2023-10-17 17:44:48,166 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,168 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 17:44:48,168 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,168 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 17:44:48,168 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,168 Train: 3575 sentences 2023-10-17 17:44:48,168 (train_with_dev=False, train_with_test=False) 2023-10-17 17:44:48,168 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,168 Training Params: 2023-10-17 17:44:48,168 - learning_rate: "5e-05" 2023-10-17 17:44:48,168 - mini_batch_size: "8" 2023-10-17 17:44:48,168 - max_epochs: "10" 2023-10-17 17:44:48,169 - shuffle: "True" 2023-10-17 17:44:48,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,169 Plugins: 2023-10-17 17:44:48,169 - TensorboardLogger 2023-10-17 17:44:48,169 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 17:44:48,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,169 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 17:44:48,169 - metric: "('micro avg', 'f1-score')" 2023-10-17 17:44:48,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,169 Computation: 2023-10-17 17:44:48,169 - compute on device: cuda:0 2023-10-17 17:44:48,169 - embedding storage: none 2023-10-17 17:44:48,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,169 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-17 17:44:48,169 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,170 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:44:48,170 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 17:44:52,654 epoch 1 - iter 44/447 - loss 3.53247519 - time (sec): 4.48 - samples/sec: 1962.45 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:44:57,042 epoch 1 - iter 88/447 - loss 2.31874710 - time (sec): 8.87 - samples/sec: 1971.29 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:45:01,148 epoch 1 - iter 132/447 - loss 1.75427682 - time (sec): 12.98 - samples/sec: 1973.78 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:45:05,253 epoch 1 - iter 176/447 - loss 1.42658690 - time (sec): 17.08 - samples/sec: 1990.33 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:45:09,368 epoch 1 - iter 220/447 - loss 1.21599396 - time (sec): 21.20 - samples/sec: 1982.09 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:45:13,538 epoch 1 - iter 264/447 - loss 1.06151430 - time (sec): 25.37 - samples/sec: 1993.82 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:45:17,496 epoch 1 - iter 308/447 - loss 0.94782877 - time (sec): 29.32 - samples/sec: 2013.04 - lr: 0.000034 - momentum: 0.000000 2023-10-17 17:45:21,524 epoch 1 - iter 352/447 - loss 0.86170498 - time (sec): 33.35 - samples/sec: 2021.61 - lr: 0.000039 - momentum: 0.000000 2023-10-17 17:45:26,668 epoch 1 - iter 396/447 - loss 0.77972033 - time (sec): 38.50 - samples/sec: 2006.47 - lr: 0.000044 - momentum: 0.000000 2023-10-17 17:45:30,614 epoch 1 - iter 440/447 - loss 0.72870630 - time (sec): 42.44 - samples/sec: 2009.37 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:45:31,257 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:45:31,257 EPOCH 1 done: loss 0.7216 - lr: 0.000049 2023-10-17 17:45:37,295 DEV : loss 0.17193150520324707 - f1-score (micro avg) 0.6114 2023-10-17 17:45:37,350 saving best model 2023-10-17 17:45:37,922 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:45:42,340 epoch 2 - iter 44/447 - loss 0.19212755 - time (sec): 4.42 - samples/sec: 1736.07 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:45:46,547 epoch 2 - iter 88/447 - loss 0.18829141 - time (sec): 8.62 - samples/sec: 1909.97 - lr: 0.000049 - momentum: 0.000000 2023-10-17 17:45:50,480 epoch 2 - iter 132/447 - loss 0.17009265 - time (sec): 12.56 - samples/sec: 1969.56 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:45:54,515 epoch 2 - iter 176/447 - loss 0.16569554 - time (sec): 16.59 - samples/sec: 2009.28 - lr: 0.000048 - momentum: 0.000000 2023-10-17 17:45:58,711 epoch 2 - iter 220/447 - loss 0.15747248 - time (sec): 20.79 - samples/sec: 2044.40 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:46:02,697 epoch 2 - iter 264/447 - loss 0.15702120 - time (sec): 24.77 - samples/sec: 2040.25 - lr: 0.000047 - momentum: 0.000000 2023-10-17 17:46:06,765 epoch 2 - iter 308/447 - loss 0.15884489 - time (sec): 28.84 - samples/sec: 2057.88 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:46:10,920 epoch 2 - iter 352/447 - loss 0.15406260 - time (sec): 33.00 - samples/sec: 2059.91 - lr: 0.000046 - momentum: 0.000000 2023-10-17 17:46:15,205 epoch 2 - iter 396/447 - loss 0.14959137 - time (sec): 37.28 - samples/sec: 2071.69 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:46:19,041 epoch 2 - iter 440/447 - loss 0.14633762 - time (sec): 41.12 - samples/sec: 2075.89 - lr: 0.000045 - momentum: 0.000000 2023-10-17 17:46:19,629 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:46:19,629 EPOCH 2 done: loss 0.1456 - lr: 0.000045 2023-10-17 17:46:30,392 DEV : loss 0.14541815221309662 - f1-score (micro avg) 0.6911 2023-10-17 17:46:30,444 saving best model 2023-10-17 17:46:31,832 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:46:35,959 epoch 3 - iter 44/447 - loss 0.09885066 - time (sec): 4.12 - samples/sec: 1899.38 - lr: 0.000044 - momentum: 0.000000 2023-10-17 17:46:39,789 epoch 3 - iter 88/447 - loss 0.08670680 - time (sec): 7.95 - samples/sec: 1930.35 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:46:43,693 epoch 3 - iter 132/447 - loss 0.08996882 - time (sec): 11.86 - samples/sec: 1948.35 - lr: 0.000043 - momentum: 0.000000 2023-10-17 17:46:47,693 epoch 3 - iter 176/447 - loss 0.08967241 - time (sec): 15.86 - samples/sec: 1982.97 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:46:51,668 epoch 3 - iter 220/447 - loss 0.08753443 - time (sec): 19.83 - samples/sec: 2017.86 - lr: 0.000042 - momentum: 0.000000 2023-10-17 17:46:55,783 epoch 3 - iter 264/447 - loss 0.08959986 - time (sec): 23.95 - samples/sec: 2032.83 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:47:00,057 epoch 3 - iter 308/447 - loss 0.08503972 - time (sec): 28.22 - samples/sec: 2050.68 - lr: 0.000041 - momentum: 0.000000 2023-10-17 17:47:04,697 epoch 3 - iter 352/447 - loss 0.08384251 - time (sec): 32.86 - samples/sec: 2062.53 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:47:08,798 epoch 3 - iter 396/447 - loss 0.08475909 - time (sec): 36.96 - samples/sec: 2064.75 - lr: 0.000040 - momentum: 0.000000 2023-10-17 17:47:12,845 epoch 3 - iter 440/447 - loss 0.08292084 - time (sec): 41.01 - samples/sec: 2081.99 - lr: 0.000039 - momentum: 0.000000 2023-10-17 17:47:13,443 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:47:13,444 EPOCH 3 done: loss 0.0828 - lr: 0.000039 2023-10-17 17:47:24,567 DEV : loss 0.18581056594848633 - f1-score (micro avg) 0.734 2023-10-17 17:47:24,619 saving best model 2023-10-17 17:47:25,193 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:47:29,381 epoch 4 - iter 44/447 - loss 0.06148268 - time (sec): 4.19 - samples/sec: 2073.49 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:47:33,657 epoch 4 - iter 88/447 - loss 0.05203947 - time (sec): 8.46 - samples/sec: 2178.64 - lr: 0.000038 - momentum: 0.000000 2023-10-17 17:47:37,580 epoch 4 - iter 132/447 - loss 0.05294970 - time (sec): 12.38 - samples/sec: 2117.16 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:47:41,665 epoch 4 - iter 176/447 - loss 0.05512343 - time (sec): 16.47 - samples/sec: 2105.44 - lr: 0.000037 - momentum: 0.000000 2023-10-17 17:47:45,882 epoch 4 - iter 220/447 - loss 0.05440061 - time (sec): 20.69 - samples/sec: 2074.33 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:47:49,882 epoch 4 - iter 264/447 - loss 0.05339531 - time (sec): 24.69 - samples/sec: 2058.85 - lr: 0.000036 - momentum: 0.000000 2023-10-17 17:47:54,034 epoch 4 - iter 308/447 - loss 0.05563142 - time (sec): 28.84 - samples/sec: 2085.27 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:47:58,609 epoch 4 - iter 352/447 - loss 0.05395382 - time (sec): 33.41 - samples/sec: 2068.53 - lr: 0.000035 - momentum: 0.000000 2023-10-17 17:48:03,017 epoch 4 - iter 396/447 - loss 0.05405361 - time (sec): 37.82 - samples/sec: 2040.32 - lr: 0.000034 - momentum: 0.000000 2023-10-17 17:48:07,090 epoch 4 - iter 440/447 - loss 0.05319170 - time (sec): 41.89 - samples/sec: 2035.85 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:48:07,746 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:48:07,747 EPOCH 4 done: loss 0.0530 - lr: 0.000033 2023-10-17 17:48:19,334 DEV : loss 0.16320064663887024 - f1-score (micro avg) 0.7421 2023-10-17 17:48:19,391 saving best model 2023-10-17 17:48:20,773 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:48:24,936 epoch 5 - iter 44/447 - loss 0.03339435 - time (sec): 4.16 - samples/sec: 2013.95 - lr: 0.000033 - momentum: 0.000000 2023-10-17 17:48:28,768 epoch 5 - iter 88/447 - loss 0.03083486 - time (sec): 7.99 - samples/sec: 2075.68 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:48:32,818 epoch 5 - iter 132/447 - loss 0.02828933 - time (sec): 12.04 - samples/sec: 2079.53 - lr: 0.000032 - momentum: 0.000000 2023-10-17 17:48:37,063 epoch 5 - iter 176/447 - loss 0.03313995 - time (sec): 16.29 - samples/sec: 2083.18 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:48:40,905 epoch 5 - iter 220/447 - loss 0.03539016 - time (sec): 20.13 - samples/sec: 2106.25 - lr: 0.000031 - momentum: 0.000000 2023-10-17 17:48:45,061 epoch 5 - iter 264/447 - loss 0.03731012 - time (sec): 24.28 - samples/sec: 2098.95 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:48:49,291 epoch 5 - iter 308/447 - loss 0.03763343 - time (sec): 28.51 - samples/sec: 2108.65 - lr: 0.000030 - momentum: 0.000000 2023-10-17 17:48:53,141 epoch 5 - iter 352/447 - loss 0.03771950 - time (sec): 32.36 - samples/sec: 2119.26 - lr: 0.000029 - momentum: 0.000000 2023-10-17 17:48:57,037 epoch 5 - iter 396/447 - loss 0.03610494 - time (sec): 36.26 - samples/sec: 2110.09 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:49:00,960 epoch 5 - iter 440/447 - loss 0.03458475 - time (sec): 40.18 - samples/sec: 2111.19 - lr: 0.000028 - momentum: 0.000000 2023-10-17 17:49:01,787 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:49:01,787 EPOCH 5 done: loss 0.0343 - lr: 0.000028 2023-10-17 17:49:12,745 DEV : loss 0.2096388190984726 - f1-score (micro avg) 0.7754 2023-10-17 17:49:12,801 saving best model 2023-10-17 17:49:13,365 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:49:17,391 epoch 6 - iter 44/447 - loss 0.02071263 - time (sec): 4.02 - samples/sec: 2067.62 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:49:21,287 epoch 6 - iter 88/447 - loss 0.02045657 - time (sec): 7.92 - samples/sec: 2084.19 - lr: 0.000027 - momentum: 0.000000 2023-10-17 17:49:25,310 epoch 6 - iter 132/447 - loss 0.02395735 - time (sec): 11.94 - samples/sec: 2103.18 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:49:29,245 epoch 6 - iter 176/447 - loss 0.02314660 - time (sec): 15.88 - samples/sec: 2120.89 - lr: 0.000026 - momentum: 0.000000 2023-10-17 17:49:33,267 epoch 6 - iter 220/447 - loss 0.02399633 - time (sec): 19.90 - samples/sec: 2074.51 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:49:37,652 epoch 6 - iter 264/447 - loss 0.02289993 - time (sec): 24.28 - samples/sec: 2079.34 - lr: 0.000025 - momentum: 0.000000 2023-10-17 17:49:41,757 epoch 6 - iter 308/447 - loss 0.02175241 - time (sec): 28.39 - samples/sec: 2078.16 - lr: 0.000024 - momentum: 0.000000 2023-10-17 17:49:46,034 epoch 6 - iter 352/447 - loss 0.02292294 - time (sec): 32.67 - samples/sec: 2060.30 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:49:50,018 epoch 6 - iter 396/447 - loss 0.02332494 - time (sec): 36.65 - samples/sec: 2058.40 - lr: 0.000023 - momentum: 0.000000 2023-10-17 17:49:54,610 epoch 6 - iter 440/447 - loss 0.02230257 - time (sec): 41.24 - samples/sec: 2069.91 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:49:55,243 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:49:55,243 EPOCH 6 done: loss 0.0220 - lr: 0.000022 2023-10-17 17:50:06,845 DEV : loss 0.21218937635421753 - f1-score (micro avg) 0.7601 2023-10-17 17:50:06,908 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:50:11,253 epoch 7 - iter 44/447 - loss 0.01285933 - time (sec): 4.34 - samples/sec: 2001.74 - lr: 0.000022 - momentum: 0.000000 2023-10-17 17:50:15,325 epoch 7 - iter 88/447 - loss 0.01388987 - time (sec): 8.42 - samples/sec: 1998.53 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:50:19,308 epoch 7 - iter 132/447 - loss 0.01336076 - time (sec): 12.40 - samples/sec: 2011.61 - lr: 0.000021 - momentum: 0.000000 2023-10-17 17:50:23,382 epoch 7 - iter 176/447 - loss 0.01261394 - time (sec): 16.47 - samples/sec: 2054.87 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:50:27,928 epoch 7 - iter 220/447 - loss 0.01097990 - time (sec): 21.02 - samples/sec: 2053.75 - lr: 0.000020 - momentum: 0.000000 2023-10-17 17:50:32,045 epoch 7 - iter 264/447 - loss 0.01111927 - time (sec): 25.14 - samples/sec: 2023.76 - lr: 0.000019 - momentum: 0.000000 2023-10-17 17:50:36,497 epoch 7 - iter 308/447 - loss 0.01188959 - time (sec): 29.59 - samples/sec: 2017.85 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:50:40,689 epoch 7 - iter 352/447 - loss 0.01124010 - time (sec): 33.78 - samples/sec: 2016.53 - lr: 0.000018 - momentum: 0.000000 2023-10-17 17:50:44,831 epoch 7 - iter 396/447 - loss 0.01118474 - time (sec): 37.92 - samples/sec: 2034.64 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:50:48,860 epoch 7 - iter 440/447 - loss 0.01185488 - time (sec): 41.95 - samples/sec: 2029.22 - lr: 0.000017 - momentum: 0.000000 2023-10-17 17:50:49,541 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:50:49,541 EPOCH 7 done: loss 0.0124 - lr: 0.000017 2023-10-17 17:51:00,437 DEV : loss 0.24467261135578156 - f1-score (micro avg) 0.7769 2023-10-17 17:51:00,497 saving best model 2023-10-17 17:51:01,918 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:05,955 epoch 8 - iter 44/447 - loss 0.00687414 - time (sec): 4.03 - samples/sec: 1946.11 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:51:10,038 epoch 8 - iter 88/447 - loss 0.00560644 - time (sec): 8.12 - samples/sec: 1995.96 - lr: 0.000016 - momentum: 0.000000 2023-10-17 17:51:14,085 epoch 8 - iter 132/447 - loss 0.00512284 - time (sec): 12.16 - samples/sec: 2000.44 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:51:18,460 epoch 8 - iter 176/447 - loss 0.00669502 - time (sec): 16.54 - samples/sec: 1975.13 - lr: 0.000015 - momentum: 0.000000 2023-10-17 17:51:23,370 epoch 8 - iter 220/447 - loss 0.00700551 - time (sec): 21.45 - samples/sec: 1936.87 - lr: 0.000014 - momentum: 0.000000 2023-10-17 17:51:27,445 epoch 8 - iter 264/447 - loss 0.00799623 - time (sec): 25.52 - samples/sec: 1967.09 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:51:31,651 epoch 8 - iter 308/447 - loss 0.00762820 - time (sec): 29.73 - samples/sec: 1973.87 - lr: 0.000013 - momentum: 0.000000 2023-10-17 17:51:35,768 epoch 8 - iter 352/447 - loss 0.00779306 - time (sec): 33.85 - samples/sec: 1982.90 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:51:39,774 epoch 8 - iter 396/447 - loss 0.00777938 - time (sec): 37.85 - samples/sec: 1994.88 - lr: 0.000012 - momentum: 0.000000 2023-10-17 17:51:44,165 epoch 8 - iter 440/447 - loss 0.00736500 - time (sec): 42.24 - samples/sec: 2019.04 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:51:44,797 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:51:44,798 EPOCH 8 done: loss 0.0073 - lr: 0.000011 2023-10-17 17:51:55,888 DEV : loss 0.24660176038742065 - f1-score (micro avg) 0.7942 2023-10-17 17:51:55,947 saving best model 2023-10-17 17:51:57,324 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:01,426 epoch 9 - iter 44/447 - loss 0.00110632 - time (sec): 4.10 - samples/sec: 2054.78 - lr: 0.000011 - momentum: 0.000000 2023-10-17 17:52:05,847 epoch 9 - iter 88/447 - loss 0.00403816 - time (sec): 8.52 - samples/sec: 2019.00 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:52:10,085 epoch 9 - iter 132/447 - loss 0.00297756 - time (sec): 12.76 - samples/sec: 2008.52 - lr: 0.000010 - momentum: 0.000000 2023-10-17 17:52:14,224 epoch 9 - iter 176/447 - loss 0.00426497 - time (sec): 16.90 - samples/sec: 1986.65 - lr: 0.000009 - momentum: 0.000000 2023-10-17 17:52:18,201 epoch 9 - iter 220/447 - loss 0.00546162 - time (sec): 20.87 - samples/sec: 2011.65 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:52:22,301 epoch 9 - iter 264/447 - loss 0.00547408 - time (sec): 24.97 - samples/sec: 2013.82 - lr: 0.000008 - momentum: 0.000000 2023-10-17 17:52:26,521 epoch 9 - iter 308/447 - loss 0.00608106 - time (sec): 29.19 - samples/sec: 2030.28 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:52:30,568 epoch 9 - iter 352/447 - loss 0.00557877 - time (sec): 33.24 - samples/sec: 2013.26 - lr: 0.000007 - momentum: 0.000000 2023-10-17 17:52:35,013 epoch 9 - iter 396/447 - loss 0.00549500 - time (sec): 37.68 - samples/sec: 2008.03 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:52:39,171 epoch 9 - iter 440/447 - loss 0.00576947 - time (sec): 41.84 - samples/sec: 2020.27 - lr: 0.000006 - momentum: 0.000000 2023-10-17 17:52:40,081 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:40,081 EPOCH 9 done: loss 0.0058 - lr: 0.000006 2023-10-17 17:52:51,569 DEV : loss 0.25680792331695557 - f1-score (micro avg) 0.7843 2023-10-17 17:52:51,627 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:52:55,624 epoch 10 - iter 44/447 - loss 0.00263929 - time (sec): 3.99 - samples/sec: 2143.95 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:52:59,919 epoch 10 - iter 88/447 - loss 0.00194551 - time (sec): 8.29 - samples/sec: 2079.76 - lr: 0.000005 - momentum: 0.000000 2023-10-17 17:53:04,432 epoch 10 - iter 132/447 - loss 0.00150227 - time (sec): 12.80 - samples/sec: 2103.00 - lr: 0.000004 - momentum: 0.000000 2023-10-17 17:53:08,350 epoch 10 - iter 176/447 - loss 0.00167795 - time (sec): 16.72 - samples/sec: 2102.13 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:53:12,303 epoch 10 - iter 220/447 - loss 0.00167062 - time (sec): 20.67 - samples/sec: 2102.03 - lr: 0.000003 - momentum: 0.000000 2023-10-17 17:53:16,389 epoch 10 - iter 264/447 - loss 0.00153587 - time (sec): 24.76 - samples/sec: 2086.20 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:53:20,663 epoch 10 - iter 308/447 - loss 0.00191345 - time (sec): 29.03 - samples/sec: 2079.68 - lr: 0.000002 - momentum: 0.000000 2023-10-17 17:53:24,664 epoch 10 - iter 352/447 - loss 0.00211922 - time (sec): 33.04 - samples/sec: 2074.21 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:53:28,695 epoch 10 - iter 396/447 - loss 0.00212426 - time (sec): 37.07 - samples/sec: 2075.22 - lr: 0.000001 - momentum: 0.000000 2023-10-17 17:53:33,014 epoch 10 - iter 440/447 - loss 0.00225616 - time (sec): 41.39 - samples/sec: 2062.25 - lr: 0.000000 - momentum: 0.000000 2023-10-17 17:53:33,689 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:33,690 EPOCH 10 done: loss 0.0025 - lr: 0.000000 2023-10-17 17:53:45,285 DEV : loss 0.264967143535614 - f1-score (micro avg) 0.7935 2023-10-17 17:53:45,874 ---------------------------------------------------------------------------------------------------- 2023-10-17 17:53:45,876 Loading model from best epoch ... 2023-10-17 17:53:48,322 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 17:53:54,591 Results: - F-score (micro) 0.7531 - F-score (macro) 0.6677 - Accuracy 0.6203 By class: precision recall f1-score support loc 0.8596 0.8523 0.8559 596 pers 0.6992 0.7538 0.7254 333 org 0.4615 0.5455 0.5000 132 prod 0.5806 0.5455 0.5625 66 time 0.7174 0.6735 0.6947 49 micro avg 0.7414 0.7653 0.7531 1176 macro avg 0.6637 0.6741 0.6677 1176 weighted avg 0.7479 0.7653 0.7558 1176 2023-10-17 17:53:54,591 ----------------------------------------------------------------------------------------------------