You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I executed multiple_train_sa_run.py and generated the attached log which shows no difference in the length of the description from start to finish. Perhaps it is due to the fact that I use conda rather than pip to install dependencies. I prefer conda for a variety of reasons and have attached the environment.yml file which, you will notice, has no version constraints so as to solve for the "best" version alignments accodring to conda.
Is the log intended to show no change in the length?
Hi! Thank you for your question. This is not an issue; rather, what you are observing is that the training has quickly found the optimal solution and is no longer improving. This usually occurs when the noise level is low. To make the training more challenging, consider changing the noise level to medium in config.py:
NOISE_LEVEL_TO_TRAIN = NoiseLevel.MEDIUM
Additionally, you can use train_sa.py to observe the training process in a simpler manner, as it trains using only one process.
I hope this helps! Feel free to ask any follow-up questions.
I executed
multiple_train_sa_run.py
and generated the attached log which shows no difference in the length of the description from start to finish. Perhaps it is due to the fact that I useconda
rather thanpip
to install dependencies. I preferconda
for a variety of reasons and have attached theenvironment.yml
file which, you will notice, has no version constraints so as to solve for the "best" version alignments accodring toconda
.Is the log intended to show no change in the length?
multiple_train_sa_run.log
environment.yml.txt
The text was updated successfully, but these errors were encountered: