results: S_min pilot selects 400; hyperparameter protocol frozen - #10
Merged
Merged
Conversation
Validation only, k=5, seed 42, lr 5e-5. Sum of validation in-scope correct across both encoders: 1978 / 3005 / 4292 at S_min 100 / 200 / 400. The optimum is at the top of the grid and small-k runs are not saturated at 400 steps; curve points for k in 1, 5, 10 are reported as performance under a 400-step budget.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Validation-only S_min pilot (k=5, seed 42, lr 5e-5). Selected 400 (sum of in-scope correct 1978 / 3005 / 4292 at 100 / 200 / 400). Optimum at the top of the grid; small-k points will be reported as performance under a 400-step budget. Fills configs/curve.yaml min_train_steps and adds a DEVLOG entry. Protocol is now frozen for the learning curves.