sileod commited on
Commit
052ab03
1 Parent(s): bc9d816

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -0
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - Anthropic/hh-rlhf
4
+ language:
5
+ - en
6
+ tags:
7
+ - rlhf
8
+ model-index:
9
+ - name: deberta-v3-large-tasksource-rlhf-reward-model
10
+ results:
11
+ - task:
12
+ type: text-classification
13
+ name: RLHF
14
+ dataset:
15
+ type: rlhf
16
+ name: Anthropic/hh-rlhf
17
+ split: validation
18
+ metrics:
19
+ - type: accuracy
20
+ value: 0,7516
21
+ verified: true
22
+ ---
23
+ `deberta-v3-large-tasksource-nli` fine-tuned on Anthropic/hh-rlhf for 1 epoch with 1e-5 learning rate.
24
+
25
+ Validation accuracy is currently the best publicly available reported: 75.16% (vs 69.25% for `OpenAssistant/reward-model-deberta-v3-large-v2`).