Upload eval_results.json with huggingface_hub
Browse files- eval_results.json +35 -0
eval_results.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"easy_bench": {
|
| 3 |
+
"task": "easy_bench",
|
| 4 |
+
"steps": 50,
|
| 5 |
+
"total_reward": 6.4762,
|
| 6 |
+
"enrolled": 0,
|
| 7 |
+
"target": 100,
|
| 8 |
+
"json_parse_rate": 1.0,
|
| 9 |
+
"action_dist": {
|
| 10 |
+
"adjust_strategy": 50
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"medium_bench": {
|
| 14 |
+
"task": "medium_bench",
|
| 15 |
+
"steps": 50,
|
| 16 |
+
"total_reward": 1.5398,
|
| 17 |
+
"enrolled": 0,
|
| 18 |
+
"target": 100,
|
| 19 |
+
"json_parse_rate": 1.0,
|
| 20 |
+
"action_dist": {
|
| 21 |
+
"adjust_strategy": 50
|
| 22 |
+
}
|
| 23 |
+
},
|
| 24 |
+
"hard_bench": {
|
| 25 |
+
"task": "hard_bench",
|
| 26 |
+
"steps": 50,
|
| 27 |
+
"total_reward": 3.0742,
|
| 28 |
+
"enrolled": 0,
|
| 29 |
+
"target": 100,
|
| 30 |
+
"json_parse_rate": 1.0,
|
| 31 |
+
"action_dist": {
|
| 32 |
+
"adjust_strategy": 50
|
| 33 |
+
}
|
| 34 |
+
}
|
| 35 |
+
}
|