Use train_rl for GRPO colab #2618
Open
Conversation
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
mydatascience
requested review from
A9isha,
NicoGrande,
NuojCheng,
RissyRan,
SurbhiJainUSC,
aireenmei,
bvandermoon,
gagika,
gobbleturk,
hengtaoguo,
jiangjy1982,
khatwanimohit,
richjames0,
shralex,
suexu1025 and
vipannalla
as code owners
Collaborator
|
Can you also remove |
| "\n", | ||
| "## Hardware Requirements\n", | ||
| "\n", | ||
| "- Single host TPUVM (v6e-8/v5p-8) or multi-host with Pathways\n", |
Collaborator
There was a problem hiding this comment.
How do we run this colab on mulit-host pathways?
Collaborator
Author
There was a problem hiding this comment.
Added the section
| "# Hardcoded defaults for Llama3.1-8B\n", | ||
| "MODEL_NAME = \"llama3.1-8b\"\n", | ||
| "TOKENIZER_PATH = \"meta-llama/Llama-3.1-8B-Instruct\"\n", | ||
| "HF_MODEL_NAME = \"meta-llama/Llama-3.1-8B-Instruct\"\n", |
Collaborator
There was a problem hiding this comment.
This is same as TOKENIZER_PATH. Can't we reuse it?
| "# Create configuration object\n", | ||
| "config = pyconfig.Config()\n", | ||
| "config.parse_flags(config_argv)\n", | ||
| "print(\"📋 Configuration parameters:\")\n", |
Collaborator
There was a problem hiding this comment.
Why do we need line 183:191? pyconfig.initialize() at line 195 will already print those configurations.
mydatascience
force-pushed
the
new_grpo_colab
branch
from
718f2e6 to
8635503
Compare
mydatascience
force-pushed
the
new_grpo_colab
branch
from
3b4b943 to
e8a9a94
Compare
mydatascience
force-pushed
the
new_grpo_colab
branch
2 times, most recently
from
12ddad6 to
dd0c16a
Compare
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Signed-off-by: Vladimir Suvorov <suvorovv@google.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
Change for using tunix based train_rl
Tests
testing colab
Checklist
Before submitting this PR, please make sure (put X in square brackets):
gemini-reviewlabel.