InstruSumEval / predictions /llama-2-13b_swap.jsonl
henryL7's picture
add benchmark results
b558422
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 2}
{"winner": 1}
{"winner": 1}
{"winner": 1}
{"winner": 1}