Adding Evaluation Results (#4)

- Adding Evaluation Results (3458bf67e3915f7c07b7025b5e04dd9ff29e0763)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -111,8 +111,98 @@ model-index:
     source:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
       name: Open LLM Leaderboard
-
-      
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 45.56
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 32.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.95
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 11.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 39.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fblgit/UNA-SimpleSmaug-34b-v1beta
+      name: Open LLM Leaderboard
 ---
 
 # UNA-SimpleSmaug-34b-v1beta
@@ -177,3 +267,17 @@ To abacusai for making Smaug-34B, the Bagel, and all the magic behind the base m
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__UNA-SimpleSmaug-34b-v1beta)
 
 
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__UNA-SimpleSmaug-34b-v1beta)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.12|
+|IFEval (0-Shot)    |45.56|
+|BBH (3-Shot)       |32.78|
+|MATH Lvl 5 (4-Shot)| 0.15|
+|GPQA (0-shot)      | 8.95|
+|MuSR (0-shot)      |11.96|
+|MMLU-PRO (5-shot)  |39.33|
+