| 2023-10-23 21:13:14,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,095 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 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 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 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Train: 3575 sentences | |
| 2023-10-23 21:13:14,096 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Training Params: | |
| 2023-10-23 21:13:14,096 - learning_rate: "5e-05" | |
| 2023-10-23 21:13:14,096 - mini_batch_size: "8" | |
| 2023-10-23 21:13:14,096 - max_epochs: "10" | |
| 2023-10-23 21:13:14,096 - shuffle: "True" | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Plugins: | |
| 2023-10-23 21:13:14,096 - TensorboardLogger | |
| 2023-10-23 21:13:14,096 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 21:13:14,096 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Computation: | |
| 2023-10-23 21:13:14,096 - compute on device: cuda:0 | |
| 2023-10-23 21:13:14,096 - embedding storage: none | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:14,096 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 21:13:17,881 epoch 1 - iter 44/447 - loss 2.49175659 - time (sec): 3.78 - samples/sec: 2075.50 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:13:21,992 epoch 1 - iter 88/447 - loss 1.47620142 - time (sec): 7.89 - samples/sec: 2092.81 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:13:26,073 epoch 1 - iter 132/447 - loss 1.09754009 - time (sec): 11.98 - samples/sec: 2087.54 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:13:30,090 epoch 1 - iter 176/447 - loss 0.91399479 - time (sec): 15.99 - samples/sec: 2082.94 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:13:33,970 epoch 1 - iter 220/447 - loss 0.79606073 - time (sec): 19.87 - samples/sec: 2107.84 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:13:37,765 epoch 1 - iter 264/447 - loss 0.71083825 - time (sec): 23.67 - samples/sec: 2107.04 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:13:41,687 epoch 1 - iter 308/447 - loss 0.64270297 - time (sec): 27.59 - samples/sec: 2109.42 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 21:13:45,652 epoch 1 - iter 352/447 - loss 0.58337536 - time (sec): 31.56 - samples/sec: 2111.17 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 21:13:50,089 epoch 1 - iter 396/447 - loss 0.53741990 - time (sec): 35.99 - samples/sec: 2126.06 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 21:13:53,893 epoch 1 - iter 440/447 - loss 0.50360530 - time (sec): 39.80 - samples/sec: 2139.48 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:13:54,507 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:13:54,507 EPOCH 1 done: loss 0.4979 - lr: 0.000049 | |
| 2023-10-23 21:13:59,344 DEV : loss 0.14264939725399017 - f1-score (micro avg) 0.649 | |
| 2023-10-23 21:13:59,365 saving best model | |
| 2023-10-23 21:13:59,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:14:03,572 epoch 2 - iter 44/447 - loss 0.17136363 - time (sec): 3.73 - samples/sec: 2204.31 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:14:07,600 epoch 2 - iter 88/447 - loss 0.14665351 - time (sec): 7.76 - samples/sec: 2168.58 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:14:11,683 epoch 2 - iter 132/447 - loss 0.13770205 - time (sec): 11.84 - samples/sec: 2165.41 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 21:14:15,810 epoch 2 - iter 176/447 - loss 0.13975349 - time (sec): 15.97 - samples/sec: 2152.86 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 21:14:19,583 epoch 2 - iter 220/447 - loss 0.13141036 - time (sec): 19.74 - samples/sec: 2131.99 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 21:14:23,712 epoch 2 - iter 264/447 - loss 0.13359602 - time (sec): 23.87 - samples/sec: 2136.28 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 21:14:27,728 epoch 2 - iter 308/447 - loss 0.13099589 - time (sec): 27.89 - samples/sec: 2141.32 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 21:14:31,359 epoch 2 - iter 352/447 - loss 0.13108938 - time (sec): 31.52 - samples/sec: 2145.97 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 21:14:35,837 epoch 2 - iter 396/447 - loss 0.13272083 - time (sec): 35.99 - samples/sec: 2139.98 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 21:14:39,654 epoch 2 - iter 440/447 - loss 0.13058338 - time (sec): 39.81 - samples/sec: 2138.26 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 21:14:40,251 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:14:40,251 EPOCH 2 done: loss 0.1303 - lr: 0.000045 | |
| 2023-10-23 21:14:46,728 DEV : loss 0.12430483102798462 - f1-score (micro avg) 0.7252 | |
| 2023-10-23 21:14:46,749 saving best model | |
| 2023-10-23 21:14:47,345 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:14:51,416 epoch 3 - iter 44/447 - loss 0.06343382 - time (sec): 4.07 - samples/sec: 2147.46 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 21:14:55,502 epoch 3 - iter 88/447 - loss 0.07942642 - time (sec): 8.16 - samples/sec: 2140.20 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 21:14:59,641 epoch 3 - iter 132/447 - loss 0.07644302 - time (sec): 12.30 - samples/sec: 2162.74 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 21:15:03,560 epoch 3 - iter 176/447 - loss 0.07415197 - time (sec): 16.21 - samples/sec: 2126.47 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 21:15:07,434 epoch 3 - iter 220/447 - loss 0.07458049 - time (sec): 20.09 - samples/sec: 2144.74 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 21:15:11,199 epoch 3 - iter 264/447 - loss 0.07373489 - time (sec): 23.85 - samples/sec: 2150.21 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 21:15:15,070 epoch 3 - iter 308/447 - loss 0.07485896 - time (sec): 27.72 - samples/sec: 2142.33 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 21:15:19,242 epoch 3 - iter 352/447 - loss 0.07147296 - time (sec): 31.90 - samples/sec: 2146.35 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 21:15:23,058 epoch 3 - iter 396/447 - loss 0.07105503 - time (sec): 35.71 - samples/sec: 2149.05 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 21:15:27,181 epoch 3 - iter 440/447 - loss 0.07201190 - time (sec): 39.83 - samples/sec: 2134.04 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 21:15:27,838 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:15:27,839 EPOCH 3 done: loss 0.0720 - lr: 0.000039 | |
| 2023-10-23 21:15:34,341 DEV : loss 0.13549202680587769 - f1-score (micro avg) 0.7124 | |
| 2023-10-23 21:15:34,361 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:15:38,090 epoch 4 - iter 44/447 - loss 0.04999690 - time (sec): 3.73 - samples/sec: 2136.07 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 21:15:42,151 epoch 4 - iter 88/447 - loss 0.04797379 - time (sec): 7.79 - samples/sec: 2115.30 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 21:15:46,201 epoch 4 - iter 132/447 - loss 0.04349472 - time (sec): 11.84 - samples/sec: 2134.54 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 21:15:50,375 epoch 4 - iter 176/447 - loss 0.04141184 - time (sec): 16.01 - samples/sec: 2118.29 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 21:15:54,562 epoch 4 - iter 220/447 - loss 0.04291677 - time (sec): 20.20 - samples/sec: 2110.96 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 21:15:58,592 epoch 4 - iter 264/447 - loss 0.04298733 - time (sec): 24.23 - samples/sec: 2118.23 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 21:16:02,830 epoch 4 - iter 308/447 - loss 0.04222533 - time (sec): 28.47 - samples/sec: 2119.43 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 21:16:06,714 epoch 4 - iter 352/447 - loss 0.04257038 - time (sec): 32.35 - samples/sec: 2124.33 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 21:16:10,630 epoch 4 - iter 396/447 - loss 0.04389888 - time (sec): 36.27 - samples/sec: 2125.21 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 21:16:14,412 epoch 4 - iter 440/447 - loss 0.04468753 - time (sec): 40.05 - samples/sec: 2129.68 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 21:16:15,005 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:16:15,005 EPOCH 4 done: loss 0.0453 - lr: 0.000033 | |
| 2023-10-23 21:16:21,523 DEV : loss 0.16867585480213165 - f1-score (micro avg) 0.7202 | |
| 2023-10-23 21:16:21,543 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:16:25,550 epoch 5 - iter 44/447 - loss 0.03485991 - time (sec): 4.01 - samples/sec: 2168.92 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 21:16:29,651 epoch 5 - iter 88/447 - loss 0.03804560 - time (sec): 8.11 - samples/sec: 2075.96 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 21:16:33,407 epoch 5 - iter 132/447 - loss 0.03565243 - time (sec): 11.86 - samples/sec: 2092.94 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 21:16:37,779 epoch 5 - iter 176/447 - loss 0.03560807 - time (sec): 16.23 - samples/sec: 2102.25 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 21:16:41,635 epoch 5 - iter 220/447 - loss 0.03534608 - time (sec): 20.09 - samples/sec: 2103.62 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 21:16:45,439 epoch 5 - iter 264/447 - loss 0.03359264 - time (sec): 23.90 - samples/sec: 2104.31 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 21:16:49,900 epoch 5 - iter 308/447 - loss 0.03114445 - time (sec): 28.36 - samples/sec: 2110.97 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 21:16:53,842 epoch 5 - iter 352/447 - loss 0.03263717 - time (sec): 32.30 - samples/sec: 2113.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:16:57,757 epoch 5 - iter 396/447 - loss 0.03153033 - time (sec): 36.21 - samples/sec: 2127.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:17:01,544 epoch 5 - iter 440/447 - loss 0.03214773 - time (sec): 40.00 - samples/sec: 2136.26 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:17:02,105 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:17:02,105 EPOCH 5 done: loss 0.0318 - lr: 0.000028 | |
| 2023-10-23 21:17:08,620 DEV : loss 0.19214682281017303 - f1-score (micro avg) 0.7459 | |
| 2023-10-23 21:17:08,640 saving best model | |
| 2023-10-23 21:17:09,235 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:17:13,106 epoch 6 - iter 44/447 - loss 0.02105748 - time (sec): 3.87 - samples/sec: 2043.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:17:17,057 epoch 6 - iter 88/447 - loss 0.01726201 - time (sec): 7.82 - samples/sec: 2046.65 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:17:21,186 epoch 6 - iter 132/447 - loss 0.01949802 - time (sec): 11.95 - samples/sec: 2075.00 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:17:25,225 epoch 6 - iter 176/447 - loss 0.02190376 - time (sec): 15.99 - samples/sec: 2125.97 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:17:29,209 epoch 6 - iter 220/447 - loss 0.02099074 - time (sec): 19.97 - samples/sec: 2137.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:17:33,283 epoch 6 - iter 264/447 - loss 0.02173912 - time (sec): 24.05 - samples/sec: 2116.13 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:17:37,096 epoch 6 - iter 308/447 - loss 0.02086471 - time (sec): 27.86 - samples/sec: 2127.79 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:17:41,021 epoch 6 - iter 352/447 - loss 0.02351890 - time (sec): 31.79 - samples/sec: 2134.36 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:17:45,297 epoch 6 - iter 396/447 - loss 0.02301478 - time (sec): 36.06 - samples/sec: 2126.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:17:49,167 epoch 6 - iter 440/447 - loss 0.02345262 - time (sec): 39.93 - samples/sec: 2139.26 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:17:49,731 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:17:49,731 EPOCH 6 done: loss 0.0235 - lr: 0.000022 | |
| 2023-10-23 21:17:56,209 DEV : loss 0.20100656151771545 - f1-score (micro avg) 0.7432 | |
| 2023-10-23 21:17:56,230 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:17:59,954 epoch 7 - iter 44/447 - loss 0.01434631 - time (sec): 3.72 - samples/sec: 2231.02 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:18:04,021 epoch 7 - iter 88/447 - loss 0.01477926 - time (sec): 7.79 - samples/sec: 2170.43 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:18:08,514 epoch 7 - iter 132/447 - loss 0.01339597 - time (sec): 12.28 - samples/sec: 2143.01 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:18:12,450 epoch 7 - iter 176/447 - loss 0.01300304 - time (sec): 16.22 - samples/sec: 2141.35 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:18:16,367 epoch 7 - iter 220/447 - loss 0.01258631 - time (sec): 20.14 - samples/sec: 2136.94 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:18:20,436 epoch 7 - iter 264/447 - loss 0.01333364 - time (sec): 24.21 - samples/sec: 2137.91 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 21:18:24,476 epoch 7 - iter 308/447 - loss 0.01331886 - time (sec): 28.25 - samples/sec: 2133.18 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:18:28,262 epoch 7 - iter 352/447 - loss 0.01320475 - time (sec): 32.03 - samples/sec: 2135.10 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:18:32,184 epoch 7 - iter 396/447 - loss 0.01306538 - time (sec): 35.95 - samples/sec: 2141.97 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:18:36,080 epoch 7 - iter 440/447 - loss 0.01247335 - time (sec): 39.85 - samples/sec: 2144.78 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:18:36,627 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:18:36,627 EPOCH 7 done: loss 0.0123 - lr: 0.000017 | |
| 2023-10-23 21:18:43,096 DEV : loss 0.2460336685180664 - f1-score (micro avg) 0.7548 | |
| 2023-10-23 21:18:43,116 saving best model | |
| 2023-10-23 21:18:43,685 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:18:47,540 epoch 8 - iter 44/447 - loss 0.01600473 - time (sec): 3.85 - samples/sec: 2174.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:18:51,458 epoch 8 - iter 88/447 - loss 0.01261638 - time (sec): 7.77 - samples/sec: 2168.27 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:18:55,297 epoch 8 - iter 132/447 - loss 0.01097643 - time (sec): 11.61 - samples/sec: 2125.13 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:18:59,926 epoch 8 - iter 176/447 - loss 0.00839399 - time (sec): 16.24 - samples/sec: 2140.26 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:19:03,883 epoch 8 - iter 220/447 - loss 0.00700836 - time (sec): 20.20 - samples/sec: 2146.24 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 21:19:07,540 epoch 8 - iter 264/447 - loss 0.00658404 - time (sec): 23.85 - samples/sec: 2123.74 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:19:11,710 epoch 8 - iter 308/447 - loss 0.00672887 - time (sec): 28.02 - samples/sec: 2123.98 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:19:15,680 epoch 8 - iter 352/447 - loss 0.00730350 - time (sec): 31.99 - samples/sec: 2126.26 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:19:20,096 epoch 8 - iter 396/447 - loss 0.00757808 - time (sec): 36.41 - samples/sec: 2121.30 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:19:23,827 epoch 8 - iter 440/447 - loss 0.00721160 - time (sec): 40.14 - samples/sec: 2121.34 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:19:24,443 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:19:24,444 EPOCH 8 done: loss 0.0080 - lr: 0.000011 | |
| 2023-10-23 21:19:30,630 DEV : loss 0.26853764057159424 - f1-score (micro avg) 0.7664 | |
| 2023-10-23 21:19:30,651 saving best model | |
| 2023-10-23 21:19:31,246 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:19:34,871 epoch 9 - iter 44/447 - loss 0.00413003 - time (sec): 3.62 - samples/sec: 2217.26 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:19:39,173 epoch 9 - iter 88/447 - loss 0.00874300 - time (sec): 7.93 - samples/sec: 2054.24 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:19:43,410 epoch 9 - iter 132/447 - loss 0.00637939 - time (sec): 12.16 - samples/sec: 2070.73 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:19:47,231 epoch 9 - iter 176/447 - loss 0.00677074 - time (sec): 15.98 - samples/sec: 2104.57 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:19:51,199 epoch 9 - iter 220/447 - loss 0.00601290 - time (sec): 19.95 - samples/sec: 2121.37 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:19:55,456 epoch 9 - iter 264/447 - loss 0.00551771 - time (sec): 24.21 - samples/sec: 2124.91 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:19:59,708 epoch 9 - iter 308/447 - loss 0.00532185 - time (sec): 28.46 - samples/sec: 2127.58 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:20:03,460 epoch 9 - iter 352/447 - loss 0.00602318 - time (sec): 32.21 - samples/sec: 2127.14 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:20:07,201 epoch 9 - iter 396/447 - loss 0.00619570 - time (sec): 35.95 - samples/sec: 2132.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:20:11,227 epoch 9 - iter 440/447 - loss 0.00584523 - time (sec): 39.98 - samples/sec: 2135.91 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:20:11,853 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:20:11,854 EPOCH 9 done: loss 0.0058 - lr: 0.000006 | |
| 2023-10-23 21:20:18,089 DEV : loss 0.259550541639328 - f1-score (micro avg) 0.768 | |
| 2023-10-23 21:20:18,110 saving best model | |
| 2023-10-23 21:20:18,700 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:20:22,576 epoch 10 - iter 44/447 - loss 0.00028617 - time (sec): 3.88 - samples/sec: 2214.84 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:20:26,741 epoch 10 - iter 88/447 - loss 0.00036442 - time (sec): 8.04 - samples/sec: 2165.17 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:20:30,674 epoch 10 - iter 132/447 - loss 0.00123632 - time (sec): 11.97 - samples/sec: 2150.91 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 21:20:34,613 epoch 10 - iter 176/447 - loss 0.00181556 - time (sec): 15.91 - samples/sec: 2137.75 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:20:38,919 epoch 10 - iter 220/447 - loss 0.00290602 - time (sec): 20.22 - samples/sec: 2145.60 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:20:42,689 epoch 10 - iter 264/447 - loss 0.00253256 - time (sec): 23.99 - samples/sec: 2136.16 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:20:46,503 epoch 10 - iter 308/447 - loss 0.00278757 - time (sec): 27.80 - samples/sec: 2147.54 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:20:50,596 epoch 10 - iter 352/447 - loss 0.00244091 - time (sec): 31.90 - samples/sec: 2139.99 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:20:54,908 epoch 10 - iter 396/447 - loss 0.00254504 - time (sec): 36.21 - samples/sec: 2122.45 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:20:58,966 epoch 10 - iter 440/447 - loss 0.00280141 - time (sec): 40.27 - samples/sec: 2116.87 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 21:20:59,589 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:20:59,589 EPOCH 10 done: loss 0.0028 - lr: 0.000000 | |
| 2023-10-23 21:21:05,787 DEV : loss 0.269205242395401 - f1-score (micro avg) 0.7664 | |
| 2023-10-23 21:21:06,277 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:21:06,278 Loading model from best epoch ... | |
| 2023-10-23 21:21:07,876 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 21:21:12,685 | |
| Results: | |
| - F-score (micro) 0.7505 | |
| - F-score (macro) 0.6658 | |
| - Accuracy 0.6185 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8249 0.8456 0.8351 596 | |
| pers 0.6959 0.7628 0.7278 333 | |
| org 0.5469 0.5303 0.5385 132 | |
| prod 0.6066 0.5606 0.5827 66 | |
| time 0.6818 0.6122 0.6452 49 | |
| micro avg 0.7403 0.7611 0.7505 1176 | |
| macro avg 0.6712 0.6623 0.6658 1176 | |
| weighted avg 0.7389 0.7611 0.7494 1176 | |
| 2023-10-23 21:21:12,685 ---------------------------------------------------------------------------------------------------- | |