fix sonnet dataset sample when prefix len is very small (#16379)
Signed-off-by: Chenyaaang <chenyangli@google.com>
This commit is contained in:
@@ -472,7 +472,7 @@ class SonnetDataset(BenchmarkDataset):
|
|||||||
|
|
||||||
# Determine how many poem lines to use.
|
# Determine how many poem lines to use.
|
||||||
num_input_lines = round((input_len - base_offset) / avg_len)
|
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]
|
prefix_lines = self.data[:num_prefix_lines]
|
||||||
|
|
||||||
samples = []
|
samples = []
|
||||||
|
|||||||
Reference in New Issue
Block a user