Commit
•
0851fe5
1
Parent(s):
ac685a1
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,21 +52,28 @@ print(generate_response(prompt), "\n")
|
|
| 52 |
|
| 53 |
## 🏆 Evaluations
|
| 54 |
|
| 55 |
-
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 56 |
-
|-------------|-------|------|-----:|--------|-----:|---|-----:|
|
| 57 |
-
|arc_challenge|Yaml |none | 0|acc |0.6067|± |0.0143|
|
| 58 |
-
| | |none | 0|acc_norm|0.6263|± |0.0141|
|
| 59 |
-
|arc_easy |Yaml |none | 0|acc |0.8211|± |0.0079|
|
| 60 |
-
| | |none | 0|acc_norm|0.8001|± |0.0082|
|
| 61 |
-
|boolq |Yaml |none | 0|acc |0.8557|± |0.0061|
|
| 62 |
-
|hellaswag |Yaml |none | 0|acc |0.6695|± |0.0047|
|
| 63 |
-
| | |none | 0|acc_norm|0.8484|± |0.0036|
|
| 64 |
-
|openbookqa |Yaml |none | 0|acc |0.3420|± |0.0212|
|
| 65 |
-
| | |none | 0|acc_norm|0.4520|± |0.0223|
|
| 66 |
-
|piqa |Yaml |none | 0|acc |0.7949|± |0.0094|
|
| 67 |
-
| | |none | 0|acc_norm|0.8058|± |0.0092|
|
| 68 |
-
|winogrande |Yaml |none | 0|acc |0.7372|± |0.0124|
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
### 📚 Citations
|
|
|
|
| 52 |
|
| 53 |
## 🏆 Evaluations
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
+
### ARC
|
| 57 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 58 |
+
|-------------|------:|--------------------|-------------|---|------|
|
| 59 |
+
|arc_challenge| 1|acc,none | 0.68| | |
|
| 60 |
+
| | |acc_stderr,none | 0.01| | |
|
| 61 |
+
| | |acc_norm,none | 0.72| | |
|
| 62 |
+
| | |acc_norm_stderr,none| 0.01| | |
|
| 63 |
+
| | |alias |arc_challenge| | |
|
| 64 |
+
|
| 65 |
+
Average: 71.76%
|
| 66 |
+
|
| 67 |
+
### HellaSwag
|
| 68 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 69 |
+
|---------|------:|--------------------|---------|---|------|
|
| 70 |
+
|hellaswag| 1|acc,none | 0.71| | |
|
| 71 |
+
| | |acc_stderr,none | 0| | |
|
| 72 |
+
| | |acc_norm,none | 0.88| | |
|
| 73 |
+
| | |acc_norm_stderr,none| 0| | |
|
| 74 |
+
| | |alias |hellaswag| | |
|
| 75 |
+
|
| 76 |
+
Average: 88.01%
|
| 77 |
|
| 78 |
|
| 79 |
### 📚 Citations
|