Upload eval-answers-20260919/gepafix-gptoss-20260919T102015Z--summary.json with huggingface_hub
Browse files
eval-answers-20260919/gepafix-gptoss-20260919T102015Z--summary.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"arm": "base",
|
| 4 |
+
"condition": "intact",
|
| 5 |
+
"n": 2000,
|
| 6 |
+
"score": 0.6249,
|
| 7 |
+
"valid": 0.993,
|
| 8 |
+
"finished": 0.9985,
|
| 9 |
+
"truncated": 0.0015,
|
| 10 |
+
"max_new_tokens": 1024,
|
| 11 |
+
"elapsed_seconds": 4813.7,
|
| 12 |
+
"ablated_experts": []
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"arm": "gepa-n1000-s42",
|
| 16 |
+
"condition": "intact",
|
| 17 |
+
"n": 2000,
|
| 18 |
+
"score": 0.7552785714285715,
|
| 19 |
+
"valid": 0.999,
|
| 20 |
+
"finished": 0.999,
|
| 21 |
+
"truncated": 0.001,
|
| 22 |
+
"max_new_tokens": 1024,
|
| 23 |
+
"elapsed_seconds": 3260.5,
|
| 24 |
+
"ablated_experts": []
|
| 25 |
+
}
|
| 26 |
+
]
|