Add evaluation report

eval-report.json

@@ -0,0 +1,138 @@
+{
+  "adapter": "Taimwe/securecoder-30b-pro",
+  "base": "unsloth/Qwen3-Coder-30B-A3B-Instruct",
+  "when": "2026-09-25T08:49:36Z",
+  "sections": [
+    {
+      "section": "tool_calls",
+      "n_prompts": 0,
+      "parse_rate": 0.0,
+      "name_rate": 0.0,
+      "schema_rate": 0.0
+    },
+    {
+      "section": "code_sanity",
+      "n_prompts": 15,
+      "ast_rate": 0.13333333333333333,
+      "compile_rate": 0.13333333333333333
+    },
+    {
+      "section": "security_mcq",
+      "error": "ValueError(\"Bad split: train. Available splits: ['test']\")",
+      "skipped": true
+    }
+  ],
+  "raw": [
+    {
+      "section": "tool_calls",
+      "n_prompts": 0,
+      "parse_rate": 0.0,
+      "name_rate": 0.0,
+      "schema_rate": 0.0,
+      "details": []
+    },
+    {
+      "section": "code_sanity",
+      "n_prompts": 15,
+      "ast_rate": 0.13333333333333333,
+      "compile_rate": 0.13333333333333333,
+      "details": [
+        {
+          "prompt": "Write a Python function `def is_palindrome(s: str) -> bool:`",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n    # Remove non-alphanumeric characters and convert to lowercase\\n    cleaned = ''.join(char.lower() for char in s if char.isalnum())\\n    # Check i"
+        },
+        {
+          "prompt": "Write a Python function `def merge_intervals(intervals: list",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom typing import List\\n\\ndef merge_intervals(intervals: List[List[int]]) -> List[List[int]]:\\n    if not intervals:\\n        return []\\n    \\n    #"
+        },
+        {
+          "prompt": "Write a Python function `def two_sum(nums: list[int], target",
+          "ast_ok": true,
+          "compile_ok": true,
+          "reply_first_160": "```python\ndef two_sum(nums: list[int], target: int) -> list[int]:\n    num_to_index = {}\n    for i, num in enumerate(nums):\n        complement = target - num\n   "
+        },
+        {
+          "prompt": "Write a Python function `def flatten(nested: list) -> list:`",
+          "ast_ok": true,
+          "compile_ok": true,
+          "reply_first_160": "```python\ndef flatten(nested: list) -> list:\n    result = []\n    for item in nested:\n        if isinstance(item, list):\n            result.extend(flatten(item))"
+        },
+        {
+          "prompt": "Write a Python function `def parse_csv_line(line: str) -> li",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nimport re\\n\\ndef parse_csv_line(line: str) -> list[str]:\\n    # Regular expression to match CSV fields, handling quoted fields and escaped quotes\\n  "
+        },
+        {
+          "prompt": "Write a Python function `def lru_cache(k: int):` returning a",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom collections import OrderedDict\\ndef lru_cache(k: int):\\n    cache = OrderedDict()\\n    def decorator(func):\\n        def wrapper(*args, **kwargs"
+        },
+        {
+          "prompt": "Write a Python function `def is_anagram(a: str, b: str) -> b",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def topological_order(graph: dict[s",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom collections import deque\\n\\ndef topological_order(graph):\\n    # Calculate in-degrees for each node\\n    in_degree = {node: 0 for node in graph}"
+        },
+        {
+          "prompt": "Write a Python function `def tokenise(s: str) -> list[str]:`",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n    tokens = []\\n    i = 0\\n    while i < len(s):\\n        if s[i].isdigit():\\n            num = ''\\n            while i < len(s) and s[i].isdigit():"
+        },
+        {
+          "prompt": "Write a Python function `def slugify(text: str) -> str:` pro",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom unicodedata import normalize\\n\\ndef slugify(text: str) -> str:\\n    # Normalize the text to NFKD form (decomposed form)\\n    normalized = normal"
+        },
+        {
+          "prompt": "Write a Python function `def read_jsonl(path: str) -> list[d",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nimport json\\n\\ndef read_jsonl(path: str) -> list[dict]:\\n    with open(path, 'r') as f:\\n        for line in f:\\n            yield json.loads(line)\\n"
+        },
+        {
+          "prompt": "Write a Python function `def binary_search(arr: list[int], t",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def unique_in_order(s: str) -> list",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom typing import List\\n\\ndef unique_in_order(s: str) -> List[str]:\\n    if not s:\\n        return []\\n    result = [s[0]]\\n    for i in range(1, le"
+        },
+        {
+          "prompt": "Write a Python function `def safe_eval(expr: str) -> int:` e",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n\\ndef safe_eval(expr: str) -> int:\\n    # Remove spaces from the expression\\n    expr = expr.replace(' ', '')\\n    \\n    # Define operator precedence"
+        },
+        {
+          "prompt": "Write a Python function `def dedupe_preserve_order(items: li",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n    seen = set()\\n    result = []\\n    for item in items:\\n        if item not in seen:\\n            seen.add(item)\\n            result.append(item)\\"
+        }
+      ]
+    },
+    {
+      "section": "security_mcq",
+      "error": "ValueError(\"Bad split: train. Available splits: ['test']\")",
+      "skipped": true
+    }
+  ]
+}