Files
nyaya-3b-v3/training/checkpoint_evals.json

151 lines
3.5 KiB
JSON
Raw Permalink Normal View History

{
"run_dir": "outputs/legal-3b-v1",
"model": "Qwen/Qwen2.5-3B-Instruct",
"frozen_eval_questions": 500,
"checkpoints": {
"checkpoint-50": {
"strict_accuracy": 0.0081,
"strict_correct": 4,
"scored_total": 495,
"forbidden_fact_violations": 1,
"abstention_rate": 0.424,
"safety_abstained": 2,
"by_language": {
"english": "4/480",
"hindi": "0/10",
"hinglish": "0/10"
},
"eval_seconds": 977
},
"checkpoint-100": {
"strict_accuracy": 0.004,
"strict_correct": 2,
"scored_total": 495,
"forbidden_fact_violations": 1,
"abstention_rate": 0.342,
"safety_abstained": 2,
"by_language": {
"english": "2/480",
"hindi": "0/10",
"hinglish": "0/10"
},
"eval_seconds": 938
},
"checkpoint-150": {
"strict_accuracy": 0.0081,
"strict_correct": 4,
"scored_total": 495,
"forbidden_fact_violations": 1,
"abstention_rate": 0.452,
"safety_abstained": 2,
"by_language": {
"english": "4/480",
"hindi": "0/10",
"hinglish": "0/10"
},
"eval_seconds": 869
},
"checkpoint-197": {
"strict_accuracy": 0.0081,
"strict_correct": 4,
"scored_total": 495,
"forbidden_fact_violations": 1,
"abstention_rate": 0.474,
"safety_abstained": 2,
"by_language": {
"english": "4/480",
"hindi": "0/10",
"hinglish": "0/10"
},
"eval_seconds": 869
},
"final": {
"strict_accuracy": 0.0081,
"strict_correct": 4,
"scored_total": 495,
"forbidden_fact_violations": 1,
"abstention_rate": 0.474,
"safety_abstained": 2,
"by_language": {
"english": "4/480",
"hindi": "0/10",
"hinglish": "0/10"
},
"eval_seconds": 868
}
},
"best": "checkpoint-50",
"best_dataset_eval": {
"total": 1068,
"citation_pass_rate": 0.9017,
"answers_with_citations": 0.9785,
"old_law_citation_rate": 0.0028,
"language_match_rate": 0.9906,
"mean_reference_similarity": 0.2515,
"by_language": {
"english": {
"total": 785,
"citation_ok": 707,
"language_ok": 784,
"old_law_cited": 3
},
"hinglish": {
"total": 168,
"citation_ok": 151,
"language_ok": 167,
"old_law_cited": 0
},
"hindi": {
"total": 115,
"citation_ok": 105,
"language_ok": 107,
"old_law_cited": 0
}
},
"by_task_type": {
"grounded_qa": {
"total": 478,
"citation_ok": 429,
"language_ok": 477,
"old_law_cited": 0
},
"terminology": {
"total": 28,
"citation_ok": 27,
"language_ok": 28,
"old_law_cited": 0
},
"hinglish_qa": {
"total": 168,
"citation_ok": 151,
"language_ok": 167,
"old_law_cited": 0
},
"law_mapping": {
"total": 24,
"citation_ok": 20,
"language_ok": 24,
"old_law_cited": 3
},
"hindi_qa": {
"total": 115,
"citation_ok": 105,
"language_ok": 107,
"old_law_cited": 0
},
"procedural": {
"total": 231,
"citation_ok": 211,
"language_ok": 231,
"old_law_cited": 0
},
"safety_abstention": {
"total": 24,
"citation_ok": 20,
"language_ok": 24,
"old_law_cited": 0
}
}
},
"evaluated_at": "2026-07-15 08:04:21"
}