| 2023-10-17 11:35:45,552 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,554 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 11:35:45,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,555 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 11:35:45,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,555 Train: 6183 sentences | |
| 2023-10-17 11:35:45,555 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 11:35:45,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,555 Training Params: | |
| 2023-10-17 11:35:45,555 - learning_rate: "5e-05" | |
| 2023-10-17 11:35:45,555 - mini_batch_size: "4" | |
| 2023-10-17 11:35:45,555 - max_epochs: "10" | |
| 2023-10-17 11:35:45,555 - shuffle: "True" | |
| 2023-10-17 11:35:45,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,555 Plugins: | |
| 2023-10-17 11:35:45,555 - TensorboardLogger | |
| 2023-10-17 11:35:45,556 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 11:35:45,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,556 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 11:35:45,556 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 11:35:45,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,556 Computation: | |
| 2023-10-17 11:35:45,556 - compute on device: cuda:0 | |
| 2023-10-17 11:35:45,556 - embedding storage: none | |
| 2023-10-17 11:35:45,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,556 Model training base path: "hmbench-topres19th/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-17 11:35:45,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:35:45,556 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 11:35:57,546 epoch 1 - iter 154/1546 - loss 1.83885851 - time (sec): 11.99 - samples/sec: 1026.62 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:36:09,631 epoch 1 - iter 308/1546 - loss 1.03146160 - time (sec): 24.07 - samples/sec: 1023.52 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:36:21,432 epoch 1 - iter 462/1546 - loss 0.72698415 - time (sec): 35.87 - samples/sec: 1043.63 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:36:33,820 epoch 1 - iter 616/1546 - loss 0.56735648 - time (sec): 48.26 - samples/sec: 1038.81 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:36:46,043 epoch 1 - iter 770/1546 - loss 0.47358265 - time (sec): 60.49 - samples/sec: 1033.96 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:36:58,100 epoch 1 - iter 924/1546 - loss 0.42155746 - time (sec): 72.54 - samples/sec: 1021.78 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:37:09,969 epoch 1 - iter 1078/1546 - loss 0.38135834 - time (sec): 84.41 - samples/sec: 1013.51 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 11:37:21,956 epoch 1 - iter 1232/1546 - loss 0.34787118 - time (sec): 96.40 - samples/sec: 1017.93 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 11:37:34,804 epoch 1 - iter 1386/1546 - loss 0.32052669 - time (sec): 109.25 - samples/sec: 1017.93 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 11:37:48,360 epoch 1 - iter 1540/1546 - loss 0.30029350 - time (sec): 122.80 - samples/sec: 1007.40 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 11:37:48,893 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:37:48,893 EPOCH 1 done: loss 0.2991 - lr: 0.000050 | |
| 2023-10-17 11:37:51,313 DEV : loss 0.07589336484670639 - f1-score (micro avg) 0.7239 | |
| 2023-10-17 11:37:51,349 saving best model | |
| 2023-10-17 11:37:51,942 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:38:04,647 epoch 2 - iter 154/1546 - loss 0.09620320 - time (sec): 12.70 - samples/sec: 933.49 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 11:38:16,990 epoch 2 - iter 308/1546 - loss 0.09650626 - time (sec): 25.04 - samples/sec: 958.28 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 11:38:28,988 epoch 2 - iter 462/1546 - loss 0.09623961 - time (sec): 37.04 - samples/sec: 983.56 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 11:38:43,408 epoch 2 - iter 616/1546 - loss 0.09668446 - time (sec): 51.46 - samples/sec: 961.53 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 11:38:55,786 epoch 2 - iter 770/1546 - loss 0.09355811 - time (sec): 63.84 - samples/sec: 963.34 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 11:39:08,327 epoch 2 - iter 924/1546 - loss 0.09142346 - time (sec): 76.38 - samples/sec: 975.58 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 11:39:21,196 epoch 2 - iter 1078/1546 - loss 0.09177734 - time (sec): 89.25 - samples/sec: 969.55 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 11:39:33,455 epoch 2 - iter 1232/1546 - loss 0.08997092 - time (sec): 101.51 - samples/sec: 966.64 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 11:39:45,555 epoch 2 - iter 1386/1546 - loss 0.08993457 - time (sec): 113.61 - samples/sec: 986.13 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 11:39:57,860 epoch 2 - iter 1540/1546 - loss 0.08963720 - time (sec): 125.92 - samples/sec: 983.69 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 11:39:58,318 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:39:58,318 EPOCH 2 done: loss 0.0903 - lr: 0.000044 | |
| 2023-10-17 11:40:01,334 DEV : loss 0.0674557313323021 - f1-score (micro avg) 0.7649 | |
| 2023-10-17 11:40:01,364 saving best model | |
| 2023-10-17 11:40:02,818 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:40:14,771 epoch 3 - iter 154/1546 - loss 0.05524478 - time (sec): 11.94 - samples/sec: 994.46 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 11:40:26,806 epoch 3 - iter 308/1546 - loss 0.06017580 - time (sec): 23.98 - samples/sec: 961.64 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 11:40:39,504 epoch 3 - iter 462/1546 - loss 0.05964897 - time (sec): 36.67 - samples/sec: 968.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 11:40:51,989 epoch 3 - iter 616/1546 - loss 0.06336051 - time (sec): 49.16 - samples/sec: 985.98 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 11:41:04,948 epoch 3 - iter 770/1546 - loss 0.06367074 - time (sec): 62.12 - samples/sec: 986.27 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 11:41:17,312 epoch 3 - iter 924/1546 - loss 0.06217703 - time (sec): 74.48 - samples/sec: 989.91 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 11:41:29,545 epoch 3 - iter 1078/1546 - loss 0.06292626 - time (sec): 86.72 - samples/sec: 993.43 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 11:41:42,319 epoch 3 - iter 1232/1546 - loss 0.06342969 - time (sec): 99.49 - samples/sec: 990.50 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 11:41:55,004 epoch 3 - iter 1386/1546 - loss 0.06375018 - time (sec): 112.17 - samples/sec: 991.19 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 11:42:07,262 epoch 3 - iter 1540/1546 - loss 0.06441018 - time (sec): 124.43 - samples/sec: 995.68 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 11:42:07,720 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:42:07,721 EPOCH 3 done: loss 0.0644 - lr: 0.000039 | |
| 2023-10-17 11:42:11,059 DEV : loss 0.08243168890476227 - f1-score (micro avg) 0.7925 | |
| 2023-10-17 11:42:11,089 saving best model | |
| 2023-10-17 11:42:12,545 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:42:24,575 epoch 4 - iter 154/1546 - loss 0.04181116 - time (sec): 12.03 - samples/sec: 1079.13 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 11:42:36,662 epoch 4 - iter 308/1546 - loss 0.04378985 - time (sec): 24.11 - samples/sec: 1093.29 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 11:42:48,869 epoch 4 - iter 462/1546 - loss 0.04961536 - time (sec): 36.32 - samples/sec: 1052.62 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 11:43:01,116 epoch 4 - iter 616/1546 - loss 0.04737236 - time (sec): 48.57 - samples/sec: 1038.49 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 11:43:13,185 epoch 4 - iter 770/1546 - loss 0.04886557 - time (sec): 60.64 - samples/sec: 1033.47 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 11:43:25,001 epoch 4 - iter 924/1546 - loss 0.04724064 - time (sec): 72.45 - samples/sec: 1034.00 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 11:43:37,214 epoch 4 - iter 1078/1546 - loss 0.04578932 - time (sec): 84.66 - samples/sec: 1023.58 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 11:43:49,462 epoch 4 - iter 1232/1546 - loss 0.04446100 - time (sec): 96.91 - samples/sec: 1014.71 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 11:44:01,995 epoch 4 - iter 1386/1546 - loss 0.04515610 - time (sec): 109.45 - samples/sec: 1017.77 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 11:44:14,511 epoch 4 - iter 1540/1546 - loss 0.04445910 - time (sec): 121.96 - samples/sec: 1014.54 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 11:44:14,992 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:44:14,992 EPOCH 4 done: loss 0.0444 - lr: 0.000033 | |
| 2023-10-17 11:44:17,824 DEV : loss 0.10114207118749619 - f1-score (micro avg) 0.7876 | |
| 2023-10-17 11:44:17,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:44:30,230 epoch 5 - iter 154/1546 - loss 0.03054617 - time (sec): 12.38 - samples/sec: 989.97 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 11:44:42,982 epoch 5 - iter 308/1546 - loss 0.02559762 - time (sec): 25.13 - samples/sec: 1019.18 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 11:44:54,994 epoch 5 - iter 462/1546 - loss 0.02893282 - time (sec): 37.14 - samples/sec: 997.64 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 11:45:07,478 epoch 5 - iter 616/1546 - loss 0.03055604 - time (sec): 49.62 - samples/sec: 984.47 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 11:45:20,590 epoch 5 - iter 770/1546 - loss 0.02918857 - time (sec): 62.74 - samples/sec: 972.04 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 11:45:33,162 epoch 5 - iter 924/1546 - loss 0.03004856 - time (sec): 75.31 - samples/sec: 973.68 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 11:45:45,194 epoch 5 - iter 1078/1546 - loss 0.02969641 - time (sec): 87.34 - samples/sec: 986.54 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:45:57,479 epoch 5 - iter 1232/1546 - loss 0.03039943 - time (sec): 99.62 - samples/sec: 992.67 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 11:46:09,808 epoch 5 - iter 1386/1546 - loss 0.03111409 - time (sec): 111.95 - samples/sec: 993.99 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:46:22,446 epoch 5 - iter 1540/1546 - loss 0.03134691 - time (sec): 124.59 - samples/sec: 991.39 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 11:46:22,971 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:46:22,971 EPOCH 5 done: loss 0.0314 - lr: 0.000028 | |
| 2023-10-17 11:46:25,840 DEV : loss 0.10744524002075195 - f1-score (micro avg) 0.7699 | |
| 2023-10-17 11:46:25,868 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:46:37,933 epoch 6 - iter 154/1546 - loss 0.02268715 - time (sec): 12.06 - samples/sec: 982.22 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:46:50,599 epoch 6 - iter 308/1546 - loss 0.02384393 - time (sec): 24.73 - samples/sec: 935.04 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 11:47:03,236 epoch 6 - iter 462/1546 - loss 0.02247440 - time (sec): 37.37 - samples/sec: 958.97 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:47:15,777 epoch 6 - iter 616/1546 - loss 0.02095738 - time (sec): 49.91 - samples/sec: 984.23 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 11:47:28,793 epoch 6 - iter 770/1546 - loss 0.02253172 - time (sec): 62.92 - samples/sec: 978.67 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 11:47:41,067 epoch 6 - iter 924/1546 - loss 0.02187836 - time (sec): 75.20 - samples/sec: 981.71 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:47:54,246 epoch 6 - iter 1078/1546 - loss 0.02149000 - time (sec): 88.38 - samples/sec: 978.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 11:48:06,750 epoch 6 - iter 1232/1546 - loss 0.02129113 - time (sec): 100.88 - samples/sec: 979.18 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:48:18,878 epoch 6 - iter 1386/1546 - loss 0.02099597 - time (sec): 113.01 - samples/sec: 985.77 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 11:48:30,988 epoch 6 - iter 1540/1546 - loss 0.02096803 - time (sec): 125.12 - samples/sec: 989.09 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:48:31,454 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:48:31,454 EPOCH 6 done: loss 0.0209 - lr: 0.000022 | |
| 2023-10-17 11:48:34,257 DEV : loss 0.12126855552196503 - f1-score (micro avg) 0.761 | |
| 2023-10-17 11:48:34,286 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:48:46,167 epoch 7 - iter 154/1546 - loss 0.01505337 - time (sec): 11.88 - samples/sec: 990.92 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 11:48:58,441 epoch 7 - iter 308/1546 - loss 0.01119824 - time (sec): 24.15 - samples/sec: 993.97 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:49:11,017 epoch 7 - iter 462/1546 - loss 0.01337559 - time (sec): 36.73 - samples/sec: 999.33 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 11:49:22,992 epoch 7 - iter 616/1546 - loss 0.01318854 - time (sec): 48.70 - samples/sec: 996.83 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 11:49:35,184 epoch 7 - iter 770/1546 - loss 0.01447548 - time (sec): 60.90 - samples/sec: 990.38 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:49:47,892 epoch 7 - iter 924/1546 - loss 0.01396535 - time (sec): 73.60 - samples/sec: 989.94 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 11:50:00,666 epoch 7 - iter 1078/1546 - loss 0.01435574 - time (sec): 86.38 - samples/sec: 1009.08 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:50:12,719 epoch 7 - iter 1232/1546 - loss 0.01381270 - time (sec): 98.43 - samples/sec: 1007.45 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 11:50:25,202 epoch 7 - iter 1386/1546 - loss 0.01396888 - time (sec): 110.91 - samples/sec: 1002.69 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:50:37,532 epoch 7 - iter 1540/1546 - loss 0.01474867 - time (sec): 123.24 - samples/sec: 1002.50 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 11:50:38,024 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:50:38,024 EPOCH 7 done: loss 0.0149 - lr: 0.000017 | |
| 2023-10-17 11:50:41,034 DEV : loss 0.12127351760864258 - f1-score (micro avg) 0.7844 | |
| 2023-10-17 11:50:41,065 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:50:53,540 epoch 8 - iter 154/1546 - loss 0.01576538 - time (sec): 12.47 - samples/sec: 935.69 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:51:05,757 epoch 8 - iter 308/1546 - loss 0.01252126 - time (sec): 24.69 - samples/sec: 980.49 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 11:51:17,966 epoch 8 - iter 462/1546 - loss 0.01184613 - time (sec): 36.90 - samples/sec: 965.34 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 11:51:30,153 epoch 8 - iter 616/1546 - loss 0.01041226 - time (sec): 49.09 - samples/sec: 963.73 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:51:42,569 epoch 8 - iter 770/1546 - loss 0.01031697 - time (sec): 61.50 - samples/sec: 983.14 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 11:51:55,445 epoch 8 - iter 924/1546 - loss 0.00954217 - time (sec): 74.38 - samples/sec: 992.65 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:52:08,027 epoch 8 - iter 1078/1546 - loss 0.00955285 - time (sec): 86.96 - samples/sec: 991.57 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 11:52:20,217 epoch 8 - iter 1232/1546 - loss 0.00938038 - time (sec): 99.15 - samples/sec: 999.30 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:52:32,586 epoch 8 - iter 1386/1546 - loss 0.00972415 - time (sec): 111.52 - samples/sec: 997.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 11:52:45,367 epoch 8 - iter 1540/1546 - loss 0.00955060 - time (sec): 124.30 - samples/sec: 995.55 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:52:45,895 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:52:45,896 EPOCH 8 done: loss 0.0095 - lr: 0.000011 | |
| 2023-10-17 11:52:49,157 DEV : loss 0.12450835853815079 - f1-score (micro avg) 0.7808 | |
| 2023-10-17 11:52:49,195 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:53:02,160 epoch 9 - iter 154/1546 - loss 0.00381374 - time (sec): 12.96 - samples/sec: 971.71 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 11:53:14,095 epoch 9 - iter 308/1546 - loss 0.00328944 - time (sec): 24.90 - samples/sec: 1050.97 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 11:53:26,475 epoch 9 - iter 462/1546 - loss 0.00423502 - time (sec): 37.28 - samples/sec: 1019.71 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:53:38,868 epoch 9 - iter 616/1546 - loss 0.00420190 - time (sec): 49.67 - samples/sec: 1020.69 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 11:53:51,185 epoch 9 - iter 770/1546 - loss 0.00420859 - time (sec): 61.99 - samples/sec: 1016.16 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:54:03,968 epoch 9 - iter 924/1546 - loss 0.00435302 - time (sec): 74.77 - samples/sec: 997.71 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 11:54:16,961 epoch 9 - iter 1078/1546 - loss 0.00505362 - time (sec): 87.76 - samples/sec: 990.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:54:29,580 epoch 9 - iter 1232/1546 - loss 0.00501432 - time (sec): 100.38 - samples/sec: 992.08 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 11:54:42,452 epoch 9 - iter 1386/1546 - loss 0.00475313 - time (sec): 113.25 - samples/sec: 994.63 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:54:55,104 epoch 9 - iter 1540/1546 - loss 0.00511714 - time (sec): 125.91 - samples/sec: 983.02 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 11:54:55,576 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:54:55,576 EPOCH 9 done: loss 0.0051 - lr: 0.000006 | |
| 2023-10-17 11:54:58,676 DEV : loss 0.13177739083766937 - f1-score (micro avg) 0.795 | |
| 2023-10-17 11:54:58,705 saving best model | |
| 2023-10-17 11:55:00,160 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:55:12,239 epoch 10 - iter 154/1546 - loss 0.00092056 - time (sec): 12.07 - samples/sec: 1002.09 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 11:55:24,900 epoch 10 - iter 308/1546 - loss 0.00262761 - time (sec): 24.73 - samples/sec: 1042.52 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:55:37,158 epoch 10 - iter 462/1546 - loss 0.00275953 - time (sec): 36.99 - samples/sec: 1035.14 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 11:55:49,156 epoch 10 - iter 616/1546 - loss 0.00356907 - time (sec): 48.99 - samples/sec: 1023.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:56:01,184 epoch 10 - iter 770/1546 - loss 0.00435324 - time (sec): 61.02 - samples/sec: 1031.31 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 11:56:13,414 epoch 10 - iter 924/1546 - loss 0.00397741 - time (sec): 73.25 - samples/sec: 1034.88 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:56:26,148 epoch 10 - iter 1078/1546 - loss 0.00379041 - time (sec): 85.98 - samples/sec: 1025.04 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 11:56:38,575 epoch 10 - iter 1232/1546 - loss 0.00369567 - time (sec): 98.41 - samples/sec: 1005.37 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:56:51,026 epoch 10 - iter 1386/1546 - loss 0.00339406 - time (sec): 110.86 - samples/sec: 1009.64 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 11:57:03,401 epoch 10 - iter 1540/1546 - loss 0.00334146 - time (sec): 123.23 - samples/sec: 1004.56 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 11:57:03,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:57:03,854 EPOCH 10 done: loss 0.0033 - lr: 0.000000 | |
| 2023-10-17 11:57:06,887 DEV : loss 0.1316857933998108 - f1-score (micro avg) 0.7951 | |
| 2023-10-17 11:57:06,916 saving best model | |
| 2023-10-17 11:57:08,961 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 11:57:08,963 Loading model from best epoch ... | |
| 2023-10-17 11:57:11,262 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 11:57:20,172 | |
| Results: | |
| - F-score (micro) 0.8057 | |
| - F-score (macro) 0.7042 | |
| - Accuracy 0.6984 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8320 0.8636 0.8475 946 | |
| BUILDING 0.6571 0.6216 0.6389 185 | |
| STREET 0.6102 0.6429 0.6261 56 | |
| micro avg 0.7961 0.8155 0.8057 1187 | |
| macro avg 0.6998 0.7094 0.7042 1187 | |
| weighted avg 0.7943 0.8155 0.8045 1187 | |
| 2023-10-17 11:57:20,172 ---------------------------------------------------------------------------------------------------- | |