eval results sync
Browse files
eval_results/agopd-v3-s90/hallusionbench_scores.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"benchmark": "hallusionbench",
|
| 3 |
+
"n_shards": 4,
|
| 4 |
+
"correct": 655,
|
| 5 |
+
"total": 951,
|
| 6 |
+
"accuracy": 0.6887486855941115,
|
| 7 |
+
"final_score": 0.6887486855941115
|
| 8 |
+
}
|