Upload submission/results.json with huggingface_hub
Browse files- submission/results.json +38 -0
submission/results.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"repo_name": "task-generator-benchmark-artifact",
|
| 3 |
+
"max_step": 1000,
|
| 4 |
+
"ordered_benchmarks": [
|
| 5 |
+
"code_generation",
|
| 6 |
+
"common_sense",
|
| 7 |
+
"creative_writing",
|
| 8 |
+
"dialogue_generation",
|
| 9 |
+
"instruction_following",
|
| 10 |
+
"knowledge_retrieval",
|
| 11 |
+
"logical_reasoning",
|
| 12 |
+
"math_reasoning",
|
| 13 |
+
"question_answering",
|
| 14 |
+
"reading_comprehension",
|
| 15 |
+
"safety_evaluation",
|
| 16 |
+
"sentiment_analysis",
|
| 17 |
+
"summarization",
|
| 18 |
+
"text_classification",
|
| 19 |
+
"translation"
|
| 20 |
+
],
|
| 21 |
+
"scores": {
|
| 22 |
+
"code_generation": 0.2296,
|
| 23 |
+
"common_sense": 0.1144,
|
| 24 |
+
"creative_writing": 0.2872,
|
| 25 |
+
"dialogue_generation": 0.002,
|
| 26 |
+
"instruction_following": 0.116,
|
| 27 |
+
"knowledge_retrieval": 0.0116,
|
| 28 |
+
"logical_reasoning": 0.3168,
|
| 29 |
+
"math_reasoning": 0.1948,
|
| 30 |
+
"question_answering": 0.3828,
|
| 31 |
+
"reading_comprehension": 0.0908,
|
| 32 |
+
"safety_evaluation": 0.3308,
|
| 33 |
+
"sentiment_analysis": 0.3784,
|
| 34 |
+
"summarization": 0.1708,
|
| 35 |
+
"text_classification": 0.0128,
|
| 36 |
+
"translation": 0.0796
|
| 37 |
+
}
|
| 38 |
+
}
|