Adding Evaluation Results (#1)

- Adding Evaluation Results (ac0935d781235e32dcea46ce39be2bb607b97a00)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,19 +1,114 @@
 ---
-base_model:
-- Qwen/Qwen2-72B-Instruct
-datasets:
-- mlabonne/orpo-dpo-mix-40k
 language:
 - en
+license: other
 library_name: transformers
 tags:
 - orpo
 - qwen2
 - rlhf
 - sft
+base_model:
+- Qwen/Qwen2-72B-Instruct
+datasets:
+- mlabonne/orpo-dpo-mix-40k
 license_name: tongyi-qianwen
 license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
-license: other
+model-index:
+- name: Qwen2-72B-Orpo-v0.1
+  results:
+  - 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: 78.8
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      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: 57.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      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: 35.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      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: 17.9
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      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: 20.87
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      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: 49.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Qwen2-72B-Orpo-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # dfurman/Qwen2-72B-Orpo-v0.1
@@ -122,4 +217,17 @@ print(outputs[0]["generated_text"][len(prompt):])
 |2|Sold in morning|Subtract morning sales|200 - 93 = 107|
 |3|Sold in afternoon|Subtract afternoon sales|107 - 39 = 68|
 |4|Returned loaves|Add returned loaves|68 + 6 = 74|
-```
+```
+# [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_dfurman__Qwen2-72B-Orpo-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |43.32|
+|IFEval (0-Shot)    |78.80|
+|BBH (3-Shot)       |57.41|
+|MATH Lvl 5 (4-Shot)|35.42|
+|GPQA (0-shot)      |17.90|
+|MuSR (0-shot)      |20.87|
+|MMLU-PRO (5-shot)  |49.50|
+