Transformers
Safetensors
fc91 commited on
Commit
7401a72
·
verified ·
1 Parent(s): 9f76d75

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -87,6 +87,12 @@ model = AutoModel.from_pretrained("fc91/phi3-mini-instruct-full_ethics-lora")
87
 
88
  ["hendrycks/ethics"](https://huggingface.co/datasets/hendrycks/ethics)
89
 
 
 
 
 
 
 
90
  ### Training Procedure
91
 
92
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
@@ -133,6 +139,12 @@ Validation Loss = 0.119734
133
 
134
  ["hendrycks/ethics"](https://huggingface.co/datasets/hendrycks/ethics)
135
 
 
 
 
 
 
 
136
  #### Factors
137
 
138
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
 
87
 
88
  ["hendrycks/ethics"](https://huggingface.co/datasets/hendrycks/ethics)
89
 
90
+ The following subsets of the above dataset were leveraged:
91
+ -commonsense (10k random samples)
92
+ -deontology (10k random samples)
93
+ -justice (10k random samples)
94
+ -utilitarianism (10k random samples)
95
+
96
  ### Training Procedure
97
 
98
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
139
 
140
  ["hendrycks/ethics"](https://huggingface.co/datasets/hendrycks/ethics)
141
 
142
+ The following subsets of the above dataset were leveraged:
143
+ -commonsense (2.5k random samples)
144
+ -deontology (2.5k random samples)
145
+ -justice (2.5k random samples)
146
+ -utilitarianism (2.5k random samples)
147
+
148
  #### Factors
149
 
150
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->