2023-10-20 00:21:21,464 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 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=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 MultiCorpus: 1085 train + 148 dev + 364 test sentences - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 Train: 1085 sentences 2023-10-20 00:21:21,465 (train_with_dev=False, train_with_test=False) 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 Training Params: 2023-10-20 00:21:21,465 - learning_rate: "5e-05" 2023-10-20 00:21:21,465 - mini_batch_size: "4" 2023-10-20 00:21:21,465 - max_epochs: "10" 2023-10-20 00:21:21,465 - shuffle: "True" 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 Plugins: 2023-10-20 00:21:21,465 - TensorboardLogger 2023-10-20 00:21:21,465 - LinearScheduler | warmup_fraction: '0.1' 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 Final evaluation on model from best epoch (best-model.pt) 2023-10-20 00:21:21,465 - metric: "('micro avg', 'f1-score')" 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,465 Computation: 2023-10-20 00:21:21,465 - compute on device: cuda:0 2023-10-20 00:21:21,465 - embedding storage: none 2023-10-20 00:21:21,465 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,466 Model training base path: "hmbench-newseye/sv-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" 2023-10-20 00:21:21,466 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,466 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:21,466 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-20 00:21:21,957 epoch 1 - iter 27/272 - loss 3.46711403 - time (sec): 0.49 - samples/sec: 10461.58 - lr: 0.000005 - momentum: 0.000000 2023-10-20 00:21:22,439 epoch 1 - iter 54/272 - loss 3.46171750 - time (sec): 0.97 - samples/sec: 10681.11 - lr: 0.000010 - momentum: 0.000000 2023-10-20 00:21:22,883 epoch 1 - iter 81/272 - loss 3.28534633 - time (sec): 1.42 - samples/sec: 10814.77 - lr: 0.000015 - momentum: 0.000000 2023-10-20 00:21:23,443 epoch 1 - iter 108/272 - loss 3.01861422 - time (sec): 1.98 - samples/sec: 10633.83 - lr: 0.000020 - momentum: 0.000000 2023-10-20 00:21:23,941 epoch 1 - iter 135/272 - loss 2.80909491 - time (sec): 2.48 - samples/sec: 10406.50 - lr: 0.000025 - momentum: 0.000000 2023-10-20 00:21:24,476 epoch 1 - iter 162/272 - loss 2.54231157 - time (sec): 3.01 - samples/sec: 10303.95 - lr: 0.000030 - momentum: 0.000000 2023-10-20 00:21:24,983 epoch 1 - iter 189/272 - loss 2.31826568 - time (sec): 3.52 - samples/sec: 10208.09 - lr: 0.000035 - momentum: 0.000000 2023-10-20 00:21:25,506 epoch 1 - iter 216/272 - loss 2.08682730 - time (sec): 4.04 - samples/sec: 10358.94 - lr: 0.000040 - momentum: 0.000000 2023-10-20 00:21:26,020 epoch 1 - iter 243/272 - loss 1.91212120 - time (sec): 4.55 - samples/sec: 10466.68 - lr: 0.000044 - momentum: 0.000000 2023-10-20 00:21:26,487 epoch 1 - iter 270/272 - loss 1.80967208 - time (sec): 5.02 - samples/sec: 10325.73 - lr: 0.000049 - momentum: 0.000000 2023-10-20 00:21:26,520 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:26,520 EPOCH 1 done: loss 1.8069 - lr: 0.000049 2023-10-20 00:21:26,937 DEV : loss 0.4722510874271393 - f1-score (micro avg) 0.0 2023-10-20 00:21:26,940 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:27,456 epoch 2 - iter 27/272 - loss 0.61178694 - time (sec): 0.52 - samples/sec: 10248.65 - lr: 0.000049 - momentum: 0.000000 2023-10-20 00:21:27,965 epoch 2 - iter 54/272 - loss 0.57067838 - time (sec): 1.02 - samples/sec: 9816.81 - lr: 0.000049 - momentum: 0.000000 2023-10-20 00:21:28,449 epoch 2 - iter 81/272 - loss 0.56029945 - time (sec): 1.51 - samples/sec: 10217.88 - lr: 0.000048 - momentum: 0.000000 2023-10-20 00:21:28,950 epoch 2 - iter 108/272 - loss 0.54873035 - time (sec): 2.01 - samples/sec: 10325.13 - lr: 0.000048 - momentum: 0.000000 2023-10-20 00:21:29,435 epoch 2 - iter 135/272 - loss 0.55233991 - time (sec): 2.49 - samples/sec: 10424.92 - lr: 0.000047 - momentum: 0.000000 2023-10-20 00:21:29,953 epoch 2 - iter 162/272 - loss 0.54109234 - time (sec): 3.01 - samples/sec: 10331.23 - lr: 0.000047 - momentum: 0.000000 2023-10-20 00:21:30,466 epoch 2 - iter 189/272 - loss 0.52309886 - time (sec): 3.53 - samples/sec: 10393.81 - lr: 0.000046 - momentum: 0.000000 2023-10-20 00:21:30,960 epoch 2 - iter 216/272 - loss 0.51818871 - time (sec): 4.02 - samples/sec: 10345.08 - lr: 0.000046 - momentum: 0.000000 2023-10-20 00:21:31,472 epoch 2 - iter 243/272 - loss 0.51911854 - time (sec): 4.53 - samples/sec: 10371.98 - lr: 0.000045 - momentum: 0.000000 2023-10-20 00:21:31,966 epoch 2 - iter 270/272 - loss 0.52018264 - time (sec): 5.03 - samples/sec: 10319.19 - lr: 0.000045 - momentum: 0.000000 2023-10-20 00:21:31,994 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:31,995 EPOCH 2 done: loss 0.5211 - lr: 0.000045 2023-10-20 00:21:32,748 DEV : loss 0.3575037121772766 - f1-score (micro avg) 0.0408 2023-10-20 00:21:32,752 saving best model 2023-10-20 00:21:32,779 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:33,275 epoch 3 - iter 27/272 - loss 0.40786242 - time (sec): 0.50 - samples/sec: 10258.65 - lr: 0.000044 - momentum: 0.000000 2023-10-20 00:21:33,777 epoch 3 - iter 54/272 - loss 0.42946260 - time (sec): 1.00 - samples/sec: 10855.41 - lr: 0.000043 - momentum: 0.000000 2023-10-20 00:21:34,302 epoch 3 - iter 81/272 - loss 0.41328076 - time (sec): 1.52 - samples/sec: 10338.48 - lr: 0.000043 - momentum: 0.000000 2023-10-20 00:21:34,828 epoch 3 - iter 108/272 - loss 0.41615591 - time (sec): 2.05 - samples/sec: 10115.61 - lr: 0.000042 - momentum: 0.000000 2023-10-20 00:21:35,349 epoch 3 - iter 135/272 - loss 0.41543348 - time (sec): 2.57 - samples/sec: 10345.89 - lr: 0.000042 - momentum: 0.000000 2023-10-20 00:21:35,842 epoch 3 - iter 162/272 - loss 0.41142926 - time (sec): 3.06 - samples/sec: 10218.54 - lr: 0.000041 - momentum: 0.000000 2023-10-20 00:21:36,336 epoch 3 - iter 189/272 - loss 0.40845834 - time (sec): 3.56 - samples/sec: 10363.90 - lr: 0.000041 - momentum: 0.000000 2023-10-20 00:21:36,841 epoch 3 - iter 216/272 - loss 0.42242963 - time (sec): 4.06 - samples/sec: 10316.37 - lr: 0.000040 - momentum: 0.000000 2023-10-20 00:21:37,327 epoch 3 - iter 243/272 - loss 0.42454515 - time (sec): 4.55 - samples/sec: 10234.41 - lr: 0.000040 - momentum: 0.000000 2023-10-20 00:21:37,837 epoch 3 - iter 270/272 - loss 0.42731990 - time (sec): 5.06 - samples/sec: 10207.20 - lr: 0.000039 - momentum: 0.000000 2023-10-20 00:21:37,871 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:37,871 EPOCH 3 done: loss 0.4266 - lr: 0.000039 2023-10-20 00:21:38,629 DEV : loss 0.3016860783100128 - f1-score (micro avg) 0.1798 2023-10-20 00:21:38,633 saving best model 2023-10-20 00:21:38,664 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:39,141 epoch 4 - iter 27/272 - loss 0.39020834 - time (sec): 0.48 - samples/sec: 9628.52 - lr: 0.000038 - momentum: 0.000000 2023-10-20 00:21:39,583 epoch 4 - iter 54/272 - loss 0.38305660 - time (sec): 0.92 - samples/sec: 9183.83 - lr: 0.000038 - momentum: 0.000000 2023-10-20 00:21:40,088 epoch 4 - iter 81/272 - loss 0.38108401 - time (sec): 1.42 - samples/sec: 9963.30 - lr: 0.000037 - momentum: 0.000000 2023-10-20 00:21:40,568 epoch 4 - iter 108/272 - loss 0.37152231 - time (sec): 1.90 - samples/sec: 10128.14 - lr: 0.000037 - momentum: 0.000000 2023-10-20 00:21:41,090 epoch 4 - iter 135/272 - loss 0.37083389 - time (sec): 2.43 - samples/sec: 9998.37 - lr: 0.000036 - momentum: 0.000000 2023-10-20 00:21:41,640 epoch 4 - iter 162/272 - loss 0.37693631 - time (sec): 2.97 - samples/sec: 10410.48 - lr: 0.000036 - momentum: 0.000000 2023-10-20 00:21:42,164 epoch 4 - iter 189/272 - loss 0.37660175 - time (sec): 3.50 - samples/sec: 10495.63 - lr: 0.000035 - momentum: 0.000000 2023-10-20 00:21:42,659 epoch 4 - iter 216/272 - loss 0.38496790 - time (sec): 3.99 - samples/sec: 10395.82 - lr: 0.000034 - momentum: 0.000000 2023-10-20 00:21:43,184 epoch 4 - iter 243/272 - loss 0.38842763 - time (sec): 4.52 - samples/sec: 10340.72 - lr: 0.000034 - momentum: 0.000000 2023-10-20 00:21:43,684 epoch 4 - iter 270/272 - loss 0.38100025 - time (sec): 5.02 - samples/sec: 10307.69 - lr: 0.000033 - momentum: 0.000000 2023-10-20 00:21:43,717 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:43,717 EPOCH 4 done: loss 0.3806 - lr: 0.000033 2023-10-20 00:21:44,623 DEV : loss 0.28507402539253235 - f1-score (micro avg) 0.3513 2023-10-20 00:21:44,626 saving best model 2023-10-20 00:21:44,658 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:45,175 epoch 5 - iter 27/272 - loss 0.30924673 - time (sec): 0.52 - samples/sec: 10765.09 - lr: 0.000033 - momentum: 0.000000 2023-10-20 00:21:45,704 epoch 5 - iter 54/272 - loss 0.34869346 - time (sec): 1.04 - samples/sec: 9934.41 - lr: 0.000032 - momentum: 0.000000 2023-10-20 00:21:46,261 epoch 5 - iter 81/272 - loss 0.34272748 - time (sec): 1.60 - samples/sec: 9845.49 - lr: 0.000032 - momentum: 0.000000 2023-10-20 00:21:46,824 epoch 5 - iter 108/272 - loss 0.33624812 - time (sec): 2.16 - samples/sec: 9475.98 - lr: 0.000031 - momentum: 0.000000 2023-10-20 00:21:47,321 epoch 5 - iter 135/272 - loss 0.34768000 - time (sec): 2.66 - samples/sec: 9471.14 - lr: 0.000031 - momentum: 0.000000 2023-10-20 00:21:47,841 epoch 5 - iter 162/272 - loss 0.34735833 - time (sec): 3.18 - samples/sec: 9453.30 - lr: 0.000030 - momentum: 0.000000 2023-10-20 00:21:48,385 epoch 5 - iter 189/272 - loss 0.34992901 - time (sec): 3.73 - samples/sec: 9530.67 - lr: 0.000029 - momentum: 0.000000 2023-10-20 00:21:48,899 epoch 5 - iter 216/272 - loss 0.34923380 - time (sec): 4.24 - samples/sec: 9511.06 - lr: 0.000029 - momentum: 0.000000 2023-10-20 00:21:49,410 epoch 5 - iter 243/272 - loss 0.34680989 - time (sec): 4.75 - samples/sec: 9621.44 - lr: 0.000028 - momentum: 0.000000 2023-10-20 00:21:49,910 epoch 5 - iter 270/272 - loss 0.34720474 - time (sec): 5.25 - samples/sec: 9831.66 - lr: 0.000028 - momentum: 0.000000 2023-10-20 00:21:49,942 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:49,942 EPOCH 5 done: loss 0.3483 - lr: 0.000028 2023-10-20 00:21:50,740 DEV : loss 0.27170366048812866 - f1-score (micro avg) 0.4177 2023-10-20 00:21:50,744 saving best model 2023-10-20 00:21:50,777 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:51,258 epoch 6 - iter 27/272 - loss 0.34835965 - time (sec): 0.48 - samples/sec: 10640.77 - lr: 0.000027 - momentum: 0.000000 2023-10-20 00:21:51,754 epoch 6 - iter 54/272 - loss 0.35236544 - time (sec): 0.98 - samples/sec: 10347.26 - lr: 0.000027 - momentum: 0.000000 2023-10-20 00:21:52,225 epoch 6 - iter 81/272 - loss 0.34898421 - time (sec): 1.45 - samples/sec: 10363.93 - lr: 0.000026 - momentum: 0.000000 2023-10-20 00:21:52,743 epoch 6 - iter 108/272 - loss 0.34103544 - time (sec): 1.97 - samples/sec: 10239.48 - lr: 0.000026 - momentum: 0.000000 2023-10-20 00:21:53,267 epoch 6 - iter 135/272 - loss 0.34258782 - time (sec): 2.49 - samples/sec: 10292.90 - lr: 0.000025 - momentum: 0.000000 2023-10-20 00:21:53,748 epoch 6 - iter 162/272 - loss 0.34092986 - time (sec): 2.97 - samples/sec: 10268.06 - lr: 0.000024 - momentum: 0.000000 2023-10-20 00:21:54,282 epoch 6 - iter 189/272 - loss 0.33967518 - time (sec): 3.50 - samples/sec: 10554.34 - lr: 0.000024 - momentum: 0.000000 2023-10-20 00:21:54,766 epoch 6 - iter 216/272 - loss 0.34503779 - time (sec): 3.99 - samples/sec: 10493.61 - lr: 0.000023 - momentum: 0.000000 2023-10-20 00:21:55,274 epoch 6 - iter 243/272 - loss 0.33713653 - time (sec): 4.50 - samples/sec: 10472.18 - lr: 0.000023 - momentum: 0.000000 2023-10-20 00:21:55,750 epoch 6 - iter 270/272 - loss 0.33500603 - time (sec): 4.97 - samples/sec: 10390.02 - lr: 0.000022 - momentum: 0.000000 2023-10-20 00:21:55,782 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:55,783 EPOCH 6 done: loss 0.3345 - lr: 0.000022 2023-10-20 00:21:56,555 DEV : loss 0.2611343264579773 - f1-score (micro avg) 0.4743 2023-10-20 00:21:56,559 saving best model 2023-10-20 00:21:56,590 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:21:57,104 epoch 7 - iter 27/272 - loss 0.26414586 - time (sec): 0.51 - samples/sec: 10785.15 - lr: 0.000022 - momentum: 0.000000 2023-10-20 00:21:57,653 epoch 7 - iter 54/272 - loss 0.28507475 - time (sec): 1.06 - samples/sec: 10182.43 - lr: 0.000021 - momentum: 0.000000 2023-10-20 00:21:58,174 epoch 7 - iter 81/272 - loss 0.32465150 - time (sec): 1.58 - samples/sec: 10141.41 - lr: 0.000021 - momentum: 0.000000 2023-10-20 00:21:58,684 epoch 7 - iter 108/272 - loss 0.33301144 - time (sec): 2.09 - samples/sec: 9808.71 - lr: 0.000020 - momentum: 0.000000 2023-10-20 00:21:59,201 epoch 7 - iter 135/272 - loss 0.31522540 - time (sec): 2.61 - samples/sec: 9762.86 - lr: 0.000019 - momentum: 0.000000 2023-10-20 00:21:59,708 epoch 7 - iter 162/272 - loss 0.31244099 - time (sec): 3.12 - samples/sec: 9829.27 - lr: 0.000019 - momentum: 0.000000 2023-10-20 00:22:00,198 epoch 7 - iter 189/272 - loss 0.30460946 - time (sec): 3.61 - samples/sec: 9951.47 - lr: 0.000018 - momentum: 0.000000 2023-10-20 00:22:00,681 epoch 7 - iter 216/272 - loss 0.30823837 - time (sec): 4.09 - samples/sec: 9918.18 - lr: 0.000018 - momentum: 0.000000 2023-10-20 00:22:01,195 epoch 7 - iter 243/272 - loss 0.31442376 - time (sec): 4.60 - samples/sec: 10046.22 - lr: 0.000017 - momentum: 0.000000 2023-10-20 00:22:01,687 epoch 7 - iter 270/272 - loss 0.31608757 - time (sec): 5.10 - samples/sec: 10151.04 - lr: 0.000017 - momentum: 0.000000 2023-10-20 00:22:01,717 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:01,717 EPOCH 7 done: loss 0.3156 - lr: 0.000017 2023-10-20 00:22:02,477 DEV : loss 0.25722736120224 - f1-score (micro avg) 0.4912 2023-10-20 00:22:02,481 saving best model 2023-10-20 00:22:02,511 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:03,016 epoch 8 - iter 27/272 - loss 0.35861152 - time (sec): 0.50 - samples/sec: 9876.68 - lr: 0.000016 - momentum: 0.000000 2023-10-20 00:22:03,506 epoch 8 - iter 54/272 - loss 0.32562148 - time (sec): 0.99 - samples/sec: 10259.78 - lr: 0.000016 - momentum: 0.000000 2023-10-20 00:22:04,042 epoch 8 - iter 81/272 - loss 0.29992941 - time (sec): 1.53 - samples/sec: 10360.30 - lr: 0.000015 - momentum: 0.000000 2023-10-20 00:22:04,546 epoch 8 - iter 108/272 - loss 0.30456466 - time (sec): 2.03 - samples/sec: 10210.32 - lr: 0.000014 - momentum: 0.000000 2023-10-20 00:22:05,050 epoch 8 - iter 135/272 - loss 0.30766248 - time (sec): 2.54 - samples/sec: 10207.99 - lr: 0.000014 - momentum: 0.000000 2023-10-20 00:22:05,558 epoch 8 - iter 162/272 - loss 0.30300256 - time (sec): 3.05 - samples/sec: 10223.82 - lr: 0.000013 - momentum: 0.000000 2023-10-20 00:22:06,057 epoch 8 - iter 189/272 - loss 0.29664404 - time (sec): 3.55 - samples/sec: 10395.75 - lr: 0.000013 - momentum: 0.000000 2023-10-20 00:22:06,577 epoch 8 - iter 216/272 - loss 0.29539590 - time (sec): 4.07 - samples/sec: 10466.18 - lr: 0.000012 - momentum: 0.000000 2023-10-20 00:22:07,059 epoch 8 - iter 243/272 - loss 0.29947757 - time (sec): 4.55 - samples/sec: 10330.59 - lr: 0.000012 - momentum: 0.000000 2023-10-20 00:22:07,541 epoch 8 - iter 270/272 - loss 0.30317529 - time (sec): 5.03 - samples/sec: 10286.12 - lr: 0.000011 - momentum: 0.000000 2023-10-20 00:22:07,570 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:07,570 EPOCH 8 done: loss 0.3029 - lr: 0.000011 2023-10-20 00:22:08,345 DEV : loss 0.25111961364746094 - f1-score (micro avg) 0.5085 2023-10-20 00:22:08,348 saving best model 2023-10-20 00:22:08,384 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:08,889 epoch 9 - iter 27/272 - loss 0.29468874 - time (sec): 0.50 - samples/sec: 10627.07 - lr: 0.000011 - momentum: 0.000000 2023-10-20 00:22:09,377 epoch 9 - iter 54/272 - loss 0.28721000 - time (sec): 0.99 - samples/sec: 10287.41 - lr: 0.000010 - momentum: 0.000000 2023-10-20 00:22:09,867 epoch 9 - iter 81/272 - loss 0.30800265 - time (sec): 1.48 - samples/sec: 10078.94 - lr: 0.000009 - momentum: 0.000000 2023-10-20 00:22:10,363 epoch 9 - iter 108/272 - loss 0.30773883 - time (sec): 1.98 - samples/sec: 10143.35 - lr: 0.000009 - momentum: 0.000000 2023-10-20 00:22:10,880 epoch 9 - iter 135/272 - loss 0.30764331 - time (sec): 2.49 - samples/sec: 10622.48 - lr: 0.000008 - momentum: 0.000000 2023-10-20 00:22:11,333 epoch 9 - iter 162/272 - loss 0.30584889 - time (sec): 2.95 - samples/sec: 10761.15 - lr: 0.000008 - momentum: 0.000000 2023-10-20 00:22:11,816 epoch 9 - iter 189/272 - loss 0.30001539 - time (sec): 3.43 - samples/sec: 10584.33 - lr: 0.000007 - momentum: 0.000000 2023-10-20 00:22:12,318 epoch 9 - iter 216/272 - loss 0.29759046 - time (sec): 3.93 - samples/sec: 10478.54 - lr: 0.000007 - momentum: 0.000000 2023-10-20 00:22:12,847 epoch 9 - iter 243/272 - loss 0.29325136 - time (sec): 4.46 - samples/sec: 10481.70 - lr: 0.000006 - momentum: 0.000000 2023-10-20 00:22:13,356 epoch 9 - iter 270/272 - loss 0.29409257 - time (sec): 4.97 - samples/sec: 10419.18 - lr: 0.000006 - momentum: 0.000000 2023-10-20 00:22:13,385 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:13,385 EPOCH 9 done: loss 0.2944 - lr: 0.000006 2023-10-20 00:22:14,303 DEV : loss 0.24987336993217468 - f1-score (micro avg) 0.5047 2023-10-20 00:22:14,307 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:14,773 epoch 10 - iter 27/272 - loss 0.32141785 - time (sec): 0.47 - samples/sec: 10482.29 - lr: 0.000005 - momentum: 0.000000 2023-10-20 00:22:15,272 epoch 10 - iter 54/272 - loss 0.31702834 - time (sec): 0.96 - samples/sec: 10922.56 - lr: 0.000004 - momentum: 0.000000 2023-10-20 00:22:15,739 epoch 10 - iter 81/272 - loss 0.29843000 - time (sec): 1.43 - samples/sec: 10748.54 - lr: 0.000004 - momentum: 0.000000 2023-10-20 00:22:16,241 epoch 10 - iter 108/272 - loss 0.29486713 - time (sec): 1.93 - samples/sec: 10407.84 - lr: 0.000003 - momentum: 0.000000 2023-10-20 00:22:16,724 epoch 10 - iter 135/272 - loss 0.30815187 - time (sec): 2.42 - samples/sec: 10305.36 - lr: 0.000003 - momentum: 0.000000 2023-10-20 00:22:17,232 epoch 10 - iter 162/272 - loss 0.30545146 - time (sec): 2.92 - samples/sec: 10301.34 - lr: 0.000002 - momentum: 0.000000 2023-10-20 00:22:17,717 epoch 10 - iter 189/272 - loss 0.29883950 - time (sec): 3.41 - samples/sec: 10355.45 - lr: 0.000002 - momentum: 0.000000 2023-10-20 00:22:18,228 epoch 10 - iter 216/272 - loss 0.29494759 - time (sec): 3.92 - samples/sec: 10502.29 - lr: 0.000001 - momentum: 0.000000 2023-10-20 00:22:18,754 epoch 10 - iter 243/272 - loss 0.28921084 - time (sec): 4.45 - samples/sec: 10547.46 - lr: 0.000001 - momentum: 0.000000 2023-10-20 00:22:19,264 epoch 10 - iter 270/272 - loss 0.28845308 - time (sec): 4.96 - samples/sec: 10461.24 - lr: 0.000000 - momentum: 0.000000 2023-10-20 00:22:19,292 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:19,292 EPOCH 10 done: loss 0.2903 - lr: 0.000000 2023-10-20 00:22:20,053 DEV : loss 0.2502773106098175 - f1-score (micro avg) 0.4971 2023-10-20 00:22:20,083 ---------------------------------------------------------------------------------------------------- 2023-10-20 00:22:20,083 Loading model from best epoch ... 2023-10-20 00:22:20,162 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG 2023-10-20 00:22:20,978 Results: - F-score (micro) 0.3892 - F-score (macro) 0.199 - Accuracy 0.2555 By class: precision recall f1-score support LOC 0.4795 0.5609 0.5170 312 PER 0.2359 0.3413 0.2790 208 ORG 0.0000 0.0000 0.0000 55 HumanProd 0.0000 0.0000 0.0000 22 micro avg 0.3688 0.4121 0.3892 597 macro avg 0.1788 0.2256 0.1990 597 weighted avg 0.3328 0.4121 0.3674 597 2023-10-20 00:22:20,979 ----------------------------------------------------------------------------------------------------