| 2023-10-23 22:21:59,802 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,803 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 22:21:59,803 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 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 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Train: 3575 sentences | |
| 2023-10-23 22:21:59,804 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Training Params: | |
| 2023-10-23 22:21:59,804 - learning_rate: "3e-05" | |
| 2023-10-23 22:21:59,804 - mini_batch_size: "8" | |
| 2023-10-23 22:21:59,804 - max_epochs: "10" | |
| 2023-10-23 22:21:59,804 - shuffle: "True" | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Plugins: | |
| 2023-10-23 22:21:59,804 - TensorboardLogger | |
| 2023-10-23 22:21:59,804 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 22:21:59,804 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Computation: | |
| 2023-10-23 22:21:59,804 - compute on device: cuda:0 | |
| 2023-10-23 22:21:59,804 - embedding storage: none | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:21:59,804 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 22:22:03,847 epoch 1 - iter 44/447 - loss 2.92018008 - time (sec): 4.04 - samples/sec: 2032.64 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:22:07,968 epoch 1 - iter 88/447 - loss 1.92758216 - time (sec): 8.16 - samples/sec: 2089.91 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:22:11,886 epoch 1 - iter 132/447 - loss 1.46261625 - time (sec): 12.08 - samples/sec: 2086.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:22:15,679 epoch 1 - iter 176/447 - loss 1.22672961 - time (sec): 15.87 - samples/sec: 2103.25 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:22:19,568 epoch 1 - iter 220/447 - loss 1.04272271 - time (sec): 19.76 - samples/sec: 2125.02 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:22:23,281 epoch 1 - iter 264/447 - loss 0.91930567 - time (sec): 23.48 - samples/sec: 2138.47 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:22:27,217 epoch 1 - iter 308/447 - loss 0.82267150 - time (sec): 27.41 - samples/sec: 2146.19 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:22:31,115 epoch 1 - iter 352/447 - loss 0.74697299 - time (sec): 31.31 - samples/sec: 2150.51 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:22:34,954 epoch 1 - iter 396/447 - loss 0.69198290 - time (sec): 35.15 - samples/sec: 2151.70 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:22:39,219 epoch 1 - iter 440/447 - loss 0.63800201 - time (sec): 39.41 - samples/sec: 2156.09 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:22:39,972 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:22:39,972 EPOCH 1 done: loss 0.6318 - lr: 0.000029 | |
| 2023-10-23 22:22:44,793 DEV : loss 0.14997614920139313 - f1-score (micro avg) 0.6314 | |
| 2023-10-23 22:22:44,814 saving best model | |
| 2023-10-23 22:22:45,370 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:22:49,085 epoch 2 - iter 44/447 - loss 0.14886525 - time (sec): 3.71 - samples/sec: 2151.01 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 22:22:52,913 epoch 2 - iter 88/447 - loss 0.14909506 - time (sec): 7.54 - samples/sec: 2231.06 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:22:57,328 epoch 2 - iter 132/447 - loss 0.14851561 - time (sec): 11.96 - samples/sec: 2173.51 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:23:01,211 epoch 2 - iter 176/447 - loss 0.15023382 - time (sec): 15.84 - samples/sec: 2163.41 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 22:23:05,281 epoch 2 - iter 220/447 - loss 0.15236516 - time (sec): 19.91 - samples/sec: 2154.22 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:23:09,340 epoch 2 - iter 264/447 - loss 0.14349368 - time (sec): 23.97 - samples/sec: 2128.94 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:23:13,120 epoch 2 - iter 308/447 - loss 0.14583098 - time (sec): 27.75 - samples/sec: 2131.92 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 22:23:16,865 epoch 2 - iter 352/447 - loss 0.14036361 - time (sec): 31.49 - samples/sec: 2124.32 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:23:21,191 epoch 2 - iter 396/447 - loss 0.13709503 - time (sec): 35.82 - samples/sec: 2125.42 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:23:25,203 epoch 2 - iter 440/447 - loss 0.13162957 - time (sec): 39.83 - samples/sec: 2136.40 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 22:23:25,803 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:23:25,803 EPOCH 2 done: loss 0.1312 - lr: 0.000027 | |
| 2023-10-23 22:23:32,296 DEV : loss 0.12065546214580536 - f1-score (micro avg) 0.7139 | |
| 2023-10-23 22:23:32,316 saving best model | |
| 2023-10-23 22:23:33,038 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:23:36,912 epoch 3 - iter 44/447 - loss 0.07762606 - time (sec): 3.87 - samples/sec: 2018.49 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:23:41,076 epoch 3 - iter 88/447 - loss 0.07919298 - time (sec): 8.04 - samples/sec: 2015.72 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:23:44,839 epoch 3 - iter 132/447 - loss 0.07541745 - time (sec): 11.80 - samples/sec: 2075.74 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 22:23:48,984 epoch 3 - iter 176/447 - loss 0.07757789 - time (sec): 15.95 - samples/sec: 2110.02 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:23:52,699 epoch 3 - iter 220/447 - loss 0.07526481 - time (sec): 19.66 - samples/sec: 2089.85 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:23:57,165 epoch 3 - iter 264/447 - loss 0.07614139 - time (sec): 24.13 - samples/sec: 2084.77 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 22:24:01,492 epoch 3 - iter 308/447 - loss 0.07545581 - time (sec): 28.45 - samples/sec: 2092.33 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:24:05,292 epoch 3 - iter 352/447 - loss 0.07211717 - time (sec): 32.25 - samples/sec: 2111.02 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:24:09,139 epoch 3 - iter 396/447 - loss 0.07279091 - time (sec): 36.10 - samples/sec: 2120.24 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 22:24:13,184 epoch 3 - iter 440/447 - loss 0.07369125 - time (sec): 40.15 - samples/sec: 2123.09 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:24:13,765 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:24:13,765 EPOCH 3 done: loss 0.0737 - lr: 0.000023 | |
| 2023-10-23 22:24:20,280 DEV : loss 0.12288995832204819 - f1-score (micro avg) 0.7436 | |
| 2023-10-23 22:24:20,300 saving best model | |
| 2023-10-23 22:24:21,019 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:24:24,930 epoch 4 - iter 44/447 - loss 0.04523597 - time (sec): 3.91 - samples/sec: 2145.55 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:24:28,688 epoch 4 - iter 88/447 - loss 0.04395548 - time (sec): 7.67 - samples/sec: 2133.79 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 22:24:32,564 epoch 4 - iter 132/447 - loss 0.04343610 - time (sec): 11.54 - samples/sec: 2165.17 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:24:36,880 epoch 4 - iter 176/447 - loss 0.04360098 - time (sec): 15.86 - samples/sec: 2160.67 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:24:41,124 epoch 4 - iter 220/447 - loss 0.04351512 - time (sec): 20.10 - samples/sec: 2135.58 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 22:24:44,974 epoch 4 - iter 264/447 - loss 0.04663272 - time (sec): 23.95 - samples/sec: 2137.05 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:24:48,692 epoch 4 - iter 308/447 - loss 0.04463606 - time (sec): 27.67 - samples/sec: 2145.58 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:24:52,690 epoch 4 - iter 352/447 - loss 0.04338000 - time (sec): 31.67 - samples/sec: 2142.49 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 22:24:56,574 epoch 4 - iter 396/447 - loss 0.04260646 - time (sec): 35.55 - samples/sec: 2139.33 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:25:00,808 epoch 4 - iter 440/447 - loss 0.04252168 - time (sec): 39.79 - samples/sec: 2139.56 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:25:01,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:25:01,477 EPOCH 4 done: loss 0.0423 - lr: 0.000020 | |
| 2023-10-23 22:25:07,998 DEV : loss 0.16860494017601013 - f1-score (micro avg) 0.7442 | |
| 2023-10-23 22:25:08,018 saving best model | |
| 2023-10-23 22:25:08,736 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:25:12,979 epoch 5 - iter 44/447 - loss 0.02802474 - time (sec): 4.24 - samples/sec: 2110.69 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 22:25:17,051 epoch 5 - iter 88/447 - loss 0.02729669 - time (sec): 8.31 - samples/sec: 2091.32 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:25:20,797 epoch 5 - iter 132/447 - loss 0.02848820 - time (sec): 12.06 - samples/sec: 2114.88 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:25:24,924 epoch 5 - iter 176/447 - loss 0.03037370 - time (sec): 16.19 - samples/sec: 2132.25 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 22:25:29,219 epoch 5 - iter 220/447 - loss 0.03160364 - time (sec): 20.48 - samples/sec: 2157.95 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:25:32,933 epoch 5 - iter 264/447 - loss 0.03281760 - time (sec): 24.20 - samples/sec: 2147.02 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:25:37,105 epoch 5 - iter 308/447 - loss 0.03205699 - time (sec): 28.37 - samples/sec: 2135.24 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 22:25:40,844 epoch 5 - iter 352/447 - loss 0.03311176 - time (sec): 32.11 - samples/sec: 2138.65 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:25:44,732 epoch 5 - iter 396/447 - loss 0.03260248 - time (sec): 36.00 - samples/sec: 2130.28 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:25:48,605 epoch 5 - iter 440/447 - loss 0.03136514 - time (sec): 39.87 - samples/sec: 2134.27 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 22:25:49,291 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:25:49,292 EPOCH 5 done: loss 0.0313 - lr: 0.000017 | |
| 2023-10-23 22:25:55,808 DEV : loss 0.200847327709198 - f1-score (micro avg) 0.7667 | |
| 2023-10-23 22:25:55,829 saving best model | |
| 2023-10-23 22:25:56,552 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:26:00,120 epoch 6 - iter 44/447 - loss 0.02177514 - time (sec): 3.57 - samples/sec: 2084.94 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:26:04,046 epoch 6 - iter 88/447 - loss 0.02190717 - time (sec): 7.49 - samples/sec: 2121.33 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:26:08,182 epoch 6 - iter 132/447 - loss 0.01946378 - time (sec): 11.63 - samples/sec: 2156.61 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 22:26:12,249 epoch 6 - iter 176/447 - loss 0.01968006 - time (sec): 15.70 - samples/sec: 2144.33 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:26:16,657 epoch 6 - iter 220/447 - loss 0.02027486 - time (sec): 20.10 - samples/sec: 2146.14 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:26:20,363 epoch 6 - iter 264/447 - loss 0.02058604 - time (sec): 23.81 - samples/sec: 2150.25 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 22:26:24,533 epoch 6 - iter 308/447 - loss 0.01936116 - time (sec): 27.98 - samples/sec: 2143.75 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:26:28,696 epoch 6 - iter 352/447 - loss 0.01879624 - time (sec): 32.14 - samples/sec: 2131.02 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:26:32,687 epoch 6 - iter 396/447 - loss 0.01900730 - time (sec): 36.13 - samples/sec: 2124.58 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 22:26:36,558 epoch 6 - iter 440/447 - loss 0.01897263 - time (sec): 40.01 - samples/sec: 2125.86 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:26:37,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:26:37,262 EPOCH 6 done: loss 0.0192 - lr: 0.000013 | |
| 2023-10-23 22:26:43,765 DEV : loss 0.1983201950788498 - f1-score (micro avg) 0.7736 | |
| 2023-10-23 22:26:43,785 saving best model | |
| 2023-10-23 22:26:44,461 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:26:48,789 epoch 7 - iter 44/447 - loss 0.01146703 - time (sec): 4.33 - samples/sec: 2167.42 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:26:52,693 epoch 7 - iter 88/447 - loss 0.00983839 - time (sec): 8.23 - samples/sec: 2132.95 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 22:26:56,465 epoch 7 - iter 132/447 - loss 0.01147917 - time (sec): 12.00 - samples/sec: 2112.49 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:27:00,181 epoch 7 - iter 176/447 - loss 0.01213536 - time (sec): 15.72 - samples/sec: 2103.43 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:27:04,208 epoch 7 - iter 220/447 - loss 0.01145021 - time (sec): 19.75 - samples/sec: 2114.57 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 22:27:08,092 epoch 7 - iter 264/447 - loss 0.01226204 - time (sec): 23.63 - samples/sec: 2104.33 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:27:12,363 epoch 7 - iter 308/447 - loss 0.01179778 - time (sec): 27.90 - samples/sec: 2117.04 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:27:16,673 epoch 7 - iter 352/447 - loss 0.01203243 - time (sec): 32.21 - samples/sec: 2136.52 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 22:27:20,542 epoch 7 - iter 396/447 - loss 0.01222001 - time (sec): 36.08 - samples/sec: 2133.49 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:27:24,318 epoch 7 - iter 440/447 - loss 0.01181947 - time (sec): 39.86 - samples/sec: 2132.84 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:27:24,945 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:27:24,945 EPOCH 7 done: loss 0.0120 - lr: 0.000010 | |
| 2023-10-23 22:27:31,441 DEV : loss 0.21346606314182281 - f1-score (micro avg) 0.7828 | |
| 2023-10-23 22:27:31,462 saving best model | |
| 2023-10-23 22:27:32,110 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:27:36,118 epoch 8 - iter 44/447 - loss 0.00685455 - time (sec): 4.01 - samples/sec: 2125.06 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 22:27:40,362 epoch 8 - iter 88/447 - loss 0.01104525 - time (sec): 8.25 - samples/sec: 2070.56 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:27:44,233 epoch 8 - iter 132/447 - loss 0.00915699 - time (sec): 12.12 - samples/sec: 2113.11 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:27:48,854 epoch 8 - iter 176/447 - loss 0.00762872 - time (sec): 16.74 - samples/sec: 2106.65 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 22:27:52,512 epoch 8 - iter 220/447 - loss 0.00683083 - time (sec): 20.40 - samples/sec: 2110.20 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:27:56,394 epoch 8 - iter 264/447 - loss 0.00802052 - time (sec): 24.28 - samples/sec: 2126.46 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:28:00,106 epoch 8 - iter 308/447 - loss 0.00865904 - time (sec): 27.99 - samples/sec: 2135.97 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 22:28:03,741 epoch 8 - iter 352/447 - loss 0.00841205 - time (sec): 31.63 - samples/sec: 2128.04 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:28:07,701 epoch 8 - iter 396/447 - loss 0.00783808 - time (sec): 35.59 - samples/sec: 2131.82 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:28:12,081 epoch 8 - iter 440/447 - loss 0.00814555 - time (sec): 39.97 - samples/sec: 2130.93 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 22:28:12,772 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:28:12,772 EPOCH 8 done: loss 0.0080 - lr: 0.000007 | |
| 2023-10-23 22:28:19,278 DEV : loss 0.2258313149213791 - f1-score (micro avg) 0.7854 | |
| 2023-10-23 22:28:19,299 saving best model | |
| 2023-10-23 22:28:19,998 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:28:23,671 epoch 9 - iter 44/447 - loss 0.00629803 - time (sec): 3.67 - samples/sec: 2175.80 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:28:27,528 epoch 9 - iter 88/447 - loss 0.00804701 - time (sec): 7.53 - samples/sec: 2141.78 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:28:31,356 epoch 9 - iter 132/447 - loss 0.00634854 - time (sec): 11.36 - samples/sec: 2175.71 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 22:28:35,001 epoch 9 - iter 176/447 - loss 0.00589061 - time (sec): 15.00 - samples/sec: 2187.76 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:28:38,990 epoch 9 - iter 220/447 - loss 0.00579974 - time (sec): 18.99 - samples/sec: 2180.18 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:28:43,354 epoch 9 - iter 264/447 - loss 0.00610104 - time (sec): 23.35 - samples/sec: 2182.46 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 22:28:47,454 epoch 9 - iter 308/447 - loss 0.00636396 - time (sec): 27.45 - samples/sec: 2171.15 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:28:51,842 epoch 9 - iter 352/447 - loss 0.00587760 - time (sec): 31.84 - samples/sec: 2164.71 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:28:55,760 epoch 9 - iter 396/447 - loss 0.00548106 - time (sec): 35.76 - samples/sec: 2152.27 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 22:28:59,716 epoch 9 - iter 440/447 - loss 0.00551406 - time (sec): 39.72 - samples/sec: 2148.37 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:29:00,334 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:29:00,334 EPOCH 9 done: loss 0.0055 - lr: 0.000003 | |
| 2023-10-23 22:29:06,821 DEV : loss 0.2376076877117157 - f1-score (micro avg) 0.779 | |
| 2023-10-23 22:29:06,841 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:29:11,130 epoch 10 - iter 44/447 - loss 0.00018174 - time (sec): 4.29 - samples/sec: 2068.38 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:29:15,127 epoch 10 - iter 88/447 - loss 0.00104477 - time (sec): 8.29 - samples/sec: 2068.77 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 22:29:18,817 epoch 10 - iter 132/447 - loss 0.00073255 - time (sec): 11.98 - samples/sec: 2148.11 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:29:22,963 epoch 10 - iter 176/447 - loss 0.00142077 - time (sec): 16.12 - samples/sec: 2160.08 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:29:26,746 epoch 10 - iter 220/447 - loss 0.00213151 - time (sec): 19.90 - samples/sec: 2152.25 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 22:29:30,414 epoch 10 - iter 264/447 - loss 0.00292525 - time (sec): 23.57 - samples/sec: 2153.18 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:29:34,566 epoch 10 - iter 308/447 - loss 0.00317358 - time (sec): 27.72 - samples/sec: 2149.54 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:29:38,286 epoch 10 - iter 352/447 - loss 0.00305912 - time (sec): 31.44 - samples/sec: 2136.75 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 22:29:42,353 epoch 10 - iter 396/447 - loss 0.00332032 - time (sec): 35.51 - samples/sec: 2142.38 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 22:29:46,365 epoch 10 - iter 440/447 - loss 0.00332155 - time (sec): 39.52 - samples/sec: 2131.35 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 22:29:47,401 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:29:47,401 EPOCH 10 done: loss 0.0033 - lr: 0.000000 | |
| 2023-10-23 22:29:53,628 DEV : loss 0.23625218868255615 - f1-score (micro avg) 0.7868 | |
| 2023-10-23 22:29:53,649 saving best model | |
| 2023-10-23 22:29:54,860 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 22:29:54,861 Loading model from best epoch ... | |
| 2023-10-23 22:29:56,906 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 22:30:01,450 | |
| Results: | |
| - F-score (micro) 0.7506 | |
| - F-score (macro) 0.6633 | |
| - Accuracy 0.6181 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8218 0.8591 0.8400 596 | |
| pers 0.6789 0.7808 0.7263 333 | |
| org 0.5161 0.4848 0.5000 132 | |
| prod 0.6600 0.5000 0.5690 66 | |
| time 0.7381 0.6327 0.6813 49 | |
| micro avg 0.7365 0.7653 0.7506 1176 | |
| macro avg 0.6830 0.6515 0.6633 1176 | |
| weighted avg 0.7345 0.7653 0.7478 1176 | |
| 2023-10-23 22:30:01,450 ---------------------------------------------------------------------------------------------------- | |