Skip to content

Integrate Eval Protocol as RL environment #276

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 28 commits into from
Oct 29, 2025
Merged

Integrate Eval Protocol as RL environment #276

merged 28 commits into from
Oct 29, 2025
+499 −2

Conversation

@1stprinciple
Copy link
Contributor

@1stprinciple 1stprinciple commented Oct 28, 2025 •
edited
Loading

Main contributor: @xzrderek

Improvement for the first 50 steps.
Stabilize for the next 250 steps.

Screenshot 2025-10-28 at 01 38 21 Screenshot 2025-10-28 at 01 40 31 Screenshot 2025-10-28 at 01 40 40

listar2000 and others added 28 commits October 28, 2025 01:36
@listar2000 @1stprinciple
fix issue rllm-org#259
f498105
@1stprinciple
init
ab9a214
@1stprinciple
print(f"Train dataset size: {len(train_dataset)}")
927aaa8
@1stprinciple
super().__init__(rollout_engine, **kwargs)
5582b45
@1stprinciple
qwen2p5-vl-32b-instruct
844b559
@1stprinciple
comment
159bfae
@1stprinciple
print
1918525
@1stprinciple
[trajectory]
96c4ba5
@1stprinciple
100 tasks
0ff9310
@1stprinciple
10
8ff23ec
@1stprinciple
n_parallel_tasks = 10
edf7391
@xzrderek @1stprinciple
update to qwen3 and new server
9a00d10
@1stprinciple
thinking
afddb03
@1stprinciple
add train_frozenlake_flow
4aaca1f
@1stprinciple
model_id = "accounts/pyroworks/deployedModels/qwen3-8b-g0m657sn"
bff3ade
@1stprinciple
print(episode.trajectories)
4a873ca
@1stprinciple
from datasets import load_dataset
61d0fa5
@xzrderek @1stprinciple
fixed concurrency
5b0f296
@1stprinciple
tracing_signal
e4cb686
@1stprinciple
signal
c7def53
@1stprinciple
trainer.val_before_train=False \
180d74c
@1stprinciple
_build_rollout_processor_config
6377878
@1stprinciple
print("model in frozen_lake_flow", model)
48eafef
@1stprinciple
semaphore=self._rollout_processor_semaphore,
3fba71d
@1stprinciple
print(error_message)
432b5f1
@1stprinciple
update self.model to deployedModel
9c0a41a
@1stprinciple
remove some codes
4221df3
@1stprinciple
formatting
cdd7efc
@jeffreysijuntan jeffreysijuntan merged commit 40c886c into rllm-org:main Oct 29, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@1stprinciple @jeffreysijuntan @listar2000 @xzrderek