Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
BF16:
|
| 2 |
+
|
| 3 |
+
```
|
| 4 |
+
arc_challenge
|
| 5 |
+
|
| 6 |
+
{'alias': 'arc_challenge', 'acc,none': 0.5332764505119454, 'acc_stderr,none': 0.014578995859605814, 'acc_norm,none': 0.5324232081911263, 'acc_norm_stderr,none': 0.014580637569995418}
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
arc_easy
|
| 10 |
+
|
| 11 |
+
{'alias': 'arc_easy', 'acc,none': 0.7558922558922558, 'acc_stderr,none': 0.008814322157999389, 'acc_norm,none': 0.6435185185185185, 'acc_norm_stderr,none': 0.009828046544504433}
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
hellaswag
|
| 15 |
+
|
| 16 |
+
{'alias': 'hellaswag', 'acc,none': 0.5852419836685919, 'acc_stderr,none': 0.004916733258140271, 'acc_norm,none': 0.6487751443935471, 'acc_norm_stderr,none': 0.00476377498183474}
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
piqa
|
| 20 |
+
|
| 21 |
+
{'alias': 'piqa', 'acc,none': 0.8003264417845484, 'acc_stderr,none': 0.009326942154519176, 'acc_norm,none': 0.7899891186071817, 'acc_norm_stderr,none': 0.00950335330581858}
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
This model:
|
| 25 |
+
|
| 26 |
+
```
|
| 27 |
+
arc_challenge
|
| 28 |
+
|
| 29 |
+
{'alias': 'arc_challenge', 'acc,none': 0.5341296928327645, 'acc_stderr,none': 0.014577311315231102, 'acc_norm,none': 0.515358361774744, 'acc_norm_stderr,none': 0.014604496129394911}
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
arc_easy
|
| 33 |
+
|
| 34 |
+
{'alias': 'arc_easy', 'acc,none': 0.7470538720538721, 'acc_stderr,none': 0.008919862739165613, 'acc_norm,none': 0.6325757575757576, 'acc_norm_stderr,none': 0.009892552616211553}
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
hellaswag
|
| 38 |
+
|
| 39 |
+
{'alias': 'hellaswag', 'acc,none': 0.5776737701653057, 'acc_stderr,none': 0.004929204864315951, 'acc_norm,none': 0.6430989842660825, 'acc_norm_stderr,none': 0.004781061390873893}
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
piqa
|
| 43 |
+
|
| 44 |
+
{'alias': 'piqa', 'acc,none': 0.7986942328618063, 'acc_stderr,none': 0.00935543109899043, 'acc_norm,none': 0.8008705114254625, 'acc_norm_stderr,none': 0.009317391893706867}
|
| 45 |
+
|
| 46 |
+
```
|