Have a problem with training
Open
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 447
- PR merge metrics
- No merged PRs in 30d
Description
Hyperparameters were set as below:
'n_epoch=10
batch_size=128
n_gpu=2
'
Now there are 1016060 sentences loaded, and been trained 189300 batch, but it doesn't match ,189300*128>1016060*10 ,can anyone tell me what cause this?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.