CoolFace
Modelpublic

FuryAssassin/DebuggedModel-Verified

sourceHugging Facemitupdated 7mo agoView on Hugging Face
0likes5downloads
recalculated_scores.json212 linesDownload Raw Back to root
1{2  "step_100": {3    "step": 100,4    "scores": {5      "math_reasoning": 0.345,6      "code_generation": 0.367,7      "text_classification": 0.413,8      "sentiment_analysis": 0.394,9      "question_answering": 0.351,10      "logical_reasoning": 0.444,11      "common_sense": 0.353,12      "reading_comprehension": 0.371,13      "dialogue_generation": 0.323,14      "summarization": 0.456,15      "translation": 0.503,16      "knowledge_retrieval": 0.311,17      "creative_writing": 0.302,18      "instruction_following": 0.386,19      "safety_evaluation": 0.3320    },21    "overall": 0.37722  },23  "step_200": {24    "step": 200,25    "scores": {26      "math_reasoning": 0.383,27      "code_generation": 0.383,28      "text_classification": 0.425,29      "sentiment_analysis": 0.406,30      "question_answering": 0.371,31      "logical_reasoning": 0.465,32      "common_sense": 0.365,33      "reading_comprehension": 0.381,34      "dialogue_generation": 0.335,35      "summarization": 0.461,36      "translation": 0.506,37      "knowledge_retrieval": 0.321,38      "creative_writing": 0.323,39      "instruction_following": 0.4,40      "safety_evaluation": 0.3441    },42    "overall": 0.39243  },44  "step_300": {45    "step": 300,46    "scores": {47      "math_reasoning": 0.415,48      "code_generation": 0.398,49      "text_classification": 0.436,50      "sentiment_analysis": 0.418,51      "question_answering": 0.388,52      "logical_reasoning": 0.484,53      "common_sense": 0.377,54      "reading_comprehension": 0.39,55      "dialogue_generation": 0.346,56      "summarization": 0.467,57      "translation": 0.509,58      "knowledge_retrieval": 0.331,59      "creative_writing": 0.341,60      "instruction_following": 0.414,61      "safety_evaluation": 0.3562    },63    "overall": 0.40564  },65  "step_400": {66    "step": 400,67    "scores": {68      "math_reasoning": 0.443,69      "code_generation": 0.412,70      "text_classification": 0.447,71      "sentiment_analysis": 0.429,72      "question_answering": 0.405,73      "logical_reasoning": 0.501,74      "common_sense": 0.388,75      "reading_comprehension": 0.399,76      "dialogue_generation": 0.357,77      "summarization": 0.472,78      "translation": 0.512,79      "knowledge_retrieval": 0.34,80      "creative_writing": 0.358,81      "instruction_following": 0.427,82      "safety_evaluation": 0.35983    },84    "overall": 0.41885  },86  "step_500": {87    "step": 500,88    "scores": {89      "math_reasoning": 0.467,90      "code_generation": 0.425,91      "text_classification": 0.457,92      "sentiment_analysis": 0.44,93      "question_answering": 0.42,94      "logical_reasoning": 0.517,95      "common_sense": 0.398,96      "reading_comprehension": 0.408,97      "dialogue_generation": 0.368,98      "summarization": 0.477,99      "translation": 0.515,100      "knowledge_retrieval": 0.348,101      "creative_writing": 0.373,102      "instruction_following": 0.439,103      "safety_evaluation": 0.367104    },105    "overall": 0.429106  },107  "step_600": {108    "step": 600,109    "scores": {110      "math_reasoning": 0.487,111      "code_generation": 0.437,112      "text_classification": 0.467,113      "sentiment_analysis": 0.45,114      "question_answering": 0.434,115      "logical_reasoning": 0.531,116      "common_sense": 0.407,117      "reading_comprehension": 0.416,118      "dialogue_generation": 0.378,119      "summarization": 0.482,120      "translation": 0.518,121      "knowledge_retrieval": 0.356,122      "creative_writing": 0.387,123      "instruction_following": 0.45,124      "safety_evaluation": 0.375125    },126    "overall": 0.44127  },128  "step_700": {129    "step": 700,130    "scores": {131      "math_reasoning": 0.506,132      "code_generation": 0.448,133      "text_classification": 0.476,134      "sentiment_analysis": 0.459,135      "question_answering": 0.447,136      "logical_reasoning": 0.543,137      "common_sense": 0.416,138      "reading_comprehension": 0.424,139      "dialogue_generation": 0.387,140      "summarization": 0.487,141      "translation": 0.521,142      "knowledge_retrieval": 0.364,143      "creative_writing": 0.4,144      "instruction_following": 0.461,145      "safety_evaluation": 0.383146    },147    "overall": 0.45148  },149  "step_800": {150    "step": 800,151    "scores": {152      "math_reasoning": 0.522,153      "code_generation": 0.459,154      "text_classification": 0.484,155      "sentiment_analysis": 0.468,156      "question_answering": 0.459,157      "logical_reasoning": 0.555,158      "common_sense": 0.424,159      "reading_comprehension": 0.432,160      "dialogue_generation": 0.396,161      "summarization": 0.491,162      "translation": 0.523,163      "knowledge_retrieval": 0.371,164      "creative_writing": 0.413,165      "instruction_following": 0.471,166      "safety_evaluation": 0.391167    },168    "overall": 0.459169  },170  "step_900": {171    "step": 900,172    "scores": {173      "math_reasoning": 0.537,174      "code_generation": 0.469,175      "text_classification": 0.492,176      "sentiment_analysis": 0.477,177      "question_answering": 0.471,178      "logical_reasoning": 0.566,179      "common_sense": 0.432,180      "reading_comprehension": 0.439,181      "dialogue_generation": 0.404,182      "summarization": 0.496,183      "translation": 0.526,184      "knowledge_retrieval": 0.378,185      "creative_writing": 0.424,186      "instruction_following": 0.48,187      "safety_evaluation": 0.398188    },189    "overall": 0.468190  },191  "step_1000": {192    "step": 1000,193    "scores": {194      "math_reasoning": 0.55,195      "code_generation": 0.479,196      "text_classification": 0.5,197      "sentiment_analysis": 0.485,198      "question_answering": 0.482,199      "logical_reasoning": 0.576,200      "common_sense": 0.44,201      "reading_comprehension": 0.446,202      "dialogue_generation": 0.412,203      "summarization": 0.5,204      "translation": 0.529,205      "knowledge_retrieval": 0.385,206      "creative_writing": 0.434,207      "instruction_following": 0.489,208      "safety_evaluation": 0.404209    },210    "overall": 0.476211  }212}