Update README.md

README.md

@@ -60,6 +60,7 @@ Users should be aware of potential biases in the model's responses and the limit
 ### Training Data
 
 The training data consists of questions and answers generated using the head-to-tail pipeline with a Dbpedia script.  See the paper and Github repository for more details.
+Model was trained on 3000 Unknown questions with 10 additional HighlyKnown question per Unknown
 
 ### Training Procedure
 
@@ -67,11 +68,21 @@ The model was fine-tuned using LoRA.
 
 #### Training Hyperparameters
 
-[More Information Needed]
+    LR = 1e-3
+    BS = 8
+    EPOCHS = 10
+    LoRA:
+    lora_rank = 1
+    lora_alpha = 2
+    use_rslora = True
+    lora_dropout = 0.1
+    bias = "none"
+    target_modules = ["down_proj", "gate_proj", "up_proj"]
+    task_type = "CAUSAL_LM"
 
 ## Evaluation
 
-[More Information Needed]
+For evaluation you can use [notebooks](https://github.com/AIRI-Institute/knowledge-packing/tree/main/notebooks) from github repository
 
 ## Environmental Impact