Repository navigation
Prepare GPU ablations and the hand-labelling dev batch - #47
Merged
Merged
Conversation
configs/experiments/ablations.toml now uses the best run-3 recipe (DeBERTa, sqrt span-tag weights, 5e-5, up to 20 epochs, min_epochs 6) with learning-curve budgets of 60 and 120 documents (the train split has 239). batch-07 draws 100 natural dev documents to be labelled by hand before the test batch, so calibration and review thresholds can be fitted on manual dev records.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
configs/experiments/ablations.toml: best run-3 recipe; budgets 60/120 (train split has 239 docs). Run withCONFIGS="ablations" bash scripts/gpu/run_neural.sh.annotations/batches/batch-07.json: 100 natural dev documents for hand labelling, before test batch-04.