From 417bcefbae024a10ddedb18e2dab58e7a4c535b3 Mon Sep 17 00:00:00 2001 From: Chenyaaang <42742451+Chenyaaang@users.noreply.github.com> Date: Wed, 9 Apr 2025 22:35:07 -0700 Subject: [PATCH] fix sonnet dataset sample when prefix len is very small (#16379) Signed-off-by: Chenyaaang --- benchmarks/benchmark_dataset.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/benchmarks/benchmark_dataset.py b/benchmarks/benchmark_dataset.py index 1d61485e70..c6630800cf 100644 --- a/benchmarks/benchmark_dataset.py +++ b/benchmarks/benchmark_dataset.py @@ -472,7 +472,7 @@ class SonnetDataset(BenchmarkDataset): # Determine how many poem lines to use. num_input_lines = round((input_len - base_offset) / avg_len) - num_prefix_lines = round((prefix_len - base_offset) / avg_len) + num_prefix_lines = max(round((prefix_len - base_offset) / avg_len), 0) prefix_lines = self.data[:num_prefix_lines] samples = []