From e43b3f8aa36c198b95c1e46bea2eaf3893b13dc3 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 17 Dec 2025 04:29:37 -0600 Subject: Initial commit (clean history) --- scripts/debug_context_file.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 scripts/debug_context_file.py (limited to 'scripts/debug_context_file.py') diff --git a/scripts/debug_context_file.py b/scripts/debug_context_file.py new file mode 100644 index 0000000..81ac6b9 --- /dev/null +++ b/scripts/debug_context_file.py @@ -0,0 +1,14 @@ +import json + +path = "data/raw_datasets/personamem/shared_contexts_32k.jsonl" +with open(path, 'r') as f: + line = f.readline() + data = json.loads(line) + print(f"Type: {type(data)}") + if isinstance(data, dict): + print(f"Keys: {list(data.keys())}") + # Peek into values + for k, v in data.items(): + print(f"Key '{k}' type: {type(v)}") + if isinstance(v, list): + print(f" Length: {len(v)}") -- cgit v1.2.3