初始化项目,由ModelHub XC社区提供模型
Model: NyayaLabs98/nyaya-3b-v3 Source: Original Platform
This commit is contained in:
564
training/rag_eval_rescored.json
Normal file
564
training/rag_eval_rescored.json
Normal file
@@ -0,0 +1,564 @@
|
||||
{
|
||||
"rescored_at": "2026-07-20 22:19:14",
|
||||
"runs": {
|
||||
"rag_dense_k8_base": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 17,
|
||||
"strict_accuracy": 0.0343,
|
||||
"lenient_correct": 29,
|
||||
"lenient_accuracy": 0.0586,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1809,
|
||||
"lenient": 0.2553
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0138
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v3-checkpoint-100": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 16,
|
||||
"strict_accuracy": 0.0323,
|
||||
"lenient_correct": 26,
|
||||
"lenient_accuracy": 0.0525,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1702,
|
||||
"lenient": 0.234
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.011
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v3-checkpoint-200": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 17,
|
||||
"strict_accuracy": 0.0343,
|
||||
"lenient_correct": 29,
|
||||
"lenient_accuracy": 0.0586,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1809,
|
||||
"lenient": 0.2553
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0138
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v3-checkpoint-300": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 27,
|
||||
"lenient_accuracy": 0.0545,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.2021,
|
||||
"lenient": 0.266
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v3-checkpoint-332": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 15,
|
||||
"strict_accuracy": 0.0303,
|
||||
"lenient_correct": 25,
|
||||
"lenient_accuracy": 0.0505,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1596,
|
||||
"lenient": 0.234
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0083
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v3-final": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 15,
|
||||
"strict_accuracy": 0.0303,
|
||||
"lenient_correct": 25,
|
||||
"lenient_accuracy": 0.0505,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1596,
|
||||
"lenient": 0.234
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0083
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v4-checkpoint-100": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 34,
|
||||
"lenient_accuracy": 0.0687,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1837,
|
||||
"lenient": 0.2449
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0192
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0261
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v4-checkpoint-200": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 18,
|
||||
"strict_accuracy": 0.0364,
|
||||
"lenient_correct": 28,
|
||||
"lenient_accuracy": 0.0566,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1735,
|
||||
"lenient": 0.2449
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0116
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v4-checkpoint-300": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 17,
|
||||
"strict_accuracy": 0.0343,
|
||||
"lenient_correct": 28,
|
||||
"lenient_accuracy": 0.0566,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1633,
|
||||
"lenient": 0.2245
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0174
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v4-checkpoint-354": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 30,
|
||||
"lenient_accuracy": 0.0606,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1837,
|
||||
"lenient": 0.2551
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0145
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_legal-3b-v4-final": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 30,
|
||||
"lenient_accuracy": 0.0606,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1837,
|
||||
"lenient": 0.2551
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0145
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_dense_k8_v3-dpo": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 17,
|
||||
"strict_accuracy": 0.0343,
|
||||
"lenient_correct": 24,
|
||||
"lenient_accuracy": 0.0485,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 94,
|
||||
"strict": 0.1809,
|
||||
"lenient": 0.234
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 38,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_base": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 29,
|
||||
"lenient_accuracy": 0.0586,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.2235,
|
||||
"lenient": 0.2706
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0165
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_checkpoint-50": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 14,
|
||||
"strict_accuracy": 0.0283,
|
||||
"lenient_correct": 17,
|
||||
"lenient_accuracy": 0.0343,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.1647,
|
||||
"lenient": 0.1765
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_legal-3b-v2-checkpoint-100": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 18,
|
||||
"strict_accuracy": 0.0364,
|
||||
"lenient_correct": 25,
|
||||
"lenient_accuracy": 0.0505,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.2118,
|
||||
"lenient": 0.2824
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0028
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_legal-3b-v2-checkpoint-150": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 16,
|
||||
"strict_accuracy": 0.0323,
|
||||
"lenient_correct": 27,
|
||||
"lenient_accuracy": 0.0545,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.1882,
|
||||
"lenient": 0.2588
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0138
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_legal-3b-v2-checkpoint-197": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 16,
|
||||
"strict_accuracy": 0.0323,
|
||||
"lenient_correct": 23,
|
||||
"lenient_accuracy": 0.0465,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.1882,
|
||||
"lenient": 0.2471
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_legal-3b-v2-checkpoint-50": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 18,
|
||||
"strict_accuracy": 0.0364,
|
||||
"lenient_correct": 24,
|
||||
"lenient_accuracy": 0.0485,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.2118,
|
||||
"lenient": 0.2588
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rag_k8_legal-3b-v2-final": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 16,
|
||||
"strict_accuracy": 0.0323,
|
||||
"lenient_correct": 23,
|
||||
"lenient_accuracy": 0.0465,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 85,
|
||||
"strict": 0.1882,
|
||||
"lenient": 0.2471
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 47,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 363,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0055
|
||||
}
|
||||
}
|
||||
},
|
||||
"rebase-r2_base": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 22,
|
||||
"strict_accuracy": 0.0444,
|
||||
"lenient_correct": 41,
|
||||
"lenient_accuracy": 0.0828,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 93,
|
||||
"strict": 0.2151,
|
||||
"lenient": 0.3011
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 57,
|
||||
"strict": 0.0175,
|
||||
"lenient": 0.0526
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.029
|
||||
}
|
||||
}
|
||||
},
|
||||
"rebase-r2_v3-ckpt300": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 21,
|
||||
"strict_accuracy": 0.0424,
|
||||
"lenient_correct": 34,
|
||||
"lenient_accuracy": 0.0687,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 93,
|
||||
"strict": 0.2151,
|
||||
"lenient": 0.2903
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 57,
|
||||
"strict": 0.0,
|
||||
"lenient": 0.0
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0203
|
||||
}
|
||||
}
|
||||
},
|
||||
"rebase-r3_base": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 19,
|
||||
"strict_accuracy": 0.0384,
|
||||
"lenient_correct": 33,
|
||||
"lenient_accuracy": 0.0667,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1735,
|
||||
"lenient": 0.2449
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0192,
|
||||
"lenient": 0.0192
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0232
|
||||
}
|
||||
}
|
||||
},
|
||||
"rebase-r3_v3-ckpt300": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 21,
|
||||
"strict_accuracy": 0.0424,
|
||||
"lenient_correct": 32,
|
||||
"lenient_accuracy": 0.0646,
|
||||
"by_retrieval": {
|
||||
"gold_in_context": {
|
||||
"n": 98,
|
||||
"strict": 0.1939,
|
||||
"lenient": 0.2245
|
||||
},
|
||||
"gold_missing": {
|
||||
"n": 52,
|
||||
"strict": 0.0192,
|
||||
"lenient": 0.0192
|
||||
},
|
||||
"no_gold": {
|
||||
"n": 345,
|
||||
"strict": 0.0029,
|
||||
"lenient": 0.0261
|
||||
}
|
||||
}
|
||||
},
|
||||
"checkpoint-50": {
|
||||
"scored_total": 495,
|
||||
"strict_correct": 4,
|
||||
"strict_accuracy": 0.0081,
|
||||
"lenient_correct": 4,
|
||||
"lenient_accuracy": 0.0081
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user