Conversation
…eprecation Three changes based on client training results (grad_norm=101, 0.00 eval delta): 1. Add max_grad_norm to TrainingConfig (was hardcoded to 1.0). When grad_norm >> max_grad_norm, gradients are clipped to a near-random direction — training makes no progress despite non-zero loss. Now warns when grad_norm > 10x the clip threshold. 2. Lower default learning_rate from 5e-6 to 1e-6. With grad_norm=101 and lr=5e-6, effective step size overshoots. lr=1e-6 with max_grad_norm=1.0 gives stable updates. 3. Remove "standalone trainer is deprecated" warning. It was premature — TRL's rollout_func doesn't support multimodal VLMs (issue #5120). The standalone trainer is the production training path until TRL PR #5323 merges. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Based on client training results: grad_norm=101 with lr=5e-6, 0.00 eval delta after 20 steps.
max_grad_normin TrainingConfig — was hardcoded to 1.0. Now configurable. Warns when grad_norm > 10x clip threshold (gradients clipped to near-random direction).Default
learning_rate5e-6 → 1e-6 — with raw grad_norm=101, effective step at lr=5e-6 overshoots. lr=1e-6 gives stable updates after clipping.Remove deprecation warning — the standalone trainer is the production path for VLM GRPO. TRL's rollout_func doesn't support multimodal (issue #5120). Replaced with info log noting TRL migration pending PR #5323.
🤖 Generated with Claude Code