Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,47 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- meta-llama/Llama-3.3-70B-Instruct
|
| 4 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- meta-llama/Llama-3.3-70B-Instruct
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
BF16:
|
| 7 |
+
```
|
| 8 |
+
arc_challenge
|
| 9 |
+
|
| 10 |
+
{'alias': 'arc_challenge', 'acc,none': 0.5332764505119454, 'acc_stderr,none': 0.014578995859605814, 'acc_norm,none': 0.5324232081911263, 'acc_norm_stderr,none': 0.014580637569995418}
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
arc_easy
|
| 14 |
+
|
| 15 |
+
{'alias': 'arc_easy', 'acc,none': 0.7558922558922558, 'acc_stderr,none': 0.008814322157999389, 'acc_norm,none': 0.6435185185185185, 'acc_norm_stderr,none': 0.009828046544504433}
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
hellaswag
|
| 19 |
+
|
| 20 |
+
{'alias': 'hellaswag', 'acc,none': 0.5852419836685919, 'acc_stderr,none': 0.004916733258140271, 'acc_norm,none': 0.6487751443935471, 'acc_norm_stderr,none': 0.00476377498183474}
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
piqa
|
| 24 |
+
|
| 25 |
+
{'alias': 'piqa', 'acc,none': 0.8003264417845484, 'acc_stderr,none': 0.009326942154519176, 'acc_norm,none': 0.7899891186071817, 'acc_norm_stderr,none': 0.00950335330581858}
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
This model:
|
| 29 |
+
|
| 30 |
+
```
|
| 31 |
+
{'alias': 'arc_challenge', 'acc,none': 0.5366894197952219, 'acc_stderr,none': 0.014572000527756989, 'acc_norm,none': 0.514505119453925, 'acc_norm_stderr,none': 0.014605241081370053}
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
arc_easy
|
| 35 |
+
|
| 36 |
+
{'alias': 'arc_easy', 'acc,none': 0.7462121212121212, 'acc_stderr,none': 0.008929657065808293, 'acc_norm,none': 0.6292087542087542, 'acc_norm_stderr,none': 0.009911292822056925}
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
hellaswag
|
| 40 |
+
|
| 41 |
+
{'alias': 'hellaswag', 'acc,none': 0.581557458673571, 'acc_stderr,none': 0.004922953651577666, 'acc_norm,none': 0.6630153355905198, 'acc_norm_stderr,none': 0.00471713572219413}
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
piqa
|
| 45 |
+
|
| 46 |
+
{'alias': 'piqa', 'acc,none': 0.8052230685527747, 'acc_stderr,none': 0.00924000669331772, 'acc_norm,none': 0.8030467899891186, 'acc_norm_stderr,none': 0.009278918898006383}
|
| 47 |
+
```
|