| 2023-10-20 09:41:09,199 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 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 | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Train: 6183 sentences | |
| 2023-10-20 09:41:09,200 (train_with_dev=False, train_with_test=False) | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Training Params: | |
| 2023-10-20 09:41:09,200 - learning_rate: "5e-05" | |
| 2023-10-20 09:41:09,200 - mini_batch_size: "4" | |
| 2023-10-20 09:41:09,200 - max_epochs: "10" | |
| 2023-10-20 09:41:09,200 - shuffle: "True" | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Plugins: | |
| 2023-10-20 09:41:09,200 - TensorboardLogger | |
| 2023-10-20 09:41:09,200 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-20 09:41:09,200 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Computation: | |
| 2023-10-20 09:41:09,200 - compute on device: cuda:0 | |
| 2023-10-20 09:41:09,200 - embedding storage: none | |
| 2023-10-20 09:41:09,200 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,200 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-20 09:41:09,201 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,201 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:09,201 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-20 09:41:11,581 epoch 1 - iter 154/1546 - loss 2.73201796 - time (sec): 2.38 - samples/sec: 5211.62 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-20 09:41:13,997 epoch 1 - iter 308/1546 - loss 2.28602428 - time (sec): 4.80 - samples/sec: 5370.04 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-20 09:41:16,612 epoch 1 - iter 462/1546 - loss 1.80447606 - time (sec): 7.41 - samples/sec: 5025.78 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-20 09:41:19,191 epoch 1 - iter 616/1546 - loss 1.45860759 - time (sec): 9.99 - samples/sec: 4859.62 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-20 09:41:21,393 epoch 1 - iter 770/1546 - loss 1.21626669 - time (sec): 12.19 - samples/sec: 4991.92 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-20 09:41:23,508 epoch 1 - iter 924/1546 - loss 1.05743701 - time (sec): 14.31 - samples/sec: 5116.89 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-20 09:41:25,915 epoch 1 - iter 1078/1546 - loss 0.93364531 - time (sec): 16.71 - samples/sec: 5203.28 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-20 09:41:28,282 epoch 1 - iter 1232/1546 - loss 0.85352136 - time (sec): 19.08 - samples/sec: 5178.04 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-20 09:41:30,632 epoch 1 - iter 1386/1546 - loss 0.78183431 - time (sec): 21.43 - samples/sec: 5187.56 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-20 09:41:32,915 epoch 1 - iter 1540/1546 - loss 0.72103837 - time (sec): 23.71 - samples/sec: 5221.53 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-20 09:41:33,007 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:33,008 EPOCH 1 done: loss 0.7187 - lr: 0.000050 | |
| 2023-10-20 09:41:33,999 DEV : loss 0.12611015141010284 - f1-score (micro avg) 0.0923 | |
| 2023-10-20 09:41:34,010 saving best model | |
| 2023-10-20 09:41:34,039 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:36,381 epoch 2 - iter 154/1546 - loss 0.19147722 - time (sec): 2.34 - samples/sec: 5814.62 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-20 09:41:38,793 epoch 2 - iter 308/1546 - loss 0.18883533 - time (sec): 4.75 - samples/sec: 5458.41 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-20 09:41:41,367 epoch 2 - iter 462/1546 - loss 0.19117660 - time (sec): 7.33 - samples/sec: 5234.09 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-20 09:41:43,731 epoch 2 - iter 616/1546 - loss 0.18776788 - time (sec): 9.69 - samples/sec: 5212.68 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-20 09:41:46,014 epoch 2 - iter 770/1546 - loss 0.19099004 - time (sec): 11.98 - samples/sec: 5248.49 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-20 09:41:48,419 epoch 2 - iter 924/1546 - loss 0.18616969 - time (sec): 14.38 - samples/sec: 5262.06 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-20 09:41:50,714 epoch 2 - iter 1078/1546 - loss 0.18577369 - time (sec): 16.67 - samples/sec: 5266.37 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-20 09:41:53,055 epoch 2 - iter 1232/1546 - loss 0.18463930 - time (sec): 19.02 - samples/sec: 5225.70 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-20 09:41:55,521 epoch 2 - iter 1386/1546 - loss 0.18415167 - time (sec): 21.48 - samples/sec: 5196.25 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-20 09:41:57,913 epoch 2 - iter 1540/1546 - loss 0.18017139 - time (sec): 23.87 - samples/sec: 5186.12 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-20 09:41:58,001 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:41:58,002 EPOCH 2 done: loss 0.1802 - lr: 0.000044 | |
| 2023-10-20 09:41:59,100 DEV : loss 0.09276499599218369 - f1-score (micro avg) 0.463 | |
| 2023-10-20 09:41:59,115 saving best model | |
| 2023-10-20 09:41:59,156 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:42:01,495 epoch 3 - iter 154/1546 - loss 0.17659999 - time (sec): 2.34 - samples/sec: 4765.94 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-20 09:42:03,992 epoch 3 - iter 308/1546 - loss 0.15431148 - time (sec): 4.84 - samples/sec: 5034.38 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-20 09:42:06,185 epoch 3 - iter 462/1546 - loss 0.15873776 - time (sec): 7.03 - samples/sec: 5224.34 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-20 09:42:08,363 epoch 3 - iter 616/1546 - loss 0.15154501 - time (sec): 9.21 - samples/sec: 5250.01 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-20 09:42:10,521 epoch 3 - iter 770/1546 - loss 0.15058689 - time (sec): 11.36 - samples/sec: 5370.97 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-20 09:42:12,875 epoch 3 - iter 924/1546 - loss 0.14854044 - time (sec): 13.72 - samples/sec: 5401.12 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-20 09:42:15,237 epoch 3 - iter 1078/1546 - loss 0.14970216 - time (sec): 16.08 - samples/sec: 5374.95 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-20 09:42:17,568 epoch 3 - iter 1232/1546 - loss 0.15198622 - time (sec): 18.41 - samples/sec: 5357.42 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-20 09:42:19,976 epoch 3 - iter 1386/1546 - loss 0.15043598 - time (sec): 20.82 - samples/sec: 5361.18 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-20 09:42:22,330 epoch 3 - iter 1540/1546 - loss 0.15010108 - time (sec): 23.17 - samples/sec: 5342.90 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-20 09:42:22,421 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:42:22,421 EPOCH 3 done: loss 0.1507 - lr: 0.000039 | |
| 2023-10-20 09:42:23,519 DEV : loss 0.09011607617139816 - f1-score (micro avg) 0.5241 | |
| 2023-10-20 09:42:23,531 saving best model | |
| 2023-10-20 09:42:23,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:42:26,002 epoch 4 - iter 154/1546 - loss 0.13234173 - time (sec): 2.43 - samples/sec: 5609.47 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-20 09:42:28,290 epoch 4 - iter 308/1546 - loss 0.13714759 - time (sec): 4.72 - samples/sec: 5340.94 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-20 09:42:30,599 epoch 4 - iter 462/1546 - loss 0.12728020 - time (sec): 7.03 - samples/sec: 5327.92 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-20 09:42:32,941 epoch 4 - iter 616/1546 - loss 0.13080542 - time (sec): 9.37 - samples/sec: 5291.06 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-20 09:42:35,381 epoch 4 - iter 770/1546 - loss 0.12845508 - time (sec): 11.81 - samples/sec: 5301.24 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-20 09:42:37,710 epoch 4 - iter 924/1546 - loss 0.13383808 - time (sec): 14.14 - samples/sec: 5289.52 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-20 09:42:40,090 epoch 4 - iter 1078/1546 - loss 0.13508658 - time (sec): 16.52 - samples/sec: 5292.52 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-20 09:42:42,510 epoch 4 - iter 1232/1546 - loss 0.13532445 - time (sec): 18.94 - samples/sec: 5289.66 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-20 09:42:44,865 epoch 4 - iter 1386/1546 - loss 0.13315587 - time (sec): 21.29 - samples/sec: 5283.64 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-20 09:42:47,186 epoch 4 - iter 1540/1546 - loss 0.13381815 - time (sec): 23.61 - samples/sec: 5244.78 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-20 09:42:47,277 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:42:47,277 EPOCH 4 done: loss 0.1337 - lr: 0.000033 | |
| 2023-10-20 09:42:48,357 DEV : loss 0.09306028485298157 - f1-score (micro avg) 0.5244 | |
| 2023-10-20 09:42:48,368 saving best model | |
| 2023-10-20 09:42:48,408 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:42:50,715 epoch 5 - iter 154/1546 - loss 0.11681683 - time (sec): 2.31 - samples/sec: 5404.86 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-20 09:42:52,960 epoch 5 - iter 308/1546 - loss 0.11485080 - time (sec): 4.55 - samples/sec: 5433.24 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-20 09:42:55,341 epoch 5 - iter 462/1546 - loss 0.12181429 - time (sec): 6.93 - samples/sec: 5293.09 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-20 09:42:57,788 epoch 5 - iter 616/1546 - loss 0.11977320 - time (sec): 9.38 - samples/sec: 5288.81 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-20 09:43:00,174 epoch 5 - iter 770/1546 - loss 0.11612074 - time (sec): 11.77 - samples/sec: 5309.53 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-20 09:43:02,601 epoch 5 - iter 924/1546 - loss 0.12322243 - time (sec): 14.19 - samples/sec: 5285.12 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-20 09:43:04,977 epoch 5 - iter 1078/1546 - loss 0.12454524 - time (sec): 16.57 - samples/sec: 5260.58 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-20 09:43:07,312 epoch 5 - iter 1232/1546 - loss 0.12565251 - time (sec): 18.90 - samples/sec: 5246.75 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-20 09:43:09,670 epoch 5 - iter 1386/1546 - loss 0.12496953 - time (sec): 21.26 - samples/sec: 5245.43 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-20 09:43:12,064 epoch 5 - iter 1540/1546 - loss 0.12186724 - time (sec): 23.66 - samples/sec: 5235.16 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-20 09:43:12,158 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:43:12,158 EPOCH 5 done: loss 0.1221 - lr: 0.000028 | |
| 2023-10-20 09:43:13,241 DEV : loss 0.09604145586490631 - f1-score (micro avg) 0.5656 | |
| 2023-10-20 09:43:13,254 saving best model | |
| 2023-10-20 09:43:13,286 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:43:15,726 epoch 6 - iter 154/1546 - loss 0.14501961 - time (sec): 2.44 - samples/sec: 5098.88 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-20 09:43:18,081 epoch 6 - iter 308/1546 - loss 0.12419256 - time (sec): 4.79 - samples/sec: 5241.47 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-20 09:43:20,410 epoch 6 - iter 462/1546 - loss 0.11952545 - time (sec): 7.12 - samples/sec: 5247.84 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-20 09:43:22,764 epoch 6 - iter 616/1546 - loss 0.12112158 - time (sec): 9.48 - samples/sec: 5154.77 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-20 09:43:25,146 epoch 6 - iter 770/1546 - loss 0.11804613 - time (sec): 11.86 - samples/sec: 5239.33 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-20 09:43:27,511 epoch 6 - iter 924/1546 - loss 0.11766846 - time (sec): 14.22 - samples/sec: 5215.77 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-20 09:43:29,890 epoch 6 - iter 1078/1546 - loss 0.11754179 - time (sec): 16.60 - samples/sec: 5214.73 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-20 09:43:32,248 epoch 6 - iter 1232/1546 - loss 0.11564541 - time (sec): 18.96 - samples/sec: 5218.61 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-20 09:43:34,677 epoch 6 - iter 1386/1546 - loss 0.11640739 - time (sec): 21.39 - samples/sec: 5238.26 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-20 09:43:36,968 epoch 6 - iter 1540/1546 - loss 0.11549879 - time (sec): 23.68 - samples/sec: 5228.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-20 09:43:37,050 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:43:37,050 EPOCH 6 done: loss 0.1151 - lr: 0.000022 | |
| 2023-10-20 09:43:38,136 DEV : loss 0.10433212667703629 - f1-score (micro avg) 0.5727 | |
| 2023-10-20 09:43:38,149 saving best model | |
| 2023-10-20 09:43:38,190 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:43:40,570 epoch 7 - iter 154/1546 - loss 0.12205843 - time (sec): 2.38 - samples/sec: 5053.28 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-20 09:43:42,919 epoch 7 - iter 308/1546 - loss 0.10630383 - time (sec): 4.73 - samples/sec: 5325.75 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-20 09:43:45,240 epoch 7 - iter 462/1546 - loss 0.11247321 - time (sec): 7.05 - samples/sec: 5240.98 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-20 09:43:47,691 epoch 7 - iter 616/1546 - loss 0.10731717 - time (sec): 9.50 - samples/sec: 5238.98 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-20 09:43:50,026 epoch 7 - iter 770/1546 - loss 0.10659080 - time (sec): 11.84 - samples/sec: 5134.02 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-20 09:43:52,380 epoch 7 - iter 924/1546 - loss 0.10675804 - time (sec): 14.19 - samples/sec: 5129.08 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-20 09:43:54,757 epoch 7 - iter 1078/1546 - loss 0.10617289 - time (sec): 16.57 - samples/sec: 5171.36 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-20 09:43:57,215 epoch 7 - iter 1232/1546 - loss 0.10595788 - time (sec): 19.02 - samples/sec: 5179.16 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-20 09:43:59,544 epoch 7 - iter 1386/1546 - loss 0.10475076 - time (sec): 21.35 - samples/sec: 5221.19 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-20 09:44:01,661 epoch 7 - iter 1540/1546 - loss 0.10684330 - time (sec): 23.47 - samples/sec: 5274.67 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-20 09:44:01,740 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:01,741 EPOCH 7 done: loss 0.1067 - lr: 0.000017 | |
| 2023-10-20 09:44:02,845 DEV : loss 0.10244878381490707 - f1-score (micro avg) 0.5978 | |
| 2023-10-20 09:44:02,858 saving best model | |
| 2023-10-20 09:44:02,900 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:05,137 epoch 8 - iter 154/1546 - loss 0.07782089 - time (sec): 2.24 - samples/sec: 5379.85 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-20 09:44:07,488 epoch 8 - iter 308/1546 - loss 0.09938386 - time (sec): 4.59 - samples/sec: 5205.84 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-20 09:44:09,760 epoch 8 - iter 462/1546 - loss 0.10503251 - time (sec): 6.86 - samples/sec: 5325.75 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-20 09:44:12,071 epoch 8 - iter 616/1546 - loss 0.09702954 - time (sec): 9.17 - samples/sec: 5452.15 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-20 09:44:14,469 epoch 8 - iter 770/1546 - loss 0.09883319 - time (sec): 11.57 - samples/sec: 5429.20 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-20 09:44:16,911 epoch 8 - iter 924/1546 - loss 0.10089289 - time (sec): 14.01 - samples/sec: 5368.77 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-20 09:44:19,253 epoch 8 - iter 1078/1546 - loss 0.10490967 - time (sec): 16.35 - samples/sec: 5317.93 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-20 09:44:21,864 epoch 8 - iter 1232/1546 - loss 0.10403049 - time (sec): 18.96 - samples/sec: 5252.66 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-20 09:44:24,326 epoch 8 - iter 1386/1546 - loss 0.10516244 - time (sec): 21.43 - samples/sec: 5188.95 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-20 09:44:26,789 epoch 8 - iter 1540/1546 - loss 0.10342984 - time (sec): 23.89 - samples/sec: 5181.70 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-20 09:44:26,877 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:26,878 EPOCH 8 done: loss 0.1032 - lr: 0.000011 | |
| 2023-10-20 09:44:27,986 DEV : loss 0.10922187566757202 - f1-score (micro avg) 0.6057 | |
| 2023-10-20 09:44:27,998 saving best model | |
| 2023-10-20 09:44:28,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:30,360 epoch 9 - iter 154/1546 - loss 0.08640753 - time (sec): 2.32 - samples/sec: 5049.90 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-20 09:44:32,771 epoch 9 - iter 308/1546 - loss 0.10139803 - time (sec): 4.73 - samples/sec: 5185.55 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-20 09:44:35,161 epoch 9 - iter 462/1546 - loss 0.10459999 - time (sec): 7.12 - samples/sec: 5147.67 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-20 09:44:37,562 epoch 9 - iter 616/1546 - loss 0.10331605 - time (sec): 9.52 - samples/sec: 5178.00 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-20 09:44:39,934 epoch 9 - iter 770/1546 - loss 0.10432797 - time (sec): 11.90 - samples/sec: 5263.07 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-20 09:44:42,272 epoch 9 - iter 924/1546 - loss 0.10164891 - time (sec): 14.23 - samples/sec: 5224.54 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-20 09:44:44,608 epoch 9 - iter 1078/1546 - loss 0.10042381 - time (sec): 16.57 - samples/sec: 5216.95 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-20 09:44:47,009 epoch 9 - iter 1232/1546 - loss 0.09913846 - time (sec): 18.97 - samples/sec: 5227.53 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-20 09:44:49,379 epoch 9 - iter 1386/1546 - loss 0.09843496 - time (sec): 21.34 - samples/sec: 5225.60 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-20 09:44:51,770 epoch 9 - iter 1540/1546 - loss 0.09869379 - time (sec): 23.73 - samples/sec: 5218.24 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-20 09:44:51,858 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:51,859 EPOCH 9 done: loss 0.0986 - lr: 0.000006 | |
| 2023-10-20 09:44:52,949 DEV : loss 0.10991593450307846 - f1-score (micro avg) 0.6157 | |
| 2023-10-20 09:44:52,962 saving best model | |
| 2023-10-20 09:44:52,995 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:44:55,276 epoch 10 - iter 154/1546 - loss 0.08007322 - time (sec): 2.28 - samples/sec: 5351.05 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-20 09:44:57,614 epoch 10 - iter 308/1546 - loss 0.07876762 - time (sec): 4.62 - samples/sec: 4959.39 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-20 09:45:00,139 epoch 10 - iter 462/1546 - loss 0.08637072 - time (sec): 7.14 - samples/sec: 5137.18 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-20 09:45:02,578 epoch 10 - iter 616/1546 - loss 0.09043747 - time (sec): 9.58 - samples/sec: 5157.41 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-20 09:45:04,930 epoch 10 - iter 770/1546 - loss 0.09135879 - time (sec): 11.93 - samples/sec: 5188.74 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-20 09:45:07,334 epoch 10 - iter 924/1546 - loss 0.09566442 - time (sec): 14.34 - samples/sec: 5196.85 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-20 09:45:09,778 epoch 10 - iter 1078/1546 - loss 0.09739706 - time (sec): 16.78 - samples/sec: 5147.91 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-20 09:45:12,353 epoch 10 - iter 1232/1546 - loss 0.09546748 - time (sec): 19.36 - samples/sec: 5149.80 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-20 09:45:14,711 epoch 10 - iter 1386/1546 - loss 0.09546014 - time (sec): 21.71 - samples/sec: 5127.46 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-20 09:45:17,110 epoch 10 - iter 1540/1546 - loss 0.09650173 - time (sec): 24.11 - samples/sec: 5137.09 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-20 09:45:17,203 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:45:17,203 EPOCH 10 done: loss 0.0964 - lr: 0.000000 | |
| 2023-10-20 09:45:18,278 DEV : loss 0.11002404242753983 - f1-score (micro avg) 0.628 | |
| 2023-10-20 09:45:18,291 saving best model | |
| 2023-10-20 09:45:18,358 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-20 09:45:18,359 Loading model from best epoch ... | |
| 2023-10-20 09:45:18,432 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 | |
| 2023-10-20 09:45:21,376 | |
| Results: | |
| - F-score (micro) 0.5802 | |
| - F-score (macro) 0.3927 | |
| - Accuracy 0.4193 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.6257 0.6681 0.6462 946 | |
| BUILDING 0.2710 0.1568 0.1986 185 | |
| STREET 0.7500 0.2143 0.3333 56 | |
| micro avg 0.5940 0.5670 0.5802 1187 | |
| macro avg 0.5489 0.3464 0.3927 1187 | |
| weighted avg 0.5763 0.5670 0.5617 1187 | |
| 2023-10-20 09:45:21,376 ---------------------------------------------------------------------------------------------------- | |