Update README.md

README.md

@@ -16,13 +16,14 @@ pipeline_tag: text-generation
 
 ### Benchmark Metrics
 
-| Metric                | Value |
-|-----------------------|-------|
-| Avg.                  | 29.85 |
-| ARC (25-shot)         | 21.76 |
-| HellaSwag (10-shot)   | 30.77 |
-| MMLU (5-shot)         | 24.66 |
-| TruthfulQA (0-shot)   | 42.22 |
+| Metric                | GPT-2-dolly | GPT-2 (base) |
+|-----------------------|-------|-------|
+| Avg.                  | 29.85 | **29.99** |
+| ARC (25-shot)         | 21.76 | **21.84** |
+| HellaSwag (10-shot)   | 30.77 | **31.6** |
+| MMLU (5-shot)         | 24.66 | **25.86** |
+| TruthfulQA (0-shot)   | **42.22** | 40.67 |
+
 
 
 We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.