fix: escape syntax in quality_reward

train_grpo_v2.py

@@ -214,7 +214,7 @@ def quality_reward(prompts, completions, completion_ids=None, **kwargs):
             reward += 0.1
         
         # Penalize generic/unhelpful responses
-        generic_phrases = ['i cannot', 'i don\\'t', 'no vulnerabilities found', 'the code looks safe']
+        generic_phrases = ['i cannot', 'i don\'t', 'no vulnerabilities found', 'the code looks safe']
         if any(p in text.lower() for p in generic_phrases):
             reward -= 0.5
         
@@ -239,42 +239,40 @@ def main():
     dataset = load_dataset(DATASET_ID, split="train")
     logger.info(f"Dataset: {len(dataset)} samples, columns={dataset.column_names}")
     
+    # For GRPO we only need 'prompt' column + metadata columns for reward
+    # The reward functions access metadata via kwargs passed from the dataset
+    
     # Log severity distribution
     sev_dist = Counter(dataset['severity'])
     logger.info(f"Severity distribution: {dict(sev_dist)}")
     
-    # Subsample for 0.5B model on T4 — use 15K most relevant samples
+    # Subsample for 0.5B model on T4 — use 10K most relevant samples
     # Prioritize: HIGH > MEDIUM > has_code > has_poc
     logger.info("Selecting high-quality training subset...")
     indices = []
-    idx_set = set()
     
     # Priority 1: HIGH severity with code (most valuable)
     for i, row in enumerate(dataset):
         if row['severity'] in ('high', 'critical') and row['has_code']:
             indices.append(i)
-            idx_set.add(i)
     logger.info(f"  HIGH+CRITICAL with code: {len(indices)}")
     
     # Priority 2: MEDIUM severity with code
     for i, row in enumerate(dataset):
-        if row['severity'] == 'medium' and row['has_code'] and i not in idx_set:
+        if row['severity'] == 'medium' and row['has_code'] and i not in set(indices):
             indices.append(i)
-            idx_set.add(i)
     logger.info(f"  + MEDIUM with code: {len(indices)}")
     
     # Priority 3: Any with PoC reference
     for i, row in enumerate(dataset):
-        if row['has_poc'] and i not in idx_set:
+        if row['has_poc'] and i not in set(indices):
             indices.append(i)
-            idx_set.add(i)
     logger.info(f"  + Has PoC: {len(indices)}")
     
     # Priority 4: Fill remaining with HIGH/MED without code
     for i, row in enumerate(dataset):
-        if row['severity'] in ('high', 'medium', 'critical') and i not in idx_set:
+        if row['severity'] in ('high', 'medium', 'critical') and i not in set(indices):
             indices.append(i)
-            idx_set.add(i)
         if len(indices) >= 15000:
             break
     logger.info(f"  Final subset: {len(indices)} samples")