Update README.md

README.md

@@ -18,16 +18,21 @@ For full model details, refer to the base model page [meta-llama/Llama-3.2-1B](h
 
 ## Evaluations
 
-| Benchmark | Accuracy | Notes |
-|-----------|----------|--------|
-| AGIEval | 20.99% | Average across multiple reasoning tasks |
-| GPT4ALL | 51.12% | Average across all categories |
-| TruthfulQA | 42.80% | MC2 accuracy |
-| BigBench | 31.75% | Average across 18 tasks |
-| MMLU | 31.23% | Average across all categories |
-| Winogrande | 61.33% | 5-shot evaluation |
-| ARC Challenge | 35.92% | 25-shot evaluation |
-| HellaSwag | 48.65% | 10-shot evaluation |
+
+| Benchmark      | Accuracy                 | Notes                                     |
+|----------------|--------------------------|-------------------------------------------|
+| AGIEval        | 22.14% (21.01% normalized) | 0-Shot Average across multiple reasoning tasks |
+| GPT4ALL        | 51.15% (54.38% normalized) | 0-Shot Average across all categories|
+| TruthfulQA     | 42.79%                   | MC2 accuracy                |
+| MMLU           | 31.22%                   | 5-Shot Average across all categories |
+| Winogrande     | 61.72%                   | 0-shot evaluation|
+| ARC Challenge  | 32.94% (36.01% normalized) | 0-shot evaluation|
+| ARC Easy       | 64.52% (60.40% normalized) | 0-shot evaluation|
+| BoolQ          | 50.24%                   | 0-shot evaluation|
+| PIQA           | 75.46% (74.37% normalized) | 0-shot evaluation|
+| HellaSwag      | 48.56% (64.71% normalized) | 0-shot evaluation|
+
+I've updated the table with the new metrics from the 15k model where applicable. Let me know if you need further adjustments or more details!
 
 [Detailed Eval Metrics Available Here](https://docs.google.com/document/d/174SRz1pb9GIJ4kIOoMOEyN6ebz3PrEX-9rNnlcVOjyM/edit?usp=sharing)