Chen Wu comments

Repositories
Issues
Comments

Results 5 comments of


                                            Chen Wu

The different results between eval mode and test mode.

Hi, Could you share the command you ran for this experiment?

The different results between eval mode and test mode.

Is the highest eval score the same as the test score?

The different results between eval mode and test mode.

Can you run the following command on the same machine (which means that the previous checkpoints are still there) and see if the results are different? ``` python -m torch.distributed.launch...

The different results between eval mode and test mode.

I just realized that the command you provided is for T5-3b without using deepspeed. I remember that we didn't manage to run without deepspeed even on an A100. What kind...

Enables semantic search to use only a subset of variables as the key.

> love this idea - but probably want to also save it on the class and use it in `select_examples`? Great idea! I implemented this in the latest commit.