Merged
Conversation
19e7a98 to
36f0095
Compare
| from eval_protocol.integrations.tinker_rollout_processor import TinkerRolloutProcessor | ||
|
|
||
| # Import test components | ||
| from examples.tinker_math_rl.test_gsm8k_eval import test_gsm8k_tinker, get_gsm8k_input_rows |
There was a problem hiding this comment.
Bug: Broken import path in training script
The script attempts to import test_gsm8k_eval using the full path examples.tinker_math_rl, which fails with ModuleNotFoundError when running python train.py from the directory as documented. The examples package is not in sys.path in that context; use a relative or direct import instead.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Introduce Tinker-based rollout/evaluation with an eval_protocol adapter-to-RL bridge and a GSM8K RL training example with metrics plotting.
EvalProtocolRLDataset,EvalProtocolEvaluator, andcreate_eval_protocol_dataset_builderto bridgeeval_protocoladapters to Tinker RL datasets/evaluators.TinkerRolloutProcessorimplementing rollouts via TinkerSamplingClient, renderer/tokenizer setup, and async batching.examples/tinker_math_rl/train.py: end-to-end RL training using GSM8K adapter, row conversion toProblemGroupBuilder, and periodic evaluation.examples/tinker_math_rl/test_gsm8k_eval.py: evaluation test usingTinkerRolloutProcessorand GSM8K rows.examples/tinker_math_rl/plot_metrics.py: plot training metrics.examples/tinker_math_rl/README.md: setup and run instructions.Written by Cursor Bugbot for commit 8a1b8f0. This will update automatically on new commits. Configure here.