Update README.md

README.md

@@ -27,10 +27,21 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Training was done on the training splits of 
+- MEDMCQA
+- MMLU
+- Sciq
+- Ai2 Arc
+- Math_qa
+- ScienceQa
+- Openbookqa
 
 ## Training procedure
 
+The procedure for training was to only leave the question that have only 4 choices to chose from, and from there we do the training 
+by only grabbing the last logit form doing a feedforward on the whole prompt (question with choices) and we do cross entropy loss on this last logit with the 4 options to choose 4 from 
+(so we don't do cross entyropy on the whole vocabulary we only do it on the tokens of the letters of the 4 options (A, B, C and D))
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -46,7 +57,9 @@ The following hyperparameters were used during training:
 - num_epochs: 2
 
 ### Training results
-
+| Model               | MMLU | MMLU-pro | arc-easy | arc-challenge | nlp4education | GPQA | Musr |
+|---------------------|--------------|-------------|---------------|---------------| ---- | ---- |
+| Qwen3-0.6B-base-MCQA | 52% | 17%   | 86%         | 72%           |  51%          |  29% | 38%  |
 
 
 ### Framework versions