Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
-license: cc-by-nc-nd-4.0
-datasets:
-  - GAIR/MathPile
 language:
-  - en
+- en
+license: cc-by-nc-nd-4.0
 tags:
-  - UNA
-  - SOLAR
-  - MathPILE
+- UNA
+- SOLAR
+- MathPILE
+datasets:
+- GAIR/MathPile
+model-index:
+- name: UNA-POLAR-10.7B-InstructMath-v2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 70.73
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 66.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 71.73
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/UNA-POLAR-10.7B-InstructMath-v2
+      name: Open LLM Leaderboard
 ---
 
 # UNA-POLAR-10.7B-InstructMath-v2
@@ -33,4 +136,17 @@ UNA-DPO over Attention and MLP's
 - Transformers 4.36.2-UNA
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.0
-- Tokenizers 0.15.
+- Tokenizers 0.15.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__UNA-POLAR-10.7B-InstructMath-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.07|
+|AI2 Reasoning Challenge (25-Shot)|70.73|
+|HellaSwag (10-Shot)              |88.20|
+|MMLU (5-Shot)                    |66.03|
+|TruthfulQA (0-shot)              |71.73|
+|Winogrande (5-shot)              |82.95|
+|GSM8k (5-shot)                   |64.75|
+