mwitiderrick
commited on
Commit
•
6b8e7ea
1
Parent(s):
dab4546
Update README.md
Browse files
README.md
CHANGED
@@ -123,35 +123,7 @@ Step 4: Make the gravy
|
|
123 |
```
|
124 |
## Truthfulaq metrics
|
125 |
```
|
126 |
-
|
127 |
-
|-----------------|-------|------|-----:|-----------|-------:|---|-----:|
|
128 |
-
|truthfulqa |N/A |none | 0|acc | 0.3166|± |0.0012|
|
129 |
-
| | |none | 0|bleu_max | 23.7766|± |0.7660|
|
130 |
-
| | |none | 0|bleu_acc | 0.3207|± |0.0163|
|
131 |
-
| | |none | 0|bleu_diff | -7.1853|± |0.7396|
|
132 |
-
| | |none | 0|rouge1_max | 48.6534|± |0.8706|
|
133 |
-
| | |none | 0|rouge1_acc | 0.2766|± |0.0157|
|
134 |
-
| | |none | 0|rouge1_diff| -9.8011|± |0.7883|
|
135 |
-
| | |none | 0|rouge2_max | 31.9289|± |0.9637|
|
136 |
-
| | |none | 0|rouge2_acc | 0.2399|± |0.0149|
|
137 |
-
| | |none | 0|rouge2_diff|-11.3958|± |0.9220|
|
138 |
-
| | |none | 0|rougeL_max | 45.4592|± |0.8754|
|
139 |
-
| | |none | 0|rougeL_acc | 0.2754|± |0.0156|
|
140 |
-
| | |none | 0|rougeL_diff|-10.0740|± |0.7807|
|
141 |
-
| - truthfulqa_gen|Yaml |none | 0|bleu_max | 23.7766|± |0.7660|
|
142 |
-
| | |none | 0|bleu_acc | 0.3207|± |0.0163|
|
143 |
-
| | |none | 0|bleu_diff | -7.1853|± |0.7396|
|
144 |
-
| | |none | 0|rouge1_max | 48.6534|± |0.8706|
|
145 |
-
| | |none | 0|rouge1_acc | 0.2766|± |0.0157|
|
146 |
-
| | |none | 0|rouge1_diff| -9.8011|± |0.7883|
|
147 |
-
| | |none | 0|rouge2_max | 31.9289|± |0.9637|
|
148 |
-
| | |none | 0|rouge2_acc | 0.2399|± |0.0149|
|
149 |
-
| | |none | 0|rouge2_diff|-11.3958|± |0.9220|
|
150 |
-
| | |none | 0|rougeL_max | 45.4592|± |0.8754|
|
151 |
-
| | |none | 0|rougeL_acc | 0.2754|± |0.0156|
|
152 |
-
| | |none | 0|rougeL_diff|-10.0740|± |0.7807|
|
153 |
-
| - truthfulqa_mc1|Yaml |none | 0|acc | 0.2534|± |0.0152|
|
154 |
-
| - truthfulqa_mc2|Yaml |none | 0|acc | 0.3798|± |0.0139|
|
155 |
|
156 |
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
157 |
|----------|-------|------|-----:|-----------|-------:|---|-----:|
|
@@ -168,7 +140,4 @@ Step 4: Make the gravy
|
|
168 |
| | |none | 0|rougeL_max | 45.4592|± |0.8754|
|
169 |
| | |none | 0|rougeL_acc | 0.2754|± |0.0156|
|
170 |
| | |none | 0|rougeL_diff|-10.0740|± |0.7807|
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
```
|
|
|
123 |
```
|
124 |
## Truthfulaq metrics
|
125 |
```
|
126 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
127 |
|
128 |
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
129 |
|----------|-------|------|-----:|-----------|-------:|---|-----:|
|
|
|
140 |
| | |none | 0|rougeL_max | 45.4592|± |0.8754|
|
141 |
| | |none | 0|rougeL_acc | 0.2754|± |0.0156|
|
142 |
| | |none | 0|rougeL_diff|-10.0740|± |0.7807|
|
|
|
|
|
|
|
143 |
```
|