This repository has been archived by the owner on Nov 3, 2023. It is now read-only.
Pull out settings for model chat onboarding #4274
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
EricMichaelSmith
changed the title
meganung
approved these changes
Dec 28, 2021
| @@ -22,7 +22,9 @@ The following flags can be passed in to specify filepaths for overriding the tex | |||
|
|
|||
| ## Onboarding | |||
|
|
|||
| In `worlds.py`, modify `ModelChatOnboardWorld.check_onboarding_answers()` to change the worker selection criteria. | |||
| Set the `"min_correct"`, `"max_incorrect"`, and `"max_failures_allowed"` fields in the JSON file passed to `mephisto.blueprint.onboard_task_data_path` in order to specify how many onboarding questions workers can pass/fail on while still passing onboarding, as well as how many times they are allowed to re-take the onboarding before being soft-blocked. (See `task_config/onboard_task_data.json` for an example.) | |||
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Patch description
"min_correct","max_incorrect", and"max_failures_allowed"fields in the JSON file passed tomephisto.blueprint.onboard_task_data_pathin order to specify how many onboarding questions workers can pass/fail on while still passing onboarding, as well as how many times they are allowed to re-take the onboarding before being soft-blockedtask_config/onboard_task_data.jsonfor an example of how this looksTesting steps
Ran test command:
UI when setting
"max_failures_allowed": 10and then getting some responses wrong: