check input length of sonnet samples (#16423)

Signed-off-by: alexey-belyakov <alexey.belyakov@intel.com>

benchmarks/benchmark_dataset.py

@@ -489,7 +489,7 @@ class SonnetDataset(BenchmarkDataset):
         prefix_lines = self.data[:num_prefix_lines]
 
         samples = []
-        for _ in range(num_requests):
+        while len(samples) < num_requests:
             extra_lines = random.choices(self.data,
                                          k=num_input_lines - num_prefix_lines)
             prompt = f"{base_prompt}{''.join(prefix_lines + extra_lines)}"
@@ -497,6 +497,7 @@ class SonnetDataset(BenchmarkDataset):
             prompt_formatted = tokenizer.apply_chat_template(
                 msg, add_generation_prompt=True, tokenize=False)
             prompt_len = len(tokenizer(prompt_formatted).input_ids)
+            if prompt_len <= input_len:
                 samples.append(
                     SampleRequest(
                         prompt=prompt_formatted