3rd-Degree-Burn commited on
Commit
874bcf9
·
verified ·
1 Parent(s): 6b7ce0c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -5
README.md CHANGED
@@ -2,11 +2,6 @@
2
 
3
  This model is a dual-head reward model trained for literary prose. It features a style head for ranking prose quality and a faithfulness head used as a veto mechanism.
4
 
5
- ## Training Metrics
6
- - **Pair Accuracy**: 0.939
7
- - **Style Pair Accuracy**: 0.939
8
- - **Faithfulness Veto Accuracy**: 1.000
9
-
10
  ## Architecture
11
  - **Backbone**: answerdotai/ModernBERT-large
12
  - **Objective**: style_primary_faith_veto_flat_copy_length_gm_v3
 
2
 
3
  This model is a dual-head reward model trained for literary prose. It features a style head for ranking prose quality and a faithfulness head used as a veto mechanism.
4
 
 
 
 
 
 
5
  ## Architecture
6
  - **Backbone**: answerdotai/ModernBERT-large
7
  - **Objective**: style_primary_faith_veto_flat_copy_length_gm_v3