-
Notifications
You must be signed in to change notification settings - Fork 4.5k
Grpo vaildate #6271
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
Grpo vaildate #6271
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.
Well done, thanks. Pls read my comments below.
"/home/yanglibing/workspace/PRIME/eval/data/AI-MO/aimo-validation-aime/aimo-validation-aime.jsonl", | ||
512, | ||
) | ||
print(dataset[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.
please remove debug code
for test_batch in self.val_dataloader: | ||
test_output = self.rollout(**test_batch) | ||
num_generations = test_output["response_idx"].size(1) | ||
print("num_generations", num_generations) |
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.
remove debug code
if i >= num_valid_microbatches: | ||
break | ||
outputs = self.rollout(**batch) | ||
outputs.update(valid_metrics) |
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.
Also need to log to wandb, please refer to code in grpo_consumer.py
@@ -0,0 +1,2 @@ | |||
export NCCL_BLOCKING_WAIT=1 |
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.
Remove this file
📌 Checklist before creating the PR
[doc/gemini/tensor/...]: A concise description
pip install pre-commit && pre-commit install
🚨 Issue number
📝 What does this PR do?
💥 Checklist before requesting a review
⭐️ Do you enjoy contributing to Colossal-AI?
Tell us more if you don't enjoy contributing to Colossal-AI.