2023-10-17 10:25:39,666 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,667 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=13, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-17 10:25:39,668 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,668 MultiCorpus: 6183 train + 680 dev + 2113 test sentences - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator 2023-10-17 10:25:39,668 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,668 Train: 6183 sentences 2023-10-17 10:25:39,668 (train_with_dev=False, train_with_test=False) 2023-10-17 10:25:39,668 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,668 Training Params: 2023-10-17 10:25:39,668 - learning_rate: "5e-05" 2023-10-17 10:25:39,668 - mini_batch_size: "4" 2023-10-17 10:25:39,668 - max_epochs: "10" 2023-10-17 10:25:39,668 - shuffle: "True" 2023-10-17 10:25:39,668 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,668 Plugins: 2023-10-17 10:25:39,669 - TensorboardLogger 2023-10-17 10:25:39,669 - LinearScheduler | warmup_fraction: '0.1' 2023-10-17 10:25:39,669 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,669 Final evaluation on model from best epoch (best-model.pt) 2023-10-17 10:25:39,669 - metric: "('micro avg', 'f1-score')" 2023-10-17 10:25:39,669 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,669 Computation: 2023-10-17 10:25:39,669 - compute on device: cuda:0 2023-10-17 10:25:39,669 - embedding storage: none 2023-10-17 10:25:39,669 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,669 Model training base path: "hmbench-topres19th/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" 2023-10-17 10:25:39,669 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,669 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:25:39,669 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-17 10:25:51,632 epoch 1 - iter 154/1546 - loss 2.02180981 - time (sec): 11.96 - samples/sec: 944.73 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:26:04,276 epoch 1 - iter 308/1546 - loss 1.05133169 - time (sec): 24.60 - samples/sec: 1008.11 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:26:16,281 epoch 1 - iter 462/1546 - loss 0.75054260 - time (sec): 36.61 - samples/sec: 1031.68 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:26:28,650 epoch 1 - iter 616/1546 - loss 0.59271900 - time (sec): 48.98 - samples/sec: 1032.05 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:26:41,225 epoch 1 - iter 770/1546 - loss 0.49705880 - time (sec): 61.55 - samples/sec: 1028.74 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:26:53,393 epoch 1 - iter 924/1546 - loss 0.43170337 - time (sec): 73.72 - samples/sec: 1033.06 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:27:05,348 epoch 1 - iter 1078/1546 - loss 0.39066886 - time (sec): 85.68 - samples/sec: 1021.48 - lr: 0.000035 - momentum: 0.000000 2023-10-17 10:27:17,415 epoch 1 - iter 1232/1546 - loss 0.35716844 - time (sec): 97.74 - samples/sec: 1020.75 - lr: 0.000040 - momentum: 0.000000 2023-10-17 10:27:29,146 epoch 1 - iter 1386/1546 - loss 0.33123533 - time (sec): 109.47 - samples/sec: 1026.36 - lr: 0.000045 - momentum: 0.000000 2023-10-17 10:27:40,598 epoch 1 - iter 1540/1546 - loss 0.31206315 - time (sec): 120.93 - samples/sec: 1024.74 - lr: 0.000050 - momentum: 0.000000 2023-10-17 10:27:41,031 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:27:41,031 EPOCH 1 done: loss 0.3115 - lr: 0.000050 2023-10-17 10:27:43,666 DEV : loss 0.07279833406209946 - f1-score (micro avg) 0.7049 2023-10-17 10:27:43,693 saving best model 2023-10-17 10:27:44,227 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:27:55,853 epoch 2 - iter 154/1546 - loss 0.17648886 - time (sec): 11.62 - samples/sec: 1047.19 - lr: 0.000049 - momentum: 0.000000 2023-10-17 10:28:07,775 epoch 2 - iter 308/1546 - loss 0.15188272 - time (sec): 23.55 - samples/sec: 1070.06 - lr: 0.000049 - momentum: 0.000000 2023-10-17 10:28:19,828 epoch 2 - iter 462/1546 - loss 0.13981404 - time (sec): 35.60 - samples/sec: 1037.47 - lr: 0.000048 - momentum: 0.000000 2023-10-17 10:28:32,332 epoch 2 - iter 616/1546 - loss 0.12814078 - time (sec): 48.10 - samples/sec: 1024.94 - lr: 0.000048 - momentum: 0.000000 2023-10-17 10:28:44,172 epoch 2 - iter 770/1546 - loss 0.12573561 - time (sec): 59.94 - samples/sec: 1022.59 - lr: 0.000047 - momentum: 0.000000 2023-10-17 10:28:56,254 epoch 2 - iter 924/1546 - loss 0.12073221 - time (sec): 72.03 - samples/sec: 1017.97 - lr: 0.000047 - momentum: 0.000000 2023-10-17 10:29:09,100 epoch 2 - iter 1078/1546 - loss 0.11547940 - time (sec): 84.87 - samples/sec: 1013.64 - lr: 0.000046 - momentum: 0.000000 2023-10-17 10:29:20,955 epoch 2 - iter 1232/1546 - loss 0.11335352 - time (sec): 96.73 - samples/sec: 1017.70 - lr: 0.000046 - momentum: 0.000000 2023-10-17 10:29:32,654 epoch 2 - iter 1386/1546 - loss 0.11157211 - time (sec): 108.42 - samples/sec: 1024.63 - lr: 0.000045 - momentum: 0.000000 2023-10-17 10:29:44,656 epoch 2 - iter 1540/1546 - loss 0.10827885 - time (sec): 120.43 - samples/sec: 1029.36 - lr: 0.000044 - momentum: 0.000000 2023-10-17 10:29:45,108 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:29:45,108 EPOCH 2 done: loss 0.1081 - lr: 0.000044 2023-10-17 10:29:48,007 DEV : loss 0.05769108608365059 - f1-score (micro avg) 0.7859 2023-10-17 10:29:48,040 saving best model 2023-10-17 10:29:49,482 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:30:01,407 epoch 3 - iter 154/1546 - loss 0.09035284 - time (sec): 11.92 - samples/sec: 985.24 - lr: 0.000044 - momentum: 0.000000 2023-10-17 10:30:12,820 epoch 3 - iter 308/1546 - loss 0.07445859 - time (sec): 23.33 - samples/sec: 1097.98 - lr: 0.000043 - momentum: 0.000000 2023-10-17 10:30:24,703 epoch 3 - iter 462/1546 - loss 0.07415434 - time (sec): 35.22 - samples/sec: 1100.85 - lr: 0.000043 - momentum: 0.000000 2023-10-17 10:30:37,609 epoch 3 - iter 616/1546 - loss 0.07540870 - time (sec): 48.12 - samples/sec: 1045.62 - lr: 0.000042 - momentum: 0.000000 2023-10-17 10:30:50,460 epoch 3 - iter 770/1546 - loss 0.07301929 - time (sec): 60.97 - samples/sec: 1021.49 - lr: 0.000042 - momentum: 0.000000 2023-10-17 10:31:04,196 epoch 3 - iter 924/1546 - loss 0.07303987 - time (sec): 74.71 - samples/sec: 1004.25 - lr: 0.000041 - momentum: 0.000000 2023-10-17 10:31:15,649 epoch 3 - iter 1078/1546 - loss 0.07020216 - time (sec): 86.16 - samples/sec: 1010.69 - lr: 0.000041 - momentum: 0.000000 2023-10-17 10:31:27,261 epoch 3 - iter 1232/1546 - loss 0.07010983 - time (sec): 97.78 - samples/sec: 1016.90 - lr: 0.000040 - momentum: 0.000000 2023-10-17 10:31:39,005 epoch 3 - iter 1386/1546 - loss 0.06794363 - time (sec): 109.52 - samples/sec: 1025.10 - lr: 0.000039 - momentum: 0.000000 2023-10-17 10:31:50,746 epoch 3 - iter 1540/1546 - loss 0.06707353 - time (sec): 121.26 - samples/sec: 1021.84 - lr: 0.000039 - momentum: 0.000000 2023-10-17 10:31:51,242 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:31:51,242 EPOCH 3 done: loss 0.0670 - lr: 0.000039 2023-10-17 10:31:54,247 DEV : loss 0.07943776994943619 - f1-score (micro avg) 0.8114 2023-10-17 10:31:54,285 saving best model 2023-10-17 10:31:55,701 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:32:07,901 epoch 4 - iter 154/1546 - loss 0.04828653 - time (sec): 12.20 - samples/sec: 1063.56 - lr: 0.000038 - momentum: 0.000000 2023-10-17 10:32:20,064 epoch 4 - iter 308/1546 - loss 0.05173450 - time (sec): 24.36 - samples/sec: 1039.44 - lr: 0.000038 - momentum: 0.000000 2023-10-17 10:32:32,324 epoch 4 - iter 462/1546 - loss 0.04954644 - time (sec): 36.62 - samples/sec: 1016.86 - lr: 0.000037 - momentum: 0.000000 2023-10-17 10:32:44,801 epoch 4 - iter 616/1546 - loss 0.05004385 - time (sec): 49.10 - samples/sec: 1003.51 - lr: 0.000037 - momentum: 0.000000 2023-10-17 10:32:56,865 epoch 4 - iter 770/1546 - loss 0.04750404 - time (sec): 61.16 - samples/sec: 1016.02 - lr: 0.000036 - momentum: 0.000000 2023-10-17 10:33:09,083 epoch 4 - iter 924/1546 - loss 0.04870217 - time (sec): 73.38 - samples/sec: 1014.04 - lr: 0.000036 - momentum: 0.000000 2023-10-17 10:33:20,791 epoch 4 - iter 1078/1546 - loss 0.04965165 - time (sec): 85.09 - samples/sec: 1018.08 - lr: 0.000035 - momentum: 0.000000 2023-10-17 10:33:32,692 epoch 4 - iter 1232/1546 - loss 0.04736677 - time (sec): 96.99 - samples/sec: 1026.67 - lr: 0.000034 - momentum: 0.000000 2023-10-17 10:33:44,844 epoch 4 - iter 1386/1546 - loss 0.04811731 - time (sec): 109.14 - samples/sec: 1026.04 - lr: 0.000034 - momentum: 0.000000 2023-10-17 10:33:57,129 epoch 4 - iter 1540/1546 - loss 0.04803105 - time (sec): 121.42 - samples/sec: 1019.68 - lr: 0.000033 - momentum: 0.000000 2023-10-17 10:33:57,607 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:33:57,608 EPOCH 4 done: loss 0.0481 - lr: 0.000033 2023-10-17 10:34:00,432 DEV : loss 0.0833667516708374 - f1-score (micro avg) 0.7711 2023-10-17 10:34:00,460 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:34:12,396 epoch 5 - iter 154/1546 - loss 0.02385740 - time (sec): 11.93 - samples/sec: 1024.45 - lr: 0.000033 - momentum: 0.000000 2023-10-17 10:34:24,347 epoch 5 - iter 308/1546 - loss 0.02748508 - time (sec): 23.89 - samples/sec: 1001.54 - lr: 0.000032 - momentum: 0.000000 2023-10-17 10:34:36,363 epoch 5 - iter 462/1546 - loss 0.02582250 - time (sec): 35.90 - samples/sec: 995.55 - lr: 0.000032 - momentum: 0.000000 2023-10-17 10:34:48,343 epoch 5 - iter 616/1546 - loss 0.02616104 - time (sec): 47.88 - samples/sec: 1005.06 - lr: 0.000031 - momentum: 0.000000 2023-10-17 10:35:00,744 epoch 5 - iter 770/1546 - loss 0.03219186 - time (sec): 60.28 - samples/sec: 1003.30 - lr: 0.000031 - momentum: 0.000000 2023-10-17 10:35:12,809 epoch 5 - iter 924/1546 - loss 0.03235715 - time (sec): 72.35 - samples/sec: 1007.34 - lr: 0.000030 - momentum: 0.000000 2023-10-17 10:35:24,651 epoch 5 - iter 1078/1546 - loss 0.03225049 - time (sec): 84.19 - samples/sec: 1029.36 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:35:36,841 epoch 5 - iter 1232/1546 - loss 0.03312944 - time (sec): 96.38 - samples/sec: 1028.66 - lr: 0.000029 - momentum: 0.000000 2023-10-17 10:35:49,293 epoch 5 - iter 1386/1546 - loss 0.03394222 - time (sec): 108.83 - samples/sec: 1020.22 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:36:01,342 epoch 5 - iter 1540/1546 - loss 0.03495607 - time (sec): 120.88 - samples/sec: 1024.69 - lr: 0.000028 - momentum: 0.000000 2023-10-17 10:36:01,814 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:36:01,814 EPOCH 5 done: loss 0.0350 - lr: 0.000028 2023-10-17 10:36:05,180 DEV : loss 0.110050730407238 - f1-score (micro avg) 0.7099 2023-10-17 10:36:05,213 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:36:17,215 epoch 6 - iter 154/1546 - loss 0.03050029 - time (sec): 12.00 - samples/sec: 1034.82 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:36:29,436 epoch 6 - iter 308/1546 - loss 0.02599671 - time (sec): 24.22 - samples/sec: 1030.57 - lr: 0.000027 - momentum: 0.000000 2023-10-17 10:36:41,414 epoch 6 - iter 462/1546 - loss 0.02421473 - time (sec): 36.20 - samples/sec: 1038.52 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:36:53,413 epoch 6 - iter 616/1546 - loss 0.02336062 - time (sec): 48.20 - samples/sec: 1040.54 - lr: 0.000026 - momentum: 0.000000 2023-10-17 10:37:05,424 epoch 6 - iter 770/1546 - loss 0.02547084 - time (sec): 60.21 - samples/sec: 1032.66 - lr: 0.000025 - momentum: 0.000000 2023-10-17 10:37:17,945 epoch 6 - iter 924/1546 - loss 0.02397867 - time (sec): 72.73 - samples/sec: 1024.75 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:37:29,949 epoch 6 - iter 1078/1546 - loss 0.02277072 - time (sec): 84.73 - samples/sec: 1036.78 - lr: 0.000024 - momentum: 0.000000 2023-10-17 10:37:41,864 epoch 6 - iter 1232/1546 - loss 0.02426498 - time (sec): 96.65 - samples/sec: 1029.50 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:37:53,712 epoch 6 - iter 1386/1546 - loss 0.02385236 - time (sec): 108.50 - samples/sec: 1028.24 - lr: 0.000023 - momentum: 0.000000 2023-10-17 10:38:05,568 epoch 6 - iter 1540/1546 - loss 0.02402382 - time (sec): 120.35 - samples/sec: 1028.83 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:38:06,019 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:38:06,019 EPOCH 6 done: loss 0.0241 - lr: 0.000022 2023-10-17 10:38:08,835 DEV : loss 0.09071236848831177 - f1-score (micro avg) 0.7718 2023-10-17 10:38:08,863 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:38:20,993 epoch 7 - iter 154/1546 - loss 0.01858194 - time (sec): 12.13 - samples/sec: 1035.21 - lr: 0.000022 - momentum: 0.000000 2023-10-17 10:38:33,142 epoch 7 - iter 308/1546 - loss 0.02029265 - time (sec): 24.28 - samples/sec: 1076.84 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:38:44,918 epoch 7 - iter 462/1546 - loss 0.01874414 - time (sec): 36.05 - samples/sec: 1064.32 - lr: 0.000021 - momentum: 0.000000 2023-10-17 10:38:56,851 epoch 7 - iter 616/1546 - loss 0.02012904 - time (sec): 47.99 - samples/sec: 1052.19 - lr: 0.000020 - momentum: 0.000000 2023-10-17 10:39:08,577 epoch 7 - iter 770/1546 - loss 0.02056826 - time (sec): 59.71 - samples/sec: 1049.28 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:39:20,396 epoch 7 - iter 924/1546 - loss 0.01990787 - time (sec): 71.53 - samples/sec: 1037.05 - lr: 0.000019 - momentum: 0.000000 2023-10-17 10:39:32,595 epoch 7 - iter 1078/1546 - loss 0.02052998 - time (sec): 83.73 - samples/sec: 1028.28 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:39:44,797 epoch 7 - iter 1232/1546 - loss 0.01888219 - time (sec): 95.93 - samples/sec: 1030.99 - lr: 0.000018 - momentum: 0.000000 2023-10-17 10:39:56,820 epoch 7 - iter 1386/1546 - loss 0.01791790 - time (sec): 107.95 - samples/sec: 1035.40 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:40:09,502 epoch 7 - iter 1540/1546 - loss 0.01840040 - time (sec): 120.64 - samples/sec: 1027.33 - lr: 0.000017 - momentum: 0.000000 2023-10-17 10:40:10,068 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:40:10,068 EPOCH 7 done: loss 0.0185 - lr: 0.000017 2023-10-17 10:40:13,083 DEV : loss 0.12031986564397812 - f1-score (micro avg) 0.7705 2023-10-17 10:40:13,114 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:40:25,169 epoch 8 - iter 154/1546 - loss 0.01247555 - time (sec): 12.05 - samples/sec: 1025.95 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:40:37,477 epoch 8 - iter 308/1546 - loss 0.00887144 - time (sec): 24.36 - samples/sec: 1038.46 - lr: 0.000016 - momentum: 0.000000 2023-10-17 10:40:49,680 epoch 8 - iter 462/1546 - loss 0.00915473 - time (sec): 36.56 - samples/sec: 1015.25 - lr: 0.000015 - momentum: 0.000000 2023-10-17 10:41:02,185 epoch 8 - iter 616/1546 - loss 0.01189933 - time (sec): 49.07 - samples/sec: 1008.89 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:41:14,290 epoch 8 - iter 770/1546 - loss 0.01107024 - time (sec): 61.17 - samples/sec: 1018.87 - lr: 0.000014 - momentum: 0.000000 2023-10-17 10:41:26,129 epoch 8 - iter 924/1546 - loss 0.01086037 - time (sec): 73.01 - samples/sec: 1027.72 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:41:38,145 epoch 8 - iter 1078/1546 - loss 0.01157159 - time (sec): 85.03 - samples/sec: 1024.92 - lr: 0.000013 - momentum: 0.000000 2023-10-17 10:41:49,914 epoch 8 - iter 1232/1546 - loss 0.01193759 - time (sec): 96.80 - samples/sec: 1024.57 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:42:02,221 epoch 8 - iter 1386/1546 - loss 0.01219084 - time (sec): 109.10 - samples/sec: 1023.58 - lr: 0.000012 - momentum: 0.000000 2023-10-17 10:42:13,995 epoch 8 - iter 1540/1546 - loss 0.01168510 - time (sec): 120.88 - samples/sec: 1023.56 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:42:14,461 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:42:14,461 EPOCH 8 done: loss 0.0117 - lr: 0.000011 2023-10-17 10:42:17,363 DEV : loss 0.11697618663311005 - f1-score (micro avg) 0.8008 2023-10-17 10:42:17,397 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:42:29,121 epoch 9 - iter 154/1546 - loss 0.01140863 - time (sec): 11.72 - samples/sec: 1045.07 - lr: 0.000011 - momentum: 0.000000 2023-10-17 10:42:40,816 epoch 9 - iter 308/1546 - loss 0.01020266 - time (sec): 23.42 - samples/sec: 1032.47 - lr: 0.000010 - momentum: 0.000000 2023-10-17 10:42:52,458 epoch 9 - iter 462/1546 - loss 0.00903518 - time (sec): 35.06 - samples/sec: 1077.02 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:43:04,002 epoch 9 - iter 616/1546 - loss 0.00887521 - time (sec): 46.60 - samples/sec: 1062.22 - lr: 0.000009 - momentum: 0.000000 2023-10-17 10:43:15,609 epoch 9 - iter 770/1546 - loss 0.00783009 - time (sec): 58.21 - samples/sec: 1056.47 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:43:28,043 epoch 9 - iter 924/1546 - loss 0.00793805 - time (sec): 70.64 - samples/sec: 1039.01 - lr: 0.000008 - momentum: 0.000000 2023-10-17 10:43:39,954 epoch 9 - iter 1078/1546 - loss 0.00743572 - time (sec): 82.55 - samples/sec: 1035.87 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:43:51,915 epoch 9 - iter 1232/1546 - loss 0.00757961 - time (sec): 94.52 - samples/sec: 1050.24 - lr: 0.000007 - momentum: 0.000000 2023-10-17 10:44:04,164 epoch 9 - iter 1386/1546 - loss 0.00743361 - time (sec): 106.76 - samples/sec: 1040.78 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:44:16,128 epoch 9 - iter 1540/1546 - loss 0.00756154 - time (sec): 118.73 - samples/sec: 1044.29 - lr: 0.000006 - momentum: 0.000000 2023-10-17 10:44:16,573 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:44:16,574 EPOCH 9 done: loss 0.0076 - lr: 0.000006 2023-10-17 10:44:19,531 DEV : loss 0.12403418123722076 - f1-score (micro avg) 0.7884 2023-10-17 10:44:19,562 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:44:31,581 epoch 10 - iter 154/1546 - loss 0.00254844 - time (sec): 12.02 - samples/sec: 1087.04 - lr: 0.000005 - momentum: 0.000000 2023-10-17 10:44:43,680 epoch 10 - iter 308/1546 - loss 0.00244110 - time (sec): 24.12 - samples/sec: 1018.42 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:44:55,700 epoch 10 - iter 462/1546 - loss 0.00305097 - time (sec): 36.14 - samples/sec: 1005.43 - lr: 0.000004 - momentum: 0.000000 2023-10-17 10:45:07,998 epoch 10 - iter 616/1546 - loss 0.00292169 - time (sec): 48.43 - samples/sec: 1012.33 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:45:20,453 epoch 10 - iter 770/1546 - loss 0.00318972 - time (sec): 60.89 - samples/sec: 1004.67 - lr: 0.000003 - momentum: 0.000000 2023-10-17 10:45:32,649 epoch 10 - iter 924/1546 - loss 0.00372386 - time (sec): 73.08 - samples/sec: 1001.91 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:45:44,939 epoch 10 - iter 1078/1546 - loss 0.00392698 - time (sec): 85.37 - samples/sec: 1008.88 - lr: 0.000002 - momentum: 0.000000 2023-10-17 10:45:57,060 epoch 10 - iter 1232/1546 - loss 0.00386062 - time (sec): 97.50 - samples/sec: 1028.14 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:46:09,103 epoch 10 - iter 1386/1546 - loss 0.00402196 - time (sec): 109.54 - samples/sec: 1020.51 - lr: 0.000001 - momentum: 0.000000 2023-10-17 10:46:20,872 epoch 10 - iter 1540/1546 - loss 0.00428314 - time (sec): 121.31 - samples/sec: 1021.41 - lr: 0.000000 - momentum: 0.000000 2023-10-17 10:46:21,321 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:46:21,322 EPOCH 10 done: loss 0.0043 - lr: 0.000000 2023-10-17 10:46:24,218 DEV : loss 0.1269896924495697 - f1-score (micro avg) 0.7866 2023-10-17 10:46:24,806 ---------------------------------------------------------------------------------------------------- 2023-10-17 10:46:24,808 Loading model from best epoch ... 2023-10-17 10:46:27,155 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET 2023-10-17 10:46:36,273 Results: - F-score (micro) 0.7831 - F-score (macro) 0.6698 - Accuracy 0.6639 By class: precision recall f1-score support LOC 0.7952 0.8700 0.8309 946 BUILDING 0.6107 0.4919 0.5449 185 STREET 0.7111 0.5714 0.6337 56 micro avg 0.7697 0.7970 0.7831 1187 macro avg 0.7057 0.6444 0.6698 1187 weighted avg 0.7625 0.7970 0.7770 1187 2023-10-17 10:46:36,274 ----------------------------------------------------------------------------------------------------