Update README.md

README.md

@@ -20,7 +20,29 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+Trained on single ID token 5K dataset filtered to 10k sequences (30% for test data = 3000)
+
+lora_alpha = 64 <--------------
+
+lora_dropout = 0.1
+
+lora_r = 128
+
+epochs = 3
+
+learning rate = 3e-4
+
+warmup_steps=500
+
+gradient_accumulation_steps = 1
+
+train_batch = 2
+
+eval_batch = 2
+
+ALL Linear layers
+
+Changed ' token to >     <--------------
 
 ## Intended uses & limitations