|
2023-10-25 10:22:52,222 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,223 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 10:22:52,223 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,223 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 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Train: 6183 sentences |
|
2023-10-25 10:22:52,224 (train_with_dev=False, train_with_test=False) |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Training Params: |
|
2023-10-25 10:22:52,224 - learning_rate: "5e-05" |
|
2023-10-25 10:22:52,224 - mini_batch_size: "4" |
|
2023-10-25 10:22:52,224 - max_epochs: "10" |
|
2023-10-25 10:22:52,224 - shuffle: "True" |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Plugins: |
|
2023-10-25 10:22:52,224 - TensorboardLogger |
|
2023-10-25 10:22:52,224 - LinearScheduler | warmup_fraction: '0.1' |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Final evaluation on model from best epoch (best-model.pt) |
|
2023-10-25 10:22:52,224 - metric: "('micro avg', 'f1-score')" |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Computation: |
|
2023-10-25 10:22:52,224 - compute on device: cuda:0 |
|
2023-10-25 10:22:52,224 - embedding storage: none |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Model training base path: "hmbench-topres19th/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:22:52,224 Logging anything other than scalars to TensorBoard is currently not supported. |
|
2023-10-25 10:23:00,167 epoch 1 - iter 154/1546 - loss 1.59682713 - time (sec): 7.94 - samples/sec: 1589.82 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-25 10:23:08,149 epoch 1 - iter 308/1546 - loss 0.89117830 - time (sec): 15.92 - samples/sec: 1593.16 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-25 10:23:15,990 epoch 1 - iter 462/1546 - loss 0.64377555 - time (sec): 23.76 - samples/sec: 1582.88 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-25 10:23:23,785 epoch 1 - iter 616/1546 - loss 0.51331082 - time (sec): 31.56 - samples/sec: 1590.22 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-25 10:23:31,477 epoch 1 - iter 770/1546 - loss 0.44305966 - time (sec): 39.25 - samples/sec: 1569.11 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-25 10:23:39,530 epoch 1 - iter 924/1546 - loss 0.38864253 - time (sec): 47.30 - samples/sec: 1562.11 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-25 10:23:47,419 epoch 1 - iter 1078/1546 - loss 0.34915936 - time (sec): 55.19 - samples/sec: 1565.46 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-25 10:23:55,487 epoch 1 - iter 1232/1546 - loss 0.32266725 - time (sec): 63.26 - samples/sec: 1570.23 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-25 10:24:03,424 epoch 1 - iter 1386/1546 - loss 0.30046509 - time (sec): 71.20 - samples/sec: 1564.37 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-25 10:24:11,358 epoch 1 - iter 1540/1546 - loss 0.28008530 - time (sec): 79.13 - samples/sec: 1567.29 - lr: 0.000050 - momentum: 0.000000 |
|
2023-10-25 10:24:11,653 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:24:11,654 EPOCH 1 done: loss 0.2798 - lr: 0.000050 |
|
2023-10-25 10:24:15,019 DEV : loss 0.08405806124210358 - f1-score (micro avg) 0.5943 |
|
2023-10-25 10:24:15,036 saving best model |
|
2023-10-25 10:24:15,582 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:24:23,571 epoch 2 - iter 154/1546 - loss 0.10858329 - time (sec): 7.99 - samples/sec: 1545.89 - lr: 0.000049 - momentum: 0.000000 |
|
2023-10-25 10:24:31,538 epoch 2 - iter 308/1546 - loss 0.10043248 - time (sec): 15.95 - samples/sec: 1532.59 - lr: 0.000049 - momentum: 0.000000 |
|
2023-10-25 10:24:39,629 epoch 2 - iter 462/1546 - loss 0.10238266 - time (sec): 24.05 - samples/sec: 1533.70 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-25 10:24:47,510 epoch 2 - iter 616/1546 - loss 0.09968080 - time (sec): 31.93 - samples/sec: 1546.93 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-25 10:24:55,393 epoch 2 - iter 770/1546 - loss 0.09894440 - time (sec): 39.81 - samples/sec: 1544.90 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-25 10:25:03,338 epoch 2 - iter 924/1546 - loss 0.09747046 - time (sec): 47.75 - samples/sec: 1546.64 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-25 10:25:11,221 epoch 2 - iter 1078/1546 - loss 0.09656863 - time (sec): 55.64 - samples/sec: 1553.87 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-25 10:25:19,121 epoch 2 - iter 1232/1546 - loss 0.09740415 - time (sec): 63.54 - samples/sec: 1559.14 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-25 10:25:27,235 epoch 2 - iter 1386/1546 - loss 0.10016234 - time (sec): 71.65 - samples/sec: 1559.71 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-25 10:25:35,143 epoch 2 - iter 1540/1546 - loss 0.10060445 - time (sec): 79.56 - samples/sec: 1557.57 - lr: 0.000044 - momentum: 0.000000 |
|
2023-10-25 10:25:35,445 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:25:35,445 EPOCH 2 done: loss 0.1005 - lr: 0.000044 |
|
2023-10-25 10:25:38,219 DEV : loss 0.06613297015428543 - f1-score (micro avg) 0.7377 |
|
2023-10-25 10:25:38,236 saving best model |
|
2023-10-25 10:25:39,002 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:25:47,193 epoch 3 - iter 154/1546 - loss 0.06284020 - time (sec): 8.19 - samples/sec: 1524.28 - lr: 0.000044 - momentum: 0.000000 |
|
2023-10-25 10:25:55,106 epoch 3 - iter 308/1546 - loss 0.06051793 - time (sec): 16.10 - samples/sec: 1517.05 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-25 10:26:03,223 epoch 3 - iter 462/1546 - loss 0.06199724 - time (sec): 24.22 - samples/sec: 1508.30 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-25 10:26:11,285 epoch 3 - iter 616/1546 - loss 0.06901668 - time (sec): 32.28 - samples/sec: 1513.06 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-25 10:26:19,396 epoch 3 - iter 770/1546 - loss 0.06769128 - time (sec): 40.39 - samples/sec: 1513.76 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-25 10:26:27,337 epoch 3 - iter 924/1546 - loss 0.06807317 - time (sec): 48.33 - samples/sec: 1532.21 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-25 10:26:35,341 epoch 3 - iter 1078/1546 - loss 0.06992824 - time (sec): 56.34 - samples/sec: 1537.05 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-25 10:26:43,266 epoch 3 - iter 1232/1546 - loss 0.07185688 - time (sec): 64.26 - samples/sec: 1539.39 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-25 10:26:51,341 epoch 3 - iter 1386/1546 - loss 0.07155532 - time (sec): 72.34 - samples/sec: 1536.08 - lr: 0.000039 - momentum: 0.000000 |
|
2023-10-25 10:26:59,470 epoch 3 - iter 1540/1546 - loss 0.07128179 - time (sec): 80.47 - samples/sec: 1536.47 - lr: 0.000039 - momentum: 0.000000 |
|
2023-10-25 10:26:59,788 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:26:59,789 EPOCH 3 done: loss 0.0713 - lr: 0.000039 |
|
2023-10-25 10:27:02,908 DEV : loss 0.0856151133775711 - f1-score (micro avg) 0.7273 |
|
2023-10-25 10:27:02,924 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:27:10,888 epoch 4 - iter 154/1546 - loss 0.04453513 - time (sec): 7.96 - samples/sec: 1615.65 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-25 10:27:19,047 epoch 4 - iter 308/1546 - loss 0.04454757 - time (sec): 16.12 - samples/sec: 1517.28 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-25 10:27:27,292 epoch 4 - iter 462/1546 - loss 0.04667982 - time (sec): 24.37 - samples/sec: 1540.54 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-25 10:27:35,480 epoch 4 - iter 616/1546 - loss 0.04770651 - time (sec): 32.55 - samples/sec: 1550.36 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-25 10:27:43,398 epoch 4 - iter 770/1546 - loss 0.04711825 - time (sec): 40.47 - samples/sec: 1538.01 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-25 10:27:51,326 epoch 4 - iter 924/1546 - loss 0.04601775 - time (sec): 48.40 - samples/sec: 1546.43 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-25 10:27:59,380 epoch 4 - iter 1078/1546 - loss 0.04649332 - time (sec): 56.45 - samples/sec: 1556.67 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-25 10:28:07,340 epoch 4 - iter 1232/1546 - loss 0.04677162 - time (sec): 64.41 - samples/sec: 1553.58 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-25 10:28:15,375 epoch 4 - iter 1386/1546 - loss 0.04686556 - time (sec): 72.45 - samples/sec: 1546.65 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-25 10:28:23,211 epoch 4 - iter 1540/1546 - loss 0.04791150 - time (sec): 80.29 - samples/sec: 1541.79 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-25 10:28:23,524 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:28:23,524 EPOCH 4 done: loss 0.0478 - lr: 0.000033 |
|
2023-10-25 10:28:26,220 DEV : loss 0.09348937124013901 - f1-score (micro avg) 0.7521 |
|
2023-10-25 10:28:26,234 saving best model |
|
2023-10-25 10:28:26,950 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:28:34,965 epoch 5 - iter 154/1546 - loss 0.04181508 - time (sec): 8.01 - samples/sec: 1421.60 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-25 10:28:42,948 epoch 5 - iter 308/1546 - loss 0.03973625 - time (sec): 16.00 - samples/sec: 1539.28 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-25 10:28:50,943 epoch 5 - iter 462/1546 - loss 0.03429687 - time (sec): 23.99 - samples/sec: 1559.42 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-25 10:28:59,030 epoch 5 - iter 616/1546 - loss 0.03909449 - time (sec): 32.08 - samples/sec: 1553.75 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-25 10:29:06,995 epoch 5 - iter 770/1546 - loss 0.03934781 - time (sec): 40.04 - samples/sec: 1549.00 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-25 10:29:14,916 epoch 5 - iter 924/1546 - loss 0.03682160 - time (sec): 47.96 - samples/sec: 1555.64 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-25 10:29:22,777 epoch 5 - iter 1078/1546 - loss 0.03663157 - time (sec): 55.82 - samples/sec: 1554.26 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-25 10:29:30,743 epoch 5 - iter 1232/1546 - loss 0.03744518 - time (sec): 63.79 - samples/sec: 1553.97 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-25 10:29:38,749 epoch 5 - iter 1386/1546 - loss 0.03709433 - time (sec): 71.80 - samples/sec: 1554.16 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-25 10:29:46,726 epoch 5 - iter 1540/1546 - loss 0.03613206 - time (sec): 79.77 - samples/sec: 1553.52 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-25 10:29:47,029 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:29:47,029 EPOCH 5 done: loss 0.0360 - lr: 0.000028 |
|
2023-10-25 10:29:49,629 DEV : loss 0.11338605731725693 - f1-score (micro avg) 0.7546 |
|
2023-10-25 10:29:49,648 saving best model |
|
2023-10-25 10:29:50,361 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:29:58,359 epoch 6 - iter 154/1546 - loss 0.01816962 - time (sec): 8.00 - samples/sec: 1573.02 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-25 10:30:06,293 epoch 6 - iter 308/1546 - loss 0.02207942 - time (sec): 15.93 - samples/sec: 1566.57 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-25 10:30:14,440 epoch 6 - iter 462/1546 - loss 0.02501555 - time (sec): 24.08 - samples/sec: 1553.46 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-25 10:30:22,341 epoch 6 - iter 616/1546 - loss 0.02802152 - time (sec): 31.98 - samples/sec: 1561.74 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-25 10:30:30,311 epoch 6 - iter 770/1546 - loss 0.02771706 - time (sec): 39.95 - samples/sec: 1527.23 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-25 10:30:38,410 epoch 6 - iter 924/1546 - loss 0.02733007 - time (sec): 48.05 - samples/sec: 1521.43 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-25 10:30:46,504 epoch 6 - iter 1078/1546 - loss 0.02629383 - time (sec): 56.14 - samples/sec: 1526.19 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-25 10:30:54,581 epoch 6 - iter 1232/1546 - loss 0.02645982 - time (sec): 64.22 - samples/sec: 1541.41 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-25 10:31:02,692 epoch 6 - iter 1386/1546 - loss 0.02607912 - time (sec): 72.33 - samples/sec: 1541.29 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-25 10:31:11,054 epoch 6 - iter 1540/1546 - loss 0.02570720 - time (sec): 80.69 - samples/sec: 1535.15 - lr: 0.000022 - momentum: 0.000000 |
|
2023-10-25 10:31:11,360 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:31:11,360 EPOCH 6 done: loss 0.0258 - lr: 0.000022 |
|
2023-10-25 10:31:14,574 DEV : loss 0.11959201842546463 - f1-score (micro avg) 0.7621 |
|
2023-10-25 10:31:14,597 saving best model |
|
2023-10-25 10:31:15,299 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:31:23,382 epoch 7 - iter 154/1546 - loss 0.01965882 - time (sec): 8.08 - samples/sec: 1508.42 - lr: 0.000022 - momentum: 0.000000 |
|
2023-10-25 10:31:31,337 epoch 7 - iter 308/1546 - loss 0.01786807 - time (sec): 16.04 - samples/sec: 1555.65 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-25 10:31:39,462 epoch 7 - iter 462/1546 - loss 0.01846085 - time (sec): 24.16 - samples/sec: 1579.01 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-25 10:31:47,507 epoch 7 - iter 616/1546 - loss 0.01777823 - time (sec): 32.21 - samples/sec: 1561.77 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-25 10:31:55,527 epoch 7 - iter 770/1546 - loss 0.01824766 - time (sec): 40.23 - samples/sec: 1552.45 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-25 10:32:03,806 epoch 7 - iter 924/1546 - loss 0.01845757 - time (sec): 48.50 - samples/sec: 1525.47 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-25 10:32:11,802 epoch 7 - iter 1078/1546 - loss 0.01958815 - time (sec): 56.50 - samples/sec: 1538.31 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-25 10:32:19,783 epoch 7 - iter 1232/1546 - loss 0.01951007 - time (sec): 64.48 - samples/sec: 1542.37 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-25 10:32:28,006 epoch 7 - iter 1386/1546 - loss 0.01948908 - time (sec): 72.70 - samples/sec: 1533.63 - lr: 0.000017 - momentum: 0.000000 |
|
2023-10-25 10:32:36,058 epoch 7 - iter 1540/1546 - loss 0.01926685 - time (sec): 80.76 - samples/sec: 1530.81 - lr: 0.000017 - momentum: 0.000000 |
|
2023-10-25 10:32:36,360 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:32:36,361 EPOCH 7 done: loss 0.0193 - lr: 0.000017 |
|
2023-10-25 10:32:39,099 DEV : loss 0.13256850838661194 - f1-score (micro avg) 0.7401 |
|
2023-10-25 10:32:39,116 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:32:47,138 epoch 8 - iter 154/1546 - loss 0.01514111 - time (sec): 8.02 - samples/sec: 1563.64 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-25 10:32:55,255 epoch 8 - iter 308/1546 - loss 0.01555329 - time (sec): 16.14 - samples/sec: 1597.67 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-25 10:33:03,313 epoch 8 - iter 462/1546 - loss 0.01647792 - time (sec): 24.20 - samples/sec: 1560.81 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-25 10:33:11,355 epoch 8 - iter 616/1546 - loss 0.01541964 - time (sec): 32.24 - samples/sec: 1536.45 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-25 10:33:19,158 epoch 8 - iter 770/1546 - loss 0.01457204 - time (sec): 40.04 - samples/sec: 1530.37 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-25 10:33:27,228 epoch 8 - iter 924/1546 - loss 0.01394284 - time (sec): 48.11 - samples/sec: 1520.42 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-25 10:33:35,360 epoch 8 - iter 1078/1546 - loss 0.01347465 - time (sec): 56.24 - samples/sec: 1510.05 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-25 10:33:43,555 epoch 8 - iter 1232/1546 - loss 0.01279755 - time (sec): 64.44 - samples/sec: 1528.63 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-25 10:33:51,990 epoch 8 - iter 1386/1546 - loss 0.01254666 - time (sec): 72.87 - samples/sec: 1528.85 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-25 10:33:59,892 epoch 8 - iter 1540/1546 - loss 0.01237466 - time (sec): 80.77 - samples/sec: 1532.22 - lr: 0.000011 - momentum: 0.000000 |
|
2023-10-25 10:34:00,209 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:34:00,209 EPOCH 8 done: loss 0.0123 - lr: 0.000011 |
|
2023-10-25 10:34:02,639 DEV : loss 0.14071506261825562 - f1-score (micro avg) 0.7454 |
|
2023-10-25 10:34:02,655 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:34:10,640 epoch 9 - iter 154/1546 - loss 0.00502645 - time (sec): 7.98 - samples/sec: 1448.38 - lr: 0.000011 - momentum: 0.000000 |
|
2023-10-25 10:34:18,629 epoch 9 - iter 308/1546 - loss 0.00689538 - time (sec): 15.97 - samples/sec: 1492.57 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-25 10:34:26,678 epoch 9 - iter 462/1546 - loss 0.00648425 - time (sec): 24.02 - samples/sec: 1525.76 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-25 10:34:34,738 epoch 9 - iter 616/1546 - loss 0.00704709 - time (sec): 32.08 - samples/sec: 1539.47 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-25 10:34:42,944 epoch 9 - iter 770/1546 - loss 0.00744508 - time (sec): 40.29 - samples/sec: 1553.43 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-25 10:34:50,993 epoch 9 - iter 924/1546 - loss 0.00672678 - time (sec): 48.34 - samples/sec: 1554.21 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-25 10:34:59,172 epoch 9 - iter 1078/1546 - loss 0.00676359 - time (sec): 56.51 - samples/sec: 1561.68 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-25 10:35:06,863 epoch 9 - iter 1232/1546 - loss 0.00666184 - time (sec): 64.21 - samples/sec: 1563.70 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-25 10:35:14,955 epoch 9 - iter 1386/1546 - loss 0.00711228 - time (sec): 72.30 - samples/sec: 1546.05 - lr: 0.000006 - momentum: 0.000000 |
|
2023-10-25 10:35:22,887 epoch 9 - iter 1540/1546 - loss 0.00784747 - time (sec): 80.23 - samples/sec: 1543.02 - lr: 0.000006 - momentum: 0.000000 |
|
2023-10-25 10:35:23,181 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:35:23,181 EPOCH 9 done: loss 0.0078 - lr: 0.000006 |
|
2023-10-25 10:35:25,925 DEV : loss 0.1457042396068573 - f1-score (micro avg) 0.7398 |
|
2023-10-25 10:35:25,943 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:35:34,044 epoch 10 - iter 154/1546 - loss 0.00461955 - time (sec): 8.10 - samples/sec: 1522.59 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-25 10:35:41,995 epoch 10 - iter 308/1546 - loss 0.00725351 - time (sec): 16.05 - samples/sec: 1462.48 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-25 10:35:49,857 epoch 10 - iter 462/1546 - loss 0.00548130 - time (sec): 23.91 - samples/sec: 1496.35 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-25 10:35:57,737 epoch 10 - iter 616/1546 - loss 0.00534302 - time (sec): 31.79 - samples/sec: 1512.74 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-25 10:36:05,860 epoch 10 - iter 770/1546 - loss 0.00521499 - time (sec): 39.92 - samples/sec: 1528.84 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-25 10:36:13,948 epoch 10 - iter 924/1546 - loss 0.00491525 - time (sec): 48.00 - samples/sec: 1528.03 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-25 10:36:21,904 epoch 10 - iter 1078/1546 - loss 0.00477326 - time (sec): 55.96 - samples/sec: 1528.56 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-25 10:36:29,926 epoch 10 - iter 1232/1546 - loss 0.00450425 - time (sec): 63.98 - samples/sec: 1535.19 - lr: 0.000001 - momentum: 0.000000 |
|
2023-10-25 10:36:38,128 epoch 10 - iter 1386/1546 - loss 0.00420305 - time (sec): 72.18 - samples/sec: 1534.30 - lr: 0.000001 - momentum: 0.000000 |
|
2023-10-25 10:36:46,085 epoch 10 - iter 1540/1546 - loss 0.00458320 - time (sec): 80.14 - samples/sec: 1544.64 - lr: 0.000000 - momentum: 0.000000 |
|
2023-10-25 10:36:46,385 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:36:46,386 EPOCH 10 done: loss 0.0046 - lr: 0.000000 |
|
2023-10-25 10:36:49,417 DEV : loss 0.14359833300113678 - f1-score (micro avg) 0.7453 |
|
2023-10-25 10:36:49,937 ---------------------------------------------------------------------------------------------------- |
|
2023-10-25 10:36:49,939 Loading model from best epoch ... |
|
2023-10-25 10:36:51,996 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 10:37:00,712 |
|
Results: |
|
- F-score (micro) 0.7736 |
|
- F-score (macro) 0.6541 |
|
- Accuracy 0.648 |
|
|
|
By class: |
|
precision recall f1-score support |
|
|
|
LOC 0.8731 0.7780 0.8228 946 |
|
BUILDING 0.6718 0.4757 0.5570 185 |
|
STREET 0.6383 0.5357 0.5825 56 |
|
|
|
micro avg 0.8364 0.7195 0.7736 1187 |
|
macro avg 0.7277 0.5965 0.6541 1187 |
|
weighted avg 0.8306 0.7195 0.7700 1187 |
|
|
|
2023-10-25 10:37:00,712 ---------------------------------------------------------------------------------------------------- |
|
|