| 2023-10-25 12:40:33,726 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,727 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 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() | |
| )" | |
| 2023-10-25 12:40:33,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,727 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 | |
| 2023-10-25 12:40:33,727 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,727 Train: 6183 sentences | |
| 2023-10-25 12:40:33,727 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Training Params: | |
| 2023-10-25 12:40:33,728 - learning_rate: "5e-05" | |
| 2023-10-25 12:40:33,728 - mini_batch_size: "4" | |
| 2023-10-25 12:40:33,728 - max_epochs: "10" | |
| 2023-10-25 12:40:33,728 - shuffle: "True" | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Plugins: | |
| 2023-10-25 12:40:33,728 - TensorboardLogger | |
| 2023-10-25 12:40:33,728 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 12:40:33,728 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Computation: | |
| 2023-10-25 12:40:33,728 - compute on device: cuda:0 | |
| 2023-10-25 12:40:33,728 - embedding storage: none | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:40:33,728 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 12:40:41,659 epoch 1 - iter 154/1546 - loss 1.41726304 - time (sec): 7.93 - samples/sec: 1652.31 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:40:49,709 epoch 1 - iter 308/1546 - loss 0.78334605 - time (sec): 15.98 - samples/sec: 1632.85 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:40:58,044 epoch 1 - iter 462/1546 - loss 0.58383305 - time (sec): 24.31 - samples/sec: 1572.77 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:41:05,930 epoch 1 - iter 616/1546 - loss 0.47426674 - time (sec): 32.20 - samples/sec: 1564.88 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:41:13,808 epoch 1 - iter 770/1546 - loss 0.40661295 - time (sec): 40.08 - samples/sec: 1566.87 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:41:21,441 epoch 1 - iter 924/1546 - loss 0.35815982 - time (sec): 47.71 - samples/sec: 1583.24 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 12:41:29,436 epoch 1 - iter 1078/1546 - loss 0.32375290 - time (sec): 55.71 - samples/sec: 1570.35 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 12:41:37,652 epoch 1 - iter 1232/1546 - loss 0.30016932 - time (sec): 63.92 - samples/sec: 1562.58 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 12:41:45,684 epoch 1 - iter 1386/1546 - loss 0.27957019 - time (sec): 71.95 - samples/sec: 1563.58 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 12:41:53,622 epoch 1 - iter 1540/1546 - loss 0.26437156 - time (sec): 79.89 - samples/sec: 1548.48 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 12:41:53,930 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:41:53,930 EPOCH 1 done: loss 0.2633 - lr: 0.000050 | |
| 2023-10-25 12:41:57,098 DEV : loss 0.07664565742015839 - f1-score (micro avg) 0.7329 | |
| 2023-10-25 12:41:57,116 saving best model | |
| 2023-10-25 12:41:57,571 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:42:05,164 epoch 2 - iter 154/1546 - loss 0.06280439 - time (sec): 7.59 - samples/sec: 1668.51 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 12:42:12,515 epoch 2 - iter 308/1546 - loss 0.07962043 - time (sec): 14.94 - samples/sec: 1723.57 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 12:42:19,928 epoch 2 - iter 462/1546 - loss 0.08081910 - time (sec): 22.36 - samples/sec: 1730.83 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 12:42:27,841 epoch 2 - iter 616/1546 - loss 0.08370390 - time (sec): 30.27 - samples/sec: 1716.24 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 12:42:35,428 epoch 2 - iter 770/1546 - loss 0.08792655 - time (sec): 37.86 - samples/sec: 1712.89 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 12:42:42,721 epoch 2 - iter 924/1546 - loss 0.08666310 - time (sec): 45.15 - samples/sec: 1698.76 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 12:42:50,788 epoch 2 - iter 1078/1546 - loss 0.08958166 - time (sec): 53.22 - samples/sec: 1664.65 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 12:42:58,616 epoch 2 - iter 1232/1546 - loss 0.08995491 - time (sec): 61.04 - samples/sec: 1633.63 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 12:43:06,266 epoch 2 - iter 1386/1546 - loss 0.09019840 - time (sec): 68.69 - samples/sec: 1620.18 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 12:43:13,908 epoch 2 - iter 1540/1546 - loss 0.09065734 - time (sec): 76.34 - samples/sec: 1623.53 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 12:43:14,190 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:43:14,190 EPOCH 2 done: loss 0.0905 - lr: 0.000044 | |
| 2023-10-25 12:43:16,711 DEV : loss 0.07949517667293549 - f1-score (micro avg) 0.7439 | |
| 2023-10-25 12:43:16,730 saving best model | |
| 2023-10-25 12:43:17,431 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:43:26,061 epoch 3 - iter 154/1546 - loss 0.05179077 - time (sec): 8.63 - samples/sec: 1378.43 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 12:43:33,982 epoch 3 - iter 308/1546 - loss 0.05873358 - time (sec): 16.55 - samples/sec: 1464.51 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 12:43:42,049 epoch 3 - iter 462/1546 - loss 0.05944140 - time (sec): 24.61 - samples/sec: 1479.22 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 12:43:50,025 epoch 3 - iter 616/1546 - loss 0.06278050 - time (sec): 32.59 - samples/sec: 1494.09 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 12:43:57,987 epoch 3 - iter 770/1546 - loss 0.06202629 - time (sec): 40.55 - samples/sec: 1494.49 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 12:44:06,002 epoch 3 - iter 924/1546 - loss 0.06475875 - time (sec): 48.57 - samples/sec: 1498.45 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 12:44:13,872 epoch 3 - iter 1078/1546 - loss 0.06354585 - time (sec): 56.44 - samples/sec: 1521.73 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 12:44:22,345 epoch 3 - iter 1232/1546 - loss 0.06184665 - time (sec): 64.91 - samples/sec: 1523.40 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 12:44:30,443 epoch 3 - iter 1386/1546 - loss 0.06209963 - time (sec): 73.01 - samples/sec: 1525.47 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 12:44:38,583 epoch 3 - iter 1540/1546 - loss 0.06163890 - time (sec): 81.15 - samples/sec: 1527.46 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 12:44:38,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:44:38,892 EPOCH 3 done: loss 0.0619 - lr: 0.000039 | |
| 2023-10-25 12:44:42,300 DEV : loss 0.06922859698534012 - f1-score (micro avg) 0.7605 | |
| 2023-10-25 12:44:42,320 saving best model | |
| 2023-10-25 12:44:42,947 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:44:50,918 epoch 4 - iter 154/1546 - loss 0.03901013 - time (sec): 7.97 - samples/sec: 1458.55 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 12:44:58,730 epoch 4 - iter 308/1546 - loss 0.04210096 - time (sec): 15.78 - samples/sec: 1534.67 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 12:45:06,744 epoch 4 - iter 462/1546 - loss 0.04262299 - time (sec): 23.80 - samples/sec: 1551.79 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 12:45:14,945 epoch 4 - iter 616/1546 - loss 0.04434207 - time (sec): 32.00 - samples/sec: 1518.38 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 12:45:23,123 epoch 4 - iter 770/1546 - loss 0.04327156 - time (sec): 40.17 - samples/sec: 1550.14 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 12:45:31,075 epoch 4 - iter 924/1546 - loss 0.04301827 - time (sec): 48.13 - samples/sec: 1545.62 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 12:45:39,265 epoch 4 - iter 1078/1546 - loss 0.04296863 - time (sec): 56.32 - samples/sec: 1544.71 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 12:45:47,542 epoch 4 - iter 1232/1546 - loss 0.04360122 - time (sec): 64.59 - samples/sec: 1516.42 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 12:45:55,696 epoch 4 - iter 1386/1546 - loss 0.04594982 - time (sec): 72.75 - samples/sec: 1526.09 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 12:46:03,770 epoch 4 - iter 1540/1546 - loss 0.04464139 - time (sec): 80.82 - samples/sec: 1530.08 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 12:46:04,132 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:46:04,133 EPOCH 4 done: loss 0.0447 - lr: 0.000033 | |
| 2023-10-25 12:46:06,598 DEV : loss 0.08324291557073593 - f1-score (micro avg) 0.7572 | |
| 2023-10-25 12:46:06,620 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:46:14,840 epoch 5 - iter 154/1546 - loss 0.02370652 - time (sec): 8.22 - samples/sec: 1553.02 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 12:46:22,953 epoch 5 - iter 308/1546 - loss 0.02057646 - time (sec): 16.33 - samples/sec: 1521.52 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 12:46:30,985 epoch 5 - iter 462/1546 - loss 0.01995930 - time (sec): 24.36 - samples/sec: 1517.64 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 12:46:39,147 epoch 5 - iter 616/1546 - loss 0.02370079 - time (sec): 32.53 - samples/sec: 1509.21 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 12:46:47,557 epoch 5 - iter 770/1546 - loss 0.02544545 - time (sec): 40.94 - samples/sec: 1507.31 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 12:46:56,039 epoch 5 - iter 924/1546 - loss 0.02732097 - time (sec): 49.42 - samples/sec: 1497.50 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 12:47:04,102 epoch 5 - iter 1078/1546 - loss 0.02830158 - time (sec): 57.48 - samples/sec: 1497.89 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:47:12,547 epoch 5 - iter 1232/1546 - loss 0.02941163 - time (sec): 65.93 - samples/sec: 1508.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 12:47:20,778 epoch 5 - iter 1386/1546 - loss 0.02936715 - time (sec): 74.16 - samples/sec: 1503.19 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:47:28,977 epoch 5 - iter 1540/1546 - loss 0.03188707 - time (sec): 82.36 - samples/sec: 1503.28 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 12:47:29,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:47:29,304 EPOCH 5 done: loss 0.0321 - lr: 0.000028 | |
| 2023-10-25 12:47:32,118 DEV : loss 0.11679282784461975 - f1-score (micro avg) 0.7362 | |
| 2023-10-25 12:47:32,137 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:47:40,246 epoch 6 - iter 154/1546 - loss 0.02165720 - time (sec): 8.11 - samples/sec: 1457.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:47:48,524 epoch 6 - iter 308/1546 - loss 0.02589341 - time (sec): 16.39 - samples/sec: 1494.16 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 12:47:56,637 epoch 6 - iter 462/1546 - loss 0.02456636 - time (sec): 24.50 - samples/sec: 1468.29 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:48:04,869 epoch 6 - iter 616/1546 - loss 0.02336449 - time (sec): 32.73 - samples/sec: 1460.83 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 12:48:13,102 epoch 6 - iter 770/1546 - loss 0.02270073 - time (sec): 40.96 - samples/sec: 1460.80 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 12:48:21,261 epoch 6 - iter 924/1546 - loss 0.02439712 - time (sec): 49.12 - samples/sec: 1477.04 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:48:29,560 epoch 6 - iter 1078/1546 - loss 0.02688108 - time (sec): 57.42 - samples/sec: 1495.60 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 12:48:37,816 epoch 6 - iter 1232/1546 - loss 0.02608661 - time (sec): 65.68 - samples/sec: 1502.81 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:48:45,940 epoch 6 - iter 1386/1546 - loss 0.02528345 - time (sec): 73.80 - samples/sec: 1511.06 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 12:48:54,010 epoch 6 - iter 1540/1546 - loss 0.02427085 - time (sec): 81.87 - samples/sec: 1510.37 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:48:54,356 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:48:54,356 EPOCH 6 done: loss 0.0241 - lr: 0.000022 | |
| 2023-10-25 12:48:57,423 DEV : loss 0.11628815531730652 - f1-score (micro avg) 0.7474 | |
| 2023-10-25 12:48:57,441 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:49:05,508 epoch 7 - iter 154/1546 - loss 0.01078099 - time (sec): 8.06 - samples/sec: 1568.16 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 12:49:13,525 epoch 7 - iter 308/1546 - loss 0.01560119 - time (sec): 16.08 - samples/sec: 1610.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:49:21,592 epoch 7 - iter 462/1546 - loss 0.01478570 - time (sec): 24.15 - samples/sec: 1583.42 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 12:49:29,721 epoch 7 - iter 616/1546 - loss 0.01384593 - time (sec): 32.28 - samples/sec: 1549.49 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 12:49:37,688 epoch 7 - iter 770/1546 - loss 0.01564758 - time (sec): 40.25 - samples/sec: 1547.58 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:49:45,706 epoch 7 - iter 924/1546 - loss 0.01731275 - time (sec): 48.26 - samples/sec: 1532.87 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 12:49:53,807 epoch 7 - iter 1078/1546 - loss 0.01694404 - time (sec): 56.36 - samples/sec: 1520.53 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:50:02,028 epoch 7 - iter 1232/1546 - loss 0.01827001 - time (sec): 64.59 - samples/sec: 1526.68 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 12:50:10,564 epoch 7 - iter 1386/1546 - loss 0.01841535 - time (sec): 73.12 - samples/sec: 1527.64 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:50:18,895 epoch 7 - iter 1540/1546 - loss 0.01841532 - time (sec): 81.45 - samples/sec: 1521.31 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 12:50:19,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:50:19,209 EPOCH 7 done: loss 0.0184 - lr: 0.000017 | |
| 2023-10-25 12:50:21,920 DEV : loss 0.12390953302383423 - f1-score (micro avg) 0.741 | |
| 2023-10-25 12:50:21,936 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:50:30,220 epoch 8 - iter 154/1546 - loss 0.00883747 - time (sec): 8.28 - samples/sec: 1467.83 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:50:38,638 epoch 8 - iter 308/1546 - loss 0.01076254 - time (sec): 16.70 - samples/sec: 1446.14 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 12:50:47,023 epoch 8 - iter 462/1546 - loss 0.00867901 - time (sec): 25.09 - samples/sec: 1477.45 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 12:50:55,109 epoch 8 - iter 616/1546 - loss 0.00802834 - time (sec): 33.17 - samples/sec: 1485.62 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:51:03,605 epoch 8 - iter 770/1546 - loss 0.00819320 - time (sec): 41.67 - samples/sec: 1496.95 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 12:51:12,106 epoch 8 - iter 924/1546 - loss 0.00965589 - time (sec): 50.17 - samples/sec: 1497.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:51:20,169 epoch 8 - iter 1078/1546 - loss 0.00978379 - time (sec): 58.23 - samples/sec: 1508.17 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 12:51:28,630 epoch 8 - iter 1232/1546 - loss 0.01084429 - time (sec): 66.69 - samples/sec: 1499.87 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:51:36,899 epoch 8 - iter 1386/1546 - loss 0.01029684 - time (sec): 74.96 - samples/sec: 1493.36 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 12:51:44,908 epoch 8 - iter 1540/1546 - loss 0.01014845 - time (sec): 82.97 - samples/sec: 1493.83 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:51:45,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:51:45,207 EPOCH 8 done: loss 0.0101 - lr: 0.000011 | |
| 2023-10-25 12:51:48,623 DEV : loss 0.12650519609451294 - f1-score (micro avg) 0.7699 | |
| 2023-10-25 12:51:48,639 saving best model | |
| 2023-10-25 12:51:49,301 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:51:57,377 epoch 9 - iter 154/1546 - loss 0.00632597 - time (sec): 8.07 - samples/sec: 1437.51 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 12:52:05,596 epoch 9 - iter 308/1546 - loss 0.00523025 - time (sec): 16.29 - samples/sec: 1494.13 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 12:52:14,043 epoch 9 - iter 462/1546 - loss 0.00617576 - time (sec): 24.74 - samples/sec: 1463.46 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:52:22,340 epoch 9 - iter 616/1546 - loss 0.00662387 - time (sec): 33.04 - samples/sec: 1469.72 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 12:52:30,644 epoch 9 - iter 770/1546 - loss 0.00580720 - time (sec): 41.34 - samples/sec: 1484.38 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:52:39,154 epoch 9 - iter 924/1546 - loss 0.00651627 - time (sec): 49.85 - samples/sec: 1488.41 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 12:52:47,418 epoch 9 - iter 1078/1546 - loss 0.00657349 - time (sec): 58.11 - samples/sec: 1492.97 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:52:55,718 epoch 9 - iter 1232/1546 - loss 0.00656388 - time (sec): 66.42 - samples/sec: 1488.80 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 12:53:03,985 epoch 9 - iter 1386/1546 - loss 0.00639141 - time (sec): 74.68 - samples/sec: 1492.93 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:53:12,253 epoch 9 - iter 1540/1546 - loss 0.00607270 - time (sec): 82.95 - samples/sec: 1490.23 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 12:53:12,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:53:12,601 EPOCH 9 done: loss 0.0060 - lr: 0.000006 | |
| 2023-10-25 12:53:15,220 DEV : loss 0.13038863241672516 - f1-score (micro avg) 0.768 | |
| 2023-10-25 12:53:15,241 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:53:23,450 epoch 10 - iter 154/1546 - loss 0.00089291 - time (sec): 8.21 - samples/sec: 1550.67 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 12:53:31,626 epoch 10 - iter 308/1546 - loss 0.00322868 - time (sec): 16.38 - samples/sec: 1492.50 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:53:39,724 epoch 10 - iter 462/1546 - loss 0.00258576 - time (sec): 24.48 - samples/sec: 1526.10 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 12:53:47,874 epoch 10 - iter 616/1546 - loss 0.00273164 - time (sec): 32.63 - samples/sec: 1538.63 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:53:55,883 epoch 10 - iter 770/1546 - loss 0.00278873 - time (sec): 40.64 - samples/sec: 1545.40 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 12:54:03,988 epoch 10 - iter 924/1546 - loss 0.00233375 - time (sec): 48.74 - samples/sec: 1552.87 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:54:12,292 epoch 10 - iter 1078/1546 - loss 0.00251685 - time (sec): 57.05 - samples/sec: 1545.34 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 12:54:20,658 epoch 10 - iter 1232/1546 - loss 0.00288018 - time (sec): 65.41 - samples/sec: 1523.54 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:54:29,004 epoch 10 - iter 1386/1546 - loss 0.00326638 - time (sec): 73.76 - samples/sec: 1520.64 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 12:54:37,324 epoch 10 - iter 1540/1546 - loss 0.00346654 - time (sec): 82.08 - samples/sec: 1508.93 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 12:54:37,650 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:54:37,650 EPOCH 10 done: loss 0.0035 - lr: 0.000000 | |
| 2023-10-25 12:54:40,520 DEV : loss 0.13788414001464844 - f1-score (micro avg) 0.7708 | |
| 2023-10-25 12:54:40,538 saving best model | |
| 2023-10-25 12:54:41,705 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 12:54:41,707 Loading model from best epoch ... | |
| 2023-10-25 12:54:43,771 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 | |
| 2023-10-25 12:54:52,828 | |
| Results: | |
| - F-score (micro) 0.802 | |
| - F-score (macro) 0.7095 | |
| - Accuracy 0.6911 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.8510 0.8393 0.8451 946 | |
| BUILDING 0.6348 0.6108 0.6226 185 | |
| STREET 0.6607 0.6607 0.6607 56 | |
| micro avg 0.8089 0.7953 0.8020 1187 | |
| macro avg 0.7155 0.7036 0.7095 1187 | |
| weighted avg 0.8083 0.7953 0.8017 1187 | |
| 2023-10-25 12:54:52,828 ---------------------------------------------------------------------------------------------------- | |