Update README.md

README.md

@@ -20,7 +20,23 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+lora_alpha = 32
+
+lora_dropout = 0.05
+
+lora_r = 16
+
+epochs = 3
+
+learning rate = 3e-5 <--------- (10x smaller)
+
+warmup_steps=0.5
+
+gradient_accumulation_steps = 8
+
+train_batch = 1
+
+eval_batch = 1
 
 ## Intended uses & limitations
 
@@ -28,7 +44,7 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+in files
 
 ## Training procedure