Hugging Face's logo

Blackroot
/
Differential-Microllama-Base

llama
Model card Files Community
Blackroot commited on
Commit
cba2e4e
·
verified ·
1 Parent(s): a024e57

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+
2
+ Each epoch represent 1 gigabyte of data. Total tokens trained ~48261120. No synthetic data was used.
3
+ Epoch 3 Summary:
4
+ Average Loss: 2.6883
5
+ Perplexity: 14.71
6
+
7
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/637f3b03932a61b89aefbf5c/Eu8hsPYrKQqFvt-54_AkY.png)