Repository navigation
Add DPO loss chart to LoRA validation docs - #22
Merged
Merged
Conversation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
micahtyong
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a chart to the "DPO on HHH: Qwen3.5-9B-Base" section of
docs/lora_validation.md. It plots DPO loss per step for the cookbook DPO recipe on Spindle and on Tinker, using the same settings (lr 1e-4, β 0.1, batch 256, 10 steps).Both runs see identical batches (same pair and token counts at every step) and follow the same loss trajectory. Step 9 dpo_loss is 0.6795 on Spindle and 0.6837 on Tinker. The section also links both W&B runs.
🤖 Generated with Claude Code