Update README.md
Browse files
README.md
CHANGED
@@ -62,15 +62,25 @@ agieval_sat_math 0 acc_norm 31.36% 3.14%
|
|
62 |
|
63 |
🏆 Evaluation
|
64 |
|
65 |
-
|
|
66 |
-
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
|
75 |
Average: 75.9% without mmlu
|
76 |
|
|
|
62 |
|
63 |
🏆 Evaluation
|
64 |
|
65 |
+
| Task | Version | Metric | Value | StdErr |
|
66 |
+
|---------------------------------|---------|--------------|--------|--------|
|
67 |
+
| agieval_aqua_rat | 0 | acc | 28.35% | 2.83% |
|
68 |
+
| agieval_aqua_rat | 0 | acc_norm | 26.38% | 2.77% |
|
69 |
+
| agieval_logiqa_en | 0 | acc | 38.25% | 1.91% |
|
70 |
+
| agieval_logiqa_en | 0 | acc_norm | 38.10% | 1.90% |
|
71 |
+
| agieval_lsat_ar | 0 | acc | 23.91% | 2.82% |
|
72 |
+
| agieval_lsat_ar | 0 | acc_norm | 23.48% | 2.80% |
|
73 |
+
| agieval_lsat_lr | 0 | acc | 52.75% | 2.21% |
|
74 |
+
| agieval_lsat_lr | 0 | acc_norm | 53.92% | 2.21% |
|
75 |
+
| agieval_lsat_rc | 0 | acc | 66.91% | 2.87% |
|
76 |
+
| agieval_lsat_rc | 0 | acc_norm | 67.29% | 2.87% |
|
77 |
+
| agieval_sat_en | 0 | acc | 78.64% | 2.86% |
|
78 |
+
| agieval_sat_en | 0 | acc_norm | 78.64% | 2.86% |
|
79 |
+
| agieval_sat_en_without_passage | 0 | acc | 45.15% | 3.48% |
|
80 |
+
| agieval_sat_en_without_passage | 0 | acc_norm | 44.17% | 3.47% |
|
81 |
+
| agieval_sat_math | 0 | acc | 33.18% | 3.18% |
|
82 |
+
| agieval_sat_math | 0 | acc_norm | 31.36% | 3.14% |
|
83 |
+
|
84 |
|
85 |
Average: 75.9% without mmlu
|
86 |
|