| 2023-10-23 23:08:41,805 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 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): 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) | |
| ) | |
| ) | |
| (1): 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) | |
| ) | |
| ) | |
| (2): 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) | |
| ) | |
| ) | |
| (3): 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) | |
| ) | |
| ) | |
| (4): 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) | |
| ) | |
| ) | |
| (5): 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) | |
| ) | |
| ) | |
| (6): 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) | |
| ) | |
| ) | |
| (7): 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) | |
| ) | |
| ) | |
| (8): 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) | |
| ) | |
| ) | |
| (9): 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) | |
| ) | |
| ) | |
| (10): 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) | |
| ) | |
| ) | |
| (11): 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 23:08:41,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-23 23:08:41,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 Train: 3575 sentences | |
| 2023-10-23 23:08:41,806 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 23:08:41,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 Training Params: | |
| 2023-10-23 23:08:41,806 - learning_rate: "5e-05" | |
| 2023-10-23 23:08:41,806 - mini_batch_size: "8" | |
| 2023-10-23 23:08:41,806 - max_epochs: "10" | |
| 2023-10-23 23:08:41,806 - shuffle: "True" | |
| 2023-10-23 23:08:41,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 Plugins: | |
| 2023-10-23 23:08:41,806 - TensorboardLogger | |
| 2023-10-23 23:08:41,806 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 23:08:41,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,806 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 23:08:41,806 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 23:08:41,807 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,807 Computation: | |
| 2023-10-23 23:08:41,807 - compute on device: cuda:0 | |
| 2023-10-23 23:08:41,807 - embedding storage: none | |
| 2023-10-23 23:08:41,807 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,807 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-23 23:08:41,807 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,807 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:41,807 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 23:08:45,910 epoch 1 - iter 44/447 - loss 2.27236626 - time (sec): 4.10 - samples/sec: 2190.58 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:08:49,783 epoch 1 - iter 88/447 - loss 1.47589070 - time (sec): 7.98 - samples/sec: 2169.45 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:08:53,739 epoch 1 - iter 132/447 - loss 1.14504662 - time (sec): 11.93 - samples/sec: 2183.40 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:08:57,410 epoch 1 - iter 176/447 - loss 0.95999639 - time (sec): 15.60 - samples/sec: 2206.17 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:09:01,957 epoch 1 - iter 220/447 - loss 0.81523692 - time (sec): 20.15 - samples/sec: 2172.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:09:05,690 epoch 1 - iter 264/447 - loss 0.73096034 - time (sec): 23.88 - samples/sec: 2166.16 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:09:09,636 epoch 1 - iter 308/447 - loss 0.66396424 - time (sec): 27.83 - samples/sec: 2151.96 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 23:09:13,363 epoch 1 - iter 352/447 - loss 0.61144599 - time (sec): 31.56 - samples/sec: 2134.84 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 23:09:17,484 epoch 1 - iter 396/447 - loss 0.56581415 - time (sec): 35.68 - samples/sec: 2144.61 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 23:09:21,621 epoch 1 - iter 440/447 - loss 0.52583326 - time (sec): 39.81 - samples/sec: 2143.06 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 23:09:22,210 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:09:22,211 EPOCH 1 done: loss 0.5212 - lr: 0.000049 | |
| 2023-10-23 23:09:27,043 DEV : loss 0.1860317587852478 - f1-score (micro avg) 0.6471 | |
| 2023-10-23 23:09:27,063 saving best model | |
| 2023-10-23 23:09:27,625 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:09:31,827 epoch 2 - iter 44/447 - loss 0.14761269 - time (sec): 4.20 - samples/sec: 2021.85 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 23:09:35,846 epoch 2 - iter 88/447 - loss 0.15284626 - time (sec): 8.22 - samples/sec: 2103.13 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 23:09:39,885 epoch 2 - iter 132/447 - loss 0.14429856 - time (sec): 12.26 - samples/sec: 2086.96 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 23:09:44,029 epoch 2 - iter 176/447 - loss 0.14832291 - time (sec): 16.40 - samples/sec: 2107.76 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 23:09:47,814 epoch 2 - iter 220/447 - loss 0.14470472 - time (sec): 20.19 - samples/sec: 2116.84 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 23:09:51,809 epoch 2 - iter 264/447 - loss 0.14200948 - time (sec): 24.18 - samples/sec: 2113.54 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 23:09:55,650 epoch 2 - iter 308/447 - loss 0.14010020 - time (sec): 28.02 - samples/sec: 2126.77 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 23:09:59,664 epoch 2 - iter 352/447 - loss 0.13626107 - time (sec): 32.04 - samples/sec: 2135.28 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 23:10:03,602 epoch 2 - iter 396/447 - loss 0.13432277 - time (sec): 35.98 - samples/sec: 2128.26 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 23:10:07,511 epoch 2 - iter 440/447 - loss 0.13033964 - time (sec): 39.89 - samples/sec: 2137.16 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 23:10:08,131 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:10:08,131 EPOCH 2 done: loss 0.1318 - lr: 0.000045 | |
| 2023-10-23 23:10:14,620 DEV : loss 0.1406162679195404 - f1-score (micro avg) 0.6881 | |
| 2023-10-23 23:10:14,640 saving best model | |
| 2023-10-23 23:10:15,340 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:10:19,694 epoch 3 - iter 44/447 - loss 0.08512096 - time (sec): 4.35 - samples/sec: 2195.81 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 23:10:23,624 epoch 3 - iter 88/447 - loss 0.07659362 - time (sec): 8.28 - samples/sec: 2246.50 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 23:10:27,642 epoch 3 - iter 132/447 - loss 0.08033167 - time (sec): 12.30 - samples/sec: 2212.91 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 23:10:31,335 epoch 3 - iter 176/447 - loss 0.07519298 - time (sec): 15.99 - samples/sec: 2203.20 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 23:10:35,695 epoch 3 - iter 220/447 - loss 0.07314322 - time (sec): 20.35 - samples/sec: 2186.49 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 23:10:39,980 epoch 3 - iter 264/447 - loss 0.07593556 - time (sec): 24.64 - samples/sec: 2176.38 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 23:10:43,901 epoch 3 - iter 308/447 - loss 0.07629546 - time (sec): 28.56 - samples/sec: 2161.66 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 23:10:47,582 epoch 3 - iter 352/447 - loss 0.07758371 - time (sec): 32.24 - samples/sec: 2141.69 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 23:10:51,499 epoch 3 - iter 396/447 - loss 0.07667548 - time (sec): 36.16 - samples/sec: 2152.05 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 23:10:55,266 epoch 3 - iter 440/447 - loss 0.07715178 - time (sec): 39.93 - samples/sec: 2140.07 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 23:10:55,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:10:55,806 EPOCH 3 done: loss 0.0770 - lr: 0.000039 | |
| 2023-10-23 23:11:02,275 DEV : loss 0.15030179917812347 - f1-score (micro avg) 0.7238 | |
| 2023-10-23 23:11:02,295 saving best model | |
| 2023-10-23 23:11:02,975 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:11:06,783 epoch 4 - iter 44/447 - loss 0.04797574 - time (sec): 3.81 - samples/sec: 2181.58 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 23:11:11,093 epoch 4 - iter 88/447 - loss 0.04426022 - time (sec): 8.12 - samples/sec: 2169.33 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 23:11:15,295 epoch 4 - iter 132/447 - loss 0.04936236 - time (sec): 12.32 - samples/sec: 2146.96 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 23:11:19,019 epoch 4 - iter 176/447 - loss 0.04772664 - time (sec): 16.04 - samples/sec: 2124.81 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 23:11:23,603 epoch 4 - iter 220/447 - loss 0.05048456 - time (sec): 20.63 - samples/sec: 2113.87 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 23:11:27,386 epoch 4 - iter 264/447 - loss 0.04914078 - time (sec): 24.41 - samples/sec: 2109.21 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 23:11:31,436 epoch 4 - iter 308/447 - loss 0.05102896 - time (sec): 28.46 - samples/sec: 2130.52 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 23:11:35,388 epoch 4 - iter 352/447 - loss 0.04983912 - time (sec): 32.41 - samples/sec: 2128.90 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 23:11:39,226 epoch 4 - iter 396/447 - loss 0.04862449 - time (sec): 36.25 - samples/sec: 2128.71 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 23:11:43,063 epoch 4 - iter 440/447 - loss 0.04914043 - time (sec): 40.09 - samples/sec: 2126.14 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 23:11:43,676 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:11:43,676 EPOCH 4 done: loss 0.0491 - lr: 0.000033 | |
| 2023-10-23 23:11:50,165 DEV : loss 0.15656068921089172 - f1-score (micro avg) 0.7269 | |
| 2023-10-23 23:11:50,185 saving best model | |
| 2023-10-23 23:11:50,988 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:11:54,902 epoch 5 - iter 44/447 - loss 0.03002117 - time (sec): 3.91 - samples/sec: 2187.36 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 23:11:59,212 epoch 5 - iter 88/447 - loss 0.02728072 - time (sec): 8.22 - samples/sec: 2120.86 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 23:12:03,032 epoch 5 - iter 132/447 - loss 0.02895759 - time (sec): 12.04 - samples/sec: 2136.02 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 23:12:06,776 epoch 5 - iter 176/447 - loss 0.03074911 - time (sec): 15.79 - samples/sec: 2136.86 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 23:12:10,831 epoch 5 - iter 220/447 - loss 0.03293494 - time (sec): 19.84 - samples/sec: 2125.55 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 23:12:14,878 epoch 5 - iter 264/447 - loss 0.03246686 - time (sec): 23.89 - samples/sec: 2117.56 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 23:12:18,517 epoch 5 - iter 308/447 - loss 0.03300365 - time (sec): 27.53 - samples/sec: 2127.25 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 23:12:22,916 epoch 5 - iter 352/447 - loss 0.03468769 - time (sec): 31.93 - samples/sec: 2128.62 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:12:26,745 epoch 5 - iter 396/447 - loss 0.03430249 - time (sec): 35.76 - samples/sec: 2140.22 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 23:12:30,698 epoch 5 - iter 440/447 - loss 0.03391188 - time (sec): 39.71 - samples/sec: 2143.57 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 23:12:31,298 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:12:31,298 EPOCH 5 done: loss 0.0339 - lr: 0.000028 | |
| 2023-10-23 23:12:37,775 DEV : loss 0.20451626181602478 - f1-score (micro avg) 0.7428 | |
| 2023-10-23 23:12:37,795 saving best model | |
| 2023-10-23 23:12:38,499 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:12:42,599 epoch 6 - iter 44/447 - loss 0.02170057 - time (sec): 4.10 - samples/sec: 2012.29 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:12:46,760 epoch 6 - iter 88/447 - loss 0.02124938 - time (sec): 8.26 - samples/sec: 2053.64 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:12:51,324 epoch 6 - iter 132/447 - loss 0.01971043 - time (sec): 12.82 - samples/sec: 2073.96 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 23:12:55,094 epoch 6 - iter 176/447 - loss 0.02017089 - time (sec): 16.59 - samples/sec: 2093.75 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 23:12:58,991 epoch 6 - iter 220/447 - loss 0.02245611 - time (sec): 20.49 - samples/sec: 2107.08 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 23:13:02,855 epoch 6 - iter 264/447 - loss 0.02192478 - time (sec): 24.36 - samples/sec: 2114.08 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 23:13:06,613 epoch 6 - iter 308/447 - loss 0.02597977 - time (sec): 28.11 - samples/sec: 2110.28 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:13:10,309 epoch 6 - iter 352/447 - loss 0.02523379 - time (sec): 31.81 - samples/sec: 2110.92 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 23:13:14,459 epoch 6 - iter 396/447 - loss 0.02528112 - time (sec): 35.96 - samples/sec: 2117.03 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 23:13:18,376 epoch 6 - iter 440/447 - loss 0.02605289 - time (sec): 39.88 - samples/sec: 2136.22 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 23:13:19,036 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:13:19,037 EPOCH 6 done: loss 0.0258 - lr: 0.000022 | |
| 2023-10-23 23:13:25,516 DEV : loss 0.2170478105545044 - f1-score (micro avg) 0.7614 | |
| 2023-10-23 23:13:25,535 saving best model | |
| 2023-10-23 23:13:26,188 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:13:30,487 epoch 7 - iter 44/447 - loss 0.01538206 - time (sec): 4.30 - samples/sec: 2125.61 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 23:13:34,505 epoch 7 - iter 88/447 - loss 0.01267065 - time (sec): 8.32 - samples/sec: 2125.87 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:13:38,226 epoch 7 - iter 132/447 - loss 0.01358387 - time (sec): 12.04 - samples/sec: 2144.81 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:13:42,418 epoch 7 - iter 176/447 - loss 0.01343420 - time (sec): 16.23 - samples/sec: 2174.12 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:13:46,425 epoch 7 - iter 220/447 - loss 0.01768025 - time (sec): 20.24 - samples/sec: 2148.41 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:13:50,570 epoch 7 - iter 264/447 - loss 0.01641940 - time (sec): 24.38 - samples/sec: 2131.58 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 23:13:54,456 epoch 7 - iter 308/447 - loss 0.01606435 - time (sec): 28.27 - samples/sec: 2137.45 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:13:58,669 epoch 7 - iter 352/447 - loss 0.01613984 - time (sec): 32.48 - samples/sec: 2138.73 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:14:02,734 epoch 7 - iter 396/447 - loss 0.01570408 - time (sec): 36.55 - samples/sec: 2134.97 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 23:14:06,299 epoch 7 - iter 440/447 - loss 0.01613572 - time (sec): 40.11 - samples/sec: 2127.49 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 23:14:06,864 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:14:06,864 EPOCH 7 done: loss 0.0161 - lr: 0.000017 | |
| 2023-10-23 23:14:13,333 DEV : loss 0.23187175393104553 - f1-score (micro avg) 0.7806 | |
| 2023-10-23 23:14:13,353 saving best model | |
| 2023-10-23 23:14:14,060 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:14:17,973 epoch 8 - iter 44/447 - loss 0.01336597 - time (sec): 3.91 - samples/sec: 2170.87 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 23:14:22,346 epoch 8 - iter 88/447 - loss 0.01477991 - time (sec): 8.29 - samples/sec: 2121.51 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 23:14:26,105 epoch 8 - iter 132/447 - loss 0.01321960 - time (sec): 12.04 - samples/sec: 2137.93 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:14:30,061 epoch 8 - iter 176/447 - loss 0.01275806 - time (sec): 16.00 - samples/sec: 2113.90 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:14:33,963 epoch 8 - iter 220/447 - loss 0.01276995 - time (sec): 19.90 - samples/sec: 2119.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 23:14:37,589 epoch 8 - iter 264/447 - loss 0.01257530 - time (sec): 23.53 - samples/sec: 2133.43 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 23:14:41,523 epoch 8 - iter 308/447 - loss 0.01188743 - time (sec): 27.46 - samples/sec: 2139.33 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 23:14:46,168 epoch 8 - iter 352/447 - loss 0.01152702 - time (sec): 32.11 - samples/sec: 2127.33 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:14:50,037 epoch 8 - iter 396/447 - loss 0.01253502 - time (sec): 35.98 - samples/sec: 2145.76 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:14:53,846 epoch 8 - iter 440/447 - loss 0.01242547 - time (sec): 39.79 - samples/sec: 2145.24 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 23:14:54,454 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:14:54,455 EPOCH 8 done: loss 0.0126 - lr: 0.000011 | |
| 2023-10-23 23:15:00,672 DEV : loss 0.25415274500846863 - f1-score (micro avg) 0.7639 | |
| 2023-10-23 23:15:00,692 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:15:04,596 epoch 9 - iter 44/447 - loss 0.00714680 - time (sec): 3.90 - samples/sec: 2135.73 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 23:15:08,853 epoch 9 - iter 88/447 - loss 0.00594912 - time (sec): 8.16 - samples/sec: 2108.50 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:15:13,106 epoch 9 - iter 132/447 - loss 0.00597966 - time (sec): 12.41 - samples/sec: 2114.70 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:15:16,844 epoch 9 - iter 176/447 - loss 0.00580727 - time (sec): 16.15 - samples/sec: 2123.16 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 23:15:20,658 epoch 9 - iter 220/447 - loss 0.00487805 - time (sec): 19.97 - samples/sec: 2143.39 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 23:15:24,215 epoch 9 - iter 264/447 - loss 0.00589291 - time (sec): 23.52 - samples/sec: 2136.72 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 23:15:28,396 epoch 9 - iter 308/447 - loss 0.00563785 - time (sec): 27.70 - samples/sec: 2132.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 23:15:32,702 epoch 9 - iter 352/447 - loss 0.00592797 - time (sec): 32.01 - samples/sec: 2146.78 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 23:15:36,654 epoch 9 - iter 396/447 - loss 0.00641546 - time (sec): 35.96 - samples/sec: 2132.53 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:15:40,759 epoch 9 - iter 440/447 - loss 0.00638558 - time (sec): 40.07 - samples/sec: 2125.63 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:15:41,327 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:15:41,327 EPOCH 9 done: loss 0.0065 - lr: 0.000006 | |
| 2023-10-23 23:15:47,534 DEV : loss 0.2673643231391907 - f1-score (micro avg) 0.7574 | |
| 2023-10-23 23:15:47,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:15:51,278 epoch 10 - iter 44/447 - loss 0.00836690 - time (sec): 3.72 - samples/sec: 2141.97 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:15:55,016 epoch 10 - iter 88/447 - loss 0.00437091 - time (sec): 7.46 - samples/sec: 2131.00 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:15:59,096 epoch 10 - iter 132/447 - loss 0.00373131 - time (sec): 11.54 - samples/sec: 2151.94 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 23:16:03,686 epoch 10 - iter 176/447 - loss 0.00354035 - time (sec): 16.13 - samples/sec: 2099.39 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:16:07,914 epoch 10 - iter 220/447 - loss 0.00388026 - time (sec): 20.36 - samples/sec: 2107.69 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:16:11,759 epoch 10 - iter 264/447 - loss 0.00333544 - time (sec): 24.20 - samples/sec: 2114.67 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 23:16:15,479 epoch 10 - iter 308/447 - loss 0.00354977 - time (sec): 27.92 - samples/sec: 2121.71 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 23:16:19,304 epoch 10 - iter 352/447 - loss 0.00329614 - time (sec): 31.75 - samples/sec: 2122.26 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:16:23,342 epoch 10 - iter 396/447 - loss 0.00360615 - time (sec): 35.79 - samples/sec: 2130.55 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:16:27,685 epoch 10 - iter 440/447 - loss 0.00375059 - time (sec): 40.13 - samples/sec: 2118.59 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 23:16:28,315 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:16:28,315 EPOCH 10 done: loss 0.0037 - lr: 0.000000 | |
| 2023-10-23 23:16:34,547 DEV : loss 0.257240891456604 - f1-score (micro avg) 0.7644 | |
| 2023-10-23 23:16:35,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:16:35,124 Loading model from best epoch ... | |
| 2023-10-23 23:16:36,865 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-23 23:16:41,683 | |
| Results: | |
| - F-score (micro) 0.746 | |
| - F-score (macro) 0.6591 | |
| - Accuracy 0.6121 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8388 0.8641 0.8512 596 | |
| pers 0.6378 0.7297 0.6807 333 | |
| org 0.5726 0.5076 0.5382 132 | |
| prod 0.6800 0.5152 0.5862 66 | |
| time 0.6458 0.6327 0.6392 49 | |
| micro avg 0.7355 0.7568 0.7460 1176 | |
| macro avg 0.6750 0.6498 0.6591 1176 | |
| weighted avg 0.7350 0.7568 0.7441 1176 | |
| 2023-10-23 23:16:41,683 ---------------------------------------------------------------------------------------------------- | |