Update README.md

README.md

@@ -67,16 +67,18 @@ output = model(**encoded)
 
 ## Evaluation
 
-|                    | GPT-α 124M | GPT-2 124M | GPT-Neo 125M | OPT 125M | Pythia 160M |
-|--------------------|:-----------------:|:----------:|:------------:|:--------:|:-----------:|
-| CommonSenseQA      |       19.2%       |    19.6%   |     19.6%    |  **20.0%**  |    19.9%    |
-| PIQA               |       **63.1%**       |    62.5%   |     62.5%    |  62.1%   |    61.3%    |
-| OpenBookQA         |       **29.8%**       |    27.2%   |     26.2%    |  28.0%   |    27.0%    |
-| TriviaQA           |       **1.3%**        |    0.3%    |     0.7%     |  1.2%    |    0.4%     |
-| TruthfulQA         |       33.1%       |    31.7%   |     **35.7%**    |  33.5%   |    34.7%    |
-| MMLU               |       23.3%       |    **25.9%**   |     25.6%    |  **25.9%**   |    25.1%    |
-| WinoGrande         |       50.2%       |    50.0%   |     **51.7%**    |  51.1%   |    48.8%    |
-| ARC Challenge      |       **29.2%**       |    23.0%   |     22.9%    |  22.1%   |    22.1%    |
-| HellaSwag          |       **35.7%**       |    31.6%   |     30.6%    |  31.7%   |    30.2%    |
-| GSM-8K             |       **2.3%**        |    0.7%    |     1.7%     |  1.7%    |    2.2%     |
-| **Average Score**  |       **28.7%**       |    27.3%   |     27.7%    |  27.7%   |    27.2%    |
+| Benchmark            | GPT-α 124M | GPT-2 124M | GPT-Neo 125M |  OPT 125M  | Pythia 160M |
+|----------------------|:----------:|:----------:|:------------:|:----------:|:-----------:|
+| CommonSenseQA        |   19.16%   |   19.57%   |    19.57%    | **19.98%** |   19.90%    |
+| PIQA                 | **63.06%** |   62.51%   |    62.46%    |   62.08%   |   61.26%    |
+| SIQA                 | **38.18%** |   36.59%   |    37.21%    |   37.21%   |   36.69%    |
+| OpenBookQA           | **29.80%** |   27.20%   |    26.20%    |   28.00%   |   27.00%    |
+| TriviaQA             | **1.31%**  |   0.30%    |     0.66%    |    1.18%   |   0.41%     |
+| TruthfulQA           |   33.13%   |   31.73%   |   **35.70%** |   33.50%   |   34.75%    |
+| MMLU                 |   23.30%   |   25.90%   |    25.58%    | **25.94%** |   25.10%    |
+| WinoGrande           |   50.20%   |   50.04%   |   **51.70%** |   51.07%   |   48.78%    |
+| ARC Challenge        | **29.18%** |   22.95%   |    22.87%    |   22.10%   |   22.10%    |
+| HellaSwag            | **35.74%** |   31.64%   |    30.58%    |   31.69%   |   30.15%    |
+| GSM-8K               | **2.27%**  |   0.68%    |     1.74%    |    1.74%   |   2.20%     |
+| **Average Score**    | **29.58%** |   28.10%   |    28.57%    |   28.59%   |   28.03%    |
+