-
Notifications
You must be signed in to change notification settings - Fork 10
Prompts per iteration #94
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
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good!
@@ -959,19 +975,13 @@ def _resolve_outputs( | |||
|
|||
iter_batch.update(env_outs) | |||
|
|||
bs = iter_batch['prompt_id'].shape[0] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
is this bs
different from the bs
above on line 807?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It should be the same
Removing the notion of
iter_batch_size.
This also enables users to specifynum_unique_prompts_per_iter
so we are able directly specify this value now. We also enforcenum_unique_prompts_per_iter * generations_per_prompt == global_train_batch_size * num_batches_per_update
default-gtbs-64-gen8-lM2EWs
- this run runs without specifying thenum_unique_prompts_per_iter
nppi128-gtbs-64-gen8-mtZcim
- this specifies the parameter explicitly