40 lines
1.1 KiB
Plaintext
40 lines
1.1 KiB
Plaintext
{
|
|
"files": {
|
|
"baseline/baseline_results.json": "873c466ed7d6bd23b5088dd03b6edc69f2e5888f3246a4dd9df241923fda85c8",
|
|
"baseline/raw_outputs.jsonl": "57a9e724ad0e71993f6c4abfdb970029d352d53aeb9adabb37162e809b86b024"
|
|
},
|
|
"model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
|
"decoding": {
|
|
"strategy": "greedy",
|
|
"temperature": 0.0,
|
|
"max_tokens": 12288,
|
|
"max_model_len": 16384,
|
|
"seed": 0,
|
|
"deterministic": true
|
|
},
|
|
"summary": {
|
|
"plain": {
|
|
"n": 500,
|
|
"verifiable_rate": 0.0,
|
|
"accuracy": 59.8,
|
|
"verified_and_correct": 0.0,
|
|
"mean_assertions_per_chain": 0.0
|
|
},
|
|
"format": {
|
|
"n": 500,
|
|
"verifiable_rate": 0.0,
|
|
"accuracy": 61.6,
|
|
"verified_and_correct": 0.0,
|
|
"mean_assertions_per_chain": 0.0
|
|
}
|
|
},
|
|
"references": {
|
|
"VERIFIER.lock": {
|
|
"verifier/step_verifier.py": "d5d146cfbb9a69e162c1a80a330c942b195bfd6d0a0961ae480cc1875989613b"
|
|
},
|
|
"EVAL.lock": {
|
|
"eval/eval_set.jsonl": "e1573cabaf44010555ef1138cbeda17bc43deb8121524cde23d94413a5d69753",
|
|
"eval/_eval_meta.json": "8d99764e00d564035fcc1cf361c7e44d45783623288763fe679477e8670fc88f"
|
|
}
|
|
}
|
|
} |