add scripts to collect rollouts for hyperparameter sweep on roc_story#2
Open
thomfoster wants to merge 21 commits intoCarperAI:mainfrom
Open
add scripts to collect rollouts for hyperparameter sweep on roc_story#2thomfoster wants to merge 21 commits intoCarperAI:mainfrom
thomfoster wants to merge 21 commits intoCarperAI:mainfrom
Conversation
Collaborator
|
@thomfoster Nice that we have the same folder name. Would you merge from the main first, and then clear things after running |
honglu2875
reviewed
Dec 13, 2022
| pipeline: "PromptPipeline" # prompt pipeline to load | ||
| orchestrator: "PPOOrchestrator" # orchestrator to load | ||
|
|
||
| rollout_logging_dir: "~/Algorithm-Distillation-RLHF/algorithm_distillation/sentiment-data/rollouts" |
Collaborator
There was a problem hiding this comment.
This line was causing some trouble for me. Is there a way to use relative dir instead of absolute?
Tried and didn't work. Maybe it's a problem of trlx, like we should use pathlib.Path instead of os.path here
https://github.com/CarperAI/trlx/blob/1a3461d592a567409e11e3c47b5b355bf219449f/trlx/model/accelerate_ppo_model.py#L115
added 19 commits
January 5, 2023 14:18
…sentiment_rollouts.py to reflect that this is the script to generate data, not the class that uses it
… just roc stories
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In this trlx pull request I add the ability to trlx to configure local rollout logging during a hyperparameter sweep.
Here, we provide scripts to use those changes to collect rollout data for short completions of the roc stories dataset scored according to sentiment
From the
sentiment-datadirectory, runpython -m trlx.sweep --config ppo_sweep.yml ppo_roc_story_sentiments.py -num-cpus 2 --num-gpus 1to start collecting rollouts.