------------------------