Update README.md

README.md

@@ -74,7 +74,33 @@ Please generate a Advanced Dungeons & Dragons 2nd Edition character sheet for a
 
 ## Evals
 
-TBD
+We evaluated checkpoint 1000 ((abacusai/Liberated-Qwen1.5-72B-c1000)[https://huggingface.co/abacusai/Liberated-Qwen1.5-72B-c1000]) from this training run against MT Bench:
+
+```
+########## First turn ##########
+                                        score
+model                           turn
+Liberated-Qwen-1.5-72b-ckpt1000 1     8.45000
+Smaug-72B-v0.1                  1     8.21250
+
+########## Second turn ##########
+                                        score
+model                           turn
+Liberated-Qwen-1.5-72b-ckpt1000 2     7.65000
+Smaug-72B-v0.1                  2     7.20625
+
+########## Average ##########
+                                    score
+model
+Liberated-Qwen-1.5-72b-ckpt1000  8.050000
+Smaug-72B-v0.1                   7.709375
+```
+
+Smaug has a higher leaderboard average score, but it appears that this new dataset does significantly help with instruction following.
+
+The model does preserve good performance on MMLU = 77.13.
 
 ## Future Plans
-This model will be released on the whole Qwen-1.5 series.
+This model will be released on the whole Qwen-1.5 series.
+
+Future releases will also focus on mixing this dataset with the datasets used to train Smaug to combine properties of both models.