Commit
·
949dbb0
1
Parent(s):
39ae128
Update README.md
Browse files
README.md
CHANGED
|
@@ -108,7 +108,7 @@ Note: You can also use a sweet chicken bugger mix to make sweet chicken buggers.
|
|
| 108 |
Enjoy your sweet chicken buggers!
|
| 109 |
"""
|
| 110 |
```
|
| 111 |
-
##
|
| 112 |
```
|
| 113 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 114 |
|---------|-------|------|-----:|--------|-----:|---|-----:|
|
|
@@ -116,4 +116,21 @@ Enjoy your sweet chicken buggers!
|
|
| 116 |
| | |none | 0|acc_norm|0.7068|± |0.0045|
|
| 117 |
|
| 118 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
```
|
|
|
|
| 108 |
Enjoy your sweet chicken buggers!
|
| 109 |
"""
|
| 110 |
```
|
| 111 |
+
## Evals
|
| 112 |
```
|
| 113 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
| 114 |
|---------|-------|------|-----:|--------|-----:|---|-----:|
|
|
|
|
| 116 |
| | |none | 0|acc_norm|0.7068|± |0.0045|
|
| 117 |
|
| 118 |
|
| 119 |
+
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
| 120 |
+
|----------|-------|------|-----:|-----------|------:|---|-----:|
|
| 121 |
+
|truthfulqa|N/A |none | 0|acc | 0.3411|± |0.0016|
|
| 122 |
+
| | |none | 0|bleu_max |19.4174|± |0.6888|
|
| 123 |
+
| | |none | 0|bleu_acc | 0.3378|± |0.0166|
|
| 124 |
+
| | |none | 0|bleu_diff |-4.4165|± |0.6611|
|
| 125 |
+
| | |none | 0|rouge1_max |43.6923|± |0.8239|
|
| 126 |
+
| | |none | 0|rouge1_acc | 0.3305|± |0.0165|
|
| 127 |
+
| | |none | 0|rouge1_diff|-6.4023|± |0.7680|
|
| 128 |
+
| | |none | 0|rouge2_max |28.4074|± |0.8883|
|
| 129 |
+
| | |none | 0|rouge2_acc | 0.2827|± |0.0158|
|
| 130 |
+
| | |none | 0|rouge2_diff|-6.7716|± |0.8844|
|
| 131 |
+
| | |none | 0|rougeL_max |40.2657|± |0.8218|
|
| 132 |
+
| | |none | 0|rougeL_acc | 0.3023|± |0.0161|
|
| 133 |
+
| | |none | 0|rougeL_diff|-6.5447|± |0.7706|
|
| 134 |
+
|
| 135 |
+
|
| 136 |
```
|