Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove assessment collection #378

Merged
merged 3 commits into from
Jan 8, 2025
Merged

Remove assessment collection #378

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8815066
Remove assessment reporting in logs since assessments are anyways sto…
bauersimon Jan 8, 2025
3b2630b
refactor, Only collect model and language IDs during testing to simpl…
bauersimon Jan 8, 2025
3ac9045
refactor, Don't collect assessments during benchmark cause it's only …
bauersimon Jan 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 1 addition & 6 deletions cmd/eval-dev-quality/cmd/evaluate.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -524,7 +524,7 @@ func (command *Evaluate) evaluateLocal(evaluationContext *evaluate.Context) (err
command.logger.Panicf("ERROR: %s", err)
}

assessments := evaluate.Evaluate(evaluationContext)
_ = evaluate.Evaluate(evaluationContext)

if err := (report.Markdown{
DateTime: command.timestamp,
Expand All @@ -534,11 +534,6 @@ func (command *Evaluate) evaluateLocal(evaluationContext *evaluate.Context) (err
command.logger.Panicf("ERROR: %s", err)
}

assessmentsPerModel := assessments.CollapseByModel()
for _, modelID := range maps.Keys(assessmentsPerModel) {
command.logger.Printf("Evaluation assessments for %q: %s", modelID, assessmentsPerModel[modelID])
}

return nil
}

Expand Down
175 changes: 35 additions & 140 deletions cmd/eval-dev-quality/cmd/evaluate_test.go
View file
Open in desktop

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions evaluate/evaluate.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,6 +295,7 @@ func Evaluate(ctx *Context) (assessments *report.AssessmentStore) {
if err != nil {
logger.Printf("ERROR: Model %q encountered a hard error for language %q, repository %q: %+v", modelID, languageID, repositoryPath, err)
}

assessments.AddAssessmentPerTask(model, language, repositoryPath, assessment)
// Write the task assessment to the evaluation CSV file.
if err := evaluationFile.WriteEvaluationRecord(model, language, temporaryRepository.Name(), runCount, assessment); err != nil {
Expand Down
Loading