| 2023-10-23 19:27:33,410 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,411 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 19:27:33,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,411 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-23 19:27:33,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,411 Train: 966 sentences | |
| 2023-10-23 19:27:33,411 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 19:27:33,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,411 Training Params: | |
| 2023-10-23 19:27:33,411 - learning_rate: "5e-05" | |
| 2023-10-23 19:27:33,411 - mini_batch_size: "8" | |
| 2023-10-23 19:27:33,411 - max_epochs: "10" | |
| 2023-10-23 19:27:33,411 - shuffle: "True" | |
| 2023-10-23 19:27:33,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,411 Plugins: | |
| 2023-10-23 19:27:33,411 - TensorboardLogger | |
| 2023-10-23 19:27:33,411 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 19:27:33,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,412 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 19:27:33,412 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 19:27:33,412 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,412 Computation: | |
| 2023-10-23 19:27:33,412 - compute on device: cuda:0 | |
| 2023-10-23 19:27:33,412 - embedding storage: none | |
| 2023-10-23 19:27:33,412 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,412 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-23 19:27:33,412 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,412 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:33,412 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 19:27:34,504 epoch 1 - iter 12/121 - loss 3.42104153 - time (sec): 1.09 - samples/sec: 2250.74 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:27:35,570 epoch 1 - iter 24/121 - loss 2.64659630 - time (sec): 2.16 - samples/sec: 2436.14 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:27:36,581 epoch 1 - iter 36/121 - loss 2.09667890 - time (sec): 3.17 - samples/sec: 2349.71 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:27:37,633 epoch 1 - iter 48/121 - loss 1.72138512 - time (sec): 4.22 - samples/sec: 2371.57 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:27:38,721 epoch 1 - iter 60/121 - loss 1.45843366 - time (sec): 5.31 - samples/sec: 2383.61 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:27:39,787 epoch 1 - iter 72/121 - loss 1.30194638 - time (sec): 6.37 - samples/sec: 2343.71 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:27:40,839 epoch 1 - iter 84/121 - loss 1.16439863 - time (sec): 7.43 - samples/sec: 2324.58 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:27:41,887 epoch 1 - iter 96/121 - loss 1.05420639 - time (sec): 8.47 - samples/sec: 2337.46 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 19:27:43,048 epoch 1 - iter 108/121 - loss 0.98046690 - time (sec): 9.64 - samples/sec: 2294.25 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 19:27:44,092 epoch 1 - iter 120/121 - loss 0.89973958 - time (sec): 10.68 - samples/sec: 2301.32 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:27:44,169 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:44,169 EPOCH 1 done: loss 0.8956 - lr: 0.000049 | |
| 2023-10-23 19:27:44,791 DEV : loss 0.17905257642269135 - f1-score (micro avg) 0.5888 | |
| 2023-10-23 19:27:44,795 saving best model | |
| 2023-10-23 19:27:45,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:46,264 epoch 2 - iter 12/121 - loss 0.17445847 - time (sec): 1.00 - samples/sec: 2412.26 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:27:47,403 epoch 2 - iter 24/121 - loss 0.19564770 - time (sec): 2.14 - samples/sec: 2330.04 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:27:48,565 epoch 2 - iter 36/121 - loss 0.17891695 - time (sec): 3.30 - samples/sec: 2377.99 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 19:27:49,573 epoch 2 - iter 48/121 - loss 0.17297150 - time (sec): 4.31 - samples/sec: 2427.86 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 19:27:50,544 epoch 2 - iter 60/121 - loss 0.16309845 - time (sec): 5.28 - samples/sec: 2407.14 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 19:27:51,663 epoch 2 - iter 72/121 - loss 0.16503656 - time (sec): 6.40 - samples/sec: 2377.11 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 19:27:52,722 epoch 2 - iter 84/121 - loss 0.16126897 - time (sec): 7.46 - samples/sec: 2351.77 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 19:27:53,739 epoch 2 - iter 96/121 - loss 0.15729330 - time (sec): 8.48 - samples/sec: 2331.63 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 19:27:54,887 epoch 2 - iter 108/121 - loss 0.15122175 - time (sec): 9.62 - samples/sec: 2316.98 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 19:27:55,899 epoch 2 - iter 120/121 - loss 0.14624853 - time (sec): 10.64 - samples/sec: 2315.38 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 19:27:55,967 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:55,967 EPOCH 2 done: loss 0.1464 - lr: 0.000045 | |
| 2023-10-23 19:27:56,779 DEV : loss 0.12970523536205292 - f1-score (micro avg) 0.7724 | |
| 2023-10-23 19:27:56,783 saving best model | |
| 2023-10-23 19:27:57,359 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:27:58,425 epoch 3 - iter 12/121 - loss 0.09499930 - time (sec): 1.06 - samples/sec: 2541.97 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 19:27:59,439 epoch 3 - iter 24/121 - loss 0.07978542 - time (sec): 2.08 - samples/sec: 2438.93 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 19:28:00,528 epoch 3 - iter 36/121 - loss 0.07229853 - time (sec): 3.17 - samples/sec: 2378.39 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 19:28:01,592 epoch 3 - iter 48/121 - loss 0.08251789 - time (sec): 4.23 - samples/sec: 2388.63 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 19:28:02,747 epoch 3 - iter 60/121 - loss 0.08365089 - time (sec): 5.39 - samples/sec: 2363.07 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 19:28:03,844 epoch 3 - iter 72/121 - loss 0.08656341 - time (sec): 6.48 - samples/sec: 2331.25 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 19:28:04,899 epoch 3 - iter 84/121 - loss 0.08457550 - time (sec): 7.54 - samples/sec: 2323.62 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 19:28:05,859 epoch 3 - iter 96/121 - loss 0.08604308 - time (sec): 8.50 - samples/sec: 2329.79 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 19:28:06,964 epoch 3 - iter 108/121 - loss 0.08775648 - time (sec): 9.60 - samples/sec: 2339.01 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 19:28:08,021 epoch 3 - iter 120/121 - loss 0.08598599 - time (sec): 10.66 - samples/sec: 2307.20 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 19:28:08,087 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:08,088 EPOCH 3 done: loss 0.0868 - lr: 0.000039 | |
| 2023-10-23 19:28:08,781 DEV : loss 0.11623530834913254 - f1-score (micro avg) 0.8147 | |
| 2023-10-23 19:28:08,785 saving best model | |
| 2023-10-23 19:28:09,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:10,461 epoch 4 - iter 12/121 - loss 0.04250684 - time (sec): 1.04 - samples/sec: 2323.85 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 19:28:11,562 epoch 4 - iter 24/121 - loss 0.05136450 - time (sec): 2.14 - samples/sec: 2246.36 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 19:28:12,563 epoch 4 - iter 36/121 - loss 0.04907237 - time (sec): 3.14 - samples/sec: 2313.00 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 19:28:13,690 epoch 4 - iter 48/121 - loss 0.04578299 - time (sec): 4.27 - samples/sec: 2343.86 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 19:28:14,752 epoch 4 - iter 60/121 - loss 0.05027930 - time (sec): 5.33 - samples/sec: 2334.82 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 19:28:15,832 epoch 4 - iter 72/121 - loss 0.06051901 - time (sec): 6.41 - samples/sec: 2290.63 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 19:28:16,845 epoch 4 - iter 84/121 - loss 0.05879935 - time (sec): 7.43 - samples/sec: 2303.50 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 19:28:18,115 epoch 4 - iter 96/121 - loss 0.05773448 - time (sec): 8.70 - samples/sec: 2316.49 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 19:28:19,141 epoch 4 - iter 108/121 - loss 0.05724558 - time (sec): 9.72 - samples/sec: 2314.85 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:28:20,159 epoch 4 - iter 120/121 - loss 0.05573016 - time (sec): 10.74 - samples/sec: 2292.77 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:28:20,227 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:20,227 EPOCH 4 done: loss 0.0568 - lr: 0.000034 | |
| 2023-10-23 19:28:20,924 DEV : loss 0.12099868804216385 - f1-score (micro avg) 0.8464 | |
| 2023-10-23 19:28:20,928 saving best model | |
| 2023-10-23 19:28:21,514 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:22,569 epoch 5 - iter 12/121 - loss 0.05775988 - time (sec): 1.05 - samples/sec: 2274.82 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 19:28:23,679 epoch 5 - iter 24/121 - loss 0.04756081 - time (sec): 2.16 - samples/sec: 2212.81 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 19:28:24,779 epoch 5 - iter 36/121 - loss 0.04524400 - time (sec): 3.26 - samples/sec: 2266.17 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 19:28:25,761 epoch 5 - iter 48/121 - loss 0.04138624 - time (sec): 4.25 - samples/sec: 2261.44 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 19:28:26,867 epoch 5 - iter 60/121 - loss 0.04433795 - time (sec): 5.35 - samples/sec: 2277.05 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 19:28:27,983 epoch 5 - iter 72/121 - loss 0.04136555 - time (sec): 6.47 - samples/sec: 2276.74 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:28:29,076 epoch 5 - iter 84/121 - loss 0.03747449 - time (sec): 7.56 - samples/sec: 2264.11 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:28:30,052 epoch 5 - iter 96/121 - loss 0.03968636 - time (sec): 8.54 - samples/sec: 2256.00 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:28:31,143 epoch 5 - iter 108/121 - loss 0.03777407 - time (sec): 9.63 - samples/sec: 2281.60 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:28:32,256 epoch 5 - iter 120/121 - loss 0.03635679 - time (sec): 10.74 - samples/sec: 2294.62 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:28:32,318 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:32,319 EPOCH 5 done: loss 0.0365 - lr: 0.000028 | |
| 2023-10-23 19:28:33,016 DEV : loss 0.16964927315711975 - f1-score (micro avg) 0.827 | |
| 2023-10-23 19:28:33,020 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:34,116 epoch 6 - iter 12/121 - loss 0.02608706 - time (sec): 1.10 - samples/sec: 2433.49 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:28:35,197 epoch 6 - iter 24/121 - loss 0.03454313 - time (sec): 2.18 - samples/sec: 2279.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:28:36,260 epoch 6 - iter 36/121 - loss 0.02844122 - time (sec): 3.24 - samples/sec: 2257.93 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:28:37,282 epoch 6 - iter 48/121 - loss 0.02416834 - time (sec): 4.26 - samples/sec: 2302.46 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:28:38,232 epoch 6 - iter 60/121 - loss 0.02810215 - time (sec): 5.21 - samples/sec: 2282.75 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:28:39,312 epoch 6 - iter 72/121 - loss 0.02722230 - time (sec): 6.29 - samples/sec: 2269.68 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:28:40,451 epoch 6 - iter 84/121 - loss 0.02476261 - time (sec): 7.43 - samples/sec: 2294.62 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:28:41,556 epoch 6 - iter 96/121 - loss 0.02578860 - time (sec): 8.54 - samples/sec: 2284.38 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:28:42,674 epoch 6 - iter 108/121 - loss 0.02617923 - time (sec): 9.65 - samples/sec: 2303.93 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:28:43,694 epoch 6 - iter 120/121 - loss 0.02707977 - time (sec): 10.67 - samples/sec: 2305.33 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:28:43,772 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:43,772 EPOCH 6 done: loss 0.0269 - lr: 0.000022 | |
| 2023-10-23 19:28:44,466 DEV : loss 0.14319932460784912 - f1-score (micro avg) 0.8501 | |
| 2023-10-23 19:28:44,470 saving best model | |
| 2023-10-23 19:28:45,087 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:46,197 epoch 7 - iter 12/121 - loss 0.00430378 - time (sec): 1.11 - samples/sec: 2291.16 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:28:47,202 epoch 7 - iter 24/121 - loss 0.01397175 - time (sec): 2.11 - samples/sec: 2318.05 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:28:48,262 epoch 7 - iter 36/121 - loss 0.02015329 - time (sec): 3.17 - samples/sec: 2329.11 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:28:49,425 epoch 7 - iter 48/121 - loss 0.01991751 - time (sec): 4.34 - samples/sec: 2312.46 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:28:50,487 epoch 7 - iter 60/121 - loss 0.01776428 - time (sec): 5.40 - samples/sec: 2326.90 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:28:51,526 epoch 7 - iter 72/121 - loss 0.01986543 - time (sec): 6.44 - samples/sec: 2335.61 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:28:52,581 epoch 7 - iter 84/121 - loss 0.01846366 - time (sec): 7.49 - samples/sec: 2309.27 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:28:53,577 epoch 7 - iter 96/121 - loss 0.01867686 - time (sec): 8.49 - samples/sec: 2315.19 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:28:54,706 epoch 7 - iter 108/121 - loss 0.01791991 - time (sec): 9.62 - samples/sec: 2315.75 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:28:55,734 epoch 7 - iter 120/121 - loss 0.01745004 - time (sec): 10.65 - samples/sec: 2305.85 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:28:55,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:55,824 EPOCH 7 done: loss 0.0174 - lr: 0.000017 | |
| 2023-10-23 19:28:56,516 DEV : loss 0.16298003494739532 - f1-score (micro avg) 0.8561 | |
| 2023-10-23 19:28:56,520 saving best model | |
| 2023-10-23 19:28:57,114 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:28:58,233 epoch 8 - iter 12/121 - loss 0.00788978 - time (sec): 1.12 - samples/sec: 2423.16 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:28:59,284 epoch 8 - iter 24/121 - loss 0.00869807 - time (sec): 2.17 - samples/sec: 2286.59 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:29:00,364 epoch 8 - iter 36/121 - loss 0.00860107 - time (sec): 3.25 - samples/sec: 2254.35 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:29:01,388 epoch 8 - iter 48/121 - loss 0.00997976 - time (sec): 4.27 - samples/sec: 2241.79 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:29:02,461 epoch 8 - iter 60/121 - loss 0.01464942 - time (sec): 5.35 - samples/sec: 2259.64 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:29:03,555 epoch 8 - iter 72/121 - loss 0.01360052 - time (sec): 6.44 - samples/sec: 2245.54 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:29:04,681 epoch 8 - iter 84/121 - loss 0.01418070 - time (sec): 7.57 - samples/sec: 2273.36 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:29:05,775 epoch 8 - iter 96/121 - loss 0.01266537 - time (sec): 8.66 - samples/sec: 2288.03 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:29:06,754 epoch 8 - iter 108/121 - loss 0.01342364 - time (sec): 9.64 - samples/sec: 2292.87 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:29:07,800 epoch 8 - iter 120/121 - loss 0.01296654 - time (sec): 10.68 - samples/sec: 2298.63 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:29:07,874 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:07,874 EPOCH 8 done: loss 0.0129 - lr: 0.000011 | |
| 2023-10-23 19:29:08,568 DEV : loss 0.17610150575637817 - f1-score (micro avg) 0.8466 | |
| 2023-10-23 19:29:08,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:09,621 epoch 9 - iter 12/121 - loss 0.01361472 - time (sec): 1.05 - samples/sec: 2432.65 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:29:10,726 epoch 9 - iter 24/121 - loss 0.00905077 - time (sec): 2.15 - samples/sec: 2337.26 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:29:11,766 epoch 9 - iter 36/121 - loss 0.00800268 - time (sec): 3.19 - samples/sec: 2301.71 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:29:12,977 epoch 9 - iter 48/121 - loss 0.00702949 - time (sec): 4.40 - samples/sec: 2294.35 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:29:13,986 epoch 9 - iter 60/121 - loss 0.00670050 - time (sec): 5.41 - samples/sec: 2323.57 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:29:15,007 epoch 9 - iter 72/121 - loss 0.00850918 - time (sec): 6.43 - samples/sec: 2318.33 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:29:16,050 epoch 9 - iter 84/121 - loss 0.00735089 - time (sec): 7.48 - samples/sec: 2334.93 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:29:17,110 epoch 9 - iter 96/121 - loss 0.00904772 - time (sec): 8.54 - samples/sec: 2338.96 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:29:18,178 epoch 9 - iter 108/121 - loss 0.00832127 - time (sec): 9.61 - samples/sec: 2309.48 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:29:19,266 epoch 9 - iter 120/121 - loss 0.00875682 - time (sec): 10.69 - samples/sec: 2303.64 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:29:19,330 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:19,330 EPOCH 9 done: loss 0.0087 - lr: 0.000006 | |
| 2023-10-23 19:29:20,024 DEV : loss 0.17735370993614197 - f1-score (micro avg) 0.8614 | |
| 2023-10-23 19:29:20,028 saving best model | |
| 2023-10-23 19:29:20,625 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:21,679 epoch 10 - iter 12/121 - loss 0.00102659 - time (sec): 1.05 - samples/sec: 2279.58 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:29:22,760 epoch 10 - iter 24/121 - loss 0.00080514 - time (sec): 2.13 - samples/sec: 2359.00 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:29:23,790 epoch 10 - iter 36/121 - loss 0.00345359 - time (sec): 3.16 - samples/sec: 2331.26 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:29:24,850 epoch 10 - iter 48/121 - loss 0.00290511 - time (sec): 4.22 - samples/sec: 2324.15 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:29:25,947 epoch 10 - iter 60/121 - loss 0.00621214 - time (sec): 5.32 - samples/sec: 2295.37 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:29:27,038 epoch 10 - iter 72/121 - loss 0.00639320 - time (sec): 6.41 - samples/sec: 2280.83 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:29:28,029 epoch 10 - iter 84/121 - loss 0.00621899 - time (sec): 7.40 - samples/sec: 2302.68 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:29:29,060 epoch 10 - iter 96/121 - loss 0.00590561 - time (sec): 8.43 - samples/sec: 2299.29 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:29:30,165 epoch 10 - iter 108/121 - loss 0.00585932 - time (sec): 9.54 - samples/sec: 2308.36 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:29:31,296 epoch 10 - iter 120/121 - loss 0.00576277 - time (sec): 10.67 - samples/sec: 2295.90 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:29:31,393 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:31,393 EPOCH 10 done: loss 0.0059 - lr: 0.000000 | |
| 2023-10-23 19:29:32,084 DEV : loss 0.18404731154441833 - f1-score (micro avg) 0.8653 | |
| 2023-10-23 19:29:32,088 saving best model | |
| 2023-10-23 19:29:33,153 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:29:33,153 Loading model from best epoch ... | |
| 2023-10-23 19:29:34,629 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-23 19:29:35,478 | |
| Results: | |
| - F-score (micro) 0.8235 | |
| - F-score (macro) 0.5918 | |
| - Accuracy 0.7218 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8841 0.8777 0.8809 139 | |
| scope 0.8248 0.8760 0.8496 129 | |
| work 0.6774 0.7875 0.7283 80 | |
| loc 1.0000 0.3333 0.5000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.8113 0.8361 0.8235 360 | |
| macro avg 0.6773 0.5749 0.5918 360 | |
| weighted avg 0.8124 0.8361 0.8189 360 | |
| 2023-10-23 19:29:35,478 ---------------------------------------------------------------------------------------------------- | |