Commit
•
0ce3442
1
Parent(s):
97b803e
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
Reward Model pretrained on openai/webgpt_comparison and humanfeedback summary. Unlike the other electra-large model this model is trained using rank loss with one more datasets.
|
| 7 |
|
| 8 |
On validation dataset the result is much more stable than usual.
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- webgpt
|
| 6 |
+
- regression
|
| 7 |
+
- reward-model
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
datasets:
|
| 10 |
+
- openai/webgpt_comparisons
|
| 11 |
+
- Tristan/summarize_from_feedback
|
| 12 |
+
metrics:
|
| 13 |
+
- accuracy
|
| 14 |
---
|
| 15 |
|
|
|
|
| 16 |
Reward Model pretrained on openai/webgpt_comparison and humanfeedback summary. Unlike the other electra-large model this model is trained using rank loss with one more datasets.
|
| 17 |
|
| 18 |
On validation dataset the result is much more stable than usual.
|