test: relax TestMLADeepseekV3.test_gsm8k threshold 0.62 -> 0.60 (#23879)
This commit is contained in:
@@ -56,7 +56,7 @@ class TestMLADeepseekV3(CustomTestCase):
|
|||||||
metrics = run_eval(args)
|
metrics = run_eval(args)
|
||||||
print(metrics)
|
print(metrics)
|
||||||
|
|
||||||
self.assertGreater(metrics["score"], 0.62)
|
self.assertGreater(metrics["score"], 0.60)
|
||||||
|
|
||||||
|
|
||||||
@unittest.skipIf(is_in_ci(), "To reduce the CI execution time.")
|
@unittest.skipIf(is_in_ci(), "To reduce the CI execution time.")
|
||||||
|
|||||||
Reference in New Issue
Block a user