| 2023-10-14 08:15:18,968 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (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): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (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): BertSelfOutput( | |
| (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): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Train: 5777 sentences | |
| 2023-10-14 08:15:18,969 (train_with_dev=False, train_with_test=False) | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Training Params: | |
| 2023-10-14 08:15:18,969 - learning_rate: "5e-05" | |
| 2023-10-14 08:15:18,969 - mini_batch_size: "4" | |
| 2023-10-14 08:15:18,969 - max_epochs: "10" | |
| 2023-10-14 08:15:18,969 - shuffle: "True" | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Plugins: | |
| 2023-10-14 08:15:18,969 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-14 08:15:18,969 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Computation: | |
| 2023-10-14 08:15:18,969 - compute on device: cuda:0 | |
| 2023-10-14 08:15:18,969 - embedding storage: none | |
| 2023-10-14 08:15:18,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,969 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-14 08:15:18,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:18,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:15:26,251 epoch 1 - iter 144/1445 - loss 1.64823894 - time (sec): 7.28 - samples/sec: 2327.55 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-14 08:15:33,424 epoch 1 - iter 288/1445 - loss 0.94267315 - time (sec): 14.45 - samples/sec: 2337.84 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-14 08:15:40,844 epoch 1 - iter 432/1445 - loss 0.67856790 - time (sec): 21.87 - samples/sec: 2388.14 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-14 08:15:48,104 epoch 1 - iter 576/1445 - loss 0.55406917 - time (sec): 29.13 - samples/sec: 2397.44 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-14 08:15:55,240 epoch 1 - iter 720/1445 - loss 0.47981540 - time (sec): 36.27 - samples/sec: 2391.61 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-14 08:16:02,180 epoch 1 - iter 864/1445 - loss 0.43508566 - time (sec): 43.21 - samples/sec: 2365.86 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-14 08:16:09,469 epoch 1 - iter 1008/1445 - loss 0.39439415 - time (sec): 50.50 - samples/sec: 2392.47 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-14 08:16:16,914 epoch 1 - iter 1152/1445 - loss 0.36462348 - time (sec): 57.94 - samples/sec: 2396.36 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-14 08:16:24,794 epoch 1 - iter 1296/1445 - loss 0.34134840 - time (sec): 65.82 - samples/sec: 2383.68 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-14 08:16:32,940 epoch 1 - iter 1440/1445 - loss 0.31936100 - time (sec): 73.97 - samples/sec: 2373.43 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-14 08:16:33,232 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:16:33,232 EPOCH 1 done: loss 0.3185 - lr: 0.000050 | |
| 2023-10-14 08:16:36,699 DEV : loss 0.14940427243709564 - f1-score (micro avg) 0.5985 | |
| 2023-10-14 08:16:36,717 saving best model | |
| 2023-10-14 08:16:37,103 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:16:44,662 epoch 2 - iter 144/1445 - loss 0.12942045 - time (sec): 7.56 - samples/sec: 2297.91 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-14 08:16:52,560 epoch 2 - iter 288/1445 - loss 0.12243824 - time (sec): 15.45 - samples/sec: 2227.86 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-14 08:16:59,832 epoch 2 - iter 432/1445 - loss 0.12297936 - time (sec): 22.73 - samples/sec: 2291.85 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-14 08:17:06,999 epoch 2 - iter 576/1445 - loss 0.11660000 - time (sec): 29.89 - samples/sec: 2318.21 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-14 08:17:14,567 epoch 2 - iter 720/1445 - loss 0.11717628 - time (sec): 37.46 - samples/sec: 2340.11 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-14 08:17:21,760 epoch 2 - iter 864/1445 - loss 0.11504791 - time (sec): 44.65 - samples/sec: 2345.59 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-14 08:17:29,231 epoch 2 - iter 1008/1445 - loss 0.11715840 - time (sec): 52.13 - samples/sec: 2354.63 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-14 08:17:36,191 epoch 2 - iter 1152/1445 - loss 0.11408128 - time (sec): 59.09 - samples/sec: 2346.22 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-14 08:17:43,759 epoch 2 - iter 1296/1445 - loss 0.11282938 - time (sec): 66.65 - samples/sec: 2367.71 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-14 08:17:51,144 epoch 2 - iter 1440/1445 - loss 0.11126139 - time (sec): 74.04 - samples/sec: 2372.49 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-14 08:17:51,422 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:17:51,422 EPOCH 2 done: loss 0.1111 - lr: 0.000044 | |
| 2023-10-14 08:17:54,946 DEV : loss 0.13982899487018585 - f1-score (micro avg) 0.6855 | |
| 2023-10-14 08:17:54,961 saving best model | |
| 2023-10-14 08:17:55,492 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:18:03,092 epoch 3 - iter 144/1445 - loss 0.07642927 - time (sec): 7.60 - samples/sec: 2331.85 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-14 08:18:10,587 epoch 3 - iter 288/1445 - loss 0.07342995 - time (sec): 15.09 - samples/sec: 2356.25 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-14 08:18:17,841 epoch 3 - iter 432/1445 - loss 0.07324502 - time (sec): 22.35 - samples/sec: 2380.66 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-14 08:18:25,239 epoch 3 - iter 576/1445 - loss 0.07198888 - time (sec): 29.75 - samples/sec: 2381.02 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-14 08:18:32,571 epoch 3 - iter 720/1445 - loss 0.07329604 - time (sec): 37.08 - samples/sec: 2387.91 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-14 08:18:39,580 epoch 3 - iter 864/1445 - loss 0.07223058 - time (sec): 44.09 - samples/sec: 2406.77 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-14 08:18:47,122 epoch 3 - iter 1008/1445 - loss 0.07418564 - time (sec): 51.63 - samples/sec: 2382.83 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-14 08:18:54,438 epoch 3 - iter 1152/1445 - loss 0.07370676 - time (sec): 58.94 - samples/sec: 2396.16 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-14 08:19:01,641 epoch 3 - iter 1296/1445 - loss 0.07403015 - time (sec): 66.15 - samples/sec: 2402.18 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-14 08:19:09,044 epoch 3 - iter 1440/1445 - loss 0.07386810 - time (sec): 73.55 - samples/sec: 2390.08 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-14 08:19:09,261 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:19:09,261 EPOCH 3 done: loss 0.0739 - lr: 0.000039 | |
| 2023-10-14 08:19:13,617 DEV : loss 0.11367038637399673 - f1-score (micro avg) 0.7623 | |
| 2023-10-14 08:19:13,642 saving best model | |
| 2023-10-14 08:19:14,163 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:19:21,776 epoch 4 - iter 144/1445 - loss 0.04581362 - time (sec): 7.61 - samples/sec: 2370.16 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-14 08:19:29,103 epoch 4 - iter 288/1445 - loss 0.04337311 - time (sec): 14.94 - samples/sec: 2450.96 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-14 08:19:36,314 epoch 4 - iter 432/1445 - loss 0.04860217 - time (sec): 22.15 - samples/sec: 2401.90 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-14 08:19:43,653 epoch 4 - iter 576/1445 - loss 0.04972909 - time (sec): 29.49 - samples/sec: 2417.58 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-14 08:19:50,773 epoch 4 - iter 720/1445 - loss 0.05476643 - time (sec): 36.61 - samples/sec: 2420.98 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-14 08:19:57,817 epoch 4 - iter 864/1445 - loss 0.05460145 - time (sec): 43.65 - samples/sec: 2411.04 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-14 08:20:04,856 epoch 4 - iter 1008/1445 - loss 0.05255163 - time (sec): 50.69 - samples/sec: 2405.89 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-14 08:20:12,336 epoch 4 - iter 1152/1445 - loss 0.05337710 - time (sec): 58.17 - samples/sec: 2415.11 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-14 08:20:19,753 epoch 4 - iter 1296/1445 - loss 0.05469107 - time (sec): 65.59 - samples/sec: 2398.02 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-14 08:20:27,109 epoch 4 - iter 1440/1445 - loss 0.05505521 - time (sec): 72.94 - samples/sec: 2409.15 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-14 08:20:27,343 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:20:27,343 EPOCH 4 done: loss 0.0558 - lr: 0.000033 | |
| 2023-10-14 08:20:30,916 DEV : loss 0.12969306111335754 - f1-score (micro avg) 0.7744 | |
| 2023-10-14 08:20:30,940 saving best model | |
| 2023-10-14 08:20:31,444 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:20:39,113 epoch 5 - iter 144/1445 - loss 0.04612436 - time (sec): 7.67 - samples/sec: 2315.46 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-14 08:20:46,441 epoch 5 - iter 288/1445 - loss 0.04420133 - time (sec): 14.99 - samples/sec: 2374.89 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-14 08:20:53,540 epoch 5 - iter 432/1445 - loss 0.04018260 - time (sec): 22.09 - samples/sec: 2375.54 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-14 08:21:00,700 epoch 5 - iter 576/1445 - loss 0.04133613 - time (sec): 29.25 - samples/sec: 2390.64 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-14 08:21:08,009 epoch 5 - iter 720/1445 - loss 0.04029888 - time (sec): 36.56 - samples/sec: 2397.70 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-14 08:21:15,905 epoch 5 - iter 864/1445 - loss 0.03888505 - time (sec): 44.46 - samples/sec: 2381.62 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-14 08:21:22,792 epoch 5 - iter 1008/1445 - loss 0.03857434 - time (sec): 51.34 - samples/sec: 2390.28 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-14 08:21:30,009 epoch 5 - iter 1152/1445 - loss 0.03791905 - time (sec): 58.56 - samples/sec: 2400.71 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-14 08:21:37,524 epoch 5 - iter 1296/1445 - loss 0.03924086 - time (sec): 66.08 - samples/sec: 2398.78 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-14 08:21:44,508 epoch 5 - iter 1440/1445 - loss 0.03949965 - time (sec): 73.06 - samples/sec: 2402.13 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-14 08:21:44,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:21:44,805 EPOCH 5 done: loss 0.0394 - lr: 0.000028 | |
| 2023-10-14 08:21:48,276 DEV : loss 0.21078866720199585 - f1-score (micro avg) 0.7504 | |
| 2023-10-14 08:21:48,291 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:21:55,561 epoch 6 - iter 144/1445 - loss 0.03043142 - time (sec): 7.27 - samples/sec: 2473.28 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-14 08:22:03,148 epoch 6 - iter 288/1445 - loss 0.02495404 - time (sec): 14.86 - samples/sec: 2433.69 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-14 08:22:10,421 epoch 6 - iter 432/1445 - loss 0.02660960 - time (sec): 22.13 - samples/sec: 2439.55 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-14 08:22:18,087 epoch 6 - iter 576/1445 - loss 0.02912055 - time (sec): 29.79 - samples/sec: 2412.69 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-14 08:22:25,105 epoch 6 - iter 720/1445 - loss 0.02608450 - time (sec): 36.81 - samples/sec: 2407.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-14 08:22:32,477 epoch 6 - iter 864/1445 - loss 0.02559760 - time (sec): 44.19 - samples/sec: 2390.04 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-14 08:22:39,837 epoch 6 - iter 1008/1445 - loss 0.02922170 - time (sec): 51.54 - samples/sec: 2393.10 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-14 08:22:47,278 epoch 6 - iter 1152/1445 - loss 0.03029099 - time (sec): 58.99 - samples/sec: 2401.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-14 08:22:54,411 epoch 6 - iter 1296/1445 - loss 0.03010830 - time (sec): 66.12 - samples/sec: 2394.91 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-14 08:23:01,494 epoch 6 - iter 1440/1445 - loss 0.03033135 - time (sec): 73.20 - samples/sec: 2399.89 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-14 08:23:01,741 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:23:01,741 EPOCH 6 done: loss 0.0304 - lr: 0.000022 | |
| 2023-10-14 08:23:05,565 DEV : loss 0.24649791419506073 - f1-score (micro avg) 0.7402 | |
| 2023-10-14 08:23:05,580 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:23:12,971 epoch 7 - iter 144/1445 - loss 0.01657038 - time (sec): 7.39 - samples/sec: 2355.54 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-14 08:23:20,172 epoch 7 - iter 288/1445 - loss 0.02025614 - time (sec): 14.59 - samples/sec: 2339.42 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-14 08:23:27,560 epoch 7 - iter 432/1445 - loss 0.02071666 - time (sec): 21.98 - samples/sec: 2387.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-14 08:23:34,837 epoch 7 - iter 576/1445 - loss 0.02132575 - time (sec): 29.26 - samples/sec: 2410.09 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-14 08:23:42,121 epoch 7 - iter 720/1445 - loss 0.02120114 - time (sec): 36.54 - samples/sec: 2408.82 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-14 08:23:49,772 epoch 7 - iter 864/1445 - loss 0.02176288 - time (sec): 44.19 - samples/sec: 2409.67 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-14 08:23:56,878 epoch 7 - iter 1008/1445 - loss 0.02230750 - time (sec): 51.30 - samples/sec: 2402.09 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-14 08:24:04,185 epoch 7 - iter 1152/1445 - loss 0.02201668 - time (sec): 58.60 - samples/sec: 2413.44 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-14 08:24:11,294 epoch 7 - iter 1296/1445 - loss 0.02270576 - time (sec): 65.71 - samples/sec: 2404.77 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-14 08:24:18,460 epoch 7 - iter 1440/1445 - loss 0.02316075 - time (sec): 72.88 - samples/sec: 2410.80 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-14 08:24:18,691 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:24:18,692 EPOCH 7 done: loss 0.0232 - lr: 0.000017 | |
| 2023-10-14 08:24:22,285 DEV : loss 0.18435220420360565 - f1-score (micro avg) 0.8055 | |
| 2023-10-14 08:24:22,305 saving best model | |
| 2023-10-14 08:24:22,836 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:24:30,556 epoch 8 - iter 144/1445 - loss 0.01173685 - time (sec): 7.72 - samples/sec: 2259.84 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-14 08:24:38,092 epoch 8 - iter 288/1445 - loss 0.01201500 - time (sec): 15.25 - samples/sec: 2313.14 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-14 08:24:45,557 epoch 8 - iter 432/1445 - loss 0.01104701 - time (sec): 22.72 - samples/sec: 2329.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-14 08:24:53,317 epoch 8 - iter 576/1445 - loss 0.01394833 - time (sec): 30.48 - samples/sec: 2302.53 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-14 08:25:00,792 epoch 8 - iter 720/1445 - loss 0.01349697 - time (sec): 37.95 - samples/sec: 2347.18 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-14 08:25:07,946 epoch 8 - iter 864/1445 - loss 0.01327706 - time (sec): 45.11 - samples/sec: 2347.90 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-14 08:25:15,059 epoch 8 - iter 1008/1445 - loss 0.01560794 - time (sec): 52.22 - samples/sec: 2365.91 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-14 08:25:22,151 epoch 8 - iter 1152/1445 - loss 0.01577549 - time (sec): 59.31 - samples/sec: 2362.24 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-14 08:25:29,734 epoch 8 - iter 1296/1445 - loss 0.01538313 - time (sec): 66.90 - samples/sec: 2368.49 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-14 08:25:36,951 epoch 8 - iter 1440/1445 - loss 0.01529247 - time (sec): 74.11 - samples/sec: 2372.81 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-14 08:25:37,177 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:25:37,177 EPOCH 8 done: loss 0.0153 - lr: 0.000011 | |
| 2023-10-14 08:25:40,654 DEV : loss 0.21136066317558289 - f1-score (micro avg) 0.7935 | |
| 2023-10-14 08:25:40,669 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:25:48,159 epoch 9 - iter 144/1445 - loss 0.01001014 - time (sec): 7.49 - samples/sec: 2434.15 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-14 08:25:55,953 epoch 9 - iter 288/1445 - loss 0.01043171 - time (sec): 15.28 - samples/sec: 2405.81 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-14 08:26:03,628 epoch 9 - iter 432/1445 - loss 0.00854045 - time (sec): 22.96 - samples/sec: 2436.37 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-14 08:26:10,997 epoch 9 - iter 576/1445 - loss 0.00869129 - time (sec): 30.33 - samples/sec: 2378.55 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-14 08:26:18,488 epoch 9 - iter 720/1445 - loss 0.00926320 - time (sec): 37.82 - samples/sec: 2401.19 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-14 08:26:25,414 epoch 9 - iter 864/1445 - loss 0.00890667 - time (sec): 44.74 - samples/sec: 2393.98 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-14 08:26:32,785 epoch 9 - iter 1008/1445 - loss 0.00902072 - time (sec): 52.12 - samples/sec: 2381.96 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-14 08:26:40,012 epoch 9 - iter 1152/1445 - loss 0.00935748 - time (sec): 59.34 - samples/sec: 2361.68 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-14 08:26:47,327 epoch 9 - iter 1296/1445 - loss 0.00932214 - time (sec): 66.66 - samples/sec: 2362.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-14 08:26:54,741 epoch 9 - iter 1440/1445 - loss 0.00919275 - time (sec): 74.07 - samples/sec: 2371.68 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-14 08:26:54,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:26:54,970 EPOCH 9 done: loss 0.0094 - lr: 0.000006 | |
| 2023-10-14 08:26:58,830 DEV : loss 0.20292457938194275 - f1-score (micro avg) 0.8054 | |
| 2023-10-14 08:26:58,845 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:27:06,259 epoch 10 - iter 144/1445 - loss 0.00347635 - time (sec): 7.41 - samples/sec: 2478.68 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-14 08:27:13,129 epoch 10 - iter 288/1445 - loss 0.00368842 - time (sec): 14.28 - samples/sec: 2428.24 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-14 08:27:20,581 epoch 10 - iter 432/1445 - loss 0.00658264 - time (sec): 21.73 - samples/sec: 2422.22 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-14 08:27:27,940 epoch 10 - iter 576/1445 - loss 0.00628559 - time (sec): 29.09 - samples/sec: 2437.35 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-14 08:27:34,939 epoch 10 - iter 720/1445 - loss 0.00657734 - time (sec): 36.09 - samples/sec: 2433.97 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-14 08:27:42,516 epoch 10 - iter 864/1445 - loss 0.00684358 - time (sec): 43.67 - samples/sec: 2452.32 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-14 08:27:49,636 epoch 10 - iter 1008/1445 - loss 0.00708911 - time (sec): 50.79 - samples/sec: 2443.68 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-14 08:27:56,748 epoch 10 - iter 1152/1445 - loss 0.00717665 - time (sec): 57.90 - samples/sec: 2437.61 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-14 08:28:03,759 epoch 10 - iter 1296/1445 - loss 0.00674554 - time (sec): 64.91 - samples/sec: 2431.08 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-14 08:28:11,172 epoch 10 - iter 1440/1445 - loss 0.00645507 - time (sec): 72.33 - samples/sec: 2431.56 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-14 08:28:11,392 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:28:11,392 EPOCH 10 done: loss 0.0065 - lr: 0.000000 | |
| 2023-10-14 08:28:14,844 DEV : loss 0.22300778329372406 - f1-score (micro avg) 0.7971 | |
| 2023-10-14 08:28:15,247 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-14 08:28:15,248 Loading model from best epoch ... | |
| 2023-10-14 08:28:16,910 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG | |
| 2023-10-14 08:28:20,000 | |
| Results: | |
| - F-score (micro) 0.7811 | |
| - F-score (macro) 0.6709 | |
| - Accuracy 0.6559 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8044 0.7510 0.7768 482 | |
| LOC 0.8859 0.7969 0.8391 458 | |
| ORG 0.4615 0.3478 0.3967 69 | |
| micro avg 0.8217 0.7443 0.7811 1009 | |
| macro avg 0.7173 0.6319 0.6709 1009 | |
| weighted avg 0.8180 0.7443 0.7791 1009 | |
| 2023-10-14 08:28:20,000 ---------------------------------------------------------------------------------------------------- | |