Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

像您请教一下为什么训练的时候并没有出现loss以及epoch #93

Open
YijianLiu opened this issue Mar 26, 2021 · 1 comment

Comments

@YijianLiu
Copy link

训练的时候显示如下日志,如何查看每个epoch的loss过程
我的训练参数是
python BERT_NER.py
--task_name="NER"
--do_lower_case=False
--crf=True
--do_train=True
--do_eval=True
--do_predict=True
--data_dir=data
--vocab_file=cased_L-12_H-768_A-12/vocab.txt
--bert_config_file=cased_L-12_H-768_A-12/bert_config.json
--init_checkpoint=cased_L-12_H-768_A-12/bert_model.ckpt
--max_seq_length=128
--train_batch_size=32
--learning_rate=2e-5
--num_train_epochs=4.0
--output_dir=./output/result_dir
如下训练日志:
INFO:tensorflow:global_step/sec: 2.44863
I0326 15:59:02.876380 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.44863
INFO:tensorflow:examples/sec: 78.3562
I0326 15:59:02.876857 139718477698816 tpu_estimator.py:2308] examples/sec: 78.3562
INFO:tensorflow:global_step/sec: 2.24293
I0326 15:59:03.322147 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.24293
INFO:tensorflow:examples/sec: 71.7736
I0326 15:59:03.322539 139718477698816 tpu_estimator.py:2308] examples/sec: 71.7736
INFO:tensorflow:global_step/sec: 2.31614
I0326 15:59:03.753919 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.31614
INFO:tensorflow:examples/sec: 74.1165
I0326 15:59:03.754283 139718477698816 tpu_estimator.py:2308] examples/sec: 74.1165
INFO:tensorflow:global_step/sec: 2.32764
I0326 15:59:04.183665 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.32764
INFO:tensorflow:examples/sec: 74.4845
I0326 15:59:04.184118 139718477698816 tpu_estimator.py:2308] examples/sec: 74.4845
INFO:tensorflow:global_step/sec: 2.34524
I0326 15:59:04.610075 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.34524
INFO:tensorflow:examples/sec: 75.0478
I0326 15:59:04.610802 139718477698816 tpu_estimator.py:2308] examples/sec: 75.0478
INFO:tensorflow:global_step/sec: 2.24035
I0326 15:59:05.056344 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.24035
INFO:tensorflow:examples/sec: 71.6911
I0326 15:59:05.056849 139718477698816 tpu_estimator.py:2308] examples/sec: 71.6911
INFO:tensorflow:global_step/sec: 2.53696
I0326 15:59:05.450423 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.53696
INFO:tensorflow:examples/sec: 81.1828
I0326 15:59:05.450799 139718477698816 tpu_estimator.py:2308] examples/sec: 81.1828
INFO:tensorflow:global_step/sec: 2.54311
I0326 15:59:05.843605 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.54311
INFO:tensorflow:examples/sec: 81.3794
I0326 15:59:05.843933 139718477698816 tpu_estimator.py:2308] examples/sec: 81.3794
INFO:tensorflow:global_step/sec: 2.25988
I0326 15:59:06.286114 139718477698816 tpu_estimator.py:2307] global_step/sec: 2.25988
INFO:tensorflow:examples/sec: 72.316
I0326 15:59:06.286518 139718477698816 tpu_estimator.py:2308] examples/sec: 72.316
^CINFO:tensorflow:training_loop marked as finished

@KangliZhang
Copy link

请问你的问题解决了么?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants