adopt-0 standardized bench
Browse files- adopt0/adopt0_bench.json +106 -19
adopt0/adopt0_bench.json
CHANGED
|
@@ -1,31 +1,118 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"aleph": {
|
| 3 |
"arc_easy": {
|
| 4 |
-
"sample_len":
|
| 5 |
-
"acc,none": 0.
|
| 6 |
-
"acc_stderr,none": 0.
|
| 7 |
-
"acc_norm,none": 0.
|
| 8 |
-
"acc_norm_stderr,none": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
},
|
| 10 |
"hellaswag": {
|
| 11 |
-
"sample_len":
|
| 12 |
-
"acc,none": 0.
|
| 13 |
-
"acc_stderr,none": 0.
|
| 14 |
-
"acc_norm,none": 0.
|
| 15 |
-
"acc_norm_stderr,none": 0.
|
| 16 |
},
|
| 17 |
"piqa": {
|
| 18 |
-
"sample_len":
|
| 19 |
-
"acc,none": 0.
|
| 20 |
-
"acc_stderr,none": 0.
|
| 21 |
-
"acc_norm,none": 0.
|
| 22 |
-
"acc_norm_stderr,none": 0.
|
| 23 |
},
|
| 24 |
"winogrande": {
|
| 25 |
-
"sample_len":
|
| 26 |
-
"acc,none": 0.
|
| 27 |
-
"acc_stderr,none": 0.
|
| 28 |
},
|
| 29 |
-
"_mean": 0.
|
| 30 |
}
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"stock": {
|
| 3 |
+
"arc_easy": {
|
| 4 |
+
"sample_len": 2376.0,
|
| 5 |
+
"acc,none": 0.6561,
|
| 6 |
+
"acc_stderr,none": 0.0097,
|
| 7 |
+
"acc_norm,none": 0.5888,
|
| 8 |
+
"acc_norm_stderr,none": 0.0101
|
| 9 |
+
},
|
| 10 |
+
"hellaswag": {
|
| 11 |
+
"sample_len": 10042.0,
|
| 12 |
+
"acc,none": 0.4055,
|
| 13 |
+
"acc_stderr,none": 0.0049,
|
| 14 |
+
"acc_norm,none": 0.5251,
|
| 15 |
+
"acc_norm_stderr,none": 0.005
|
| 16 |
+
},
|
| 17 |
+
"piqa": {
|
| 18 |
+
"sample_len": 1838.0,
|
| 19 |
+
"acc,none": 0.7057,
|
| 20 |
+
"acc_stderr,none": 0.0106,
|
| 21 |
+
"acc_norm,none": 0.7051,
|
| 22 |
+
"acc_norm_stderr,none": 0.0106
|
| 23 |
+
},
|
| 24 |
+
"winogrande": {
|
| 25 |
+
"sample_len": 1267.0,
|
| 26 |
+
"acc,none": 0.5564,
|
| 27 |
+
"acc_stderr,none": 0.014
|
| 28 |
+
},
|
| 29 |
+
"_mean": 0.5939
|
| 30 |
+
},
|
| 31 |
"aleph": {
|
| 32 |
"arc_easy": {
|
| 33 |
+
"sample_len": 2376.0,
|
| 34 |
+
"acc,none": 0.6393,
|
| 35 |
+
"acc_stderr,none": 0.0099,
|
| 36 |
+
"acc_norm,none": 0.596,
|
| 37 |
+
"acc_norm_stderr,none": 0.0101
|
| 38 |
+
},
|
| 39 |
+
"hellaswag": {
|
| 40 |
+
"sample_len": 10042.0,
|
| 41 |
+
"acc,none": 0.3754,
|
| 42 |
+
"acc_stderr,none": 0.0048,
|
| 43 |
+
"acc_norm,none": 0.4669,
|
| 44 |
+
"acc_norm_stderr,none": 0.005
|
| 45 |
+
},
|
| 46 |
+
"piqa": {
|
| 47 |
+
"sample_len": 1838.0,
|
| 48 |
+
"acc,none": 0.6806,
|
| 49 |
+
"acc_stderr,none": 0.0109,
|
| 50 |
+
"acc_norm,none": 0.6779,
|
| 51 |
+
"acc_norm_stderr,none": 0.0109
|
| 52 |
+
},
|
| 53 |
+
"winogrande": {
|
| 54 |
+
"sample_len": 1267.0,
|
| 55 |
+
"acc,none": 0.5675,
|
| 56 |
+
"acc_stderr,none": 0.0139
|
| 57 |
+
},
|
| 58 |
+
"_mean": 0.5771
|
| 59 |
+
},
|
| 60 |
+
"mlp": {
|
| 61 |
+
"arc_easy": {
|
| 62 |
+
"sample_len": 2376.0,
|
| 63 |
+
"acc,none": 0.6423,
|
| 64 |
+
"acc_stderr,none": 0.0098,
|
| 65 |
+
"acc_norm,none": 0.5968,
|
| 66 |
+
"acc_norm_stderr,none": 0.0101
|
| 67 |
+
},
|
| 68 |
+
"hellaswag": {
|
| 69 |
+
"sample_len": 10042.0,
|
| 70 |
+
"acc,none": 0.3789,
|
| 71 |
+
"acc_stderr,none": 0.0048,
|
| 72 |
+
"acc_norm,none": 0.4743,
|
| 73 |
+
"acc_norm_stderr,none": 0.005
|
| 74 |
+
},
|
| 75 |
+
"piqa": {
|
| 76 |
+
"sample_len": 1838.0,
|
| 77 |
+
"acc,none": 0.6915,
|
| 78 |
+
"acc_stderr,none": 0.0108,
|
| 79 |
+
"acc_norm,none": 0.6746,
|
| 80 |
+
"acc_norm_stderr,none": 0.0109
|
| 81 |
+
},
|
| 82 |
+
"winogrande": {
|
| 83 |
+
"sample_len": 1267.0,
|
| 84 |
+
"acc,none": 0.5462,
|
| 85 |
+
"acc_stderr,none": 0.014
|
| 86 |
+
},
|
| 87 |
+
"_mean": 0.573
|
| 88 |
+
},
|
| 89 |
+
"teacher": {
|
| 90 |
+
"arc_easy": {
|
| 91 |
+
"sample_len": 2376.0,
|
| 92 |
+
"acc,none": 0.7668,
|
| 93 |
+
"acc_stderr,none": 0.0087,
|
| 94 |
+
"acc_norm,none": 0.7584,
|
| 95 |
+
"acc_norm_stderr,none": 0.0088
|
| 96 |
},
|
| 97 |
"hellaswag": {
|
| 98 |
+
"sample_len": 10042.0,
|
| 99 |
+
"acc,none": 0.5086,
|
| 100 |
+
"acc_stderr,none": 0.005,
|
| 101 |
+
"acc_norm,none": 0.6822,
|
| 102 |
+
"acc_norm_stderr,none": 0.0046
|
| 103 |
},
|
| 104 |
"piqa": {
|
| 105 |
+
"sample_len": 1838.0,
|
| 106 |
+
"acc,none": 0.7612,
|
| 107 |
+
"acc_stderr,none": 0.0099,
|
| 108 |
+
"acc_norm,none": 0.7601,
|
| 109 |
+
"acc_norm_stderr,none": 0.01
|
| 110 |
},
|
| 111 |
"winogrande": {
|
| 112 |
+
"sample_len": 1267.0,
|
| 113 |
+
"acc,none": 0.629,
|
| 114 |
+
"acc_stderr,none": 0.0136
|
| 115 |
},
|
| 116 |
+
"_mean": 0.7074
|
| 117 |
}
|
| 118 |
}
|