DebuggedModel-Verified / recalculated_scores.json
FuryAssassin's picture
Upload recalculated_scores.json with huggingface_hub
366a59f verified
{
"step_100": {
"step": 100,
"scores": {
"math_reasoning": 0.345,
"code_generation": 0.367,
"text_classification": 0.413,
"sentiment_analysis": 0.394,
"question_answering": 0.351,
"logical_reasoning": 0.444,
"common_sense": 0.353,
"reading_comprehension": 0.371,
"dialogue_generation": 0.323,
"summarization": 0.456,
"translation": 0.503,
"knowledge_retrieval": 0.311,
"creative_writing": 0.302,
"instruction_following": 0.386,
"safety_evaluation": 0.33
},
"overall": 0.377
},
"step_200": {
"step": 200,
"scores": {
"math_reasoning": 0.383,
"code_generation": 0.383,
"text_classification": 0.425,
"sentiment_analysis": 0.406,
"question_answering": 0.371,
"logical_reasoning": 0.465,
"common_sense": 0.365,
"reading_comprehension": 0.381,
"dialogue_generation": 0.335,
"summarization": 0.461,
"translation": 0.506,
"knowledge_retrieval": 0.321,
"creative_writing": 0.323,
"instruction_following": 0.4,
"safety_evaluation": 0.34
},
"overall": 0.392
},
"step_300": {
"step": 300,
"scores": {
"math_reasoning": 0.415,
"code_generation": 0.398,
"text_classification": 0.436,
"sentiment_analysis": 0.418,
"question_answering": 0.388,
"logical_reasoning": 0.484,
"common_sense": 0.377,
"reading_comprehension": 0.39,
"dialogue_generation": 0.346,
"summarization": 0.467,
"translation": 0.509,
"knowledge_retrieval": 0.331,
"creative_writing": 0.341,
"instruction_following": 0.414,
"safety_evaluation": 0.35
},
"overall": 0.405
},
"step_400": {
"step": 400,
"scores": {
"math_reasoning": 0.443,
"code_generation": 0.412,
"text_classification": 0.447,
"sentiment_analysis": 0.429,
"question_answering": 0.405,
"logical_reasoning": 0.501,
"common_sense": 0.388,
"reading_comprehension": 0.399,
"dialogue_generation": 0.357,
"summarization": 0.472,
"translation": 0.512,
"knowledge_retrieval": 0.34,
"creative_writing": 0.358,
"instruction_following": 0.427,
"safety_evaluation": 0.359
},
"overall": 0.418
},
"step_500": {
"step": 500,
"scores": {
"math_reasoning": 0.467,
"code_generation": 0.425,
"text_classification": 0.457,
"sentiment_analysis": 0.44,
"question_answering": 0.42,
"logical_reasoning": 0.517,
"common_sense": 0.398,
"reading_comprehension": 0.408,
"dialogue_generation": 0.368,
"summarization": 0.477,
"translation": 0.515,
"knowledge_retrieval": 0.348,
"creative_writing": 0.373,
"instruction_following": 0.439,
"safety_evaluation": 0.367
},
"overall": 0.429
},
"step_600": {
"step": 600,
"scores": {
"math_reasoning": 0.487,
"code_generation": 0.437,
"text_classification": 0.467,
"sentiment_analysis": 0.45,
"question_answering": 0.434,
"logical_reasoning": 0.531,
"common_sense": 0.407,
"reading_comprehension": 0.416,
"dialogue_generation": 0.378,
"summarization": 0.482,
"translation": 0.518,
"knowledge_retrieval": 0.356,
"creative_writing": 0.387,
"instruction_following": 0.45,
"safety_evaluation": 0.375
},
"overall": 0.44
},
"step_700": {
"step": 700,
"scores": {
"math_reasoning": 0.506,
"code_generation": 0.448,
"text_classification": 0.476,
"sentiment_analysis": 0.459,
"question_answering": 0.447,
"logical_reasoning": 0.543,
"common_sense": 0.416,
"reading_comprehension": 0.424,
"dialogue_generation": 0.387,
"summarization": 0.487,
"translation": 0.521,
"knowledge_retrieval": 0.364,
"creative_writing": 0.4,
"instruction_following": 0.461,
"safety_evaluation": 0.383
},
"overall": 0.45
},
"step_800": {
"step": 800,
"scores": {
"math_reasoning": 0.522,
"code_generation": 0.459,
"text_classification": 0.484,
"sentiment_analysis": 0.468,
"question_answering": 0.459,
"logical_reasoning": 0.555,
"common_sense": 0.424,
"reading_comprehension": 0.432,
"dialogue_generation": 0.396,
"summarization": 0.491,
"translation": 0.523,
"knowledge_retrieval": 0.371,
"creative_writing": 0.413,
"instruction_following": 0.471,
"safety_evaluation": 0.391
},
"overall": 0.459
},
"step_900": {
"step": 900,
"scores": {
"math_reasoning": 0.537,
"code_generation": 0.469,
"text_classification": 0.492,
"sentiment_analysis": 0.477,
"question_answering": 0.471,
"logical_reasoning": 0.566,
"common_sense": 0.432,
"reading_comprehension": 0.439,
"dialogue_generation": 0.404,
"summarization": 0.496,
"translation": 0.526,
"knowledge_retrieval": 0.378,
"creative_writing": 0.424,
"instruction_following": 0.48,
"safety_evaluation": 0.398
},
"overall": 0.468
},
"step_1000": {
"step": 1000,
"scores": {
"math_reasoning": 0.55,
"code_generation": 0.479,
"text_classification": 0.5,
"sentiment_analysis": 0.485,
"question_answering": 0.482,
"logical_reasoning": 0.576,
"common_sense": 0.44,
"reading_comprehension": 0.446,
"dialogue_generation": 0.412,
"summarization": 0.5,
"translation": 0.529,
"knowledge_retrieval": 0.385,
"creative_writing": 0.434,
"instruction_following": 0.489,
"safety_evaluation": 0.404
},
"overall": 0.476
}
}