| 2023-10-25 11:09:44,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,813 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 11:09:44,813 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,813 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 11:09:44,813 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,813 Train: 6183 sentences | |
| 2023-10-25 11:09:44,813 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 11:09:44,813 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,813 Training Params: | |
| 2023-10-25 11:09:44,813 - learning_rate: "5e-05" | |
| 2023-10-25 11:09:44,813 - mini_batch_size: "4" | |
| 2023-10-25 11:09:44,813 - max_epochs: "10" | |
| 2023-10-25 11:09:44,813 - shuffle: "True" | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 Plugins: | |
| 2023-10-25 11:09:44,814 - TensorboardLogger | |
| 2023-10-25 11:09:44,814 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 11:09:44,814 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 Computation: | |
| 2023-10-25 11:09:44,814 - compute on device: cuda:0 | |
| 2023-10-25 11:09:44,814 - embedding storage: none | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:44,814 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 11:09:52,765 epoch 1 - iter 154/1546 - loss 1.39827012 - time (sec): 7.95 - samples/sec: 1603.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 11:10:00,589 epoch 1 - iter 308/1546 - loss 0.79365423 - time (sec): 15.77 - samples/sec: 1579.66 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 11:10:08,586 epoch 1 - iter 462/1546 - loss 0.58832416 - time (sec): 23.77 - samples/sec: 1554.59 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 11:10:16,610 epoch 1 - iter 616/1546 - loss 0.46941104 - time (sec): 31.79 - samples/sec: 1566.89 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 11:10:24,511 epoch 1 - iter 770/1546 - loss 0.39745577 - time (sec): 39.70 - samples/sec: 1566.88 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 11:10:31,922 epoch 1 - iter 924/1546 - loss 0.35399657 - time (sec): 47.11 - samples/sec: 1570.00 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 11:10:39,970 epoch 1 - iter 1078/1546 - loss 0.31818671 - time (sec): 55.16 - samples/sec: 1574.31 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 11:10:48,118 epoch 1 - iter 1232/1546 - loss 0.29058398 - time (sec): 63.30 - samples/sec: 1573.48 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 11:10:55,376 epoch 1 - iter 1386/1546 - loss 0.26861461 - time (sec): 70.56 - samples/sec: 1585.51 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 11:11:02,749 epoch 1 - iter 1540/1546 - loss 0.25444733 - time (sec): 77.93 - samples/sec: 1588.75 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 11:11:03,027 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:11:03,028 EPOCH 1 done: loss 0.2541 - lr: 0.000050 | |
| 2023-10-25 11:11:06,025 DEV : loss 0.06385146081447601 - f1-score (micro avg) 0.7017 | |
| 2023-10-25 11:11:06,042 saving best model | |
| 2023-10-25 11:11:06,525 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:11:13,626 epoch 2 - iter 154/1546 - loss 0.09488847 - time (sec): 7.10 - samples/sec: 1730.89 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 11:11:20,971 epoch 2 - iter 308/1546 - loss 0.10778745 - time (sec): 14.44 - samples/sec: 1715.52 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 11:11:28,649 epoch 2 - iter 462/1546 - loss 0.11055818 - time (sec): 22.12 - samples/sec: 1629.86 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 11:11:36,322 epoch 2 - iter 616/1546 - loss 0.11130533 - time (sec): 29.80 - samples/sec: 1642.98 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 11:11:43,818 epoch 2 - iter 770/1546 - loss 0.10922038 - time (sec): 37.29 - samples/sec: 1652.66 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 11:11:51,413 epoch 2 - iter 924/1546 - loss 0.10434596 - time (sec): 44.89 - samples/sec: 1655.00 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 11:11:59,068 epoch 2 - iter 1078/1546 - loss 0.10272933 - time (sec): 52.54 - samples/sec: 1656.95 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 11:12:06,766 epoch 2 - iter 1232/1546 - loss 0.10378889 - time (sec): 60.24 - samples/sec: 1638.89 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 11:12:14,551 epoch 2 - iter 1386/1546 - loss 0.10412134 - time (sec): 68.02 - samples/sec: 1623.95 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 11:12:22,579 epoch 2 - iter 1540/1546 - loss 0.10282784 - time (sec): 76.05 - samples/sec: 1627.32 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 11:12:22,910 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:12:22,911 EPOCH 2 done: loss 0.1025 - lr: 0.000044 | |
| 2023-10-25 11:12:26,118 DEV : loss 0.07249868661165237 - f1-score (micro avg) 0.6709 | |
| 2023-10-25 11:12:26,136 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:12:34,057 epoch 3 - iter 154/1546 - loss 0.08239162 - time (sec): 7.92 - samples/sec: 1541.67 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 11:12:42,132 epoch 3 - iter 308/1546 - loss 0.08525049 - time (sec): 15.99 - samples/sec: 1491.70 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 11:12:50,138 epoch 3 - iter 462/1546 - loss 0.09511193 - time (sec): 24.00 - samples/sec: 1490.47 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 11:12:58,169 epoch 3 - iter 616/1546 - loss 0.09228841 - time (sec): 32.03 - samples/sec: 1509.57 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 11:13:05,743 epoch 3 - iter 770/1546 - loss 0.09043310 - time (sec): 39.61 - samples/sec: 1528.40 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 11:13:13,430 epoch 3 - iter 924/1546 - loss 0.09088492 - time (sec): 47.29 - samples/sec: 1555.45 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 11:13:20,912 epoch 3 - iter 1078/1546 - loss 0.08784368 - time (sec): 54.77 - samples/sec: 1571.93 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 11:13:28,582 epoch 3 - iter 1232/1546 - loss 0.08895776 - time (sec): 62.44 - samples/sec: 1580.75 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 11:13:36,529 epoch 3 - iter 1386/1546 - loss 0.09241618 - time (sec): 70.39 - samples/sec: 1584.84 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 11:13:44,167 epoch 3 - iter 1540/1546 - loss 0.09420123 - time (sec): 78.03 - samples/sec: 1587.64 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 11:13:44,460 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:13:44,460 EPOCH 3 done: loss 0.0946 - lr: 0.000039 | |
| 2023-10-25 11:13:47,023 DEV : loss 0.12890027463436127 - f1-score (micro avg) 0.1172 | |
| 2023-10-25 11:13:47,041 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:13:54,766 epoch 4 - iter 154/1546 - loss 0.11099350 - time (sec): 7.72 - samples/sec: 1616.00 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 11:14:02,797 epoch 4 - iter 308/1546 - loss 0.10769660 - time (sec): 15.75 - samples/sec: 1603.82 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 11:14:11,199 epoch 4 - iter 462/1546 - loss 0.11044706 - time (sec): 24.16 - samples/sec: 1563.30 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 11:14:18,951 epoch 4 - iter 616/1546 - loss 0.11922458 - time (sec): 31.91 - samples/sec: 1576.57 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 11:14:26,513 epoch 4 - iter 770/1546 - loss 0.12538625 - time (sec): 39.47 - samples/sec: 1577.04 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 11:14:34,286 epoch 4 - iter 924/1546 - loss 0.12355127 - time (sec): 47.24 - samples/sec: 1569.11 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 11:14:41,832 epoch 4 - iter 1078/1546 - loss 0.11819929 - time (sec): 54.79 - samples/sec: 1585.03 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 11:14:49,035 epoch 4 - iter 1232/1546 - loss 0.12030925 - time (sec): 61.99 - samples/sec: 1606.47 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 11:14:56,231 epoch 4 - iter 1386/1546 - loss 0.12228058 - time (sec): 69.19 - samples/sec: 1623.65 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 11:15:03,827 epoch 4 - iter 1540/1546 - loss 0.12339988 - time (sec): 76.78 - samples/sec: 1612.47 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 11:15:04,109 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:15:04,110 EPOCH 4 done: loss 0.1235 - lr: 0.000033 | |
| 2023-10-25 11:15:07,027 DEV : loss 0.10868637263774872 - f1-score (micro avg) 0.1429 | |
| 2023-10-25 11:15:07,046 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:15:15,120 epoch 5 - iter 154/1546 - loss 0.11165339 - time (sec): 8.07 - samples/sec: 1524.83 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 11:15:23,116 epoch 5 - iter 308/1546 - loss 0.12504210 - time (sec): 16.07 - samples/sec: 1535.64 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 11:15:31,442 epoch 5 - iter 462/1546 - loss 0.12726076 - time (sec): 24.39 - samples/sec: 1541.40 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 11:15:39,449 epoch 5 - iter 616/1546 - loss 0.12576134 - time (sec): 32.40 - samples/sec: 1535.35 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 11:15:47,550 epoch 5 - iter 770/1546 - loss 0.12009921 - time (sec): 40.50 - samples/sec: 1548.38 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 11:15:55,542 epoch 5 - iter 924/1546 - loss 0.11502711 - time (sec): 48.49 - samples/sec: 1556.16 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 11:16:03,686 epoch 5 - iter 1078/1546 - loss 0.11521075 - time (sec): 56.64 - samples/sec: 1557.46 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 11:16:11,972 epoch 5 - iter 1232/1546 - loss 0.11520498 - time (sec): 64.92 - samples/sec: 1536.08 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 11:16:20,183 epoch 5 - iter 1386/1546 - loss 0.11537618 - time (sec): 73.13 - samples/sec: 1535.38 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 11:16:27,958 epoch 5 - iter 1540/1546 - loss 0.11790749 - time (sec): 80.91 - samples/sec: 1530.48 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 11:16:28,257 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:16:28,258 EPOCH 5 done: loss 0.1178 - lr: 0.000028 | |
| 2023-10-25 11:16:31,002 DEV : loss 0.11433909088373184 - f1-score (micro avg) 0.1883 | |
| 2023-10-25 11:16:31,020 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:16:38,691 epoch 6 - iter 154/1546 - loss 0.10020310 - time (sec): 7.67 - samples/sec: 1648.37 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 11:16:46,152 epoch 6 - iter 308/1546 - loss 0.10900828 - time (sec): 15.13 - samples/sec: 1661.66 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 11:16:53,391 epoch 6 - iter 462/1546 - loss 0.10940982 - time (sec): 22.37 - samples/sec: 1650.89 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 11:17:00,801 epoch 6 - iter 616/1546 - loss 0.10940260 - time (sec): 29.78 - samples/sec: 1671.80 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 11:17:08,109 epoch 6 - iter 770/1546 - loss 0.10974972 - time (sec): 37.09 - samples/sec: 1700.38 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 11:17:15,641 epoch 6 - iter 924/1546 - loss 0.10710202 - time (sec): 44.62 - samples/sec: 1699.14 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 11:17:22,875 epoch 6 - iter 1078/1546 - loss 0.10353632 - time (sec): 51.85 - samples/sec: 1694.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 11:17:30,263 epoch 6 - iter 1232/1546 - loss 0.10346170 - time (sec): 59.24 - samples/sec: 1681.21 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 11:17:37,778 epoch 6 - iter 1386/1546 - loss 0.10512181 - time (sec): 66.76 - samples/sec: 1673.90 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 11:17:44,991 epoch 6 - iter 1540/1546 - loss 0.10561514 - time (sec): 73.97 - samples/sec: 1675.03 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 11:17:45,268 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:17:45,268 EPOCH 6 done: loss 0.1057 - lr: 0.000022 | |
| 2023-10-25 11:17:47,817 DEV : loss 0.12019870430231094 - f1-score (micro avg) 0.1275 | |
| 2023-10-25 11:17:47,836 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:17:55,710 epoch 7 - iter 154/1546 - loss 0.11566978 - time (sec): 7.87 - samples/sec: 1617.98 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 11:18:03,627 epoch 7 - iter 308/1546 - loss 0.11355535 - time (sec): 15.79 - samples/sec: 1574.00 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 11:18:11,606 epoch 7 - iter 462/1546 - loss 0.11602233 - time (sec): 23.77 - samples/sec: 1630.59 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 11:18:19,336 epoch 7 - iter 616/1546 - loss 0.11997274 - time (sec): 31.50 - samples/sec: 1575.06 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 11:18:26,900 epoch 7 - iter 770/1546 - loss 0.12479200 - time (sec): 39.06 - samples/sec: 1583.24 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 11:18:34,136 epoch 7 - iter 924/1546 - loss 0.12527361 - time (sec): 46.30 - samples/sec: 1609.07 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 11:18:41,534 epoch 7 - iter 1078/1546 - loss 0.12872154 - time (sec): 53.70 - samples/sec: 1599.75 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 11:18:49,559 epoch 7 - iter 1232/1546 - loss 0.12912406 - time (sec): 61.72 - samples/sec: 1585.74 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 11:18:58,411 epoch 7 - iter 1386/1546 - loss 0.12867892 - time (sec): 70.57 - samples/sec: 1572.16 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 11:19:06,582 epoch 7 - iter 1540/1546 - loss 0.12892147 - time (sec): 78.74 - samples/sec: 1571.08 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 11:19:06,887 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:19:06,887 EPOCH 7 done: loss 0.1287 - lr: 0.000017 | |
| 2023-10-25 11:19:09,823 DEV : loss 0.12551754713058472 - f1-score (micro avg) 0.1484 | |
| 2023-10-25 11:19:09,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:19:17,900 epoch 8 - iter 154/1546 - loss 0.08892515 - time (sec): 8.06 - samples/sec: 1530.35 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 11:19:25,967 epoch 8 - iter 308/1546 - loss 0.08918773 - time (sec): 16.12 - samples/sec: 1540.16 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 11:19:33,972 epoch 8 - iter 462/1546 - loss 0.09723290 - time (sec): 24.13 - samples/sec: 1508.23 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 11:19:42,163 epoch 8 - iter 616/1546 - loss 0.09395443 - time (sec): 32.32 - samples/sec: 1502.95 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 11:19:50,082 epoch 8 - iter 770/1546 - loss 0.09754016 - time (sec): 40.24 - samples/sec: 1519.30 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 11:19:58,129 epoch 8 - iter 924/1546 - loss 0.10104510 - time (sec): 48.29 - samples/sec: 1541.73 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 11:20:06,298 epoch 8 - iter 1078/1546 - loss 0.10345539 - time (sec): 56.45 - samples/sec: 1540.41 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 11:20:13,663 epoch 8 - iter 1232/1546 - loss 0.10514366 - time (sec): 63.82 - samples/sec: 1554.05 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 11:20:21,088 epoch 8 - iter 1386/1546 - loss 0.10454299 - time (sec): 71.24 - samples/sec: 1561.24 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 11:20:28,350 epoch 8 - iter 1540/1546 - loss 0.10473009 - time (sec): 78.51 - samples/sec: 1576.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 11:20:28,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:20:28,630 EPOCH 8 done: loss 0.1046 - lr: 0.000011 | |
| 2023-10-25 11:20:31,098 DEV : loss 0.13076254725456238 - f1-score (micro avg) 0.0333 | |
| 2023-10-25 11:20:31,116 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:20:38,660 epoch 9 - iter 154/1546 - loss 0.09304619 - time (sec): 7.54 - samples/sec: 1670.31 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 11:20:46,491 epoch 9 - iter 308/1546 - loss 0.11325144 - time (sec): 15.37 - samples/sec: 1627.95 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 11:20:53,712 epoch 9 - iter 462/1546 - loss 0.11878095 - time (sec): 22.59 - samples/sec: 1655.41 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 11:21:00,914 epoch 9 - iter 616/1546 - loss 0.11890975 - time (sec): 29.80 - samples/sec: 1690.89 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 11:21:08,419 epoch 9 - iter 770/1546 - loss 0.12259251 - time (sec): 37.30 - samples/sec: 1680.01 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 11:21:16,009 epoch 9 - iter 924/1546 - loss 0.12174320 - time (sec): 44.89 - samples/sec: 1669.55 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 11:21:23,204 epoch 9 - iter 1078/1546 - loss 0.12084631 - time (sec): 52.09 - samples/sec: 1669.17 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 11:21:30,742 epoch 9 - iter 1232/1546 - loss 0.12297667 - time (sec): 59.62 - samples/sec: 1660.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 11:21:38,280 epoch 9 - iter 1386/1546 - loss 0.12347069 - time (sec): 67.16 - samples/sec: 1670.58 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 11:21:45,932 epoch 9 - iter 1540/1546 - loss 0.12128285 - time (sec): 74.81 - samples/sec: 1657.22 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 11:21:46,221 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:21:46,222 EPOCH 9 done: loss 0.1211 - lr: 0.000006 | |
| 2023-10-25 11:21:48,919 DEV : loss 0.13703128695487976 - f1-score (micro avg) 0.0408 | |
| 2023-10-25 11:21:48,938 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:21:56,774 epoch 10 - iter 154/1546 - loss 0.11553428 - time (sec): 7.83 - samples/sec: 1511.35 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 11:22:04,527 epoch 10 - iter 308/1546 - loss 0.12482497 - time (sec): 15.59 - samples/sec: 1508.18 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 11:22:12,502 epoch 10 - iter 462/1546 - loss 0.11936489 - time (sec): 23.56 - samples/sec: 1504.55 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 11:22:20,360 epoch 10 - iter 616/1546 - loss 0.12050578 - time (sec): 31.42 - samples/sec: 1519.12 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 11:22:28,455 epoch 10 - iter 770/1546 - loss 0.12137981 - time (sec): 39.52 - samples/sec: 1499.55 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 11:22:36,482 epoch 10 - iter 924/1546 - loss 0.11943526 - time (sec): 47.54 - samples/sec: 1517.53 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 11:22:44,350 epoch 10 - iter 1078/1546 - loss 0.11806455 - time (sec): 55.41 - samples/sec: 1535.68 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 11:22:52,120 epoch 10 - iter 1232/1546 - loss 0.11705393 - time (sec): 63.18 - samples/sec: 1555.27 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 11:22:59,826 epoch 10 - iter 1386/1546 - loss 0.11574693 - time (sec): 70.89 - samples/sec: 1570.23 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 11:23:07,838 epoch 10 - iter 1540/1546 - loss 0.11619891 - time (sec): 78.90 - samples/sec: 1566.16 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 11:23:08,173 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:23:08,173 EPOCH 10 done: loss 0.1161 - lr: 0.000000 | |
| 2023-10-25 11:23:11,111 DEV : loss 0.13759513199329376 - f1-score (micro avg) 0.0473 | |
| 2023-10-25 11:23:11,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:23:11,632 Loading model from best epoch ... | |
| 2023-10-25 11:23:13,455 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 11:23:22,239 | |
| Results: | |
| - F-score (micro) 0.7133 | |
| - F-score (macro) 0.5136 | |
| - Accuracy 0.5675 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.7834 0.7992 0.7912 946 | |
| BUILDING 0.4245 0.3189 0.3642 185 | |
| STREET 0.3962 0.3750 0.3853 56 | |
| micro avg 0.7226 0.7043 0.7133 1187 | |
| macro avg 0.5347 0.4977 0.5136 1187 | |
| weighted avg 0.7092 0.7043 0.7055 1187 | |
| 2023-10-25 11:23:22,287 ---------------------------------------------------------------------------------------------------- | |