We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 40bdeb4 commit c608779Copy full SHA for c608779
evals/config.ts
@@ -19,7 +19,7 @@ function getTestCasesVersion(): string {
19
// Models to evaluate
20
export const MODELS_TO_EVALUATE = [
21
'gpt-4o-mini',
22
- 'claude-3-5-haiku-latest',
+ // 'claude-3-5-haiku-latest',
23
];
24
25
export const PASS_THRESHOLD = 0.8;
evals/run-evaluation.ts
@@ -226,6 +226,7 @@ async function main(): Promise<number> {
226
experimentDescription,
227
concurrency: 10,
228
});
229
+ log.info(`Experiment run completed. View details at: ${experiment}`);
230
231
const runsMap = experiment.runs ?? {};
232
const evalRuns = experiment.evaluationRuns ?? [];
0 commit comments