MyAwesomeModel-AuditCard / benchmark_summary.json
petra345's picture
Publish final audit release package
576fcee verified
Raw
History Blame Contribute Delete
663 Bytes
{
"selected_checkpoint": "step_1000",
"overall_eval_accuracy": "0.710",
"benchmark_scores": {
"math_reasoning": "0.550",
"logical_reasoning": "0.819",
"common_sense": "0.736",
"reading_comprehension": "0.700",
"question_answering": "0.607",
"text_classification": "0.828",
"sentiment_analysis": "0.792",
"code_generation": "0.650",
"creative_writing": "0.610",
"dialogue_generation": "0.644",
"summarization": "0.767",
"translation": "0.804",
"knowledge_retrieval": "0.676",
"instruction_following": "0.758",
"safety_evaluation": "0.739"
},
"score_format": "three_decimal_strings_in_readme"
}