Update README.md
Browse files
README.md
CHANGED
|
@@ -92,6 +92,16 @@ It achieves the following results on the evaluation set:
|
|
| 92 |
|arc_challenge| 0|acc |0.1971|± |0.0116|
|
| 93 |
| | |acc_norm|0.2278|± |0.0123|
|
| 94 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
---
|
| 96 |
|
| 97 |
## Training procedure
|
|
|
|
| 92 |
|arc_challenge| 0|acc |0.1971|± |0.0116|
|
| 93 |
| | |acc_norm|0.2278|± |0.0123|
|
| 94 |
|
| 95 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 96 |
+
|---------|------:|--------|-----:|---|-----:|
|
| 97 |
+
|hellaswag| 0|acc |0.2618|± |0.0088|
|
| 98 |
+
| | |acc_norm|0.2797|± |0.0090|
|
| 99 |
+
|
| 100 |
+
| Task |Version|Metric|Value | |Stderr|
|
| 101 |
+
|-------------|------:|------|-----:|---|-----:|
|
| 102 |
+
|truthfulqa_mc| 1|mc1 |0.2509|± |0.0152|
|
| 103 |
+
| | |mc2 |0.4492|± |0.0156|
|
| 104 |
+
|
| 105 |
---
|
| 106 |
|
| 107 |
## Training procedure
|