anupam413
/

phi2-finetuned-lora

Text Generation

text-generation-inference

Model card Files Files and versions

anupam413 commited on Apr 19, 2024

Commit

5401a25

·

verified ·

1 Parent(s): 7629f16

Update README.md

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -5,7 +5,6 @@ license: mit
 Finetuned the Microsoft's Phi-2 model using the email dataset.
 Model:
-Step	Training Loss	Validation Loss \n
-100	    1.093000	    0.079683 \n
-200	    0.070900	    0.058024 \n
-300	    0.054800	    0.050852

 Finetuned the Microsoft's Phi-2 model using the email dataset.
 Model:
+Step 300
+Training Loss 0.054800
+Validation Loss 0.050852