初始化项目,由ModelHub XC社区提供模型
Model: ramankrishna10/npc-reason Source: Original Platform
This commit is contained in:
40
locks/BASELINE.lock
Normal file
40
locks/BASELINE.lock
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"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"
|
||||
}
|
||||
}
|
||||
}
|
||||
7
locks/RL_RESULT.lock
Normal file
7
locks/RL_RESULT.lock
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"files": {
|
||||
"rl/rl_eval_result.json": "d443b4b2c3da8a16c906c687f9d76befbfe0063008b42df8251a602c65302997",
|
||||
"rl/rl_eval_raw.jsonl": "50ba30b5d305c3339c5bc710a446ff6cda8d2060fc3c529cf0a056ba0d4792d7",
|
||||
"rl/RL_DATA.lock": "aa26db37d0245e9ec0057959b20056123148ef6bfdbfb2f740ac20d326a54c4b"
|
||||
}
|
||||
}
|
||||
6
locks/SFT_RESULT.lock
Normal file
6
locks/SFT_RESULT.lock
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"files": {
|
||||
"eval/eval_result.json": "095c87775e77c89af55f64a2fd644ceeabfc52c57c7f3e31754575867f3e1be7",
|
||||
"eval/eval_raw.jsonl": "aaa36cb7de26bd4366040aa86a5564009bafa22136b8a2241f656fd6bfd28b7c"
|
||||
}
|
||||
}
|
||||
29
locks/TRAINSET.lock
Normal file
29
locks/TRAINSET.lock
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"files": {
|
||||
"data/sft_train.jsonl": "39ee5e9920f480736f42c80acd3ff76a1e62cc1cb250b0dace94fda239e3e68f"
|
||||
},
|
||||
"count": 7546,
|
||||
"filter_stats": {
|
||||
"raw_chains": 13245,
|
||||
"kept": 7546,
|
||||
"surplus_held": 0,
|
||||
"decontam_dropped": 0,
|
||||
"rejects": {
|
||||
"no_assertions": 3894,
|
||||
"bad_arithmetic": 1211,
|
||||
"non_composing": 387,
|
||||
"wrong_answer": 206,
|
||||
"dup_problem": 1
|
||||
},
|
||||
"keep_rate_pct": 56.97,
|
||||
"cap": 20000
|
||||
},
|
||||
"verifier_ref": {
|
||||
"verifier/step_verifier.py": "d5d146cfbb9a69e162c1a80a330c942b195bfd6d0a0961ae480cc1875989613b"
|
||||
},
|
||||
"eval_ref": {
|
||||
"eval/eval_set.jsonl": "e1573cabaf44010555ef1138cbeda17bc43deb8121524cde23d94413a5d69753",
|
||||
"eval/_eval_meta.json": "8d99764e00d564035fcc1cf361c7e44d45783623288763fe679477e8670fc88f"
|
||||
},
|
||||
"criterion": "verifiable AND correct, decontaminated vs EVAL.lock, dedup by problem text"
|
||||
}
|
||||
Reference in New Issue
Block a user